Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations
Soil moisture is a fundamental variable in the Earth’s hydrological cycle and vital for development of agricultural water management practices. The present study provided a comprehensive evaluation of a wide range of advanced machine learning algorithms for Soil Moisture (SM) estimation from microwa...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Remote Sensing |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frsen.2024.1513620/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543797624799232 |
|---|---|
| author | Deepanshu Lakra Deepanshu Lakra Shobhit Pipil Prashant K. Srivastava Suraj Kumar Singh Manika Gupta Rajendra Prasad |
| author_facet | Deepanshu Lakra Deepanshu Lakra Shobhit Pipil Prashant K. Srivastava Suraj Kumar Singh Manika Gupta Rajendra Prasad |
| author_sort | Deepanshu Lakra |
| collection | DOAJ |
| description | Soil moisture is a fundamental variable in the Earth’s hydrological cycle and vital for development of agricultural water management practices. The present study provided a comprehensive evaluation of a wide range of advanced machine learning algorithms for Soil Moisture (SM) estimation from microwave Synthetic Aperture Radar (SAR) backscatter observations over the wheat fields. From the wheat fields, samplings were performed to collect the in situ datasets on three different dates concurrent to the Sentinel-1 overpasses. The backscattering coefficients were taken as the input variables and SM as the output variable for the training and testing of different models. The performance analysis of RMSE, R-squared, and correlation coefficients revealed that the Random Forest (RF) and Convolutional Neural Network (CNN) models demonstrated superior performance for SM estimation over the wheat field. Specifically, the RF model exhibited outstanding accuracy and robustness in both the training [RMSE (%): 3.44, R-squared: 0.88, correlation: 0.95] and validation phases [RMSE (%): 7.06, R-squared: 0.61, correlation: 0.8], marking it as the most effective model followed by the CNN model with [RMSE (%): 3.9, R-squared: 0.84, correlation: 0.92] during training and [RMSE (%): 8.44, R-squared: 0.43, correlation: 0.67] for validation, highlighting challenges in the model generalisation. |
| format | Article |
| id | doaj-art-e18b1bc7dfce4475b73669ecf51a6ed5 |
| institution | Kabale University |
| issn | 2673-6187 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Remote Sensing |
| spelling | doaj-art-e18b1bc7dfce4475b73669ecf51a6ed52025-01-13T06:10:17ZengFrontiers Media S.A.Frontiers in Remote Sensing2673-61872025-01-01510.3389/frsen.2024.15136201513620Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observationsDeepanshu Lakra0Deepanshu Lakra1Shobhit Pipil2Prashant K. Srivastava3Suraj Kumar Singh4Manika Gupta5Rajendra Prasad6Remote Sensing Laboratory, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, IndiaCentre for Climate Change and Water Research, Suresh Gyan Vihar University, Jaipur, IndiaRemote Sensing Laboratory, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, IndiaRemote Sensing Laboratory, Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, IndiaCentre for Climate Change and Water Research, Suresh Gyan Vihar University, Jaipur, IndiaDepartment of Geology, University of Delhi, Delhi, IndiaDepartment of Physics, Indian Institute of Technology (BHU), Varanasi, IndiaSoil moisture is a fundamental variable in the Earth’s hydrological cycle and vital for development of agricultural water management practices. The present study provided a comprehensive evaluation of a wide range of advanced machine learning algorithms for Soil Moisture (SM) estimation from microwave Synthetic Aperture Radar (SAR) backscatter observations over the wheat fields. From the wheat fields, samplings were performed to collect the in situ datasets on three different dates concurrent to the Sentinel-1 overpasses. The backscattering coefficients were taken as the input variables and SM as the output variable for the training and testing of different models. The performance analysis of RMSE, R-squared, and correlation coefficients revealed that the Random Forest (RF) and Convolutional Neural Network (CNN) models demonstrated superior performance for SM estimation over the wheat field. Specifically, the RF model exhibited outstanding accuracy and robustness in both the training [RMSE (%): 3.44, R-squared: 0.88, correlation: 0.95] and validation phases [RMSE (%): 7.06, R-squared: 0.61, correlation: 0.8], marking it as the most effective model followed by the CNN model with [RMSE (%): 3.9, R-squared: 0.84, correlation: 0.92] during training and [RMSE (%): 8.44, R-squared: 0.43, correlation: 0.67] for validation, highlighting challenges in the model generalisation.https://www.frontiersin.org/articles/10.3389/frsen.2024.1513620/fullsoil moistureremote sensingsynthetic aperture radarradar vegetation indexmachine learning |
| spellingShingle | Deepanshu Lakra Deepanshu Lakra Shobhit Pipil Prashant K. Srivastava Suraj Kumar Singh Manika Gupta Rajendra Prasad Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations Frontiers in Remote Sensing soil moisture remote sensing synthetic aperture radar radar vegetation index machine learning |
| title | Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| title_full | Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| title_fullStr | Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| title_full_unstemmed | Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| title_short | Soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| title_sort | soil moisture retrieval over agricultural region through machine learning and sentinel 1 observations |
| topic | soil moisture remote sensing synthetic aperture radar radar vegetation index machine learning |
| url | https://www.frontiersin.org/articles/10.3389/frsen.2024.1513620/full |
| work_keys_str_mv | AT deepanshulakra soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT deepanshulakra soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT shobhitpipil soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT prashantksrivastava soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT surajkumarsingh soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT manikagupta soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations AT rajendraprasad soilmoistureretrievaloveragriculturalregionthroughmachinelearningandsentinel1observations |