Prediction of lead in agricultural soils: An integrated approach using machine learning, terrain attributes and reflectance spectra

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41210%2F25%3A103037" target="_blank" >RIV/60460709:41210/25:103037 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.pedsph.2024.01.002" target="_blank" >https://doi.org/10.1016/j.pedsph.2024.01.002</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.pedsph.2024.01.002" target="_blank" >10.1016/j.pedsph.2024.01.002</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Prediction of lead in agricultural soils: An integrated approach using machine learning, terrain attributes and reflectance spectra

Popis výsledku v původním jazyce

Very few studies have benefited from the synergetic implementation of visible, near-infrared, and shortwave infrared (VNIR-SWIR) spectra and terrain attributes in predicting Pb content in agricultural soils. To fill this gap, this study aimed to predict lead (Pb) contents in agricultural soils by combining machine learning algorithms (MLAs) with VNIR-SWIR spectra or/and terrain attributes under three distinct approaches. Six MLAs were tested, including artificial neural network (ANN), partial least squares regression, support vector machine (SVM), Gaussian process regression (GPR), extreme gradient boosting (EGB), and Cubist. The VNIR-SWIR spectral data were preprocessed by methods of discrete wavelet transformation, logarithmic transformation-Savitzky Golay smoothing, standard normal variate (SNV), multiplicative scatter correction, first derivative (FiD), and second derivative. In approach 1, MLAs were combined with the preprocessed VNIR-SWIR spectral data. The Cubist-FiD combination was the most effective, achieving a coefficient of determination (H2) of 0.63, a concordance correlation coefficient (CCC) of 0.51, a mean absolute error (MAE) of 6.87 mg kg-1, and a root mean square error (RMSE) of 8.66 mg kg-1. In approach 2, MLAs were combined with both preprocessed VNIR-SWIR spectral data and terrain attributes, and the EGB-SNV combination yielded superior results with H2 of 0.75, CCC of 0.65, MAE of 5.48 mg kg-1, and RMSE of 7.34 mg kg-1. Approach 3 combined MLAs and terrain attributes, and Cubist demonstrated the best prediction results, with H2 of 0.75, CCC of 0.66, MAE of 6.18 mg kg-1, and RMSE of 7.71 mg kg-1. The cumulative assessment identified the fusion of terrain properties, SNV-preprocessed VNIR-SWIR spectra, and EGB as the optimal method for estimating Pb content in agricultural soils, yielding the highest H2 value and minimal error. Comparatively, GPR, ANN, and SVM techniques achieved higher H2 values in approaches 2 and 3 but also exhibited higher estimation errors. In conclusion, the study underscores the significance of using relevant auxiliary datasets and appropriate MLAs for accurate Pb content prediction with minimal error in agricultural soils. The findings contribute valuable insights for developing successful soil management strategies based on predictive modeling.

Název v anglickém jazyce

Prediction of lead in agricultural soils: An integrated approach using machine learning, terrain attributes and reflectance spectra

Popis výsledku anglicky

Very few studies have benefited from the synergetic implementation of visible, near-infrared, and shortwave infrared (VNIR-SWIR) spectra and terrain attributes in predicting Pb content in agricultural soils. To fill this gap, this study aimed to predict lead (Pb) contents in agricultural soils by combining machine learning algorithms (MLAs) with VNIR-SWIR spectra or/and terrain attributes under three distinct approaches. Six MLAs were tested, including artificial neural network (ANN), partial least squares regression, support vector machine (SVM), Gaussian process regression (GPR), extreme gradient boosting (EGB), and Cubist. The VNIR-SWIR spectral data were preprocessed by methods of discrete wavelet transformation, logarithmic transformation-Savitzky Golay smoothing, standard normal variate (SNV), multiplicative scatter correction, first derivative (FiD), and second derivative. In approach 1, MLAs were combined with the preprocessed VNIR-SWIR spectral data. The Cubist-FiD combination was the most effective, achieving a coefficient of determination (H2) of 0.63, a concordance correlation coefficient (CCC) of 0.51, a mean absolute error (MAE) of 6.87 mg kg-1, and a root mean square error (RMSE) of 8.66 mg kg-1. In approach 2, MLAs were combined with both preprocessed VNIR-SWIR spectral data and terrain attributes, and the EGB-SNV combination yielded superior results with H2 of 0.75, CCC of 0.65, MAE of 5.48 mg kg-1, and RMSE of 7.34 mg kg-1. Approach 3 combined MLAs and terrain attributes, and Cubist demonstrated the best prediction results, with H2 of 0.75, CCC of 0.66, MAE of 6.18 mg kg-1, and RMSE of 7.71 mg kg-1. The cumulative assessment identified the fusion of terrain properties, SNV-preprocessed VNIR-SWIR spectra, and EGB as the optimal method for estimating Pb content in agricultural soils, yielding the highest H2 value and minimal error. Comparatively, GPR, ANN, and SVM techniques achieved higher H2 values in approaches 2 and 3 but also exhibited higher estimation errors. In conclusion, the study underscores the significance of using relevant auxiliary datasets and appropriate MLAs for accurate Pb content prediction with minimal error in agricultural soils. The findings contribute valuable insights for developing successful soil management strategies based on predictive modeling.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40104 - Soil science

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Pedosphere

ISSN

1002-0160

e-ISSN

2210-5107

Svazek periodika

35

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

13

Strana od-do

325-337

Kód UT WoS článku

001459604500001

EID výsledku v databázi Scopus

2-s2.0-105000851087