Cargando…
Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning
In this paper, different machine learning methodologies have been evaluated for the estimation of the multiple soil characteristics of a continental-wide area corresponding to the European region, using multispectral Sentinel-3 satellite imagery and digital elevation model (DEM) derivatives. The res...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10538194/ https://www.ncbi.nlm.nih.gov/pubmed/37765932 http://dx.doi.org/10.3390/s23187876 |
_version_ | 1785113270768631808 |
---|---|
author | Piccoli, Flavio Barbato, Mirko Paolo Peracchi, Marco Napoletano, Paolo |
author_facet | Piccoli, Flavio Barbato, Mirko Paolo Peracchi, Marco Napoletano, Paolo |
author_sort | Piccoli, Flavio |
collection | PubMed |
description | In this paper, different machine learning methodologies have been evaluated for the estimation of the multiple soil characteristics of a continental-wide area corresponding to the European region, using multispectral Sentinel-3 satellite imagery and digital elevation model (DEM) derivatives. The results confirm the importance of multispectral imagery in the estimation of soil properties and specifically show that the use of DEM derivatives improves the quality of the estimates, in terms of [Formula: see text] , by about 19% on average. In particular, the estimation of soil texture increases by about 43%, and that of cation exchange capacity (CEC) by about 65%. The importance of each input source (multispectral and DEM) in predicting the soil properties using machine learning has been traced back. It has been found that, overall, the use of multispectral features is more important than the use of DEM derivatives with a ration, on average, of 60% versus 40%. |
format | Online Article Text |
id | pubmed-10538194 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-105381942023-09-29 Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning Piccoli, Flavio Barbato, Mirko Paolo Peracchi, Marco Napoletano, Paolo Sensors (Basel) Article In this paper, different machine learning methodologies have been evaluated for the estimation of the multiple soil characteristics of a continental-wide area corresponding to the European region, using multispectral Sentinel-3 satellite imagery and digital elevation model (DEM) derivatives. The results confirm the importance of multispectral imagery in the estimation of soil properties and specifically show that the use of DEM derivatives improves the quality of the estimates, in terms of [Formula: see text] , by about 19% on average. In particular, the estimation of soil texture increases by about 43%, and that of cation exchange capacity (CEC) by about 65%. The importance of each input source (multispectral and DEM) in predicting the soil properties using machine learning has been traced back. It has been found that, overall, the use of multispectral features is more important than the use of DEM derivatives with a ration, on average, of 60% versus 40%. MDPI 2023-09-14 /pmc/articles/PMC10538194/ /pubmed/37765932 http://dx.doi.org/10.3390/s23187876 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Piccoli, Flavio Barbato, Mirko Paolo Peracchi, Marco Napoletano, Paolo Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title | Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title_full | Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title_fullStr | Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title_full_unstemmed | Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title_short | Estimation of Soil Characteristics from Multispectral Sentinel-3 Imagery and DEM Derivatives Using Machine Learning |
title_sort | estimation of soil characteristics from multispectral sentinel-3 imagery and dem derivatives using machine learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10538194/ https://www.ncbi.nlm.nih.gov/pubmed/37765932 http://dx.doi.org/10.3390/s23187876 |
work_keys_str_mv | AT piccoliflavio estimationofsoilcharacteristicsfrommultispectralsentinel3imageryanddemderivativesusingmachinelearning AT barbatomirkopaolo estimationofsoilcharacteristicsfrommultispectralsentinel3imageryanddemderivativesusingmachinelearning AT peracchimarco estimationofsoilcharacteristicsfrommultispectralsentinel3imageryanddemderivativesusingmachinelearning AT napoletanopaolo estimationofsoilcharacteristicsfrommultispectralsentinel3imageryanddemderivativesusingmachinelearning |