Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Pingping Jia
  • Junhua Zhang
  • Wei He
  • Yi Hu
  • Rong Zeng
  • Kazem Zamanian
  • Keli Jia
  • Xiaoning Zhao

Research Organisations

External Research Organisations

  • Nanjing University of Information Science and Technology
  • Ningxia University
View graph of relations

Details

Original languageEnglish
Article number2602
JournalRemote sensing
Volume14
Issue number11
Publication statusPublished - 28 May 2022

Abstract

An accurate estimation of soil electrical conductivity (EC) using hyperspectral techniques is of great significance for understanding the spatial distribution of solutes and soil salinization. Although spectral transformation has been widely used in data pre-processing, the performance of different pre-processing techniques (or combination methods) on different models of the same data set is still ambiguous. Moreover, extremely randomized trees (ERT) and light gradient boosting machine (LightGBM) models are new learning algorithms with good generalization performance (soil moisture and above-ground biomass), but are less studied in estimating soil salinity in the visible and near-infrared spectra. In this study, 130 soil EC data, soil measured hyperspectral data, topographic factors, conventional salinity indices such as Salinity Index 1, and two-band (2D) salinity indices such as ratio indices, were introduced. The five spectral pre-processing methods of standard normal variate (SNV), standard normal variate and detrend (SNV-DT), inverse (1/OR) (OR is original spectrum), inverse-log (Log(1/OR) and fractional order derivative (FOD) (range 0–2, with intervals of 0.25) were performed. A gradient boosting machine (GBM) was used to select sensitive spectral parameters. Models (extreme gradient boosting (XGBoost), LightGBM, random forest (RF), ERT, classification and regression tree (CART), and ridge regression (RR)) were used for inversion soil EC and model validation. The results reveal that the two-dimensional correlation coefficient highlighted EC more effectively than the one-dimensional. Under SNV and the second order derivative, the two-dimensional correlation coefficient increased by 0.286 and 0.258 compared to the one-dimension, respectively. The 13 characteristic factors of slope, NDI, SI-T, RI, profile curvature, DOA, plane curvature, SI (conventional), elevation, Int2, aspect, S1 and TWI provided 90% of the cumulative importance for EC using GBM. Among the six machine models, the ERT model performed the best for simulation (R2 = 0.98) and validation (R2 = 0.96). The ERT model showed the best performance among the EC estimation models from the reference data. The kriging map based on the ERT simulation showed a close relationship with the measured data. Our study selected the effective pre-processing methods (SNV and the 2 order derivative) using one-and two-dimensional correlation, 13 important factors and the ERT model for EC hyperspectral inversion. This provides a theoretical support for the quantitative monitoring of soil salinization on a larger scale using remote sensing techniques.

Keywords

    extremely randomized trees, hyperspectral reflectance, light gradient boosting machine, northwestern China, soil EC inversion

ASJC Scopus subject areas

Cite this

Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity. / Jia, Pingping; Zhang, Junhua; He, Wei et al.
In: Remote sensing, Vol. 14, No. 11, 2602, 28.05.2022.

Research output: Contribution to journalArticleResearchpeer review

Jia, P., Zhang, J., He, W., Hu, Y., Zeng, R., Zamanian, K., Jia, K., & Zhao, X. (2022). Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity. Remote sensing, 14(11), Article 2602. https://doi.org/10.3390/rs14112602
Jia P, Zhang J, He W, Hu Y, Zeng R, Zamanian K et al. Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity. Remote sensing. 2022 May 28;14(11):2602. doi: 10.3390/rs14112602
Jia, Pingping ; Zhang, Junhua ; He, Wei et al. / Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity. In: Remote sensing. 2022 ; Vol. 14, No. 11.
Download
@article{64c1c946ecea4a1b8543e2675f53502e,
title = "Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity",
abstract = "An accurate estimation of soil electrical conductivity (EC) using hyperspectral techniques is of great significance for understanding the spatial distribution of solutes and soil salinization. Although spectral transformation has been widely used in data pre-processing, the performance of different pre-processing techniques (or combination methods) on different models of the same data set is still ambiguous. Moreover, extremely randomized trees (ERT) and light gradient boosting machine (LightGBM) models are new learning algorithms with good generalization performance (soil moisture and above-ground biomass), but are less studied in estimating soil salinity in the visible and near-infrared spectra. In this study, 130 soil EC data, soil measured hyperspectral data, topographic factors, conventional salinity indices such as Salinity Index 1, and two-band (2D) salinity indices such as ratio indices, were introduced. The five spectral pre-processing methods of standard normal variate (SNV), standard normal variate and detrend (SNV-DT), inverse (1/OR) (OR is original spectrum), inverse-log (Log(1/OR) and fractional order derivative (FOD) (range 0–2, with intervals of 0.25) were performed. A gradient boosting machine (GBM) was used to select sensitive spectral parameters. Models (extreme gradient boosting (XGBoost), LightGBM, random forest (RF), ERT, classification and regression tree (CART), and ridge regression (RR)) were used for inversion soil EC and model validation. The results reveal that the two-dimensional correlation coefficient highlighted EC more effectively than the one-dimensional. Under SNV and the second order derivative, the two-dimensional correlation coefficient increased by 0.286 and 0.258 compared to the one-dimension, respectively. The 13 characteristic factors of slope, NDI, SI-T, RI, profile curvature, DOA, plane curvature, SI (conventional), elevation, Int2, aspect, S1 and TWI provided 90% of the cumulative importance for EC using GBM. Among the six machine models, the ERT model performed the best for simulation (R2 = 0.98) and validation (R2 = 0.96). The ERT model showed the best performance among the EC estimation models from the reference data. The kriging map based on the ERT simulation showed a close relationship with the measured data. Our study selected the effective pre-processing methods (SNV and the 2 order derivative) using one-and two-dimensional correlation, 13 important factors and the ERT model for EC hyperspectral inversion. This provides a theoretical support for the quantitative monitoring of soil salinization on a larger scale using remote sensing techniques.",
keywords = "extremely randomized trees, hyperspectral reflectance, light gradient boosting machine, northwestern China, soil EC inversion",
author = "Pingping Jia and Junhua Zhang and Wei He and Yi Hu and Rong Zeng and Kazem Zamanian and Keli Jia and Xiaoning Zhao",
note = "Funding Information: This work was supported by the National Natural Science Foundation of China (Grant numbers 41877109; 42050410320; 42067003; 42061047); the Jiangsu Specially-Appointed Professor Project, China (Grant number R2020T29); the Key R&D Project of Ningxia, China (Grant number 2021BEG03002); the National Key R&D Program of China (Grant number 2021YFD1900602); and the Thousand Young Talents Program, China (Grant number Y772121).",
year = "2022",
month = may,
day = "28",
doi = "10.3390/rs14112602",
language = "English",
volume = "14",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "11",

}

Download

TY - JOUR

T1 - Combination of Hyperspectral and Machine Learning to Invert Soil Electrical Conductivity

AU - Jia, Pingping

AU - Zhang, Junhua

AU - He, Wei

AU - Hu, Yi

AU - Zeng, Rong

AU - Zamanian, Kazem

AU - Jia, Keli

AU - Zhao, Xiaoning

N1 - Funding Information: This work was supported by the National Natural Science Foundation of China (Grant numbers 41877109; 42050410320; 42067003; 42061047); the Jiangsu Specially-Appointed Professor Project, China (Grant number R2020T29); the Key R&D Project of Ningxia, China (Grant number 2021BEG03002); the National Key R&D Program of China (Grant number 2021YFD1900602); and the Thousand Young Talents Program, China (Grant number Y772121).

PY - 2022/5/28

Y1 - 2022/5/28

N2 - An accurate estimation of soil electrical conductivity (EC) using hyperspectral techniques is of great significance for understanding the spatial distribution of solutes and soil salinization. Although spectral transformation has been widely used in data pre-processing, the performance of different pre-processing techniques (or combination methods) on different models of the same data set is still ambiguous. Moreover, extremely randomized trees (ERT) and light gradient boosting machine (LightGBM) models are new learning algorithms with good generalization performance (soil moisture and above-ground biomass), but are less studied in estimating soil salinity in the visible and near-infrared spectra. In this study, 130 soil EC data, soil measured hyperspectral data, topographic factors, conventional salinity indices such as Salinity Index 1, and two-band (2D) salinity indices such as ratio indices, were introduced. The five spectral pre-processing methods of standard normal variate (SNV), standard normal variate and detrend (SNV-DT), inverse (1/OR) (OR is original spectrum), inverse-log (Log(1/OR) and fractional order derivative (FOD) (range 0–2, with intervals of 0.25) were performed. A gradient boosting machine (GBM) was used to select sensitive spectral parameters. Models (extreme gradient boosting (XGBoost), LightGBM, random forest (RF), ERT, classification and regression tree (CART), and ridge regression (RR)) were used for inversion soil EC and model validation. The results reveal that the two-dimensional correlation coefficient highlighted EC more effectively than the one-dimensional. Under SNV and the second order derivative, the two-dimensional correlation coefficient increased by 0.286 and 0.258 compared to the one-dimension, respectively. The 13 characteristic factors of slope, NDI, SI-T, RI, profile curvature, DOA, plane curvature, SI (conventional), elevation, Int2, aspect, S1 and TWI provided 90% of the cumulative importance for EC using GBM. Among the six machine models, the ERT model performed the best for simulation (R2 = 0.98) and validation (R2 = 0.96). The ERT model showed the best performance among the EC estimation models from the reference data. The kriging map based on the ERT simulation showed a close relationship with the measured data. Our study selected the effective pre-processing methods (SNV and the 2 order derivative) using one-and two-dimensional correlation, 13 important factors and the ERT model for EC hyperspectral inversion. This provides a theoretical support for the quantitative monitoring of soil salinization on a larger scale using remote sensing techniques.

AB - An accurate estimation of soil electrical conductivity (EC) using hyperspectral techniques is of great significance for understanding the spatial distribution of solutes and soil salinization. Although spectral transformation has been widely used in data pre-processing, the performance of different pre-processing techniques (or combination methods) on different models of the same data set is still ambiguous. Moreover, extremely randomized trees (ERT) and light gradient boosting machine (LightGBM) models are new learning algorithms with good generalization performance (soil moisture and above-ground biomass), but are less studied in estimating soil salinity in the visible and near-infrared spectra. In this study, 130 soil EC data, soil measured hyperspectral data, topographic factors, conventional salinity indices such as Salinity Index 1, and two-band (2D) salinity indices such as ratio indices, were introduced. The five spectral pre-processing methods of standard normal variate (SNV), standard normal variate and detrend (SNV-DT), inverse (1/OR) (OR is original spectrum), inverse-log (Log(1/OR) and fractional order derivative (FOD) (range 0–2, with intervals of 0.25) were performed. A gradient boosting machine (GBM) was used to select sensitive spectral parameters. Models (extreme gradient boosting (XGBoost), LightGBM, random forest (RF), ERT, classification and regression tree (CART), and ridge regression (RR)) were used for inversion soil EC and model validation. The results reveal that the two-dimensional correlation coefficient highlighted EC more effectively than the one-dimensional. Under SNV and the second order derivative, the two-dimensional correlation coefficient increased by 0.286 and 0.258 compared to the one-dimension, respectively. The 13 characteristic factors of slope, NDI, SI-T, RI, profile curvature, DOA, plane curvature, SI (conventional), elevation, Int2, aspect, S1 and TWI provided 90% of the cumulative importance for EC using GBM. Among the six machine models, the ERT model performed the best for simulation (R2 = 0.98) and validation (R2 = 0.96). The ERT model showed the best performance among the EC estimation models from the reference data. The kriging map based on the ERT simulation showed a close relationship with the measured data. Our study selected the effective pre-processing methods (SNV and the 2 order derivative) using one-and two-dimensional correlation, 13 important factors and the ERT model for EC hyperspectral inversion. This provides a theoretical support for the quantitative monitoring of soil salinization on a larger scale using remote sensing techniques.

KW - extremely randomized trees

KW - hyperspectral reflectance

KW - light gradient boosting machine

KW - northwestern China

KW - soil EC inversion

UR - http://www.scopus.com/inward/record.url?scp=85131385535&partnerID=8YFLogxK

U2 - 10.3390/rs14112602

DO - 10.3390/rs14112602

M3 - Article

AN - SCOPUS:85131385535

VL - 14

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 11

M1 - 2602

ER -

By the same author(s)