Supervised Regionalization Methods: A Survey

Duque, Juan Carlos; Ramos, Raúl; Suriñach, Jordi

doi:10.1177/0160017607301605

Cited by 250 publications

(176 citation statements)

References 72 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…These constraints impose that the spatial units within a region must be geographically connected. In this context, Duque et al (2007) make an interesting review of different techniques, grouping them with respect to the strategy applied for satisfying the spatial contiguity constraints, directly or indirectly expressed. Also, Jacquez (2008) and Aldstadt (2010) describe different approaches for spatial clustering, whereas Guo (2008) and Duque et al (2010) employ them in geographical sciences for the 2004 US presidential election data and georeferenced socio-demographic data in Accra, Ghana, respectively.…”

Section: Introductionmentioning

confidence: 99%

Functional zoning for air quality

2012

View full text Add to dashboard Cite

This paper presents a land classification in zones featured by different criticality levels of atmospheric pollution, considering pollutant time series as functional data: we call this proposal "Functional Zoning". We aim to meet a request of European laws that impose to distinguish zones needing further actions from those needing only maintenance according to air quality status. To carry out zoning for Piemonte (northern Italy), we consider the hourly concentration fields of the main pollutants produced by a deterministic air quality model, and we preprocess them by assimilating observations gathered by monitoring networks. In order to consider administrative units which policy makers refer to, we present three different alternatives to upscale data to municipality scale. Then, to aggregate by pollutant, we evaluate two strategies

show abstract

Section: Introductionmentioning

confidence: 99%

Functional zoning for air quality

2012

View full text Add to dashboard Cite

show abstract

“…Spatial contiguity can be modeled by creating a set (or cluster) of neighbors for each sample point. Contiguity-constrained classification imposes a constraint, which determines individuals or groups that can be joined to form a cluster (Openshaw, 1977, Ferligoj and Batagelj, 1982, Davidson and Basu 2007, Duque 2007. The third approach is to build a model that encompasses spatial information.…”

Section: Methodsmentioning

confidence: 99%

Supervised Machine Learning for Regionalization of Environmental Data: Distribution of Uranium in Groundwater in Ukraine

Govorov

Gienko

Putrenko³

2018

Proc. Int. Cartogr. Assoc.

View full text Add to dashboard Cite

Abstract:In this paper, several supervised machine learning algorithms were explored to define homogeneous regions of con-centration of uranium in surface waters in Ukraine using multiple environmental parameters. The previous study was focused on finding the primary environmental parameters related to uranium in ground waters using several methods of spatial statistics and unsupervised classification. At this step, we refined the regionalization using Artifi-cial Neural Networks (ANN) techniques including Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Convolutional Neural Network (CNN). The study is focused on building local ANN models which may significantly improve the prediction results of machine learning algorithms by taking into considerations non-stationarity and autocorrelation in spatial data.

show abstract

“…It is important to note that this subsection does not attempt to provide a survey of the different regionalization methods suggested in the literature nor to assess their relative performance. Literature reviews of regionalization methods have been done by Fischer (1980), Murtagh (1985, Gordon (1996Gordon ( , 1999 and Duque et al (2006).…”

Section: Spatial Aggregation Methodsmentioning

confidence: 99%

The ecological fallacy in a time series context: evidence from Spanish regional unemployment rates

2006

Self Cite

View full text Add to dashboard Cite

Abstract:The ecological fallacy (EF) is a common problem regional scientists have to deal with when using aggregated data in their analyses. Although there is a wide number of studies considering different aspects of this problem, little attention has been paid to the potential negative effects of the EF in a time series context. Using Spanish regional unemployment data, this paper shows that EF effects are not only observed at the cross-section level, but also in a time series framework. The empirical evidence obtained shows that analytical regional configurations are the least susceptible to time effects relative to both normative and random regional configurations, while normative configurations are an improvement over random ones.

show abstract

Supervised Regionalization Methods: A Survey

Cited by 250 publications

References 72 publications

Functional zoning for air quality

Functional zoning for air quality

Supervised Machine Learning for Regionalization of Environmental Data: Distribution of Uranium in Groundwater in Ukraine

The ecological fallacy in a time series context: evidence from Spanish regional unemployment rates

Contact Info

Product

Resources

About