In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy

Visible near-infrared (VNIR) spectroscopy is a reliable method for estimating soil properties. However, its effectiveness in accurately predicting soil organic carbon (SOC) contents, particularly in wheat-rice rotation fields, remains uncertain. In this study, we collected 202 samples from wheat-ric...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingju Dai, Jie Xue, Rui Lu, Zheng Wang, Zhongxing Chen, Qiangyi Yu, Zhou Shi, Songchao Chen
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Soil & Environmental Health
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949919424000566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165826125692928
author Lingju Dai
Jie Xue
Rui Lu
Zheng Wang
Zhongxing Chen
Qiangyi Yu
Zhou Shi
Songchao Chen
author_facet Lingju Dai
Jie Xue
Rui Lu
Zheng Wang
Zhongxing Chen
Qiangyi Yu
Zhou Shi
Songchao Chen
author_sort Lingju Dai
collection DOAJ
description Visible near-infrared (VNIR) spectroscopy is a reliable method for estimating soil properties. However, its effectiveness in accurately predicting soil organic carbon (SOC) contents, particularly in wheat-rice rotation fields, remains uncertain. In this study, we collected 202 samples from wheat-rice fields (0–20 ​cm) in southeastern China and measured in-situ spectra of the vertical surface of the soil cores and the laboratory spectra of the dried and sieved soil samples. Our study focused on evaluating three algorithms - external parameter orthogonalization (EPO), direct standardization (DS), and piecewise direct standardization (PDS) - to address the influence of external factors, particularly soil moisture. To carry out our analysis, the dataset was divided into calibration (141 samples) and validation (61 samples) sets via the Kennard-Stone algorithm. A subset of the corresponding in-situ and laboratory spectra in the calibration set (transfer set) was used to derive the transfer matrix for EPO, DS, and PDS, enabling the conversion of in-situ spectra to laboratory spectra by characterizing their differences. Four machine learning models, including cubist, partial least squares regression (PLSR), random forest (RF), and memory-based learning (MBL), were used to predict the SOC, particulate organic carbon (POC), and mineral-associated organic carbon (MAOC) contents based on the laboratory, in-situ, and corrected in-situ spectra. The results revealed that the laboratory spectra outperformed the non-corrected in-situ spectra, with coefficients of determination (R2) of 0.91, 0.75, and 0.80 for SOC, POC, and MAOC, respectively. Among the models, MBL and PLSR exhibited the highest average R2 at 0.85–0.86. EPO marginally improved the prediction accuracy (R2 increased from 0.85 to 0.87 for SOC, 0.64 to 0.69 for POC, and 0.75 to 0.82 for MAOC). These promising prediction accuracies underscore the potential of VNIR spectra for in-situ predictions in wheat-rice fields in Southeast China, offering insights for predicting SOC contents via in-situ spectroscopy.
format Article
id doaj-art-42da9344e21d47d9ac56bc6ffa5075b6
institution Kabale University
issn 2949-9194
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Soil & Environmental Health
spelling doaj-art-42da9344e21d47d9ac56bc6ffa5075b62024-11-17T04:53:02ZengElsevierSoil & Environmental Health2949-91942024-11-0124100113In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopyLingju Dai0Jie Xue1Rui Lu2Zheng Wang3Zhongxing Chen4Qiangyi Yu5Zhou Shi6Songchao Chen7College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China; ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, ChinaDepartment of Land Management, Zhejiang University, Hangzhou 310058, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China; ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, ChinaInstitute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, ChinaCollege of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China; ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 311215, China; Corresponding author. College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China.Visible near-infrared (VNIR) spectroscopy is a reliable method for estimating soil properties. However, its effectiveness in accurately predicting soil organic carbon (SOC) contents, particularly in wheat-rice rotation fields, remains uncertain. In this study, we collected 202 samples from wheat-rice fields (0–20 ​cm) in southeastern China and measured in-situ spectra of the vertical surface of the soil cores and the laboratory spectra of the dried and sieved soil samples. Our study focused on evaluating three algorithms - external parameter orthogonalization (EPO), direct standardization (DS), and piecewise direct standardization (PDS) - to address the influence of external factors, particularly soil moisture. To carry out our analysis, the dataset was divided into calibration (141 samples) and validation (61 samples) sets via the Kennard-Stone algorithm. A subset of the corresponding in-situ and laboratory spectra in the calibration set (transfer set) was used to derive the transfer matrix for EPO, DS, and PDS, enabling the conversion of in-situ spectra to laboratory spectra by characterizing their differences. Four machine learning models, including cubist, partial least squares regression (PLSR), random forest (RF), and memory-based learning (MBL), were used to predict the SOC, particulate organic carbon (POC), and mineral-associated organic carbon (MAOC) contents based on the laboratory, in-situ, and corrected in-situ spectra. The results revealed that the laboratory spectra outperformed the non-corrected in-situ spectra, with coefficients of determination (R2) of 0.91, 0.75, and 0.80 for SOC, POC, and MAOC, respectively. Among the models, MBL and PLSR exhibited the highest average R2 at 0.85–0.86. EPO marginally improved the prediction accuracy (R2 increased from 0.85 to 0.87 for SOC, 0.64 to 0.69 for POC, and 0.75 to 0.82 for MAOC). These promising prediction accuracies underscore the potential of VNIR spectra for in-situ predictions in wheat-rice fields in Southeast China, offering insights for predicting SOC contents via in-situ spectroscopy.http://www.sciencedirect.com/science/article/pii/S2949919424000566External parameter orthogonalizationMineral-associated organic carbonPiecewise direct standardizationPartial least squares regressionCalibration transfer methodsParticulate organic carbon
spellingShingle Lingju Dai
Jie Xue
Rui Lu
Zheng Wang
Zhongxing Chen
Qiangyi Yu
Zhou Shi
Songchao Chen
In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
Soil & Environmental Health
External parameter orthogonalization
Mineral-associated organic carbon
Piecewise direct standardization
Partial least squares regression
Calibration transfer methods
Particulate organic carbon
title In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
title_full In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
title_fullStr In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
title_full_unstemmed In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
title_short In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy
title_sort in situ prediction of soil organic carbon contents in wheat rice rotation fields via visible near infrared spectroscopy
topic External parameter orthogonalization
Mineral-associated organic carbon
Piecewise direct standardization
Partial least squares regression
Calibration transfer methods
Particulate organic carbon
url http://www.sciencedirect.com/science/article/pii/S2949919424000566
work_keys_str_mv AT lingjudai insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT jiexue insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT ruilu insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT zhengwang insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT zhongxingchen insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT qiangyiyu insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT zhoushi insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy
AT songchaochen insitupredictionofsoilorganiccarboncontentsinwheatricerotationfieldsviavisiblenearinfraredspectroscopy