Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach

Land use/land cover (LULC) is one of the most impactful global change phenomenon. As a result, considerable effort has been devoted to creating large-scale LULC products from remote sensing data, enabling the scientific community to use these products for a wide range of downstream applications. Unf...

Full description

Saved in:
Bibliographic Details
Main Authors: Denis Valle, Rodrigo Leite, Rafael Izbicki, Carlos Silva, Leo Haneda
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843224006447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053778884001792
author Denis Valle
Rodrigo Leite
Rafael Izbicki
Carlos Silva
Leo Haneda
author_facet Denis Valle
Rodrigo Leite
Rafael Izbicki
Carlos Silva
Leo Haneda
author_sort Denis Valle
collection DOAJ
description Land use/land cover (LULC) is one of the most impactful global change phenomenon. As a result, considerable effort has been devoted to creating large-scale LULC products from remote sensing data, enabling the scientific community to use these products for a wide range of downstream applications. Unfortunately, uncertainty associated with these products is seldom quantified because most approaches are too computationally intensive. Furthermore, uncertainty maps developed for large regions might fail to perform adequately at the spatial scale in which they will be used and might need to be customized to suit the specific applications of end-users.In this study, we describe the class-conditional conformal statistics method, an approach that quantifies uncertainty more uniformly for each class but that requires more calibration data than the conventional conformal method. Using the class-conditional method, we show that it is possible to create customized local uncertainty maps using local calibration data without requiring remote sensing and modeling work and that these local uncertainty maps outperform uncertainty maps calibrated based on global data. We use empirical data from Brazil (i.e., Dynamic World LULC product and Mapbiomas validation data) to demonstrate this methodology. The analysis of these data reveals substantial heterogeneity in observations of the same LULC class between Brazilian states, an indication that national-level data are not representative of the focal state, thus explaining why uncertainty maps calibrated using focal state-level data outperform maps calibrated using national-level data. Importantly, we develop straight-forward approaches to determine the spatial extent over which calibration data are still representative of the area of interest, ensuring that these data can be used to reliably quantify uncertainty. We illustrate the class-conformal methodology by creating uncertainty maps for a selected number of sites in Brazil. Finally, we show how these uncertainty maps can yield valuable insights for LULC map producers.Our methodology paves the way for users to generate customized local uncertainty maps that are likely to be better than uncertainty maps calibrated based on global data while at the same time being more relevant for the specific applications of these users. A tutorial is provided to show how this methodology can be implemented without requiring remote sensing and modeling expertise to generate uncertainty maps.
format Article
id doaj-art-81bb3b0b6f0a4d84aeae0bb1194a2180
institution DOAJ
issn 1569-8432
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-81bb3b0b6f0a4d84aeae0bb1194a21802025-08-20T02:52:27ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-12-0113510428810.1016/j.jag.2024.104288Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approachDenis Valle0Rodrigo Leite1Rafael Izbicki2Carlos Silva3Leo Haneda4School of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, FL, USA; Corresponding author.NASA Postdoctoral Program Fellow, Goddard Space Flight Center, Greenbelt, MD, USADepartment of Statistics, Federal University of Sao Carlos, Sao Paulo, BrazilSchool of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, FL, USASchool of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, FL, USALand use/land cover (LULC) is one of the most impactful global change phenomenon. As a result, considerable effort has been devoted to creating large-scale LULC products from remote sensing data, enabling the scientific community to use these products for a wide range of downstream applications. Unfortunately, uncertainty associated with these products is seldom quantified because most approaches are too computationally intensive. Furthermore, uncertainty maps developed for large regions might fail to perform adequately at the spatial scale in which they will be used and might need to be customized to suit the specific applications of end-users.In this study, we describe the class-conditional conformal statistics method, an approach that quantifies uncertainty more uniformly for each class but that requires more calibration data than the conventional conformal method. Using the class-conditional method, we show that it is possible to create customized local uncertainty maps using local calibration data without requiring remote sensing and modeling work and that these local uncertainty maps outperform uncertainty maps calibrated based on global data. We use empirical data from Brazil (i.e., Dynamic World LULC product and Mapbiomas validation data) to demonstrate this methodology. The analysis of these data reveals substantial heterogeneity in observations of the same LULC class between Brazilian states, an indication that national-level data are not representative of the focal state, thus explaining why uncertainty maps calibrated using focal state-level data outperform maps calibrated using national-level data. Importantly, we develop straight-forward approaches to determine the spatial extent over which calibration data are still representative of the area of interest, ensuring that these data can be used to reliably quantify uncertainty. We illustrate the class-conformal methodology by creating uncertainty maps for a selected number of sites in Brazil. Finally, we show how these uncertainty maps can yield valuable insights for LULC map producers.Our methodology paves the way for users to generate customized local uncertainty maps that are likely to be better than uncertainty maps calibrated based on global data while at the same time being more relevant for the specific applications of these users. A tutorial is provided to show how this methodology can be implemented without requiring remote sensing and modeling expertise to generate uncertainty maps.http://www.sciencedirect.com/science/article/pii/S1569843224006447Conformal statisticsClassification uncertaintyLand-use land-coverLULCImage classification
spellingShingle Denis Valle
Rodrigo Leite
Rafael Izbicki
Carlos Silva
Leo Haneda
Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
International Journal of Applied Earth Observations and Geoinformation
Conformal statistics
Classification uncertainty
Land-use land-cover
LULC
Image classification
title Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
title_full Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
title_fullStr Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
title_full_unstemmed Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
title_short Local uncertainty maps for land-use/land-cover classification without remote sensing and modeling work using a class-conditional conformal approach
title_sort local uncertainty maps for land use land cover classification without remote sensing and modeling work using a class conditional conformal approach
topic Conformal statistics
Classification uncertainty
Land-use land-cover
LULC
Image classification
url http://www.sciencedirect.com/science/article/pii/S1569843224006447
work_keys_str_mv AT denisvalle localuncertaintymapsforlanduselandcoverclassificationwithoutremotesensingandmodelingworkusingaclassconditionalconformalapproach
AT rodrigoleite localuncertaintymapsforlanduselandcoverclassificationwithoutremotesensingandmodelingworkusingaclassconditionalconformalapproach
AT rafaelizbicki localuncertaintymapsforlanduselandcoverclassificationwithoutremotesensingandmodelingworkusingaclassconditionalconformalapproach
AT carlossilva localuncertaintymapsforlanduselandcoverclassificationwithoutremotesensingandmodelingworkusingaclassconditionalconformalapproach
AT leohaneda localuncertaintymapsforlanduselandcoverclassificationwithoutremotesensingandmodelingworkusingaclassconditionalconformalapproach