Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data
Soil moisture is a critical factor that supports plant growth, improves crop yields, and reduces erosion. Therefore, obtaining accurate and timely information about soil moisture across large regions is crucial. Remote sensing techniques, such as microwave remote sensing, have emerged as powerful to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/18/3539 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850259571290931200 |
|---|---|
| author | Dev Dinesh Shashi Kumar Sameer Saran |
| author_facet | Dev Dinesh Shashi Kumar Sameer Saran |
| author_sort | Dev Dinesh |
| collection | DOAJ |
| description | Soil moisture is a critical factor that supports plant growth, improves crop yields, and reduces erosion. Therefore, obtaining accurate and timely information about soil moisture across large regions is crucial. Remote sensing techniques, such as microwave remote sensing, have emerged as powerful tools for monitoring and mapping soil moisture. Synthetic aperture radar (SAR) is beneficial for estimating soil moisture at both global and local levels. This study aimed to assess soil moisture and dielectric constant retrieval over agricultural land using machine learning (ML) algorithms and decomposition techniques. Three polarimetric decomposition models were used to extract features from simulated NASA-ISRO SAR (NISAR) L-Band radar images. Machine learning techniques such as random forest regression, decision tree regression, stochastic gradient descent (SGD), XGBoost, K-nearest neighbors (KNN) regression, neural network regression, and multilinear regression were used to retrieve soil moisture from three different crop fields: wheat, soybean, and corn. The study found that the random forest regression technique produced the most precise soil moisture estimations for soybean fields, with an R<sup>2</sup> of 0.89 and RMSE of 0.050 without considering vegetation effects and an R<sup>2</sup> of 0.92 and RMSE of 0.042 considering vegetation effects. The results for real dielectric constant retrieval for the soybean field were an R<sup>2</sup> of 0.89 and RMSE of 6.79 without considering vegetation effects and an R<sup>2</sup> of 0.89 and RMSE of 6.78 with considering vegetation effects. These findings suggest that machine learning algorithms and decomposition techniques, along with a semi-empirical technique like Water Cloud Model (WCM), can be effective tools for estimating soil moisture and dielectric constant values precisely. The methodology applied in the current research contributes essential insights that could benefit upcoming missions, such as the Radar Observing System for Europe in L-band (ROSE-L) and the collaborative NASA-ISRO SAR (NISAR) mission, for future data analysis in soil moisture applications. |
| format | Article |
| id | doaj-art-74b3e545659d4c5d9d5ca31e6fc75b72 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-74b3e545659d4c5d9d5ca31e6fc75b722025-08-20T01:55:49ZengMDPI AGRemote Sensing2072-42922024-09-011618353910.3390/rs16183539Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band DataDev Dinesh0Shashi Kumar1Sameer Saran2Indian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO), Dehradun 248001, IndiaIndian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO), Dehradun 248001, IndiaRegional Remote Sensing Center-North, Indian Space Research Organisation (ISRO), New Delhi 110049, IndiaSoil moisture is a critical factor that supports plant growth, improves crop yields, and reduces erosion. Therefore, obtaining accurate and timely information about soil moisture across large regions is crucial. Remote sensing techniques, such as microwave remote sensing, have emerged as powerful tools for monitoring and mapping soil moisture. Synthetic aperture radar (SAR) is beneficial for estimating soil moisture at both global and local levels. This study aimed to assess soil moisture and dielectric constant retrieval over agricultural land using machine learning (ML) algorithms and decomposition techniques. Three polarimetric decomposition models were used to extract features from simulated NASA-ISRO SAR (NISAR) L-Band radar images. Machine learning techniques such as random forest regression, decision tree regression, stochastic gradient descent (SGD), XGBoost, K-nearest neighbors (KNN) regression, neural network regression, and multilinear regression were used to retrieve soil moisture from three different crop fields: wheat, soybean, and corn. The study found that the random forest regression technique produced the most precise soil moisture estimations for soybean fields, with an R<sup>2</sup> of 0.89 and RMSE of 0.050 without considering vegetation effects and an R<sup>2</sup> of 0.92 and RMSE of 0.042 considering vegetation effects. The results for real dielectric constant retrieval for the soybean field were an R<sup>2</sup> of 0.89 and RMSE of 6.79 without considering vegetation effects and an R<sup>2</sup> of 0.89 and RMSE of 6.78 with considering vegetation effects. These findings suggest that machine learning algorithms and decomposition techniques, along with a semi-empirical technique like Water Cloud Model (WCM), can be effective tools for estimating soil moisture and dielectric constant values precisely. The methodology applied in the current research contributes essential insights that could benefit upcoming missions, such as the Radar Observing System for Europe in L-band (ROSE-L) and the collaborative NASA-ISRO SAR (NISAR) mission, for future data analysis in soil moisture applications.https://www.mdpi.com/2072-4292/16/18/3539soil moisturesoil dielectric constantmachine learningpolarimetric decompositionrandom forestNISAR |
| spellingShingle | Dev Dinesh Shashi Kumar Sameer Saran Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data Remote Sensing soil moisture soil dielectric constant machine learning polarimetric decomposition random forest NISAR |
| title | Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data |
| title_full | Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data |
| title_fullStr | Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data |
| title_full_unstemmed | Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data |
| title_short | Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data |
| title_sort | machine learning modelling for soil moisture retrieval from simulated nasa isro sar nisar l band data |
| topic | soil moisture soil dielectric constant machine learning polarimetric decomposition random forest NISAR |
| url | https://www.mdpi.com/2072-4292/16/18/3539 |
| work_keys_str_mv | AT devdinesh machinelearningmodellingforsoilmoistureretrievalfromsimulatednasaisrosarnisarlbanddata AT shashikumar machinelearningmodellingforsoilmoistureretrievalfromsimulatednasaisrosarnisarlbanddata AT sameersaran machinelearningmodellingforsoilmoistureretrievalfromsimulatednasaisrosarnisarlbanddata |