Evaluation of machine learning algorithms to classify and map landforms in Antarctica
Abstract The detailed geomorphology of ice‐free landscapes of Antarctica is key to understanding how their highly fragile environments respond to climate change, at different temporal and spatial scales. Despite the recent advances in geomorphological studies of ice‐free areas, machine learning appl...
Published in: | Earth Surface Processes and Landforms |
---|---|
Main Authors: | , , , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2021
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/pdf/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/esp.5253 |
id |
crwiley:10.1002/esp.5253 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1002/esp.5253 2024-09-15T17:46:26+00:00 Evaluation of machine learning algorithms to classify and map landforms in Antarctica Siqueira, Rafael G. Veloso, Gustavo V. Fernandes‐Filho, Elpídio I. Francelino, Márcio R. Schaefer, Carlos Ernesto G. R. Corrêa, Guilherme R. Coordenação de Aperfeiçoamento de Pessoal de Nível Superior 2021 http://dx.doi.org/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/pdf/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/esp.5253 en eng Wiley http://onlinelibrary.wiley.com/termsAndConditions#vor Earth Surface Processes and Landforms volume 47, issue 2, page 367-382 ISSN 0197-9337 1096-9837 journal-article 2021 crwiley https://doi.org/10.1002/esp.5253 2024-07-25T04:24:07Z Abstract The detailed geomorphology of ice‐free landscapes of Antarctica is key to understanding how their highly fragile environments respond to climate change, at different temporal and spatial scales. Despite the recent advances in geomorphological studies of ice‐free areas, machine learning applications to produce landform maps are still scarce on the Antarctic continent. In this study, we evaluated the predictive performance of different supervised machine learning algorithms to produce digital geomorphological maps in Vega Island—Antarctic Peninsula region. We tested six different models: average artificial neural networks, C5.0 decision tree, random forest, support vector machine, supervised self‐organizing map and weighted k ‐nearest neighbours. We used an initial set of 54 geomorphometric and spectral predictors, from which redundant variables with Pearson correlation coefficient >|0.95| were removed, and only the most important predictors for each model were selected using recursive feature elimination. For training, we ran each model 100 times and predictions were assessed by the kappa and global accuracy values. The best predictors were the Red Edge 6 and SWIR 11 bands, roughness concentration index, elevation and drainage density. The decision trees C5.0 and random forest had the best performance, with average validation kappa of 0.85 ± 0.03 and 0.84 ± 0.03, respectively, evidencing excellent prediction. Despite the similar performance, random forest showed greater uncertainty degree and accuracy when classifying complex landforms, attesting to its great robustness. From sensitivity and specificity values, we observed that the glaciers and talus showed higher accuracy, whereas cryoplanated platforms and scree slopes had the worst classification. The presented methodology optimized the classification by selecting the most important predictors, assessing accuracy and evaluating uncertainty. The results indicated that machine learning methods have great potential to produce geomorphological mappings ... Article in Journal/Newspaper Antarc* Antarctic Antarctic Peninsula Antarctica Vega Island Wiley Online Library Earth Surface Processes and Landforms |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Abstract The detailed geomorphology of ice‐free landscapes of Antarctica is key to understanding how their highly fragile environments respond to climate change, at different temporal and spatial scales. Despite the recent advances in geomorphological studies of ice‐free areas, machine learning applications to produce landform maps are still scarce on the Antarctic continent. In this study, we evaluated the predictive performance of different supervised machine learning algorithms to produce digital geomorphological maps in Vega Island—Antarctic Peninsula region. We tested six different models: average artificial neural networks, C5.0 decision tree, random forest, support vector machine, supervised self‐organizing map and weighted k ‐nearest neighbours. We used an initial set of 54 geomorphometric and spectral predictors, from which redundant variables with Pearson correlation coefficient >|0.95| were removed, and only the most important predictors for each model were selected using recursive feature elimination. For training, we ran each model 100 times and predictions were assessed by the kappa and global accuracy values. The best predictors were the Red Edge 6 and SWIR 11 bands, roughness concentration index, elevation and drainage density. The decision trees C5.0 and random forest had the best performance, with average validation kappa of 0.85 ± 0.03 and 0.84 ± 0.03, respectively, evidencing excellent prediction. Despite the similar performance, random forest showed greater uncertainty degree and accuracy when classifying complex landforms, attesting to its great robustness. From sensitivity and specificity values, we observed that the glaciers and talus showed higher accuracy, whereas cryoplanated platforms and scree slopes had the worst classification. The presented methodology optimized the classification by selecting the most important predictors, assessing accuracy and evaluating uncertainty. The results indicated that machine learning methods have great potential to produce geomorphological mappings ... |
author2 |
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior |
format |
Article in Journal/Newspaper |
author |
Siqueira, Rafael G. Veloso, Gustavo V. Fernandes‐Filho, Elpídio I. Francelino, Márcio R. Schaefer, Carlos Ernesto G. R. Corrêa, Guilherme R. |
spellingShingle |
Siqueira, Rafael G. Veloso, Gustavo V. Fernandes‐Filho, Elpídio I. Francelino, Márcio R. Schaefer, Carlos Ernesto G. R. Corrêa, Guilherme R. Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
author_facet |
Siqueira, Rafael G. Veloso, Gustavo V. Fernandes‐Filho, Elpídio I. Francelino, Márcio R. Schaefer, Carlos Ernesto G. R. Corrêa, Guilherme R. |
author_sort |
Siqueira, Rafael G. |
title |
Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
title_short |
Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
title_full |
Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
title_fullStr |
Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
title_full_unstemmed |
Evaluation of machine learning algorithms to classify and map landforms in Antarctica |
title_sort |
evaluation of machine learning algorithms to classify and map landforms in antarctica |
publisher |
Wiley |
publishDate |
2021 |
url |
http://dx.doi.org/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/pdf/10.1002/esp.5253 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/esp.5253 |
genre |
Antarc* Antarctic Antarctic Peninsula Antarctica Vega Island |
genre_facet |
Antarc* Antarctic Antarctic Peninsula Antarctica Vega Island |
op_source |
Earth Surface Processes and Landforms volume 47, issue 2, page 367-382 ISSN 0197-9337 1096-9837 |
op_rights |
http://onlinelibrary.wiley.com/termsAndConditions#vor |
op_doi |
https://doi.org/10.1002/esp.5253 |
container_title |
Earth Surface Processes and Landforms |
_version_ |
1810494562434547712 |