Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection
Passive microwave (PMW) remote sensing is increasingly employed for generating seamless all-weather land surface temperature (LST) data due to its ability to penetrate cloud cover and capture the actual surface conditions underneath. Existing PMW retrieval methods often utilize large amounts of remo...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10849807/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857173820604416 |
|---|---|
| author | Yang Dai Yingbao Yang Xin Pan Penghua Hu Xiangjin Meng Fanggang Li Zhenwei Wang |
| author_facet | Yang Dai Yingbao Yang Xin Pan Penghua Hu Xiangjin Meng Fanggang Li Zhenwei Wang |
| author_sort | Yang Dai |
| collection | DOAJ |
| description | Passive microwave (PMW) remote sensing is increasingly employed for generating seamless all-weather land surface temperature (LST) data due to its ability to penetrate cloud cover and capture the actual surface conditions underneath. Existing PMW retrieval methods often utilize large amounts of remote sensing data, overlooking the fact that redundant data can increase computational and time costs, reduce model interpretability, and may negatively impact accuracy. In this article, we proposed a PMW-LST retrieval method that integrates CatBoost-Based adaptive feature selection. First, we categorized the data into six groups based on the underlying surface types and data view time. Next, for each group, we ranked the feature sets according to their importance and employed the recursive feature elimination (RFE) method for feature selection. Finally, the optimized feature sets were used in the CatBoost algorithm to construct the PMW-LST retrieval model. We compared the accuracy of the proposed method with the Holmes, multichannel, and Random Forest algorithms. Results showed that the proposed method had lowest RMSE, with the value of 3.28 K (1.95 K), 2.69 K (1.65 K), and 3.71 K (2.22 K) on grassland, cropland, and barren land at daytime (nighttime), respectively. The verification at sites in Heihe river basin shows that the ubRMSE ranges from 1.73 to 4.48 K at daytime and 2.71 to 3.19 K at nighttime under clear-sky conditions, and from 1.83 to 5.23 K at daytime and 2.77 to 3.93 K at nighttime under cloudy-sky conditions. These results indicate the proposed method achieves higher accuracy in generating seamless all-weather LST data. |
| format | Article |
| id | doaj-art-f3a12ad9e9fc4a1988b9381534e3b54a |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-f3a12ad9e9fc4a1988b9381534e3b54a2025-02-12T00:00:32ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184949496310.1109/JSTARS.2025.353260510849807Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature SelectionYang Dai0https://orcid.org/0009-0002-9917-5611Yingbao Yang1https://orcid.org/0000-0002-3092-5683Xin Pan2https://orcid.org/0000-0003-3176-8218Penghua Hu3https://orcid.org/0000-0002-9084-0251Xiangjin Meng4https://orcid.org/0000-0003-2643-5064Fanggang Li5Zhenwei Wang6https://orcid.org/0009-0003-5323-7167School of Earth Science and Engineering, Hohai University, Nanjing, ChinaCollege of Geography and Remote Sensing, Hohai University, Nanjing, ChinaCollege of Geography and Remote Sensing, Hohai University, Nanjing, ChinaSchool of Earth Science and Engineering, Hohai University, Nanjing, ChinaCollege of Geography and Remote Sensing, Hohai University, Nanjing, ChinaSchool of Earth Science and Engineering, Hohai University, Nanjing, ChinaSchool of Earth Science and Engineering, Hohai University, Nanjing, ChinaPassive microwave (PMW) remote sensing is increasingly employed for generating seamless all-weather land surface temperature (LST) data due to its ability to penetrate cloud cover and capture the actual surface conditions underneath. Existing PMW retrieval methods often utilize large amounts of remote sensing data, overlooking the fact that redundant data can increase computational and time costs, reduce model interpretability, and may negatively impact accuracy. In this article, we proposed a PMW-LST retrieval method that integrates CatBoost-Based adaptive feature selection. First, we categorized the data into six groups based on the underlying surface types and data view time. Next, for each group, we ranked the feature sets according to their importance and employed the recursive feature elimination (RFE) method for feature selection. Finally, the optimized feature sets were used in the CatBoost algorithm to construct the PMW-LST retrieval model. We compared the accuracy of the proposed method with the Holmes, multichannel, and Random Forest algorithms. Results showed that the proposed method had lowest RMSE, with the value of 3.28 K (1.95 K), 2.69 K (1.65 K), and 3.71 K (2.22 K) on grassland, cropland, and barren land at daytime (nighttime), respectively. The verification at sites in Heihe river basin shows that the ubRMSE ranges from 1.73 to 4.48 K at daytime and 2.71 to 3.19 K at nighttime under clear-sky conditions, and from 1.83 to 5.23 K at daytime and 2.77 to 3.93 K at nighttime under cloudy-sky conditions. These results indicate the proposed method achieves higher accuracy in generating seamless all-weather LST data.https://ieeexplore.ieee.org/document/10849807/Catboostland surface temperature (LST)passive microwave (PMW)recursive feature elimination (RFE)remote sensing |
| spellingShingle | Yang Dai Yingbao Yang Xin Pan Penghua Hu Xiangjin Meng Fanggang Li Zhenwei Wang Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Catboost land surface temperature (LST) passive microwave (PMW) recursive feature elimination (RFE) remote sensing |
| title | Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection |
| title_full | Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection |
| title_fullStr | Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection |
| title_full_unstemmed | Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection |
| title_short | Retrieval of Land Surface Temperature From Passive Microwave Observations Using CatBoost-Based Adaptive Feature Selection |
| title_sort | retrieval of land surface temperature from passive microwave observations using catboost based adaptive feature selection |
| topic | Catboost land surface temperature (LST) passive microwave (PMW) recursive feature elimination (RFE) remote sensing |
| url | https://ieeexplore.ieee.org/document/10849807/ |
| work_keys_str_mv | AT yangdai retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT yingbaoyang retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT xinpan retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT penghuahu retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT xiangjinmeng retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT fanggangli retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection AT zhenweiwang retrievaloflandsurfacetemperaturefrompassivemicrowaveobservationsusingcatboostbasedadaptivefeatureselection |