Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms
Soil salinization seriously affects the sustainable development of agricultural production; thus, the timely, efficient, and accurate estimation of soil salt content (SSC) has important research significance. In this study, the feasibility of soil salt content retrieval using machine learning models...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/21/5254 |
| _version_ | 1797631323742928896 |
|---|---|
| author | Jiawei Cui Xiangwei Chen Wenting Han Xin Cui Weitong Ma Guang Li |
| author_facet | Jiawei Cui Xiangwei Chen Wenting Han Xin Cui Weitong Ma Guang Li |
| author_sort | Jiawei Cui |
| collection | DOAJ |
| description | Soil salinization seriously affects the sustainable development of agricultural production; thus, the timely, efficient, and accurate estimation of soil salt content (SSC) has important research significance. In this study, the feasibility of soil salt content retrieval using machine learning models was explored based on a UAV (unmanned aerial vehicle) multi-spectral remote sensing platform. First, two variable screening methods (Pearson correlation analysis and Grey relational analysis) are used to screen the characteristic importance of 20 commonly used spectral indices. Then, the sensitive spectral variables were divided into a vegetation index group, a salt index group, and a combination variable group, which represent the model. To estimate SSC information for soil depths of 0–20 cm and 20–40 cm, three machine learning regression models were constructed: Support Vector Machine (SVM), Random Forest (RF), and Backpropagation Neural Network (BPNN). Finally, the salt distribution map for a 0–20 cm soil depth was drawn based on the best estimation model. The results of experiments show that GRA is better than PCA in improving the accuracy of the estimation model, and the combination variable group containing soil moisture information performs best. The three machine learning models have achieved good prediction effects to some extent. The accuracy and stability of the model are considered comprehensively, the prediction effect of 0–20 cm is higher than that of 20–40 cm, and the validation set coefficient of determination (<i>R</i><sup>2</sup>), Root-Mean-Square-Error (<i>RMSE</i>), and Mean Absolute Error (<i>MAE</i>) of the best inversion model are 0.775, 0.055, and 0.038, and the soil salt spatial map based on the optimal estimation model can reflect the salinization distribution in the study area. Therefore, this study shows that a UAV multi-spectral remote sensing platform combined with machine learning models can better monitor farmland soil salt content. |
| first_indexed | 2024-03-11T11:22:08Z |
| format | Article |
| id | doaj.art-39b57788c241437bb824924d8e252bf1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T11:22:08Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-39b57788c241437bb824924d8e252bf12023-11-10T15:11:32ZengMDPI AGRemote Sensing2072-42922023-11-011521525410.3390/rs15215254Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning AlgorithmsJiawei Cui0Xiangwei Chen1Wenting Han2Xin Cui3Weitong Ma4Guang Li5College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling 712100, ChinaInstitute of Water-Saving Agriculture in Arid Regions of China, Northwest A&F University, Yangling 712100, ChinaInstitute of Water-Saving Agriculture in Arid Regions of China, Northwest A&F University, Yangling 712100, ChinaInstitute of Water-Saving Agriculture in Arid Regions of China, Northwest A&F University, Yangling 712100, ChinaCollege of Water Resources and Architectural Engineering, Northwest A&F University, Yangling 712100, ChinaInstitute of Water-Saving Agriculture in Arid Regions of China, Northwest A&F University, Yangling 712100, ChinaSoil salinization seriously affects the sustainable development of agricultural production; thus, the timely, efficient, and accurate estimation of soil salt content (SSC) has important research significance. In this study, the feasibility of soil salt content retrieval using machine learning models was explored based on a UAV (unmanned aerial vehicle) multi-spectral remote sensing platform. First, two variable screening methods (Pearson correlation analysis and Grey relational analysis) are used to screen the characteristic importance of 20 commonly used spectral indices. Then, the sensitive spectral variables were divided into a vegetation index group, a salt index group, and a combination variable group, which represent the model. To estimate SSC information for soil depths of 0–20 cm and 20–40 cm, three machine learning regression models were constructed: Support Vector Machine (SVM), Random Forest (RF), and Backpropagation Neural Network (BPNN). Finally, the salt distribution map for a 0–20 cm soil depth was drawn based on the best estimation model. The results of experiments show that GRA is better than PCA in improving the accuracy of the estimation model, and the combination variable group containing soil moisture information performs best. The three machine learning models have achieved good prediction effects to some extent. The accuracy and stability of the model are considered comprehensively, the prediction effect of 0–20 cm is higher than that of 20–40 cm, and the validation set coefficient of determination (<i>R</i><sup>2</sup>), Root-Mean-Square-Error (<i>RMSE</i>), and Mean Absolute Error (<i>MAE</i>) of the best inversion model are 0.775, 0.055, and 0.038, and the soil salt spatial map based on the optimal estimation model can reflect the salinization distribution in the study area. Therefore, this study shows that a UAV multi-spectral remote sensing platform combined with machine learning models can better monitor farmland soil salt content.https://www.mdpi.com/2072-4292/15/21/5254soil salt contentunmanned aerial vehicle (UAV)multi-spectral remote sensingmachine learningvariable screeningsalt distribution map |
| spellingShingle | Jiawei Cui Xiangwei Chen Wenting Han Xin Cui Weitong Ma Guang Li Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms Remote Sensing soil salt content unmanned aerial vehicle (UAV) multi-spectral remote sensing machine learning variable screening salt distribution map |
| title | Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms |
| title_full | Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms |
| title_fullStr | Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms |
| title_full_unstemmed | Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms |
| title_short | Estimation of Soil Salt Content at Different Depths Using UAV Multi-Spectral Remote Sensing Combined with Machine Learning Algorithms |
| title_sort | estimation of soil salt content at different depths using uav multi spectral remote sensing combined with machine learning algorithms |
| topic | soil salt content unmanned aerial vehicle (UAV) multi-spectral remote sensing machine learning variable screening salt distribution map |
| url | https://www.mdpi.com/2072-4292/15/21/5254 |
| work_keys_str_mv | AT jiaweicui estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms AT xiangweichen estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms AT wentinghan estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms AT xincui estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms AT weitongma estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms AT guangli estimationofsoilsaltcontentatdifferentdepthsusinguavmultispectralremotesensingcombinedwithmachinelearningalgorithms |