Cargando…
A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat
A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use/Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including five million harmoniz...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9308969/ https://www.ncbi.nlm.nih.gov/pubmed/35891647 http://dx.doi.org/10.7717/peerj.13573 |
_version_ | 1784753057084473344 |
---|---|
author | Witjes, Martijn Parente, Leandro van Diemen, Chris J. Hengl, Tomislav Landa, Martin Brodský, Lukáš Halounova, Lena Križan, Josip Antonić, Luka Ilie, Codrina Maria Craciunescu, Vasile Kilibarda, Milan Antonijević, Ognjen Glušica, Luka |
author_facet | Witjes, Martijn Parente, Leandro van Diemen, Chris J. Hengl, Tomislav Landa, Martin Brodský, Lukáš Halounova, Lena Križan, Josip Antonić, Luka Ilie, Codrina Maria Craciunescu, Vasile Kilibarda, Milan Antonijević, Ognjen Glušica, Luka |
author_sort | Witjes, Martijn |
collection | PubMed |
description | A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use/Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including five million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and model variance of predicted probabilities per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model consists of a random forest, gradient boosted tree classifier, and an artificial neural network, with a logistic regressor as meta-learner. The results show that the most important variables for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, long-term surface water probability, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with overall accuracy (a weighted F1-score) of 0.49, 0.63, and 0.83 when predicting 43 (level-3), 14 (level-2), and five classes (level-1). Additional experiments show that spatiotemporal models generalize better to unknown years, outperforming single-year models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest forest loss in large parts of Sweden, the Alps, and Scotland. Positive and negative trends in NDVI in general match the land degradation and land restoration classes, with “urbanization” showing the most negative NDVI trend. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict LULC for years prior to 2000 and beyond 2020. The generated LULC time-series data stack (ODSE-LULC), including the training points, is publicly available via the ODSE Viewer. Functions used to prepare data and run modeling are available via the eumap library for Python. |
format | Online Article Text |
id | pubmed-9308969 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-93089692022-07-25 A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat Witjes, Martijn Parente, Leandro van Diemen, Chris J. Hengl, Tomislav Landa, Martin Brodský, Lukáš Halounova, Lena Križan, Josip Antonić, Luka Ilie, Codrina Maria Craciunescu, Vasile Kilibarda, Milan Antonijević, Ognjen Glušica, Luka PeerJ Data Mining and Machine Learning A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use/Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including five million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and model variance of predicted probabilities per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model consists of a random forest, gradient boosted tree classifier, and an artificial neural network, with a logistic regressor as meta-learner. The results show that the most important variables for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, long-term surface water probability, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with overall accuracy (a weighted F1-score) of 0.49, 0.63, and 0.83 when predicting 43 (level-3), 14 (level-2), and five classes (level-1). Additional experiments show that spatiotemporal models generalize better to unknown years, outperforming single-year models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest forest loss in large parts of Sweden, the Alps, and Scotland. Positive and negative trends in NDVI in general match the land degradation and land restoration classes, with “urbanization” showing the most negative NDVI trend. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict LULC for years prior to 2000 and beyond 2020. The generated LULC time-series data stack (ODSE-LULC), including the training points, is publicly available via the ODSE Viewer. Functions used to prepare data and run modeling are available via the eumap library for Python. PeerJ Inc. 2022-07-21 /pmc/articles/PMC9308969/ /pubmed/35891647 http://dx.doi.org/10.7717/peerj.13573 Text en ©2022 Witjes et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
spellingShingle | Data Mining and Machine Learning Witjes, Martijn Parente, Leandro van Diemen, Chris J. Hengl, Tomislav Landa, Martin Brodský, Lukáš Halounova, Lena Križan, Josip Antonić, Luka Ilie, Codrina Maria Craciunescu, Vasile Kilibarda, Milan Antonijević, Ognjen Glušica, Luka A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title | A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title_full | A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title_fullStr | A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title_full_unstemmed | A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title_short | A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000–2019) based on LUCAS, CORINE and GLAD Landsat |
title_sort | spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for europe (2000–2019) based on lucas, corine and glad landsat |
topic | Data Mining and Machine Learning |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9308969/ https://www.ncbi.nlm.nih.gov/pubmed/35891647 http://dx.doi.org/10.7717/peerj.13573 |
work_keys_str_mv | AT witjesmartijn aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT parenteleandro aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT vandiemenchrisj aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT hengltomislav aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT landamartin aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT brodskylukas aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT halounovalena aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT krizanjosip aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT antonicluka aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT iliecodrinamaria aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT craciunescuvasile aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT kilibardamilan aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT antonijevicognjen aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT glusicaluka aspatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT witjesmartijn spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT parenteleandro spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT vandiemenchrisj spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT hengltomislav spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT landamartin spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT brodskylukas spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT halounovalena spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT krizanjosip spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT antonicluka spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT iliecodrinamaria spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT craciunescuvasile spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT kilibardamilan spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT antonijevicognjen spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat AT glusicaluka spatiotemporalensemblemachinelearningframeworkforgeneratinglanduselandcovertimeseriesmapsforeurope20002019basedonlucascorineandgladlandsat |