EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH
Regional climate is a critical factor in public health research, adaptation studies, climate change burden analysis, and decision support frameworks. Existing climate regionalization schemes are not well suited for these tasks as they rarely take population density into account. In this work, we are...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2016-06-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B8/209/2016/isprs-archives-XLI-B8-209-2016.pdf |
_version_ | 1818193852981313536 |
---|---|
author | A. Liss Y. R. Gel A. Kulinkina E. N. Naumova E. N. Naumova |
author_facet | A. Liss Y. R. Gel A. Kulinkina E. N. Naumova E. N. Naumova |
author_sort | A. Liss |
collection | DOAJ |
description | Regional climate is a critical factor in public health research, adaptation studies, climate change burden analysis, and decision support frameworks. Existing climate regionalization schemes are not well suited for these tasks as they rarely take population density into account. In this work, we are extending our recently developed method for automated climate regionalization (LKN-method) to incorporate the spatial features of target population. The LKN method consists of the data limiting step (L-step) to reduce dimensionality by applying principal component analysis, a classification step (K-step) to produce hierarchical candidate regions using k-means unsupervised classification algorithm, and a nomination step (N-step) to determine the number of candidate climate regions using cluster validity indexes. LKN method uses a comprehensive set of multiple satellite data streams, arranged as time series, and allows us to define homogeneous climate regions. The proposed approach extends the LKN method to include regularization terms reflecting the spatial distribution of target population. Such tailoring allows us to determine the optimal number and spatial distribution of climate regions and thus, to ensure more uniform population coverage across selected climate categories. We demonstrate how the extended LKN method produces climate regionalization can be better tailored to epidemiological research in the context of decision support framework. |
first_indexed | 2024-12-12T00:52:59Z |
format | Article |
id | doaj.art-3edcba7dd39c4906b02fbbcd3ece4bbc |
institution | Directory Open Access Journal |
issn | 1682-1750 2194-9034 |
language | English |
last_indexed | 2024-12-12T00:52:59Z |
publishDate | 2016-06-01 |
publisher | Copernicus Publications |
record_format | Article |
series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
spelling | doaj.art-3edcba7dd39c4906b02fbbcd3ece4bbc2022-12-22T00:43:57ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342016-06-01XLI-B820921310.5194/isprs-archives-XLI-B8-209-2016EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCHA. Liss0Y. R. Gel1A. Kulinkina2E. N. Naumova3E. N. Naumova4Department of Civil and Environmental Engineering, Tufts University, Medford, USAUniversity of Texas, Dallas, USADepartment of Civil and Environmental Engineering, Tufts University, Medford, USADepartment of Civil and Environmental Engineering, Tufts University, Medford, USAFriedman School of Nutrition Science and Policy, Tufts University, Boston, USARegional climate is a critical factor in public health research, adaptation studies, climate change burden analysis, and decision support frameworks. Existing climate regionalization schemes are not well suited for these tasks as they rarely take population density into account. In this work, we are extending our recently developed method for automated climate regionalization (LKN-method) to incorporate the spatial features of target population. The LKN method consists of the data limiting step (L-step) to reduce dimensionality by applying principal component analysis, a classification step (K-step) to produce hierarchical candidate regions using k-means unsupervised classification algorithm, and a nomination step (N-step) to determine the number of candidate climate regions using cluster validity indexes. LKN method uses a comprehensive set of multiple satellite data streams, arranged as time series, and allows us to define homogeneous climate regions. The proposed approach extends the LKN method to include regularization terms reflecting the spatial distribution of target population. Such tailoring allows us to determine the optimal number and spatial distribution of climate regions and thus, to ensure more uniform population coverage across selected climate categories. We demonstrate how the extended LKN method produces climate regionalization can be better tailored to epidemiological research in the context of decision support framework.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B8/209/2016/isprs-archives-XLI-B8-209-2016.pdf |
spellingShingle | A. Liss Y. R. Gel A. Kulinkina E. N. Naumova E. N. Naumova EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
title | EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH |
title_full | EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH |
title_fullStr | EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH |
title_full_unstemmed | EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH |
title_short | EXTENDING LKN CLIMATE REGIONALIZATION WITH SPATIAL REGULARIZATION: AN APPLICATION TO EPIDEMIOLOGICAL RESEARCH |
title_sort | extending lkn climate regionalization with spatial regularization an application to epidemiological research |
url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B8/209/2016/isprs-archives-XLI-B8-209-2016.pdf |
work_keys_str_mv | AT aliss extendinglknclimateregionalizationwithspatialregularizationanapplicationtoepidemiologicalresearch AT yrgel extendinglknclimateregionalizationwithspatialregularizationanapplicationtoepidemiologicalresearch AT akulinkina extendinglknclimateregionalizationwithspatialregularizationanapplicationtoepidemiologicalresearch AT ennaumova extendinglknclimateregionalizationwithspatialregularizationanapplicationtoepidemiologicalresearch AT ennaumova extendinglknclimateregionalizationwithspatialregularizationanapplicationtoepidemiologicalresearch |