There is a strong correlation between greenness and self-reported happiness. • The probability of... more There is a strong correlation between greenness and self-reported happiness. • The probability of reporting high levels of happiness also increases with age. • Gender and socioeconomic status don't relate significantly to happiness. • The quality of the green areas also matters and relates significantly to happiness. • Increasing greenness would raise the quality of life and well-being of the elderly.
This paper presents a general framework for modeling the growth of three important variables for ... more 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. ...
This paper presents a general framework for modeling the growth of three important variables for ... more 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. ...
This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in g... more 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 Fores...
ABSTRACT This paper introduces an exploratory space-time analysis tool for determining the two co... more ABSTRACT This paper introduces an exploratory space-time analysis tool for determining the two components of a spatial redistribution process: (i) the shock, which is the moment that triggers a spatial redistribution process; for example, a new policy, a war, an earthquake, etc.; and (ii) the duration of the regime fade, which is the time between the shock and the moment in which a new regime emerges as a better representation of the spatial distribution of the attribute. Two examples are provided: the first uses China's provincial per capita GDP between 1978 and 2008, and the second uses state level housing price and unemployment rate data for the US between 2002 and 2012.
Abstract The globalisation era in which we live has made the world an interconnected space with s... more Abstract The globalisation era in which we live has made the world an interconnected space with several global trends. We find developing countries with very high growth rates, what helps to find world economic convergence. As a complement to this trend, within those countries there is a dramatic growth pattern of cities into megacities, as economic activity concentrates in space to exploit agglomeration economies. According to UN-Habitat, in the next two decades the global population living in urban areas will move from 50% to 70%.
This article compares the German research in regional science in the period 1991-2000 with resear... more This article compares the German research in regional science in the period 1991-2000 with research that has been carried out internationally and in particular with that developed in continental Europe. We have dane this on the basis of the publications in a sample of nine top regional and urban international journals. We found that the publication patterns of German contributions were very similar to international patterns, though there were several interesting peculiarities. Results show that Germany’s share in regional and urban research is relatively high, fourth in the world.
S URIñACH J., D UQUE JC, R AMOS R. and R OYUELA V.(2003) Publication patterns in regional and urb... more S URIñACH J., D UQUE JC, R AMOS R. and R OYUELA V.(2003) Publication patterns in regional and urban analysis: have topics, techniques and applications changed during the 1990s?, Reg. Studies 37, 351-363. The current state of regional and urban science has been much discussed and a number of studies have speculated on possible future trends in the development of the discipline. However, there has been little empirical analysis of current publication patterns in regional and urban journals. This paper studies the kinds of ...
Page 1. The Max-p-Regions Problem Juan C. Duque 1 Research in Spatial Economics (RiSE). Departmen... more Page 1. The Max-p-Regions Problem Juan C. Duque 1 Research in Spatial Economics (RiSE). Department of Economics, EAFIT University. jduquec1@eafit.edu.co Luc Anselin GeoDa Center for Geospatial Anaysis and Computation ...
There is a strong correlation between greenness and self-reported happiness. • The probability of... more There is a strong correlation between greenness and self-reported happiness. • The probability of reporting high levels of happiness also increases with age. • Gender and socioeconomic status don't relate significantly to happiness. • The quality of the green areas also matters and relates significantly to happiness. • Increasing greenness would raise the quality of life and well-being of the elderly.
This paper presents a general framework for modeling the growth of three important variables for ... more 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. ...
This paper presents a general framework for modeling the growth of three important variables for ... more 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. ...
This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in g... more 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 Fores...
ABSTRACT This paper introduces an exploratory space-time analysis tool for determining the two co... more ABSTRACT This paper introduces an exploratory space-time analysis tool for determining the two components of a spatial redistribution process: (i) the shock, which is the moment that triggers a spatial redistribution process; for example, a new policy, a war, an earthquake, etc.; and (ii) the duration of the regime fade, which is the time between the shock and the moment in which a new regime emerges as a better representation of the spatial distribution of the attribute. Two examples are provided: the first uses China's provincial per capita GDP between 1978 and 2008, and the second uses state level housing price and unemployment rate data for the US between 2002 and 2012.
Abstract The globalisation era in which we live has made the world an interconnected space with s... more Abstract The globalisation era in which we live has made the world an interconnected space with several global trends. We find developing countries with very high growth rates, what helps to find world economic convergence. As a complement to this trend, within those countries there is a dramatic growth pattern of cities into megacities, as economic activity concentrates in space to exploit agglomeration economies. According to UN-Habitat, in the next two decades the global population living in urban areas will move from 50% to 70%.
This article compares the German research in regional science in the period 1991-2000 with resear... more This article compares the German research in regional science in the period 1991-2000 with research that has been carried out internationally and in particular with that developed in continental Europe. We have dane this on the basis of the publications in a sample of nine top regional and urban international journals. We found that the publication patterns of German contributions were very similar to international patterns, though there were several interesting peculiarities. Results show that Germany’s share in regional and urban research is relatively high, fourth in the world.
S URIñACH J., D UQUE JC, R AMOS R. and R OYUELA V.(2003) Publication patterns in regional and urb... more S URIñACH J., D UQUE JC, R AMOS R. and R OYUELA V.(2003) Publication patterns in regional and urban analysis: have topics, techniques and applications changed during the 1990s?, Reg. Studies 37, 351-363. The current state of regional and urban science has been much discussed and a number of studies have speculated on possible future trends in the development of the discipline. However, there has been little empirical analysis of current publication patterns in regional and urban journals. This paper studies the kinds of ...
Page 1. The Max-p-Regions Problem Juan C. Duque 1 Research in Spatial Economics (RiSE). Departmen... more Page 1. The Max-p-Regions Problem Juan C. Duque 1 Research in Spatial Economics (RiSE). Department of Economics, EAFIT University. jduquec1@eafit.edu.co Luc Anselin GeoDa Center for Geospatial Anaysis and Computation ...
Uploads
Papers by Juan Duque