Estimation of Soil Nutrient Content Using Hyperspectral Data

Soil nutrients play a vital role in plant growth and thus the rapid acquisition of soil nutrient content is of great significance for agricultural sustainable development. Hyperspectral remote-sensing techniques allow for the quick monitoring of soil nutrients. However, at present, obtaining accurat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yiping Peng, Lu Wang, Li Zhao, Zhenhua Liu, Chenjie Lin, Yueming Hu, Luo Liu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	VIS-NIR spectroscopy screening algorithm estimation model HJ-1A imagery Agriculture (General) S1-972
Acceso en línea:	https://doaj.org/article/aa57121ca6064862a64e8ecc0515d66d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:aa57121ca6064862a64e8ecc0515d66d
record_format	dspace
spelling	oai:doaj.org-article:aa57121ca6064862a64e8ecc0515d66d2021-11-25T15:59:45ZEstimation of Soil Nutrient Content Using Hyperspectral Data10.3390/agriculture111111292077-0472https://doaj.org/article/aa57121ca6064862a64e8ecc0515d66d2021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0472/11/11/1129https://doaj.org/toc/2077-0472Soil nutrients play a vital role in plant growth and thus the rapid acquisition of soil nutrient content is of great significance for agricultural sustainable development. Hyperspectral remote-sensing techniques allow for the quick monitoring of soil nutrients. However, at present, obtaining accurate estimates proves to be difficult due to the weak spectral features of soil nutrients and the low accuracy of soil nutrient estimation models. This study proposed a new method to improve soil nutrient estimation. Firstly, for obtaining characteristic variables, we employed partial least squares regression (PLSR) fit degree to select an optimal screening algorithm from three algorithms (Pearson correlation coefficient, PCC; least absolute shrinkage and selection operator, LASSO; and gradient boosting decision tree, GBDT). Secondly, linear (multi-linear regression, MLR; ridge regression, RR) and nonlinear (support vector machine, SVM; and back propagation neural network with genetic algorithm optimization, GABP) algorithms with 10-fold cross-validation were implemented to determine the most accurate model for estimating soil total nitrogen (TN), total phosphorus (TP), and total potassium (TK) contents. Finally, the new method was used to map the soil TK content at a regional scale using the soil component spectral variables retrieved by the fully constrained least squares (FCLS) method based on an image from the HuanJing-1A Hyperspectral Imager (HJ-1A HSI) of the Conghua District of Guangzhou, China. The results identified the GBDT-GABP was observed as the most accurate estimation method of soil TN ( of 0.69, the root mean square error of cross-validation (RMSECV) of 0.35 g kg<sup>−1</sup> and ratio of performance to interquartile range (RPIQ) of 2.03) and TP ( of 0.73, RMSECV of 0.30 g kg<sup>−1</sup> and RPIQ = 2.10), and the LASSO-GABP proved to be optimal for soil TK estimations ( of 0.82, RMSECV of 3.39 g kg<sup>−1</sup> and RPIQ = 3.57). Additionally, the highly accurate LASSO-GABP-estimated soil TK (R<sup>2</sup> = 0.79) reveals the feasibility of the LASSO-GABP method to retrieve soil TK content at the regional scale.Yiping PengLu WangLi ZhaoZhenhua LiuChenjie LinYueming HuLuo LiuMDPI AGarticleVIS-NIR spectroscopyscreening algorithmestimation modelHJ-1A imageryAgriculture (General)S1-972ENAgriculture, Vol 11, Iss 1129, p 1129 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	VIS-NIR spectroscopy screening algorithm estimation model HJ-1A imagery Agriculture (General) S1-972
spellingShingle	VIS-NIR spectroscopy screening algorithm estimation model HJ-1A imagery Agriculture (General) S1-972 Yiping Peng Lu Wang Li Zhao Zhenhua Liu Chenjie Lin Yueming Hu Luo Liu Estimation of Soil Nutrient Content Using Hyperspectral Data
description	Soil nutrients play a vital role in plant growth and thus the rapid acquisition of soil nutrient content is of great significance for agricultural sustainable development. Hyperspectral remote-sensing techniques allow for the quick monitoring of soil nutrients. However, at present, obtaining accurate estimates proves to be difficult due to the weak spectral features of soil nutrients and the low accuracy of soil nutrient estimation models. This study proposed a new method to improve soil nutrient estimation. Firstly, for obtaining characteristic variables, we employed partial least squares regression (PLSR) fit degree to select an optimal screening algorithm from three algorithms (Pearson correlation coefficient, PCC; least absolute shrinkage and selection operator, LASSO; and gradient boosting decision tree, GBDT). Secondly, linear (multi-linear regression, MLR; ridge regression, RR) and nonlinear (support vector machine, SVM; and back propagation neural network with genetic algorithm optimization, GABP) algorithms with 10-fold cross-validation were implemented to determine the most accurate model for estimating soil total nitrogen (TN), total phosphorus (TP), and total potassium (TK) contents. Finally, the new method was used to map the soil TK content at a regional scale using the soil component spectral variables retrieved by the fully constrained least squares (FCLS) method based on an image from the HuanJing-1A Hyperspectral Imager (HJ-1A HSI) of the Conghua District of Guangzhou, China. The results identified the GBDT-GABP was observed as the most accurate estimation method of soil TN ( of 0.69, the root mean square error of cross-validation (RMSECV) of 0.35 g kg<sup>−1</sup> and ratio of performance to interquartile range (RPIQ) of 2.03) and TP ( of 0.73, RMSECV of 0.30 g kg<sup>−1</sup> and RPIQ = 2.10), and the LASSO-GABP proved to be optimal for soil TK estimations ( of 0.82, RMSECV of 3.39 g kg<sup>−1</sup> and RPIQ = 3.57). Additionally, the highly accurate LASSO-GABP-estimated soil TK (R<sup>2</sup> = 0.79) reveals the feasibility of the LASSO-GABP method to retrieve soil TK content at the regional scale.
format	article
author	Yiping Peng Lu Wang Li Zhao Zhenhua Liu Chenjie Lin Yueming Hu Luo Liu
author_facet	Yiping Peng Lu Wang Li Zhao Zhenhua Liu Chenjie Lin Yueming Hu Luo Liu
author_sort	Yiping Peng
title	Estimation of Soil Nutrient Content Using Hyperspectral Data
title_short	Estimation of Soil Nutrient Content Using Hyperspectral Data
title_full	Estimation of Soil Nutrient Content Using Hyperspectral Data
title_fullStr	Estimation of Soil Nutrient Content Using Hyperspectral Data
title_full_unstemmed	Estimation of Soil Nutrient Content Using Hyperspectral Data
title_sort	estimation of soil nutrient content using hyperspectral data
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/aa57121ca6064862a64e8ecc0515d66d
work_keys_str_mv	AT yipingpeng estimationofsoilnutrientcontentusinghyperspectraldata AT luwang estimationofsoilnutrientcontentusinghyperspectraldata AT lizhao estimationofsoilnutrientcontentusinghyperspectraldata AT zhenhualiu estimationofsoilnutrientcontentusinghyperspectraldata AT chenjielin estimationofsoilnutrientcontentusinghyperspectraldata AT yueminghu estimationofsoilnutrientcontentusinghyperspectraldata AT luoliu estimationofsoilnutrientcontentusinghyperspectraldata
_version_	1718413398931144704

Estimation of Soil Nutrient Content Using Hyperspectral Data

Ejemplares similares