Downscaling model of SMAP L4 soil moisture product in Inner Mongolia region based on machine learning

doi:10.13474/j.cnki.11-2246.2025.0904

Abstract

Abstract: With the intensification of global warming,drought disasters are increasingly frequent in Inner Mongolia region,posing a serious threat to agricultural and animal husbandry production,ecological environment and regional sustainable development.Soil moisture,as the most direct indicator reflecting drought disasters,has a significant impact on agricultural and animal husbandry production and ecological environment in Inner Mongolia region.However,there are difficulties in obtaining soil moisture data with high temporal and spatial resolutions at present,and traditional monitoring methods are difficult to meet the demand.This study utilizes the powerful cloud storage and computing capabilities of Google Earth Engine to obtain long-time series remote sensing data including Sentinel-1 SAR,SMAP L4,Landsat 8,MODIS LST,DEM and other products of Inner Mongolia region,and performs preprocessing,unifying time scales and spatial resolutions.Through correlation analysis,downscaling factors with the greatest correlation with SMAP L4 soil moisture are selected.Random forest,support vector machine and classification and regression tree algorithms are respectively used,combined with the selected downscaling factors,to carry out soil moisture downscaling experiments and obtain soil moisture data with 1 km high spatial resolution and high accuracy in the study area.Finally,the downscaling results are compared and verified with SMAP L4 resampling data and public soil moisture datasets.The results show that the downscaling model based on random forest achieves an average R value of up to 0.84,an average MAE of 0.049 m³/m³,and both RMSE and ubRMSD are significantly smaller than the other two models,demonstrating the best downscaling performance in the study area.Based on innovative data processing methods,fine downscaling factor screening mechanisms,and comparative application of multiple machine learning algorithms,this paper provides an effective solution for obtaining long-term series,high-resolution,and high-precision soil moisture data in Inner Mongolia region,which is of great significance for local agriculture and animal husbandry,drought monitoring,and sustainable development.

Key words: GEE, machine learning, SMAP, soil moisture downscaling, active and passive microwave remote sensing

CLC Number:

P237

BIAN Chaoyang, HUANG Fang, HE Weibing, ZHANG Qiaofeng, LU Tongtong, GUAN Hao. Downscaling model of SMAP L4 soil moisture product in Inner Mongolia region based on machine learning[J]. Bulletin of Surveying and Mapping, 2025, 0(9): 19-25.

References

[1] 张建辉.气象灾害对内蒙古地区玉米生产量影响及预防对策探析[J].内蒙古科技与经济, 2023(24):99-101.
[2] 刘宪锋, 朱秀芳, 潘耀忠, 等.农业干旱监测研究进展与展望[J].地理学报, 2015, 70(11):1835-1848.
[3] EL HAJJ M, BAGHDADI N, ZRIBI M, et al.Soil moisture retrieval over irrigated grassland using X-band SAR data[J].Remote Sensing of Environment, 2016, 176:202-218.
[4] 郑曼迪, 刘忠, 许昭辉, 等.基于微波遥感的土壤水分反演估算研究进展[J].土壤学报, 2024, 61(1):16-28.
[5] 孙亚勇.基于C和L波段主被动微波遥感的土壤水分协同反演研究[D].北京:中国水利水电科学研究院, 2018.
[6] 赵伟, 文凤平, 蔡俊飞.被动微波土壤水分遥感产品空间降尺度研究:方法、进展及挑战[J].遥感学报, 2022, 26(9):1699-1722.
[7] TORIDE K, SAWADA Y, AIDA K, et al.Toward high-resolution soil moisture monitoring by combining active-passive microwave and optical vegetation remote sensing products with land surface model[J].Sensors, 2019, 19(18):3924.
[8] IM J, PARK S, RHEE J, et al.Downscaling of AMSR-E soil moisture with MODIS products using machine learning approaches[J].Environmental Earth Sciences, 2016, 75(15):1120.
[9] MALBÉTEAU Y, MERLIN O, MOLERO B, et al.DisPATCh as a tool to evaluate coarse-scale remotely sensed soil moisture using localized in situ measurements:Application to SMOS and AMSR-E data in Southeastern Australia[J].International Journal of Applied Earth Observation and Geoinformation, 2016, 45:221-234.
[10] CARLSON T N, GILLIES R R, SCHMUGGE T J.An interpretation of methodologies for indirect measurement of soil water content[J].Agricultural and Forest Meteorology, 1995, 77(3/4):191-205.
[11] SANTI E, DABBOOR M, PETTINATO S, et al.Combining machine learning and compact polarimetry for estimating soil moisture from C-band SAR data[J].Remote Sensing, 2019, 11(20):2451.
[12] ZHAO Wei, SÁNCHEZ N, LU Hui, et al.A spatial downscaling approach for the SMAP passive surface soil moisture product using random forest regression[J].Journal of Hydrology, 2018, 563:1009-1024.
[13] WEI Zushuai, MENG Yizhuo, ZHANG Wen, et al.Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau[J].Remote Sensing of Environment, 2019, 225:30-44.
[14] ZHENG C, JIA L, ZHAO T.A 21 year da-taset(2000—2020) of gap-free global daily surface soil moisture at 1km grid resolution[J].Secientific Data, 2023, 10(1):139.

[1]	YUAN Lili, YANG Xinwei, LI Menghua, CHEN Yuquan, TANG Bohui. Forest aboveground biomass mapping in the Greater Mekong Subregion using multi-source remote sensing data fusion [J]. Bulletin of Surveying and Mapping, 2025, 0(8): 43-47.
[2]	WANG Liqi, CHENG Bo, ZHANG Xiaoping, LI Kedong, SONG Menglong, YAN Tao. Aboveground biomass inversion of semi desertified grassland based on Landsat image: a case study of Damao banner [J]. Bulletin of Surveying and Mapping, 2025, 0(7): 52-57.
[3]	LI Wendong, YE Yu, LI Xia, WEI Wei, XIN Cunlin. Evaluation of landslide susceptibility by fusing SBAS-InSAR deformation and machine learning model [J]. Bulletin of Surveying and Mapping, 2025, 0(7): 126-131,146.
[4]	GUO Bin, ZHANG Liye, ZOU Bin, GUO Xianan, BAI Haorui, ZHANG Bo, GUO Tengyue, WU Min. Hyperspectral remote sensing inversion of zinc content in farmland around metal smelter [J]. Bulletin of Surveying and Mapping, 2025, 0(5): 27-33.
[5]	YANG Yang, JIA Hongguo, BAI Zhenghang, LIU Yuchen. Integrated monitoring of permafrost deformation in the Qinghai-Xizang Plateau using machine learning and SBAS-InSAR [J]. Bulletin of Surveying and Mapping, 2025, 0(4): 45-50.
[6]	CHEN Baofeng, CHEN Yunzhi, CHEN Hongmei. Chemical oxygen demand inversion in typical coastal breeding areas in Fujian based on Sentinel-2 data [J]. Bulletin of Surveying and Mapping, 2025, 0(4): 75-81.
[7]	YANG Guozhu, SUN Shirui, TIAN Maojie, SUN Huamin, HU Wei, LI Junlei. Building recognition in transmission line corridors based on high-resolution images and improved YOLOv7 model [J]. Bulletin of Surveying and Mapping, 2025, 0(4): 82-89.
[8]	WANG Rongkang, XIONG Junnan, TANG Haoran, TU Caisen, SONG Nanxiao. Improved region merging algorithm combining elevation information with random forest model [J]. Bulletin of Surveying and Mapping, 2025, 0(4): 114-119.
[9]	ZHANG Lei, SUI Tianbo, HUANG Chengbing, ZHANG Jing. Co-seismic landslide classification in Luding using multi-source remote sensing data [J]. Bulletin of Surveying and Mapping, 2025, 0(1): 83-87,126.
[10]	LIU Yiming, XU Shenghua, LIU Chunyang, MA Yu. Landslide susceptibility assessment considering multi-method integrated feature selection and negative sample optimization [J]. Bulletin of Surveying and Mapping, 2024, 0(9): 74-79.
[11]	WEI Mengsha, GONG Yun, ZHANG Xiaoyu, LIU Tengfei. Underground space LiDAR point cloud segmentation based on multi-dimensional feature GS-SVM [J]. Bulletin of Surveying and Mapping, 2024, 0(9): 117-122.
[12]	WANG Yue, YAN Meichun, XU Jiahui. A study on the pollen allergy network attention and influencing factors in urban agglomerations [J]. Bulletin of Surveying and Mapping, 2024, 0(4): 41-47.
[13]	CHEN Chang, ZHANG Yan, LI Kunheng, YANG Runze, ZHANG Junbin, LIANG Yanrong. A method of automatic mapping of gullies based on GF-7 satellite image in the black soil region in Northeast China [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 1-7.
[14]	LI Wenkang, ZHAO Quanhua, JIA Shuhan, LI Yu. Multi-feature and multi-level Sentinel-2 image extraction of lake and reservoir water bodies in Liaoning province [J]. Bulletin of Surveying and Mapping, 2024, 0(3): 37-42,106.
[15]	ZHANG Shengnan, LU Miao, WEN Caiyun, SONG Yingqiang, KANG Lu, SHEN Junhui, YANG Minzhi. Study of soil salinity remote sensing inversion method integrating crop type [J]. Bulletin of Surveying and Mapping, 2024, 0(2): 1-7.