Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data
Recent years have seen an increase in the use of remote-sensing based methods to assess soil erosion, mainly due to the availability of freely accessible satellite data, with successful results on a consistent basis. There would be valuable benefits from applying these techniques to the Arctic areas...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15020482 https://doaj.org/article/fde8dd649dfa42b88dd87e461741029c |
id |
ftdoajarticles:oai:doaj.org/article:fde8dd649dfa42b88dd87e461741029c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:fde8dd649dfa42b88dd87e461741029c 2023-05-15T14:57:42+02:00 Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data Daniel Fernández Eromanga Adermann Marco Pizzolato Roman Pechenkin Christina G. Rodríguez Alireza Taravat 2023-01-01T00:00:00Z https://doi.org/10.3390/rs15020482 https://doaj.org/article/fde8dd649dfa42b88dd87e461741029c EN eng MDPI AG https://www.mdpi.com/2072-4292/15/2/482 https://doaj.org/toc/2072-4292 doi:10.3390/rs15020482 2072-4292 https://doaj.org/article/fde8dd649dfa42b88dd87e461741029c Remote Sensing, Vol 15, Iss 482, p 482 (2023) soil erosion Sentinel-2 remote sensing machine learning support vector machine random forest Science Q article 2023 ftdoajarticles https://doi.org/10.3390/rs15020482 2023-01-22T01:26:17Z Recent years have seen an increase in the use of remote-sensing based methods to assess soil erosion, mainly due to the availability of freely accessible satellite data, with successful results on a consistent basis. There would be valuable benefits from applying these techniques to the Arctic areas, where ground local studies are typically difficult to perform due to hardly accessible roads and lands. At the same time, however, the application of remote-sensing methods comes with its own set of challenges when it comes to the peculiar features of the Arctic: short growing periods, winter storms, wind, and frequent cloud and snow cover. In this study we perform a comparative analysis of three commonly used classification algorithms: Support Vector Machine (SVM), Random Forest (RF) and Multilayer Perceptron (MLP), in combination with ground truth samples from regions all over Iceland, provided by Iceland’s Soil Conservation Service department. The process can be automated to predict soil erosion risk for larger, less accessible areas from Sentinel-2 images. The analysis performed on validation data sets supports the effectiveness of both approaches for modeling soil erosion, albeit differences are highlighted. Article in Journal/Newspaper Arctic Iceland Directory of Open Access Journals: DOAJ Articles Arctic Remote Sensing 15 2 482 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
soil erosion Sentinel-2 remote sensing machine learning support vector machine random forest Science Q |
spellingShingle |
soil erosion Sentinel-2 remote sensing machine learning support vector machine random forest Science Q Daniel Fernández Eromanga Adermann Marco Pizzolato Roman Pechenkin Christina G. Rodríguez Alireza Taravat Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
topic_facet |
soil erosion Sentinel-2 remote sensing machine learning support vector machine random forest Science Q |
description |
Recent years have seen an increase in the use of remote-sensing based methods to assess soil erosion, mainly due to the availability of freely accessible satellite data, with successful results on a consistent basis. There would be valuable benefits from applying these techniques to the Arctic areas, where ground local studies are typically difficult to perform due to hardly accessible roads and lands. At the same time, however, the application of remote-sensing methods comes with its own set of challenges when it comes to the peculiar features of the Arctic: short growing periods, winter storms, wind, and frequent cloud and snow cover. In this study we perform a comparative analysis of three commonly used classification algorithms: Support Vector Machine (SVM), Random Forest (RF) and Multilayer Perceptron (MLP), in combination with ground truth samples from regions all over Iceland, provided by Iceland’s Soil Conservation Service department. The process can be automated to predict soil erosion risk for larger, less accessible areas from Sentinel-2 images. The analysis performed on validation data sets supports the effectiveness of both approaches for modeling soil erosion, albeit differences are highlighted. |
format |
Article in Journal/Newspaper |
author |
Daniel Fernández Eromanga Adermann Marco Pizzolato Roman Pechenkin Christina G. Rodríguez Alireza Taravat |
author_facet |
Daniel Fernández Eromanga Adermann Marco Pizzolato Roman Pechenkin Christina G. Rodríguez Alireza Taravat |
author_sort |
Daniel Fernández |
title |
Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
title_short |
Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
title_full |
Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
title_fullStr |
Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
title_full_unstemmed |
Comparative Analysis of Machine Learning Algorithms for Soil Erosion Modelling Based on Remotely Sensed Data |
title_sort |
comparative analysis of machine learning algorithms for soil erosion modelling based on remotely sensed data |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15020482 https://doaj.org/article/fde8dd649dfa42b88dd87e461741029c |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Iceland |
genre_facet |
Arctic Iceland |
op_source |
Remote Sensing, Vol 15, Iss 482, p 482 (2023) |
op_relation |
https://www.mdpi.com/2072-4292/15/2/482 https://doaj.org/toc/2072-4292 doi:10.3390/rs15020482 2072-4292 https://doaj.org/article/fde8dd649dfa42b88dd87e461741029c |
op_doi |
https://doi.org/10.3390/rs15020482 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
2 |
container_start_page |
482 |
_version_ |
1766329836041666560 |