Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America

The impact of land cover change across the planet continues to necessitate accurate methods to detect and monitor evolving processes from satellite imagery. In this context, regional and global land cover mapping over time has largely treated time as independent and addressed temporal map consistenc...

Full description

Bibliographic Details
Main Authors: Graesser, Jordan, Stanimirova, Radost, Tarrio, Katelyn, Copati, Esteban J., Volante, Jose Norberto, Veron, Santiago Ramón, Banchero, Santiago, Elena, Hernan Javier, De Abelleyra, Diego, Friedl, Mark A.
Format: Artículo
Language:Inglés
Published: MDPI 2022
Subjects:
Online Access:http://hdl.handle.net/20.500.12123/12812
https://www.mdpi.com/2072-4292/14/16/4005
https://doi.org/10.3390/rs14164005
_version_ 1855485049009340416
author Graesser, Jordan
Stanimirova, Radost
Tarrio, Katelyn
Copati, Esteban J.
Volante, Jose Norberto
Veron, Santiago Ramón
Banchero, Santiago
Elena, Hernan Javier
De Abelleyra, Diego
Friedl, Mark A.
author_browse Banchero, Santiago
Copati, Esteban J.
De Abelleyra, Diego
Elena, Hernan Javier
Friedl, Mark A.
Graesser, Jordan
Stanimirova, Radost
Tarrio, Katelyn
Veron, Santiago Ramón
Volante, Jose Norberto
author_facet Graesser, Jordan
Stanimirova, Radost
Tarrio, Katelyn
Copati, Esteban J.
Volante, Jose Norberto
Veron, Santiago Ramón
Banchero, Santiago
Elena, Hernan Javier
De Abelleyra, Diego
Friedl, Mark A.
author_sort Graesser, Jordan
collection INTA Digital
description The impact of land cover change across the planet continues to necessitate accurate methods to detect and monitor evolving processes from satellite imagery. In this context, regional and global land cover mapping over time has largely treated time as independent and addressed temporal map consistency as a post-classification endeavor. However, we argue that time can be better modeled as codependent during the model classification stage to produce more consistent land cover estimates over long time periods and gradual change events. To produce temporally-dependent land cover estimates—meaning land cover is predicted over time in connected sequences as opposed to predictions made for a given time period without consideration of past land cover—we use structured learning with conditional random fields (CRFs), coupled with a land cover augmentation method to produce time series training data and bi-weekly Landsat imagery over 20 years (1999–2018) across the Southern Cone region of South America. A CRF accounts for the natural dependencies of land change processes. As a result, it is able to produce land cover estimates over time that better reflect real change and stability by reducing pixel-level annual noise. Using CRF, we produced a twenty-year dataset of land cover over the region, depicting key change processes such as cropland expansion and tree cover loss at the Landsat scale. The augmentation and CRF approach introduced here provides a more temporally consistent land cover product over traditional mapping methods.
format Artículo
id INTA12812
institution Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina)
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher MDPI
publisherStr MDPI
record_format dspace
spelling INTA128122022-09-07T13:34:07Z Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America Graesser, Jordan Stanimirova, Radost Tarrio, Katelyn Copati, Esteban J. Volante, Jose Norberto Veron, Santiago Ramón Banchero, Santiago Elena, Hernan Javier De Abelleyra, Diego Friedl, Mark A. Cobertura de Suelos Alteración de la Cubierta Vegetal Teledetección Imágenes por Satélites América del Sur Land Cover Land Cover Change Landsat Remote Sensing Satellite Imagery South America Imágenes de Landsat The impact of land cover change across the planet continues to necessitate accurate methods to detect and monitor evolving processes from satellite imagery. In this context, regional and global land cover mapping over time has largely treated time as independent and addressed temporal map consistency as a post-classification endeavor. However, we argue that time can be better modeled as codependent during the model classification stage to produce more consistent land cover estimates over long time periods and gradual change events. To produce temporally-dependent land cover estimates—meaning land cover is predicted over time in connected sequences as opposed to predictions made for a given time period without consideration of past land cover—we use structured learning with conditional random fields (CRFs), coupled with a land cover augmentation method to produce time series training data and bi-weekly Landsat imagery over 20 years (1999–2018) across the Southern Cone region of South America. A CRF accounts for the natural dependencies of land change processes. As a result, it is able to produce land cover estimates over time that better reflect real change and stability by reducing pixel-level annual noise. Using CRF, we produced a twenty-year dataset of land cover over the region, depicting key change processes such as cropland expansion and tree cover loss at the Landsat scale. The augmentation and CRF approach introduced here provides a more temporally consistent land cover product over traditional mapping methods. EEA Salta Fil: Graesser, Jordan. Boston University. Department of Earth and Environment; Estados Unidos Fil: Stanimirova, Radost. Boston University. Department of Earth and Environment; Estados Unidos Fil: Tarrio, Katelyn. Boston University. Department of Earth and Environment; Estados Unidos Fil: Copati, Esteban J. Bolsa de Cereales (Buenos Aires); Argentina Fil: Volante, J. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Salta; Argentina Fil: Verón, S. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina Fil: Verón, Sebastian. Universidad de Buenos Aires. Facultad de Agronomía; Argentina Fil: Verón, Sebastian. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina Fil: Banchero, S. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina Fil: Elena, Hernan Javier. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Salta; Argentina Fil: Abelleyra, D. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina Fil: Friedl, Mark A. Boston University. Department of Earth and Environment; Estados Unidos 2022-09-07T13:30:46Z 2022-09-07T13:30:46Z 2022-08 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/12812 https://www.mdpi.com/2072-4292/14/16/4005 2072-4292 https://doi.org/10.3390/rs14164005 eng info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf MDPI Remote Sensing 14 (16) : 4005. (August 2022)
spellingShingle Cobertura de Suelos
Alteración de la Cubierta Vegetal
Teledetección
Imágenes por Satélites
América del Sur
Land Cover
Land Cover Change
Landsat
Remote Sensing
Satellite Imagery
South America
Imágenes de Landsat
Graesser, Jordan
Stanimirova, Radost
Tarrio, Katelyn
Copati, Esteban J.
Volante, Jose Norberto
Veron, Santiago Ramón
Banchero, Santiago
Elena, Hernan Javier
De Abelleyra, Diego
Friedl, Mark A.
Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title_full Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title_fullStr Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title_full_unstemmed Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title_short Temporally-Consistent Annual Land Cover from Landsat Time Series in the Southern Cone of South America
title_sort temporally consistent annual land cover from landsat time series in the southern cone of south america
topic Cobertura de Suelos
Alteración de la Cubierta Vegetal
Teledetección
Imágenes por Satélites
América del Sur
Land Cover
Land Cover Change
Landsat
Remote Sensing
Satellite Imagery
South America
Imágenes de Landsat
url http://hdl.handle.net/20.500.12123/12812
https://www.mdpi.com/2072-4292/14/16/4005
https://doi.org/10.3390/rs14164005
work_keys_str_mv AT graesserjordan temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT stanimirovaradost temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT tarriokatelyn temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT copatiestebanj temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT volantejosenorberto temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT veronsantiagoramon temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT bancherosantiago temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT elenahernanjavier temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT deabelleyradiego temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica
AT friedlmarka temporallyconsistentannuallandcoverfromlandsattimeseriesinthesouthernconeofsouthamerica