Artículos de revista |
2021 |
Hong A., Martínez Patino Duque Rahimi L M J E J C K Neighbourhood green space and health disparities in the global South: Evidence from Cali, Colombia Artículo de revista Health and Place, 72 (102690), pp. 1-9, 2021, ISSN: 1353-8292. Resumen | Enlaces | BibTeX | Etiquetas: ODS 11, Sostenibilidad de ciudades @article{HongMartinezEtal2021, title = {Neighbourhood green space and health disparities in the global South: Evidence from Cali, Colombia}, author = {Hong, A., Martínez L.M., Patino J.E., Duque J.C., Rahimi K.}, editor = {Elsevier}, doi = {10.1016/j.healthplace.2021.102690}, issn = {1353-8292}, year = {2021}, date = {2021-10-04}, journal = {Health and Place}, volume = {72}, number = {102690}, pages = {1-9}, abstract = {Increasing attention has been given to the role of green space in reducing health disparities. However, robust evidence to support decision making is lacking in the global South. We investigate the relationship between green space and health as well as its underlying mechanism in Cali, Colombia. Results indicate that neigh- bourhood greenness is associated with enhanced self-rated ‘good’ health and reduced physical and mental distress. The health benefits of green space appear to be stronger for people living in wealthier neighbourhoods than those in poor neighbourhoods. Results highlight the importance of considering health disparities for future green infrastructure planning in the global South context.}, keywords = {ODS 11, Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } Increasing attention has been given to the role of green space in reducing health disparities. However, robust evidence to support decision making is lacking in the global South. We investigate the relationship between green space and health as well as its underlying mechanism in Cali, Colombia. Results indicate that neigh- bourhood greenness is associated with enhanced self-rated ‘good’ health and reduced physical and mental distress. The health benefits of green space appear to be stronger for people living in wealthier neighbourhoods than those in poor neighbourhoods. Results highlight the importance of considering health disparities for future green infrastructure planning in the global South context. |
Martínez L.M., Valencia Trofimoff Vidal Robles Duque Sarmiento Tuiran I V N E J C O L A Quality of life, health, and government perception during COVID-19 times: Data from Colombia Artículo de revista Data in Brief, 37 (107268), pp. 1-11, 2021, ISSN: 2352-3409. Resumen | Enlaces | BibTeX | Etiquetas: covid-19 @article{martinez2021quality, title = {Quality of life, health, and government perception during COVID-19 times: Data from Colombia}, author = {Martínez, L.M.,Valencia,I., Trofimoff, V., Vidal, N., Robles, E., Duque, J.C., Sarmiento, O.L, Tuiran, A.}, editor = {Elsevier}, doi = {10.1016/j.dib.2021.107268}, issn = {2352-3409}, year = {2021}, date = {2021-07-30}, journal = {Data in Brief}, volume = {37}, number = {107268}, pages = {1-11}, abstract = {This analysis presents data collected through an online sur- vey about the quality of life, health, subjective wellbeing, and government perception in four cities in Colombia during the COVID-19 crisis. Four universities and a local news- paper promoted the survey to assess how the pandemic affected the population’s quality of life in a broad range of social and economic aspects. Respondents were adults (+18 years old) living in the largest Colombia cities: Bogotá, Medellín, Cali, and Barranquilla, totaling 1637 complete observations. Researchers used snowballing sampling strategy, social networks, a web page, and an advertisement in the partner newspaper for data collection. This data set helps to conduct social research and policy reports about the consequences of the pandemic. The data enclosed in this paper includes socioeconomic variables, income reduction, employment, household composition, teleworking, indebtedness, physical and mental health, physical activity behavior, subjective wellbeing, affective and communal relationships, institutional trust, and perception of government performance during COVID-19. We aim at contributing to a better understating of the consequences of the pandemic in Colombia and general in the Global South through the collection and dissemination of data for academic and policy purposes.}, keywords = {covid-19}, pubstate = {published}, tppubtype = {article} } This analysis presents data collected through an online sur- vey about the quality of life, health, subjective wellbeing, and government perception in four cities in Colombia during the COVID-19 crisis. Four universities and a local news- paper promoted the survey to assess how the pandemic affected the population’s quality of life in a broad range of social and economic aspects. Respondents were adults (+18 years old) living in the largest Colombia cities: Bogotá, Medellín, Cali, and Barranquilla, totaling 1637 complete observations. Researchers used snowballing sampling strategy, social networks, a web page, and an advertisement in the partner newspaper for data collection. This data set helps to conduct social research and policy reports about the consequences of the pandemic. The data enclosed in this paper includes socioeconomic variables, income reduction, employment, household composition, teleworking, indebtedness, physical and mental health, physical activity behavior, subjective wellbeing, affective and communal relationships, institutional trust, and perception of government performance during COVID-19. We aim at contributing to a better understating of the consequences of the pandemic in Colombia and general in the Global South through the collection and dissemination of data for academic and policy purposes. |
Prieto-Curiel, Rafael ; González-Ramírez, Humberto ; Quiñones, Mauricio ; Orjuela-Mendoza, Juan Pablo A paradox of traffic and extra cars in a city as a collective behaviour Artículo de revista R. Soc. Open Sci., 8 (6), pp. 17, 2021, ISSN: 2054-5703. Resumen | Enlaces | BibTeX | Etiquetas: Transporte en ciudades del sur global @article{Prieto_traffic_2021, title = {A paradox of traffic and extra cars in a city as a collective behaviour}, author = {Prieto-Curiel, Rafael and González-Ramírez, Humberto and Quiñones, Mauricio and Orjuela-Mendoza, Juan Pablo}, editor = {The Royal Society Publishing}, url = {https://doi.org/10.1098/rsos.201808}, doi = {10.1098/rsos.201808}, issn = {2054-5703}, year = {2021}, date = {2021-06-23}, journal = {R. Soc. Open Sci.}, volume = {8}, number = {6}, pages = {17}, abstract = { Promoting walking or cycling and reducing cars’ use is one of the city planners’ main targets, contributing to a sustainable transport method. Yet, the number of vehicles worldwide is increasing as fast as the population, and motorized mobility has become the primary transport method in most cities. Here, we consider modal share as an emergent behaviour of personal decisions. All individuals minimize their commuting time and reach an equilibrium under which no person is willing to change their transportation mode. In terms of the minimum travel time, the best-case scenario is used to determine the extra commuting time and the excess cars, computed as a social inefficiency. Results show that commuting times could increase up to 25% with many more vehicles than optimum. Paradoxically, all individuals trying to minimize their time could collectively reach the maximum commuting times in the extreme case, with all individuals driving during rush hour.}, keywords = {Transporte en ciudades del sur global}, pubstate = {published}, tppubtype = {article} } Promoting walking or cycling and reducing cars’ use is one of the city planners’ main targets, contributing to a sustainable transport method. Yet, the number of vehicles worldwide is increasing as fast as the population, and motorized mobility has become the primary transport method in most cities. Here, we consider modal share as an emergent behaviour of personal decisions. All individuals minimize their commuting time and reach an equilibrium under which no person is willing to change their transportation mode. In terms of the minimum travel time, the best-case scenario is used to determine the extra commuting time and the excess cars, computed as a social inefficiency. Results show that commuting times could increase up to 25% with many more vehicles than optimum. Paradoxically, all individuals trying to minimize their time could collectively reach the maximum commuting times in the extreme case, with all individuals driving during rush hour. |
Quiñones, M; L.M., Martínez; J.C., Duque; O., Mejía A targeting policy for tackling inequality in the developing world: Lessons learned from the system of cross-subsidies to fund utilities in Colombia Artículo de revista Cities, 116 (103306), pp. 4, 2021, ISSN: 0264-2751. Resumen | Enlaces | BibTeX | Etiquetas: Ciudades y su economía, ODS 11 @article{Quinonez_2021, title = {A targeting policy for tackling inequality in the developing world: Lessons learned from the system of cross-subsidies to fund utilities in Colombia}, author = {Quiñones, M. and Martínez L.M. and Duque J.C. and Mejía O.}, editor = {Elseviere}, url = {https://authors.elsevier.com/c/1dFxZy5jOjTPJ}, doi = {10.1016/j.cities.2021.103306}, issn = {0264-2751}, year = {2021}, date = {2021-06-17}, journal = {Cities}, volume = {116}, number = {103306}, pages = {4}, abstract = {This paper contributes to the discussion on policies for providing utilities and on their contribution to reducing inequality. The uniqueness of the Colombian scheme to target subsidy beneficiaries and contributors provides valuable lessons for policymakers, academics, and urban planners regarding the difficulties and implications of such a segmenting government intervention in countries of the Global South. Among the unintended consequences of the scheme are deepening spatial segregation, distorted economic incentives, and poor correspondence of the welfare system with stratification categories.}, keywords = {Ciudades y su economía, ODS 11}, pubstate = {published}, tppubtype = {article} } This paper contributes to the discussion on policies for providing utilities and on their contribution to reducing inequality. The uniqueness of the Colombian scheme to target subsidy beneficiaries and contributors provides valuable lessons for policymakers, academics, and urban planners regarding the difficulties and implications of such a segmenting government intervention in countries of the Global South. Among the unintended consequences of the scheme are deepening spatial segregation, distorted economic incentives, and poor correspondence of the welfare system with stratification categories. |
Patiño, Jorge E; Hong, Andy ; Duque, Juan C; Rahimi, Kazem ; Zapata, Silvana ; Lopera, Verónica M Built environment and mortality risk from cardiovascular disease and diabetes in Medellín, Colombia: An ecological study. Artículo de revista Landscape and Urban Planning, 213 (104126), pp. 12, 2021, ISBN: 0169-2046. Resumen | Enlaces | BibTeX | Etiquetas: Sostenibilidad de ciudades @article{Patino2021, title = {Built environment and mortality risk from cardiovascular disease and diabetes in Medellín, Colombia: An ecological study.}, author = {Patiño, Jorge E. and Hong, Andy and Duque, Juan C. and Rahimi, Kazem and Zapata, Silvana and Lopera, Verónica M.}, url = {https://doi.org/10.1016/j.landurbplan.2021.104126}, doi = {10.1016/j.landurbplan.2021.104126}, isbn = {0169-2046}, year = {2021}, date = {2021-05-01}, journal = {Landscape and Urban Planning}, volume = {213}, number = {104126}, pages = {12}, abstract = {• We analyze the built-environment and public health outcomes in Medellin (CO). • Greenness showed the strongest negative association with the mortality measures. • We found curvilinear relationships with some urban features. • Intersection density relates negatively to the mortality rates after 200 int./km2. • The densities of amenities and population show the opposite: U-shape relationships.}, keywords = {Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } • We analyze the built-environment and public health outcomes in Medellin (CO). • Greenness showed the strongest negative association with the mortality measures. • We found curvilinear relationships with some urban features. • Intersection density relates negatively to the mortality rates after 200 int./km2. • The densities of amenities and population show the opposite: U-shape relationships. |
Duque, Juan C; Lozano-Gracia, Nancy ; Patiño, Jorge E; Restrepo, Paula Urban form and productivity: What shapes are Latin-American cities? Artículo de revista Environment and Planning B: Urban Analytics and City Science, 8697 , pp. 20, 2021, ISBN: 2399-8083. Resumen | Enlaces | BibTeX | Etiquetas: Ciudades y su economía, ODS 11 @article{duque_productivity_2021, title = {Urban form and productivity: What shapes are Latin-American cities?}, author = {Duque, Juan C. and Lozano-Gracia, Nancy and Patiño, Jorge E. and Restrepo, Paula}, editor = {Sage}, url = {https://doi.org/10.1177/2399808321999309}, doi = {10.1177/2399808321999309}, isbn = {2399-8083}, year = {2021}, date = {2021-03-08}, journal = {Environment and Planning B: Urban Analytics and City Science}, volume = {8697}, pages = {20}, abstract = {This paper examines the linkages between urban form and city productivity using seven alternative metrics for urban form and applying them to a comprehensive sample of Latin-American cities. While most of the literature has concentrated on the effects of population density (compact vs. sprawling urban development), this paper seeks to assess whether different dimensions of a city’s urban form, such as shape, structure, and land use, affect its economic performance. We found that both the shape of the urban extent and the inner-city connectedness have a statistically significant association with the productivity level of a city.}, keywords = {Ciudades y su economía, ODS 11}, pubstate = {published}, tppubtype = {article} } This paper examines the linkages between urban form and city productivity using seven alternative metrics for urban form and applying them to a comprehensive sample of Latin-American cities. While most of the literature has concentrated on the effects of population density (compact vs. sprawling urban development), this paper seeks to assess whether different dimensions of a city’s urban form, such as shape, structure, and land use, affect its economic performance. We found that both the shape of the urban extent and the inner-city connectedness have a statistically significant association with the productivity level of a city. |
Prieto-Curiel, Rafael ; Patiño, Jorge E; Duque, Juan C; O'Cleary, Neave The heartbeat of the city Artículo de revista Plos One, 16 (2), pp. 30, 2021, ISBN: 1932-6203. Resumen | Enlaces | BibTeX | Etiquetas: crimen, ODS 11, Transporte en ciudades del sur global @article{prieto_heartbeat_2021, title = {The heartbeat of the city}, author = {Prieto-Curiel, Rafael and Patiño, Jorge E. and Duque, Juan C. and O'Cleary, Neave}, url = {https://doi.org/10.1371/journal.pone.0246714}, doi = {10.1371/journal.pone.0246714}, isbn = {1932-6203}, year = {2021}, date = {2021-02-24}, journal = {Plos One}, volume = {16}, number = {2}, pages = {30}, abstract = {Human activity is organised around daily and weekly cycles, which should, in turn, dominate all types of social interactions, such as transactions, communications, gatherings and so on. Yet, despite their strategic importance for policing and security, cyclical weekly patterns in crime and road incidents have been unexplored at the city and neighbourhood level. Here we construct a novel method to capture the weekly trace, or “heartbeat” of events and use geotagged data capturing the time and location of more than 200,000 violent crimes and nearly one million crashes in Mexico City. On aggregate, our findings show that the heartbeats of crime and crashes follow a similar pattern. We observe valleys during the night and peaks in the evening, where the intensity during a peak is 7.5 times the intensity of valleys in terms of crime and 12.3 times in terms of road accidents. Although distinct types of events, crimes and crashes reach their respective intensity peak on Friday night and valley on Tuesday morning, the result of a hyper-synchronised society. Next, heartbeats are computed for city neighbourhood ‘tiles’, a division of space within the city based on the distance to Metro and other public transport stations. We find that heartbeats are spatially heterogeneous with some diffusion, so that nearby tiles have similar heartbeats. Tiles are then clustered based on the shape of their heartbeat, e.g., tiles within groups suffer peaks and valleys of crime or crashes at similar times during the week. The clusters found are similar to those based on economic activities. This enables us to anticipate temporal traces of crime and crashes based on local amenities.}, keywords = {crimen, ODS 11, Transporte en ciudades del sur global}, pubstate = {published}, tppubtype = {article} } Human activity is organised around daily and weekly cycles, which should, in turn, dominate all types of social interactions, such as transactions, communications, gatherings and so on. Yet, despite their strategic importance for policing and security, cyclical weekly patterns in crime and road incidents have been unexplored at the city and neighbourhood level. Here we construct a novel method to capture the weekly trace, or “heartbeat” of events and use geotagged data capturing the time and location of more than 200,000 violent crimes and nearly one million crashes in Mexico City. On aggregate, our findings show that the heartbeats of crime and crashes follow a similar pattern. We observe valleys during the night and peaks in the evening, where the intensity during a peak is 7.5 times the intensity of valleys in terms of crime and 12.3 times in terms of road accidents. Although distinct types of events, crimes and crashes reach their respective intensity peak on Friday night and valley on Tuesday morning, the result of a hyper-synchronised society. Next, heartbeats are computed for city neighbourhood ‘tiles’, a division of space within the city based on the distance to Metro and other public transport stations. We find that heartbeats are spatially heterogeneous with some diffusion, so that nearby tiles have similar heartbeats. Tiles are then clustered based on the shape of their heartbeat, e.g., tiles within groups suffer peaks and valleys of crime or crashes at similar times during the week. The clusters found are similar to those based on economic activities. This enables us to anticipate temporal traces of crime and crashes based on local amenities. |
Gómez, Jairo A; Guan, ChengHe ; Tripathy, Pratyush ; Duque, Juan C; Passos, Santiago ; Keith, Michael ; Liu, Jialin Analyzing the Spatiotemporal Uncertainty in Urbanization Predictions Artículo de revista Remote Sensing, 13 (3), pp. 28, 2021, ISSN: 2072-4292. Resumen | Enlaces | BibTeX | Etiquetas: Aprendizaje de máquina, Crecimiento de ciudades @article{rs13030512, title = {Analyzing the Spatiotemporal Uncertainty in Urbanization Predictions}, author = {Gómez, Jairo A. and Guan, ChengHe and Tripathy, Pratyush and Duque, Juan C. and Passos, Santiago and Keith, Michael and Liu, Jialin}, editor = {MDPI}, url = {https://doi.org/10.3390/rs13030512}, doi = {10.3390/rs13030512}, issn = {2072-4292}, year = {2021}, date = {2021-02-01}, journal = {Remote Sensing}, volume = {13}, number = {3}, pages = {28}, abstract = {With the availability of computational resources, geographical information systems, and remote sensing data, urban growth modeling has become a viable tool for predicting urbanization of cities and towns, regions, and nations around the world. This information allows policy makers, urban planners, environmental and civil organizations to make investments, design infrastructure, extend public utility networks, plan housing solutions, and mitigate adverse environmental impacts. Despite its importance, urban growth models often discard the spatiotemporal uncertainties in their prediction estimates. In this paper, we analyzed the uncertainty in the urban land predictions by comparing the outcomes of two different growth models, one based on a widely applied cellular automata model known as the SLEUTH CA and the other one based on a previously published machine learning framework. We selected these two models because they are complementary, the first is based on human knowledge and pre-defined and understandable policies while the second is more data-driven and might be less influenced by any a priori knowledge or bias. To test our methodology, we chose the cities of Jiaxing and Lishui in China because they are representative of new town planning policies and have different characteristics in terms of land extension, geographical conditions, growth rates, and economic drivers. We focused on the spatiotemporal uncertainty, understood as the inherent doubt in the predictions of where and when will a piece of land become urban, using the concepts of certainty area in space and certainty area in time. The proposed analyses in this paper aim to contribute to better urban planning exercises, and they can be extended to other cities worldwide.}, keywords = {Aprendizaje de máquina, Crecimiento de ciudades}, pubstate = {published}, tppubtype = {article} } With the availability of computational resources, geographical information systems, and remote sensing data, urban growth modeling has become a viable tool for predicting urbanization of cities and towns, regions, and nations around the world. This information allows policy makers, urban planners, environmental and civil organizations to make investments, design infrastructure, extend public utility networks, plan housing solutions, and mitigate adverse environmental impacts. Despite its importance, urban growth models often discard the spatiotemporal uncertainties in their prediction estimates. In this paper, we analyzed the uncertainty in the urban land predictions by comparing the outcomes of two different growth models, one based on a widely applied cellular automata model known as the SLEUTH CA and the other one based on a previously published machine learning framework. We selected these two models because they are complementary, the first is based on human knowledge and pre-defined and understandable policies while the second is more data-driven and might be less influenced by any a priori knowledge or bias. To test our methodology, we chose the cities of Jiaxing and Lishui in China because they are representative of new town planning policies and have different characteristics in terms of land extension, geographical conditions, growth rates, and economic drivers. We focused on the spatiotemporal uncertainty, understood as the inherent doubt in the predictions of where and when will a piece of land become urban, using the concepts of certainty area in space and certainty area in time. The proposed analyses in this paper aim to contribute to better urban planning exercises, and they can be extended to other cities worldwide. |
2020 |
Rueda-Plata, Diego ; Gonzales, Daniela ; Acevedo, Ana B; Duque, Juan C; Ramos-Pollán, Raúl. Use of deep learning models in street-level images to classify one-story unreinforced masonry buildings based on roof diaphragms Artículo de revista Building and Environment, 189 (107517), pp. 1-10, 2020, ISSN: 0360-1323. Resumen | Enlaces | BibTeX | Etiquetas: Redes neuronales, Sostenibilidad de ciudades @article{Rueda2020, title = {Use of deep learning models in street-level images to classify one-story unreinforced masonry buildings based on roof diaphragms}, author = {Rueda-Plata, Diego and Gonzales, Daniela and Acevedo, Ana B. and Duque, Juan C. and Ramos-Pollán, Raúl.}, url = {https://doi.org/10.1016/j.buildenv.2020.107517}, doi = {10.1016/j.buildenv.2020.107517}, issn = {0360-1323}, year = {2020}, date = {2020-12-21}, journal = {Building and Environment}, volume = {189}, number = {107517}, pages = {1-10}, abstract = {In this paper, we explore the potential of convolutional neural networks to classify street-level imagery of one-story unreinforced masonry buildings (MURs) according to the flexibility of the roof diaphragm (rigid or flexible). This information is critical for vulnerability studies, disaster risk assessments, disaster management strategies, etc., and is of great relevance in cities where unreinforced masonry is the most common building typology or where the majority of the population resides in such buildings. Our contribution could be useful for local governments of cities in developing countries seeking to significantly reduce the number of deaths caused by disasters. Our research results indicate that VGG19 is the convolutional neural network architecture with the best performance, with an accuracy of 0.80, a precision of 0.88, and a recall of 0.84. The results are encouraging and could be used to reduce the amount of resources (both human and economic) for the development of detailed exposure models for unreinforced masonry buildings.}, keywords = {Redes neuronales, Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } In this paper, we explore the potential of convolutional neural networks to classify street-level imagery of one-story unreinforced masonry buildings (MURs) according to the flexibility of the roof diaphragm (rigid or flexible). This information is critical for vulnerability studies, disaster risk assessments, disaster management strategies, etc., and is of great relevance in cities where unreinforced masonry is the most common building typology or where the majority of the population resides in such buildings. Our contribution could be useful for local governments of cities in developing countries seeking to significantly reduce the number of deaths caused by disasters. Our research results indicate that VGG19 is the convolutional neural network architecture with the best performance, with an accuracy of 0.80, a precision of 0.88, and a recall of 0.84. The results are encouraging and could be used to reduce the amount of resources (both human and economic) for the development of detailed exposure models for unreinforced masonry buildings. |
Ospina, Juan P; López-Ríos, Víctor I; Botero-Fernández, Verónica ; Duque, Juan C A database to analyze cycling routes in Medellin, Colombia Artículo de revista Data in Brief, 32 (106162), pp. 1-14, 2020, ISSN: 2352-3409. Resumen | Enlaces | BibTeX | Etiquetas: bicicletas, Transporte en ciudades del sur global @article{ospina2020database, title = {A database to analyze cycling routes in Medellin, Colombia}, author = {Ospina, Juan P. and López-Ríos, Víctor I. and Botero-Fernández, Verónica and Duque, Juan C.}, url = {https://doi.org/10.1016/j.dib.2020.106162}, doi = {10.1016/j.dib.2020.106162}, issn = {2352-3409}, year = {2020}, date = {2020-10-01}, journal = {Data in Brief}, volume = {32}, number = {106162}, pages = {1-14}, abstract = {A bicycle route questionnaire was designed to collect information about the characteristics of cyclists and the routes they take. Medellin is used as a case study in this paper due to its strong sociodemographic inequality, land use, urban form diversity, and topographical variability. The survey execution targeted bicycle commuters in the city by distributing the questionnaires online, personally by telephone, and personally on the street. These data will be useful to support strategies aiming to promote bicycling as a mode of transportation. Several types of analysis may be derived from the data, including an explanation of the factors determining the route choice and route comparisons according to the sociodemographics and locations of users. For instance, these data have already been used by Ospina et al. (2020) where they sought to understand cycling travel distance in Medellin city.}, keywords = {bicicletas, Transporte en ciudades del sur global}, pubstate = {published}, tppubtype = {article} } A bicycle route questionnaire was designed to collect information about the characteristics of cyclists and the routes they take. Medellin is used as a case study in this paper due to its strong sociodemographic inequality, land use, urban form diversity, and topographical variability. The survey execution targeted bicycle commuters in the city by distributing the questionnaires online, personally by telephone, and personally on the street. These data will be useful to support strategies aiming to promote bicycling as a mode of transportation. Several types of analysis may be derived from the data, including an explanation of the factors determining the route choice and route comparisons according to the sociodemographics and locations of users. For instance, these data have already been used by Ospina et al. (2020) where they sought to understand cycling travel distance in Medellin city. |
Ospina, Juan P; Botero-Fernández, Verónica ; Duque, Juan C; Brussel, Mark Understanding cycling travel distance: The case of Medellin city (Colombia) Artículo de revista Transportation Research Part D: Transport and Environment, 86 (102423), pp. 1-22, 2020, ISSN: 1361-9209. Resumen | Enlaces | BibTeX | Etiquetas: bicicletas, Transporte en ciudades del sur global @article{ospina2020understanding, title = {Understanding cycling travel distance: The case of Medellin city (Colombia)}, author = {Ospina, Juan P. and Botero-Fernández, Verónica and Duque, Juan C. and Brussel, Mark}, url = {https://doi.org/10.1016/j.trd.2020.102423}, doi = {10.1016/j.trd.2020.102423}, issn = {1361-9209}, year = {2020}, date = {2020-09-01}, journal = {Transportation Research Part D: Transport and Environment}, volume = {86}, number = {102423}, pages = {1-22}, abstract = {The relevance of cycling as a mode of transportation is increasingly being recognized in many cities around the world, and the city of Medellin (Colombia) is no exception. To better understand cycling travel behavior in Medellin, we perform a multiple regression to analyze the importance of route characteristics in explaining cycling travel distance. We control for socioeconomic and built environment variables at the origin and destination. Our results reveal that the effects of the socio-economic and built environment characteristics at the origin and destination are modest or statistically insignificant in explaining travel distance. However, the variables that characterize the built and natural environment along the route are significant and appreciably improve the explanatory power of the baseline econometric model. An analysis of interacting effects shows that the interaction between the dedicated infrastructure along the route and the degree of deviation from direct routes has a relevant effect on explaining travel distance. The findings of this work are useful for designing cycling policy and developing more usable cycling infrastructure.}, keywords = {bicicletas, Transporte en ciudades del sur global}, pubstate = {published}, tppubtype = {article} } The relevance of cycling as a mode of transportation is increasingly being recognized in many cities around the world, and the city of Medellin (Colombia) is no exception. To better understand cycling travel behavior in Medellin, we perform a multiple regression to analyze the importance of route characteristics in explaining cycling travel distance. We control for socioeconomic and built environment variables at the origin and destination. Our results reveal that the effects of the socio-economic and built environment characteristics at the origin and destination are modest or statistically insignificant in explaining travel distance. However, the variables that characterize the built and natural environment along the route are significant and appreciably improve the explanatory power of the baseline econometric model. An analysis of interacting effects shows that the interaction between the dedicated infrastructure along the route and the degree of deviation from direct routes has a relevant effect on explaining travel distance. The findings of this work are useful for designing cycling policy and developing more usable cycling infrastructure. |
Duque, Juan C; Lozano-Gracia, Nancy ; Patino, Jorge E; Restrepo, Paula Institutional fragmentation and metropolitan coordination in Latin American cities: Are there links with city productivity? Artículo de revista Regional Science Policy & Practice, pp. 1-33, 2020, ISSN: 1757-7802. Resumen | Enlaces | BibTeX | Etiquetas: Ciudades y su economía, imágenes satelitales, productividad @article{duque2020institutional, title = {Institutional fragmentation and metropolitan coordination in Latin American cities: Are there links with city productivity?}, author = {Duque, Juan C. and Lozano-Gracia, Nancy and Patino, Jorge E. and Restrepo, Paula}, url = {https://doi.org/10.1111/rsp3.12314}, doi = {10.1111/rsp3.12314}, issn = {1757-7802}, year = {2020}, date = {2020-07-08}, journal = {Regional Science Policy & Practice}, pages = {1-33}, abstract = {This paper provides empirical evidence on the impact of institutional fragmentation and metropolitan coordination on urban productivity in Latin American Cities. The use of night‐time lights satellite imagery and high-resolution population data allow us to use a definition of metropolitan area based on the urban extents that result from the union between the formally defined metropolitan areas and the contiguous patches of urbanized areas with more than 500,000 inhabitants. Initial results suggest that the presence of multiple local governments within metropolitan areas generate opposite effects in urban productivity. On the one hand, smaller governments tend to be more responsive and efficient, which increases productivity. But, on the other hand, multiple local governments face co‐ordination costs that result in lower productivity levels.}, keywords = {Ciudades y su economía, imágenes satelitales, productividad}, pubstate = {published}, tppubtype = {article} } This paper provides empirical evidence on the impact of institutional fragmentation and metropolitan coordination on urban productivity in Latin American Cities. The use of night‐time lights satellite imagery and high-resolution population data allow us to use a definition of metropolitan area based on the urban extents that result from the union between the formally defined metropolitan areas and the contiguous patches of urbanized areas with more than 500,000 inhabitants. Initial results suggest that the presence of multiple local governments within metropolitan areas generate opposite effects in urban productivity. On the one hand, smaller governments tend to be more responsive and efficient, which increases productivity. But, on the other hand, multiple local governments face co‐ordination costs that result in lower productivity levels. |
Gonzalez, Daniela ; Rueda-Plata, Diego ; Acevedo, Ana B; Duque, Juan C; Ramos-Pollán, Raúl ; Betancourt, Alejandro ; García, Sebastian Automatic detection of building typology using deep learning methods on street level image Artículo de revista Building and Environment, 177 (106805), pp. 1-12, 2020, ISSN: 0360-1323. Resumen | Enlaces | BibTeX | Etiquetas: Redes neuronales, Sostenibilidad de ciudades @article{gonzalez2020automatic, title = {Automatic detection of building typology using deep learning methods on street level image}, author = {Gonzalez, Daniela and Rueda-Plata, Diego and Acevedo, Ana B. and Duque, Juan C. and Ramos-Pollán, Raúl and Betancourt, Alejandro and García, Sebastian}, url = {https://doi.org/10.1016/j.buildenv.2020.106805}, doi = {10.1016/j.buildenv.2020.106805}, issn = {0360-1323}, year = {2020}, date = {2020-06-15}, journal = {Building and Environment}, volume = {177}, number = {106805}, pages = {1-12}, abstract = {An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models.}, keywords = {Redes neuronales, Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. |
Gómez, Jairo A; Patiño, Jorge E; Duque, Juan C; Passos, Santiago Spatiotemporal Modeling of Urban Growth Using Machine Learning Artículo de revista Remote Sensing, 12(1) (109), pp. 1-41, 2020, ISSN: 2072-4292. Resumen | Enlaces | BibTeX | Etiquetas: Aprendizaje de máquina, Crecimiento de ciudades, imágenes satelitales @article{gomez2020spatiotemporal, title = {Spatiotemporal Modeling of Urban Growth Using Machine Learning}, author = {Gómez, Jairo A. and Patiño, Jorge E. and Duque, Juan C. and Passos, Santiago }, url = {https://doi.org/10.3390/rs12010109}, doi = {10.3390/rs12010109}, issn = {2072-4292}, year = {2020}, date = {2020-01-01}, journal = {Remote Sensing}, volume = {12(1)}, number = {109}, pages = {1-41}, abstract = {This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains the binary urban footprint from the population distribution through a binary classifier plus a temporal correction for existing urban regions. The framework estimates the urban footprint in color from its previous value, as well as from past and current values of the binary urban footprint using a semantic inpainting algorithm. By combining this framework with free data from the Landsat archive and the Global Human Settlement Layer framework, interested users can get approximate growth predictions of any city in the world. These predictions can be improved with the inclusion in the framework of additional spatially distributed input variables over time subject to availability. Unlike widely used growth models based on cellular automata, there are two main advantages of using the proposed machine learning-based framework. Firstly, it does not require to define rules a priori because the model learns the dynamics of growth directly from the historical data. Secondly, it is very easy to train new machine learning models using different explanatory input variables to assess their impact. As a proof of concept, we tested the framework in Valledupar and Rionegro, two Latin American cities located in Colombia with different geomorphological characteristics, and found that the model predictions were in close agreement with the ground-truth based on performance metrics, such as the root-mean-square error, zero-mean normalized cross-correlation, Pearson’s correlation coefficient for continuous variables, and a few others for discrete variables such as the intersection over union, accuracy, and the f1 metric. In summary, our framework for modeling urban growth is flexible, allows sensitivity analyses, and can help policymakers worldwide to assess different what-if scenarios during the planning cycle of sustainable and resilient cities.}, keywords = {Aprendizaje de máquina, Crecimiento de ciudades, imágenes satelitales}, pubstate = {published}, tppubtype = {article} } This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains the binary urban footprint from the population distribution through a binary classifier plus a temporal correction for existing urban regions. The framework estimates the urban footprint in color from its previous value, as well as from past and current values of the binary urban footprint using a semantic inpainting algorithm. By combining this framework with free data from the Landsat archive and the Global Human Settlement Layer framework, interested users can get approximate growth predictions of any city in the world. These predictions can be improved with the inclusion in the framework of additional spatially distributed input variables over time subject to availability. Unlike widely used growth models based on cellular automata, there are two main advantages of using the proposed machine learning-based framework. Firstly, it does not require to define rules a priori because the model learns the dynamics of growth directly from the historical data. Secondly, it is very easy to train new machine learning models using different explanatory input variables to assess their impact. As a proof of concept, we tested the framework in Valledupar and Rionegro, two Latin American cities located in Colombia with different geomorphological characteristics, and found that the model predictions were in close agreement with the ground-truth based on performance metrics, such as the root-mean-square error, zero-mean normalized cross-correlation, Pearson’s correlation coefficient for continuous variables, and a few others for discrete variables such as the intersection over union, accuracy, and the f1 metric. In summary, our framework for modeling urban growth is flexible, allows sensitivity analyses, and can help policymakers worldwide to assess different what-if scenarios during the planning cycle of sustainable and resilient cities. |
2019 |
Duque, Juan C; Lozano-Gracia, Nancy ; Patino, Jorge E; Restrepo, Paula ; Velasquez, Wilson A Spatiotemporal dynamics of urban growth in Latin American cities: An analysis using nighttime light imagery Artículo de revista Landscape and Urban Planning, 191 (103640), pp. 1-15, 2019, ISSN: 0169-2046. Resumen | Enlaces | BibTeX | Etiquetas: Crecimiento de ciudades, imágenes satelitales @article{duque2019spatiotemporal, title = {Spatiotemporal dynamics of urban growth in Latin American cities: An analysis using nighttime light imagery}, author = {Duque, Juan C. and Lozano-Gracia, Nancy and Patino, Jorge E. and Restrepo, Paula and Velasquez, Wilson A.}, url = {https://doi.org/10.1016/j.landurbplan.2019.103640}, doi = {10.1016/j.landurbplan.2019.103640}, issn = {0169-2046}, year = {2019}, date = {2019-11-01}, journal = {Landscape and Urban Planning}, volume = {191}, number = {103640}, pages = {1-15}, abstract = {The impact of urban form on economic performance and quality of life has been widely recognized. Studies regarding urban form have focused on developed countries; only a small number of cities in developing countries have been studied. This paper utilizes nighttime light imagery and information regarding street networks, automatically retrieved from OpenStreetMap, to calculate a series of spatial metrics that capture different aspects of the urban form of 919 Latin American and Caribbean cities. We study the relationship between the urban form metrics and several factors that can correlate with urban form (topography, size, colony, and economic performance) and perform a spatiotemporal analysis of urban growth from 1996 to 2010. Among the results, we highlight the tendency of a group of cities to grow on steeper slopes and several worrying aspects, specifically urban growth in protected areas and a trend to sprawl-growing in certain Latin American and Caribbean cities.}, keywords = {Crecimiento de ciudades, imágenes satelitales}, pubstate = {published}, tppubtype = {article} } The impact of urban form on economic performance and quality of life has been widely recognized. Studies regarding urban form have focused on developed countries; only a small number of cities in developing countries have been studied. This paper utilizes nighttime light imagery and information regarding street networks, automatically retrieved from OpenStreetMap, to calculate a series of spatial metrics that capture different aspects of the urban form of 919 Latin American and Caribbean cities. We study the relationship between the urban form metrics and several factors that can correlate with urban form (topography, size, colony, and economic performance) and perform a spatiotemporal analysis of urban growth from 1996 to 2010. Among the results, we highlight the tendency of a group of cities to grow on steeper slopes and several worrying aspects, specifically urban growth in protected areas and a trend to sprawl-growing in certain Latin American and Caribbean cities. |
2018 |
Duque, Juan C; Laniado, Henry ; Polo, Adriano S-maup: Statistical test to measure the sensitivity to the modifiable areal unit problem Artículo de revista PloS one, 13 (11), pp. 1-25, 2018, ISSN: 1932-6203. Resumen | Enlaces | BibTeX | Etiquetas: Análisis espacial @article{duque2018s, title = {S-maup: Statistical test to measure the sensitivity to the modifiable areal unit problem}, author = {Duque, Juan C. and Laniado, Henry and Polo, Adriano}, url = {https://doi.org/10.1371/journal.pone.0207377}, doi = {10.1371/journal.pone.0207377}, issn = {1932-6203}, year = {2018}, date = {2018-11-27}, journal = {PloS one}, volume = {13}, number = {11}, pages = {1-25}, abstract = {This work presents a nonparametric statistical test, S-maup, to measure the sensitivity of a spatially intensive variable to the effects of the Modifiable Areal Unit Problem (MAUP). To the best of our knowledge, S-maup is the first statistic of its type and focuses on determining how much the distribution of the variable, at its highest level of spatial disaggregation, will change when it is spatially aggregated. Through a computational experiment, we obtain the basis for the design of the statistical test under the null hypothesis of non-sensitivity to MAUP. We performed an exhaustive simulation study for approaching the empirical distribution of the statistical test, obtaining its critical values, and computing its power and size. The results indicate that, in general, both the statistical size and power improve with increasing sample size. Finally, for illustrative purposes, an empirical application is made using the Mincer equation in South Africa, where starting from 206 municipalities, the S-maup statistic is used to find the maximum level of spatial aggregation that avoids the negative consequences of the MAUP.}, keywords = {Análisis espacial}, pubstate = {published}, tppubtype = {article} } This work presents a nonparametric statistical test, S-maup, to measure the sensitivity of a spatially intensive variable to the effects of the Modifiable Areal Unit Problem (MAUP). To the best of our knowledge, S-maup is the first statistic of its type and focuses on determining how much the distribution of the variable, at its highest level of spatial disaggregation, will change when it is spatially aggregated. Through a computational experiment, we obtain the basis for the design of the statistical test under the null hypothesis of non-sensitivity to MAUP. We performed an exhaustive simulation study for approaching the empirical distribution of the statistical test, obtaining its critical values, and computing its power and size. The results indicate that, in general, both the statistical size and power improve with increasing sample size. Finally, for illustrative purposes, an empirical application is made using the Mincer equation in South Africa, where starting from 206 municipalities, the S-maup statistic is used to find the maximum level of spatial aggregation that avoids the negative consequences of the MAUP. |
Duque, Juan C; Vélez-Gallego, Mario C; Echeverri, Laura C On the Performance of the Subtour Elimination Constraints Approach for the p-Regions Problem: A Computational Study Artículo de revista Geographical Analysis, 50 (1), pp. 32-52, 2018, ISSN: 1538-4632. Resumen | Enlaces | BibTeX | Etiquetas: Diseño de regiones @article{duque2018performance, title = {On the Performance of the Subtour Elimination Constraints Approach for the p-Regions Problem: A Computational Study}, author = {Duque, Juan C. and Vélez-Gallego, Mario C. and Echeverri, Laura C.}, url = {https://doi.org/10.1111/gean.12132}, doi = {10.1111/gean.12132}, issn = {1538-4632}, year = {2018}, date = {2018-01-22}, journal = {Geographical Analysis}, volume = {50}, number = {1}, pages = {32-52}, abstract = {The p‐regions is a mixed integer programming (MIP) model for the exhaustive clustering of a set of n geographic areas into p spatially contiguous regions while minimizing measures of intraregional heterogeneity. This is an NP‐hard problem that requires a constant research of strategies to increase the size of instances that can be solved using exact optimization techniques. In this article, we explore the benefits of an iterative process that begins by solving the relaxed version of the p‐regions that removes the constraints that guarantee the spatial contiguity of the regions. Then, additional constraints are incorporated iteratively to solve spatial discontinuities in the regions. In particular we explore the relationship between the level of spatial autocorrelation of the aggregation variable and the benefits obtained from this iterative process. The results show that high levels of spatial autocorrelation reduce computational times because the spatial patterns tend to create spatially contiguous regions. However, we found that the greatest benefits are obtained in two situations: (1) when urn:x-wiley:00167363:media:gean12132:gean12132-math-0001; and (2) when the parameter p is close to the number of clusters in the spatial pattern of the aggregation variable.}, keywords = {Diseño de regiones}, pubstate = {published}, tppubtype = {article} } The p‐regions is a mixed integer programming (MIP) model for the exhaustive clustering of a set of n geographic areas into p spatially contiguous regions while minimizing measures of intraregional heterogeneity. This is an NP‐hard problem that requires a constant research of strategies to increase the size of instances that can be solved using exact optimization techniques. In this article, we explore the benefits of an iterative process that begins by solving the relaxed version of the p‐regions that removes the constraints that guarantee the spatial contiguity of the regions. Then, additional constraints are incorporated iteratively to solve spatial discontinuities in the regions. In particular we explore the relationship between the level of spatial autocorrelation of the aggregation variable and the benefits obtained from this iterative process. The results show that high levels of spatial autocorrelation reduce computational times because the spatial patterns tend to create spatially contiguous regions. However, we found that the greatest benefits are obtained in two situations: (1) when urn:x-wiley:00167363:media:gean12132:gean12132-math-0001; and (2) when the parameter p is close to the number of clusters in the spatial pattern of the aggregation variable. |
2017 |
Duque, Juan C; Patino, Jorge E; Betancourt, Alejandro Exploring the potential of machine learning for automatic slum identification from VHR imagery Artículo de revista Remote Sensing, 9(9) (895), pp. 1-23, 2017, ISSN: 2072-4292. Resumen | Enlaces | BibTeX | Etiquetas: Aprendizaje de máquina, imágenes satelitales, pobreza, Sostenibilidad de ciudades @article{duque2017exploring, title = {Exploring the potential of machine learning for automatic slum identification from VHR imagery}, author = {Duque, Juan C. and Patino, Jorge E. and Betancourt, Alejandro}, url = {https://doi.org/10.3390/rs9090895}, doi = {10.3390/rs9090895}, issn = {2072-4292}, year = {2017}, date = {2017-08-30}, journal = {Remote Sensing}, volume = {9(9)}, number = {895}, pages = {1-23}, abstract = {Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model.}, keywords = {Aprendizaje de máquina, imágenes satelitales, pobreza, Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model. |
Arribas-Bel, Daniel ; Patino, Jorge E; Duque, Juan C Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning Artículo de revista PloS one, 12 (4), pp. 1-25, 2017, ISSN: 1932-6203. Resumen | Enlaces | BibTeX | Etiquetas: Aprendizaje de máquina, pobreza, Sostenibilidad de ciudades @article{arribas2017remote, title = {Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning}, author = {Arribas-Bel, Daniel and Patino, Jorge E. and Duque, Juan C.}, url = {https://doi.org/10.1371/journal.pone.0176684}, doi = {10.1371/journal.pone.0176684}, issn = { 1932-6203}, year = {2017}, date = {2017-05-02}, journal = {PloS one}, volume = {12}, number = {4}, pages = {1-25}, abstract = {This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements. We use land cover, spectral, structure and texture features extracted from a Google Earth image of Liverpool (UK) to evaluate their potential to predict Living Environment Deprivation at a small statistical area level. We also contribute to the methodological literature on the estimation of socioeconomic indices with remote-sensing data by introducing elements from modern machine learning. In addition to classical approaches such as Ordinary Least Squares (OLS) regression and a spatial lag model, we explore the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy. In addition to novel predicting methods, we also introduce tools for model interpretation and evaluation such as feature importance and partial dependence plots, or cross-validation. Our results show that Random Forest proved to be the best model with an R2 of around 0.54, followed by Gradient Boost Regressor with 0.5. Both the spatial lag model and the OLS fall behind with significantly lower performances of 0.43 and 0.3, respectively.}, keywords = {Aprendizaje de máquina, pobreza, Sostenibilidad de ciudades}, pubstate = {published}, tppubtype = {article} } This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements. We use land cover, spectral, structure and texture features extracted from a Google Earth image of Liverpool (UK) to evaluate their potential to predict Living Environment Deprivation at a small statistical area level. We also contribute to the methodological literature on the estimation of socioeconomic indices with remote-sensing data by introducing elements from modern machine learning. In addition to classical approaches such as Ordinary Least Squares (OLS) regression and a spatial lag model, we explore the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy. In addition to novel predicting methods, we also introduce tools for model interpretation and evaluation such as feature importance and partial dependence plots, or cross-validation. Our results show that Random Forest proved to be the best model with an R2 of around 0.54, followed by Gradient Boost Regressor with 0.5. Both the spatial lag model and the OLS fall behind with significantly lower performances of 0.43 and 0.3, respectively. |
2016 |
She, Bing ; Duque, Juan C; Ye, Xinyue The network-max-P-regions model Artículo de revista International Journal of Geographical Information Science, 31 (5), pp. 962-981, 2016, ISSN: 1362-3087. Resumen | Enlaces | BibTeX | Etiquetas: Análisis espacial, Diseño de regiones @article{she2017network, title = {The network-max-P-regions model}, author = {She, Bing and Duque, Juan C. and Ye, Xinyue}, url = {https://doi.org/10.1080/13658816.2016.1252987}, doi = {10.1080/13658816.2016.1252987}, issn = {1362-3087}, year = {2016}, date = {2016-11-04}, journal = {International Journal of Geographical Information Science}, volume = {31}, number = {5}, pages = {962-981}, abstract = {This paper introduces a new p-regions model called the Network-Max-P-Regions (NMPR) model. The NMPR is a regionalization model that aims to aggregate n areas into the maximum number of regions (max-p) that satisfy a threshold constraint and to minimize the heterogeneity while taking into account the influence of a street network. The exact formulation of the NMPR is presented, and a heuristic solution is proposed to effectively compute the near-optimized partitions in several simulation datasets and a case study in Wuhan, China.}, keywords = {Análisis espacial, Diseño de regiones}, pubstate = {published}, tppubtype = {article} } This paper introduces a new p-regions model called the Network-Max-P-Regions (NMPR) model. The NMPR is a regionalization model that aims to aggregate n areas into the maximum number of regions (max-p) that satisfy a threshold constraint and to minimize the heterogeneity while taking into account the influence of a street network. The exact formulation of the NMPR is presented, and a heuristic solution is proposed to effectively compute the near-optimized partitions in several simulation datasets and a case study in Wuhan, China. |
Duque, Juan C; Hierro, María Shocks and spatial regime fades in Spain's international migration distribution Artículo de revista International Migration, 54 (6), pp. 26-42, 2016, ISSN: 1468-2435. Resumen | Enlaces | BibTeX | Etiquetas: migración @article{duque2016shocks, title = {Shocks and spatial regime fades in Spain's international migration distribution}, author = {Duque, Juan C. and Hierro, María}, url = {https://doi.org/10.1111/imig.12254}, doi = {10.1111/imig.12254}, issn = {1468-2435}, year = {2016}, date = {2016-05-04}, journal = {International Migration}, volume = {54}, number = {6}, pages = {26-42}, abstract = {Using an exploratory space‐time analysis called spMorph, this article explores how the spatial distribution of international migration across the Spanish provinces has evolved over the period 1998‐2010. The chief advantage of this approach is that it permits the unambiguous identification of two key components in a spatial redistribution process, namely the shocks to the spatial distribution and the duration of regime fades. The results of the analysis show that administrative regions do not provide a reliable picture of the real dynamics in Spain's international migration distribution. In addition, the identification of two spatial shocks reveals the existence of three spatial regimes that consistently characterize the various phases that international migration has been through since the late 1990s.}, keywords = {migración}, pubstate = {published}, tppubtype = {article} } Using an exploratory space‐time analysis called spMorph, this article explores how the spatial distribution of international migration across the Spanish provinces has evolved over the period 1998‐2010. The chief advantage of this approach is that it permits the unambiguous identification of two key components in a spatial redistribution process, namely the shocks to the spatial distribution and the duration of regime fades. The results of the analysis show that administrative regions do not provide a reliable picture of the real dynamics in Spain's international migration distribution. In addition, the identification of two spatial shocks reveals the existence of three spatial regimes that consistently characterize the various phases that international migration has been through since the late 1990s. |
Ramos, Raul ; Duque, Juan C; Nieto, Sandra Decomposing the rural-urban differential in student achievement in Colombia using PISA microdata Artículo de revista Estudios de Economía Aplicada, 34 (2), pp. 379-412, 2016, ISSN: 1133-3197. Resumen | Enlaces | BibTeX | Etiquetas: educación @article{ramos2016decomposing, title = {Decomposing the rural-urban differential in student achievement in Colombia using PISA microdata}, author = {Ramos, Raul and Duque, Juan C. and Nieto, Sandra}, url = {http://ojs.ual.es/ojs/index.php/eea/article/view/3044}, doi = {10.25115/eae.v34i2.3044}, issn = {1133-3197}, year = {2016}, date = {2016-04-01}, journal = {Estudios de Economía Aplicada}, volume = {34}, number = {2}, pages = {379-412}, abstract = {This article examines the differences in educational outcomes between students attending schools in rural areas and those enrolled in urban schools in Colombia. Using microdata from the 2006, 2009 and 2012 PISA surveys, we find that educational outcomes of rural students are worse than those of urban ones. In order to identify the factors underpinning this differential, we apply decomposition methods and we find that most of the differential is attributable to family characteristics as opposed to those of the school. Our evidence supports the need to complement actions addressed to rural schools with policies improving household conditions.}, keywords = {educación}, pubstate = {published}, tppubtype = {article} } This article examines the differences in educational outcomes between students attending schools in rural areas and those enrolled in urban schools in Colombia. Using microdata from the 2006, 2009 and 2012 PISA surveys, we find that educational outcomes of rural students are worse than those of urban ones. In order to identify the factors underpinning this differential, we apply decomposition methods and we find that most of the differential is attributable to family characteristics as opposed to those of the school. Our evidence supports the need to complement actions addressed to rural schools with policies improving household conditions. |
2015 |
Duque, Juan C; Jetter, Michael ; Sosa, Santiago UN interventions: The role of geography Artículo de revista The Review of International Organizations, 10 (1), pp. 67-95, 2015, ISSN: 1559-7431. Resumen | Enlaces | BibTeX | Etiquetas: conflictos @article{duque2015interventions, title = {UN interventions: The role of geography}, author = {Duque, Juan C. and Jetter, Michael and Sosa, Santiago}, url = {https://doi.org/10.1007/s11558-014-9199-z}, doi = {10.1007/s11558-014-9199-z}, issn = {1559-7431}, year = {2015}, date = {2015-03-01}, journal = {The Review of International Organizations}, volume = {10}, number = {1}, pages = {67-95}, abstract = {This paper argues that UN military interventions are geographically biased. For every 1,000 kilometers of distance from the three permanent Western UNSC members (France, UK, US), the probability of a UN military intervention decreases by 4 percent. We are able to rule out several alternative explanations for the distance finding, such as differences by continent, colonial origin, bilateral trade relationships, foreign aid flows, political regime forms, or the characteristics of the Cold War. We do not observe this geographical bias for non-military interventions, providing evidence that practical considerations could be important factors for UNSC decisions to intervene militarily. In fact, UNSC interventions are also more likely in smaller and poorer countries – both of which are indications of less costly interventions and higher chances of success, everything else equal.}, keywords = {conflictos}, pubstate = {published}, tppubtype = {article} } This paper argues that UN military interventions are geographically biased. For every 1,000 kilometers of distance from the three permanent Western UNSC members (France, UK, US), the probability of a UN military intervention decreases by 4 percent. We are able to rule out several alternative explanations for the distance finding, such as differences by continent, colonial origin, bilateral trade relationships, foreign aid flows, political regime forms, or the characteristics of the Cold War. We do not observe this geographical bias for non-military interventions, providing evidence that practical considerations could be important factors for UNSC decisions to intervene militarily. In fact, UNSC interventions are also more likely in smaller and poorer countries – both of which are indications of less costly interventions and higher chances of success, everything else equal. |
Artículos de revista |
2021 |
Neighbourhood green space and health disparities in the global South: Evidence from Cali, Colombia Artículo de revista Health and Place, 72 (102690), pp. 1-9, 2021, ISSN: 1353-8292. |
Quality of life, health, and government perception during COVID-19 times: Data from Colombia Artículo de revista Data in Brief, 37 (107268), pp. 1-11, 2021, ISSN: 2352-3409. |
A paradox of traffic and extra cars in a city as a collective behaviour Artículo de revista R. Soc. Open Sci., 8 (6), pp. 17, 2021, ISSN: 2054-5703. |
A targeting policy for tackling inequality in the developing world: Lessons learned from the system of cross-subsidies to fund utilities in Colombia Artículo de revista Cities, 116 (103306), pp. 4, 2021, ISSN: 0264-2751. |
Built environment and mortality risk from cardiovascular disease and diabetes in Medellín, Colombia: An ecological study. Artículo de revista Landscape and Urban Planning, 213 (104126), pp. 12, 2021, ISBN: 0169-2046. |
Urban form and productivity: What shapes are Latin-American cities? Artículo de revista Environment and Planning B: Urban Analytics and City Science, 8697 , pp. 20, 2021, ISBN: 2399-8083. |
The heartbeat of the city Artículo de revista Plos One, 16 (2), pp. 30, 2021, ISBN: 1932-6203. |
Analyzing the Spatiotemporal Uncertainty in Urbanization Predictions Artículo de revista Remote Sensing, 13 (3), pp. 28, 2021, ISSN: 2072-4292. |
2020 |
Use of deep learning models in street-level images to classify one-story unreinforced masonry buildings based on roof diaphragms Artículo de revista Building and Environment, 189 (107517), pp. 1-10, 2020, ISSN: 0360-1323. |
A database to analyze cycling routes in Medellin, Colombia Artículo de revista Data in Brief, 32 (106162), pp. 1-14, 2020, ISSN: 2352-3409. |
Understanding cycling travel distance: The case of Medellin city (Colombia) Artículo de revista Transportation Research Part D: Transport and Environment, 86 (102423), pp. 1-22, 2020, ISSN: 1361-9209. |
Institutional fragmentation and metropolitan coordination in Latin American cities: Are there links with city productivity? Artículo de revista Regional Science Policy & Practice, pp. 1-33, 2020, ISSN: 1757-7802. |
Automatic detection of building typology using deep learning methods on street level image Artículo de revista Building and Environment, 177 (106805), pp. 1-12, 2020, ISSN: 0360-1323. |
Spatiotemporal Modeling of Urban Growth Using Machine Learning Artículo de revista Remote Sensing, 12(1) (109), pp. 1-41, 2020, ISSN: 2072-4292. |
2019 |
Spatiotemporal dynamics of urban growth in Latin American cities: An analysis using nighttime light imagery Artículo de revista Landscape and Urban Planning, 191 (103640), pp. 1-15, 2019, ISSN: 0169-2046. |
2018 |
S-maup: Statistical test to measure the sensitivity to the modifiable areal unit problem Artículo de revista PloS one, 13 (11), pp. 1-25, 2018, ISSN: 1932-6203. |
On the Performance of the Subtour Elimination Constraints Approach for the p-Regions Problem: A Computational Study Artículo de revista Geographical Analysis, 50 (1), pp. 32-52, 2018, ISSN: 1538-4632. |
2017 |
Exploring the potential of machine learning for automatic slum identification from VHR imagery Artículo de revista Remote Sensing, 9(9) (895), pp. 1-23, 2017, ISSN: 2072-4292. |
Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning Artículo de revista PloS one, 12 (4), pp. 1-25, 2017, ISSN: 1932-6203. |
2016 |
The network-max-P-regions model Artículo de revista International Journal of Geographical Information Science, 31 (5), pp. 962-981, 2016, ISSN: 1362-3087. |
Shocks and spatial regime fades in Spain's international migration distribution Artículo de revista International Migration, 54 (6), pp. 26-42, 2016, ISSN: 1468-2435. |
Decomposing the rural-urban differential in student achievement in Colombia using PISA microdata Artículo de revista Estudios de Economía Aplicada, 34 (2), pp. 379-412, 2016, ISSN: 1133-3197. |
2015 |
UN interventions: The role of geography Artículo de revista The Review of International Organizations, 10 (1), pp. 67-95, 2015, ISSN: 1559-7431. |