Digital mapping of soil salinity with time-windows features optimization and ensemble learning model
Soil salinization poses considerable global environmental and ecological risks. Remote-sensing time-series data enable more accurate monitoring and prediction of soil salinity levels, offering a refined approach to soil salinization assessment. However, the current limitations of time-series data an...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124005247 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595439892824064 |
|---|---|
| author | Shuaishuai Shi Nan Wang Songchao Chen Bifeng Hu Jie Peng Zhou Shi |
| author_facet | Shuaishuai Shi Nan Wang Songchao Chen Bifeng Hu Jie Peng Zhou Shi |
| author_sort | Shuaishuai Shi |
| collection | DOAJ |
| description | Soil salinization poses considerable global environmental and ecological risks. Remote-sensing time-series data enable more accurate monitoring and prediction of soil salinity levels, offering a refined approach to soil salinization assessment. However, the current limitations of time-series data analysis—particularly in terms of timely and effective information extraction—hinder high-precision soil salinity assessments. This study proposes a data mining approach using Sentinel-1 time-series data, integrating time-series decomposition and feature selection to capture seasonal and trend components correlated with soil salinity, and determine optimal time windows and effective time spans. An advanced feature-selection algorithm was then applied to refine the model-relevant features, and the transferability of the method across different regions was validated through empirical testing. The results revealed a 12 month periodicity in the correlation between Sentinel-1 time-series features and soil salinity, with an annual decay rate of 0.0019. In the study area, the optimal time window was from July to September, with the maximum effective years ranging from 19 to 21. Recursive feature elimination has shown a gradually increasing trend in the importance of SAR features from single-temporal to multi-temporal to time-series data. The time-series analysis combined with feature selection not only significantly reduced data volumes, but also improved the prediction accuracy of the model—increased R2 of the prediction set was improved by 0.11, and a reduced root mean square error of 3.08 g kg−1, compared to single-temporal data. Furthermore, the results demonstrate that the ensemble model outperforms the individual models in terms of inversion accuracy, whereas the time-series mining method exhibits generalizability across diverse study areas and metrics. The combination of the time-series mining method with the ensemble model helps achieve a higher accuracy in digital soil mapping. |
| format | Article |
| id | doaj-art-fcb0fc03553e4c57ad93fc838db2a41e |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-fcb0fc03553e4c57ad93fc838db2a41e2025-01-19T06:24:43ZengElsevierEcological Informatics1574-95412025-03-0185102982Digital mapping of soil salinity with time-windows features optimization and ensemble learning modelShuaishuai Shi0Nan Wang1Songchao Chen2Bifeng Hu3Jie Peng4Zhou Shi5College of Agriculture, Tarim University, Alar 843300, China; Key Laboratory of Genetic Improvement and Efficient Production for Specialty Crops in Arid Southern Xinjiang of Xinjiang Corps, Alar 843300, ChinaDepartment of Earth System Science, Ministry of Education Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University, 100084 Beijing, ChinaCollege 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 Resource Management, School of Tourism and Urban Management, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaCollege of Agriculture, Tarim University, Alar 843300, China; Key Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Alar 843300, China; Research Center of Oasis Agricultural Resources and Environment in Southern Xinjiang, Tarim University, Alar 843300, China; Corresponding author at: College of Agriculture, Tarim University, Alar 843300, China.College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, ChinaSoil salinization poses considerable global environmental and ecological risks. Remote-sensing time-series data enable more accurate monitoring and prediction of soil salinity levels, offering a refined approach to soil salinization assessment. However, the current limitations of time-series data analysis—particularly in terms of timely and effective information extraction—hinder high-precision soil salinity assessments. This study proposes a data mining approach using Sentinel-1 time-series data, integrating time-series decomposition and feature selection to capture seasonal and trend components correlated with soil salinity, and determine optimal time windows and effective time spans. An advanced feature-selection algorithm was then applied to refine the model-relevant features, and the transferability of the method across different regions was validated through empirical testing. The results revealed a 12 month periodicity in the correlation between Sentinel-1 time-series features and soil salinity, with an annual decay rate of 0.0019. In the study area, the optimal time window was from July to September, with the maximum effective years ranging from 19 to 21. Recursive feature elimination has shown a gradually increasing trend in the importance of SAR features from single-temporal to multi-temporal to time-series data. The time-series analysis combined with feature selection not only significantly reduced data volumes, but also improved the prediction accuracy of the model—increased R2 of the prediction set was improved by 0.11, and a reduced root mean square error of 3.08 g kg−1, compared to single-temporal data. Furthermore, the results demonstrate that the ensemble model outperforms the individual models in terms of inversion accuracy, whereas the time-series mining method exhibits generalizability across diverse study areas and metrics. The combination of the time-series mining method with the ensemble model helps achieve a higher accuracy in digital soil mapping.http://www.sciencedirect.com/science/article/pii/S1574954124005247Soil salinizationTime-series data miningFeature selectionEnsemble learningDigital soil mapping |
| spellingShingle | Shuaishuai Shi Nan Wang Songchao Chen Bifeng Hu Jie Peng Zhou Shi Digital mapping of soil salinity with time-windows features optimization and ensemble learning model Ecological Informatics Soil salinization Time-series data mining Feature selection Ensemble learning Digital soil mapping |
| title | Digital mapping of soil salinity with time-windows features optimization and ensemble learning model |
| title_full | Digital mapping of soil salinity with time-windows features optimization and ensemble learning model |
| title_fullStr | Digital mapping of soil salinity with time-windows features optimization and ensemble learning model |
| title_full_unstemmed | Digital mapping of soil salinity with time-windows features optimization and ensemble learning model |
| title_short | Digital mapping of soil salinity with time-windows features optimization and ensemble learning model |
| title_sort | digital mapping of soil salinity with time windows features optimization and ensemble learning model |
| topic | Soil salinization Time-series data mining Feature selection Ensemble learning Digital soil mapping |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124005247 |
| work_keys_str_mv | AT shuaishuaishi digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel AT nanwang digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel AT songchaochen digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel AT bifenghu digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel AT jiepeng digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel AT zhoushi digitalmappingofsoilsalinitywithtimewindowsfeaturesoptimizationandensemblelearningmodel |