Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data

Nitrogen is one of the key nutrients that indicate soil quality and an important component for plant development. Accurate knowledge and management of soil nitrogen is crucial for food security in rural communities, especially for smallholder maize farms. However, less research has been done on gene...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zinhle Mashaba-Munghemezulu, George Johannes Chirima, Cilence Munghemezulu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	satellite data random forest gradient boosting extreme gradient boosting soil fertility digital mapping Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/916003236adb4e26a2d5cd5f864d3971
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:916003236adb4e26a2d5cd5f864d3971
record_format	dspace
spelling	oai:doaj.org-article:916003236adb4e26a2d5cd5f864d39712021-11-11T19:21:29ZModeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data10.3390/su1321115912071-1050https://doaj.org/article/916003236adb4e26a2d5cd5f864d39712021-10-01T00:00:00Zhttps://www.mdpi.com/2071-1050/13/21/11591https://doaj.org/toc/2071-1050Nitrogen is one of the key nutrients that indicate soil quality and an important component for plant development. Accurate knowledge and management of soil nitrogen is crucial for food security in rural communities, especially for smallholder maize farms. However, less research has been done on generating digital soil nitrogen maps for these farmers. This study examines the utility of Sentinel-2 satellite data and environmental variables to map soil nitrogen at smallholder maize farms. Three machine learning algorithms—random forest (RF), gradient boosting (GB), and extreme gradient boosting (XG) were investigated for this purpose. The findings indicate that the RF (R<sup>2</sup> = 0.90, RMSE = 0.0076%) model performs slightly better than the GB (R<sup>2</sup> = 0.88, RMSE = 0.0083%) and XG (R<sup>2</sup> = 0.89, RMSE = 0.0077%) models. Furthermore, the variable importance measure showed that the Sentinel-2 bands, particularly the red and red-edge bands, have a superior performance in comparison to the environmental variables and soil indices. The digital maps generated in this study show the high capability of Sentinel-2 satellite data to generate accurate nitrogen content maps with the application of machine learning. The developed framework can be implemented to map the spatial pattern of soil nitrogen. This will also contribute to soil fertility interventions and nitrogen fertilization management to improve food security in rural communities. This application contributes to Sustainable Development Goal number 2.Zinhle Mashaba-MunghemezuluGeorge Johannes ChirimaCilence MunghemezuluMDPI AGarticlesatellite datarandom forestgradient boostingextreme gradient boostingsoil fertilitydigital mappingEnvironmental effects of industries and plantsTD194-195Renewable energy sourcesTJ807-830Environmental sciencesGE1-350ENSustainability, Vol 13, Iss 11591, p 11591 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	satellite data random forest gradient boosting extreme gradient boosting soil fertility digital mapping Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350
spellingShingle	satellite data random forest gradient boosting extreme gradient boosting soil fertility digital mapping Environmental effects of industries and plants TD194-195 Renewable energy sources TJ807-830 Environmental sciences GE1-350 Zinhle Mashaba-Munghemezulu George Johannes Chirima Cilence Munghemezulu Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
description	Nitrogen is one of the key nutrients that indicate soil quality and an important component for plant development. Accurate knowledge and management of soil nitrogen is crucial for food security in rural communities, especially for smallholder maize farms. However, less research has been done on generating digital soil nitrogen maps for these farmers. This study examines the utility of Sentinel-2 satellite data and environmental variables to map soil nitrogen at smallholder maize farms. Three machine learning algorithms—random forest (RF), gradient boosting (GB), and extreme gradient boosting (XG) were investigated for this purpose. The findings indicate that the RF (R<sup>2</sup> = 0.90, RMSE = 0.0076%) model performs slightly better than the GB (R<sup>2</sup> = 0.88, RMSE = 0.0083%) and XG (R<sup>2</sup> = 0.89, RMSE = 0.0077%) models. Furthermore, the variable importance measure showed that the Sentinel-2 bands, particularly the red and red-edge bands, have a superior performance in comparison to the environmental variables and soil indices. The digital maps generated in this study show the high capability of Sentinel-2 satellite data to generate accurate nitrogen content maps with the application of machine learning. The developed framework can be implemented to map the spatial pattern of soil nitrogen. This will also contribute to soil fertility interventions and nitrogen fertilization management to improve food security in rural communities. This application contributes to Sustainable Development Goal number 2.
format	article
author	Zinhle Mashaba-Munghemezulu George Johannes Chirima Cilence Munghemezulu
author_facet	Zinhle Mashaba-Munghemezulu George Johannes Chirima Cilence Munghemezulu
author_sort	Zinhle Mashaba-Munghemezulu
title	Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
title_short	Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
title_full	Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
title_fullStr	Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
title_full_unstemmed	Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data
title_sort	modeling the spatial distribution of soil nitrogen content at smallholder maize farms using machine learning regression and sentinel-2 data
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/916003236adb4e26a2d5cd5f864d3971
work_keys_str_mv	AT zinhlemashabamunghemezulu modelingthespatialdistributionofsoilnitrogencontentatsmallholdermaizefarmsusingmachinelearningregressionandsentinel2data AT georgejohanneschirima modelingthespatialdistributionofsoilnitrogencontentatsmallholdermaizefarmsusingmachinelearningregressionandsentinel2data AT cilencemunghemezulu modelingthespatialdistributionofsoilnitrogencontentatsmallholdermaizefarmsusingmachinelearningregressionandsentinel2data
_version_	1718431539390316544

Modeling the Spatial Distribution of Soil Nitrogen Content at Smallholder Maize Farms Using Machine Learning Regression and Sentinel-2 Data

Ejemplares similares