TY - JOUR

T1 - Enhancing soil organic carbon prediction of LUCAS soil database using deep learning and deep feature selection

AU - Saberioon, Mohammadmehdi

AU - Gholizadeh, Asa

AU - Ghaznavi, Ali

AU - Chabrillat, Sabine

AU - Khosravi, Vahid

N1 - Publisher Copyright: © 2024 The Authors

PY - 2024/12

Y1 - 2024/12

N2 - The main terrestrial carbon (C) fraction is soil organic carbon (SOC), which has a considerable effect on climate change and greenhouse gas emissions through the absorption and sequestration of carbon dioxide (CO2). This has made SOC assessment very important from both economic and environmental viewpoints. The growing count of soil spectral libraries (SSLs) from regional to global scales has brought a tremendous opportunity for the quantification of SOC through developing spectral-based prediction models. Hence, there is a need to take advantage of big data analytics for spectral data processing. The unique ability of deep learning (DL) techniques to leverage important features of high-dimensional large-scale SSLs has made them top-demanding for more sophisticated modeling. The core objective of the present study was to assess the ability of two different DL algorithms, i.e., one-dimensional convolutional neural network (1DCNN) and fully connected neural network (FCNN) coupled with stacked autoencoder (SAE) feature extraction for SOC prediction based on the data from the land use/cover area frame statistical survey (LUCAS) database. SAE extracted the high-level deep features from the visible–near-infrared–shortwave infrared (Vis–NIR–SWIR) spectra of 11441 soil samples, which were then considered as inputs to the 1DCNN and FCNN models for predicting the SOC content. Both SAE-DL feature-selected models yielded higher accuracy than those the DL developed on the entire spectra and a random forest (RF) model was constructed for comparison. The best prediction was achieved by SAE-1DCNN (R2= 0.78, RMSE = 3.94%, RPD = 4.88, RPIQ = 3.91) followed by 1DCNN (R2= 0.73, RMSE = 5.43%, RPD = 3.67, RPIQ = 2.84) proving the superiority of 1DCNN over FCNN in this study. These results supported the applicability of combined deep features extraction and regression methods for predicting SOC using high dimensional large-scale SSLs.

AB - The main terrestrial carbon (C) fraction is soil organic carbon (SOC), which has a considerable effect on climate change and greenhouse gas emissions through the absorption and sequestration of carbon dioxide (CO2). This has made SOC assessment very important from both economic and environmental viewpoints. The growing count of soil spectral libraries (SSLs) from regional to global scales has brought a tremendous opportunity for the quantification of SOC through developing spectral-based prediction models. Hence, there is a need to take advantage of big data analytics for spectral data processing. The unique ability of deep learning (DL) techniques to leverage important features of high-dimensional large-scale SSLs has made them top-demanding for more sophisticated modeling. The core objective of the present study was to assess the ability of two different DL algorithms, i.e., one-dimensional convolutional neural network (1DCNN) and fully connected neural network (FCNN) coupled with stacked autoencoder (SAE) feature extraction for SOC prediction based on the data from the land use/cover area frame statistical survey (LUCAS) database. SAE extracted the high-level deep features from the visible–near-infrared–shortwave infrared (Vis–NIR–SWIR) spectra of 11441 soil samples, which were then considered as inputs to the 1DCNN and FCNN models for predicting the SOC content. Both SAE-DL feature-selected models yielded higher accuracy than those the DL developed on the entire spectra and a random forest (RF) model was constructed for comparison. The best prediction was achieved by SAE-1DCNN (R2= 0.78, RMSE = 3.94%, RPD = 4.88, RPIQ = 3.91) followed by 1DCNN (R2= 0.73, RMSE = 5.43%, RPD = 3.67, RPIQ = 2.84) proving the superiority of 1DCNN over FCNN in this study. These results supported the applicability of combined deep features extraction and regression methods for predicting SOC using high dimensional large-scale SSLs.

KW - Convolutional neural network

KW - Deep feature extraction

KW - Fully connected neural network

KW - Large-scale

KW - Soil organic carbon

KW - Soil spectral library

KW - Stacked autoencoder

UR - http://www.scopus.com/inward/record.url?scp=85204972149&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2024.109494

DO - 10.1016/j.compag.2024.109494

M3 - Article

AN - SCOPUS:85204972149

VL - 227

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 1

M1 - 109494

ER -