面向地面观测稀缺区域的土壤湿度短期预测方法

doi:10.3799/dqkx.2026.187

面向地面观测稀缺区域的土壤湿度短期预测方法

doi: 10.3799/dqkx.2026.187

1. 中国地质大学(武汉) 地质探测与评估教育部重点实验室, 湖北武汉 430074;
2. 中国地质大学(武汉) 计算机学院, 湖北武汉 430074;
3. 中国地质调查局自然资源航空物探遥感中心, 北京海淀, 100083

基金项目:

中国地质调查局项目（DD20220301601,20251960420），地质探测与评估教育部重点实验室主任基金（GLAB2024ZR01）

详细信息

作者简介:
王瑞禛(1993-),男,博士研究生,主要从事智能地学信息处理理论与方法研究,E-mail:ruizhen.wang@cug.edu.cn

中图分类号: TP18;S152.71
计量
- 文章访问数: 34
- HTML全文浏览量: 0
- PDF下载量: 8
- 被引次数: 0
出版历程
- 收稿日期: 2026-02-02
- 网络出版日期: 2026-08-25

Short-Term Forecast of Soil Moisture in Regions with Limited Ground Observations

1. Key Laboratory of Geological Survey and Evaluation of Ministary of Education, China University of Geoscience, Wuhan, C hina;
2. Faculty of Computer Science, China University of Geoscience, Wuhan, China;
3. China Aero Geophysical & Remote Sensing Center for Natural Resources, Beijing, China

摘要

摘要: 高分辨率、高时效性的土壤湿度信息对农业、水文及生态领域的精细化管理至关重要。然而，现有土壤湿度制图方法多依赖历史遥感影像反演，或基于站点观测与低分辨率产品开展时间序列预测，难以同步实现空间连续性与短期预测能力，且在缺乏地面观测区域的应用受限。本研究提出一种集成“影像融合-偏差校正-空间降尺度-短期预测”的级联框架，旨在不依赖研究区本地观测数据生成30 m分辨率、未来时相的多层土壤湿度分布图。首先，在GEE平台融合Landsat与MODIS数据生成时空连续的高分辨率光谱指数；其次，利用GLDASv2.1产品对SMCI1.0土壤湿度产品数据进行全局偏差校正；再结合地形、气象与土壤属性，采用极端梯度提升模型将校正后SMCI1.0产品降尺度至30 m分辨率；最后，基于降尺度结果与滞后/未来气象变量，构建XGBoost模型，实现给定日期未来三天土壤湿度预测。基于闪电河流域地面观测网络（SDR-SMN）的验证表明：偏差校正和降尺度过程均提升了原始SMCI1.0数据与地面观测的空间一致性；预测模型在时间与空间独立交叉验证中表现稳健，各层土壤湿度未来三天预测的R>0.6。该框架能够为缺乏地面观测地区提供高分辨率土壤湿度短期预测方案。
- 土壤湿度 /
- 时空融合 /
- 短期预测 /
- 高分辨率制图 /
- 空间降尺度
Abstract: High-resolution and timely soil moisture information is essential for fine-scale management in agricultural, hydrological, and ecological applications. However, existing soil moisture mapping approaches mainly rely on historical remote sensing retrievals or time-series prediction based on in-situ observations and coarse-resolution products, making it difficult to simultaneously achieve spatial continuity and short-term forecasting capability. Moreover, their applicability is limited in regions lacking ground observations. This study proposed a cascading framework integrating image fusion, bias correction, spatial downscaling, and short-term prediction to generate multi-layer soil moisture maps at 30 m spatial resolution for near future without relying on local in-situ observations for model construction. First, Landsat-8 and MODIS data are fused on the Google Earth Engine platform to produce spatiotemporally continuous high-resolution spectral indices. Second, the SMCI1.0 soil moisture product is globally bias-corrected using the GLDASv2.1 product. Subsequently, the bias-corrected SMCI1.0 data are downscaled to 30 m resolution by incorporating terrain, meteorological, and soil properties through an Extreme Gradient Boosting (XGBoost) model. Finally, based on the downscaled soil moisture and lagged/forecast meteorological variables, XGBoost based prediction models are constructed to forecast soil moisture for up to three days ahead from a given date. Validation using the in situ observation network in the Shandian River Basin (SDR-SMN) demonstrates that both the bias correction and downscaling processes significantly improve the spatial consistency between the original SMCI1.0 product and ground measurements. The prediction model exhibits robust performance under temporally and spatially independent cross-validation, achieving correlation coefficients (R) greater than 0.6 for three-day-ahead soil moisture prediction across multiple soil layers. The proposed framework provides a practical solution for high-resolution short-term soil moisture prediction in regions with limited or no ground observations.
- soil moisture /
- spatial-temporal fusion /
- short-term forecast /
- high-resolution /
- downscaling

HTML全文

参考文献(40)

Aitchison, J., 1982. The Statistical Analysis of Compositional Data. J. R. Stat. Soc. Ser. B Methodol. 44, 139-160. https://doi.org/10.1111/j.2517-6161.1982.tb01195.x
Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., Tian, Q., 2023. Accurate medium-range global weather forecasting with 3D neural networks. Nature 619, 533-538. https://doi.org/10.1038/s41586-023-06185-3
Bojinski, S., Verstraete, M., Peterson, T.C., Richter, C., Simmons, A., Zemp, M., 2014. The concept of essential climate variables in support of climate research, applications, and policy. Bull. Am. Meteorol. Soc. 95, 1431-1443.
Brocca, L., Gaona, J., Bavera, D., Fioravanti, G., Puca, S., Ciabatta, L., Filippucci, P., Mosaffa, H., Esposito, G., Roberto, N., Dari, J., Vreugdenhil, M., Wagner, W., 2024. Exploring the actual spatial resolution of 1 km satellite soil moisture products. Sci. Total Environ. 945, 174087. https://doi.org/10.1016/j.scitotenv.2024.174087
Chandra Joshi, R., Ryu, D., Lane, P.N.J., Sheridan, G.J., 2023. Seasonal forecast of soil moisture over Mediterranean-climate forest catchments using a machine learning approach. J. Hydrol. 619, 129307. https://doi.org/10.1016/j.jhydrol.2023.129307
Chen, L., Hu, B., Sun, J., Xu, Y.J., Zhang, G., Ma, H., Ren, J., 2025. Using remote sensing and machine learning to generate 100-cm soil moisture at 30-m resolution for the black soil region of China: Implication for agricultural water management. Agric. Water Manag. 309, 109353. https://doi.org/10.1016/j.agwat.2025.109353
Chen, T., Guestrin, C., 2016. Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. pp. 785-794.
Distefano, P., Peres, D.J., Piciullo, L., Palazzolo, N., Scandura, P., Cancelliere, A., 2023. Hydro-meteorological landslide triggering thresholds based on artificial neural networks using observed precipitation and ERA5-Land soil moisture. Landslides 20, 2725-2739.
Du, J., Kimball, J.S., Jencso, K., Hoylman, Z., Brust, C., Ketchum, D., Xu, Y., Lu, H., Sheffield, J., 2024. Machine-Learning Based Multi-Layer Soil Moisture Forecasts-An Application Case Study of the Montana 2017 Flash Drought. Water Resour. Res. 60, e2023WR036973. https://doi.org/10.1029/2023WR036973
Fang, K., Shen, C., 2020. Near-Real-Time Forecast of Satellite-Based Soil Moisture Using Long Short-Term Memory with an Adaptive Data Integration Kernel. J. Hydrometeorol. 21, 399-413. https://doi.org/10.1175/JHM-D-19-0169.1
Fischer, S.C., Niemann, J.D., Scalia, J., Bullock, M.D., Proulx, H.E., Kim, B., Green, T.R., Grazaitis, P.J., 2025. Assessing the influence of model inputs on performance of the EMT + VS soil moisture downscaling model for a large foothills region in Northern Colorado. J. Hydrol. 650, 132397. https://doi.org/10.1016/j.jhydrol.2024.132397
Frankenstein, S., Stevens, M., Scott, C., 2015. Ingestion of Simulated SMAP L3 Soil Moisture Data into Military Maneuver Planning. J. Hydrometeorol. 16, 427-440. https://doi.org/10.1175/JHM-D-14-0032.1
Karthikeyan, L., Mishra, A.K., 2021. Multi-layer high-resolution soil moisture estimation using machine learning over the United States. Remote Sens. Environ. 266, 112706. https://doi.org/10.1016/j.rse.2021.112706
Ke, Y., Im, J., Park, S., Gong, H., 2017. Spatiotemporal downscaling approaches for monitoring 8-day 30 m actual evapotranspiration. ISPRS J. Photogramm. Remote Sens. 126, 79-93. https://doi.org/10.1016/j.isprsjprs.2017.02.006
Li, Q., Shi, G., Shangguan, W., Nourani, V., Li, J., Li, L., Huang, F., Zhang, Y., Wang, C., Wang, D., Qiu, J., Lu, X., Dai, Y., 2022. A 1 km daily soil moisture dataset over China using in situ measurement and machine learning. Earth Syst. Sci. Data 14, 5267-5286. https://doi.org/10.5194/essd-14-5267-2022
Li, Z., Yuan, Q., Su, X., 2024. High-spatial-resolution surface soil moisture retrieval using the Deep Forest model in the cloud environment over the Tibetan Plateau. Geo-Spat. Inf. Sci. 1-20. https://doi.org/10.1080/10095020.2024.2307931
Liu, F., Zhang, G., 2021. Basic soil property dataset of high-resolution China Soil Information Grids (2010-2018). Natl. Tibet. Plateau Data Cent.
Ma, H., Zeng, J., Zhang, X., Peng, J., Li, X., Fu, P., Cosh, M.H., Letu, H., Wang, S., Chen, N., Wigneron, J.-P., 2024. Surface soil moisture from combined active and passive microwave observations: Integrating ASCAT and SMAP observations based on machine learning approaches. Remote Sens. Environ. 308, 114197. https://doi.org/10.1016/j.rse.2024.114197
Ma, L., Qi, S., Guo, S., 2025. Hydrologic Characteristics and Settlement Deformation of Backfilled Loess in Yan’an, China. J. Earth Sci. 36, 1198-1212. https://doi.org/10.1007/s12583-024-1990-z
Nietupski, T.C., Kennedy, R.E., Temesgen, H., Kerns, B.K., 2021. Spatiotemporal image fusion in Google Earth Engine for annual estimates of land surface phenology in a heterogenous landscape. Int. J. Appl. Earth Obs. Geoinformation 99, 102323. https://doi.org/10.1016/j.jag.2021.102323
Ning, J., Yao, Y., Tang, Q., Li, Y., Fisher, J.B., Zhang, Xiaotong, Jia, K., Xu, J., Shang, K., Yang, J., Yu, R., Liu, L., Zhang, Xueyi, Xie, Z., Fan, J., 2023. Soil moisture at 30 m from multiple satellite datasets fused by random forest. J. Hydrol. 625, 130010. https://doi.org/10.1016/j.jhydrol.2023.130010
Rodell, M., Houser, P., Jambor, U., Gottschalck, J., Mitchell, K., Meng, C.-J., Arsenault, K., Cosgrove, B., Radakovich, J., Bosilovich, M., others, 2004. The global land data assimilation system. Bull. Am. Meteorol. Soc. 85, 381-394.
Rosenbaum, U., Bogena, H.R., Herbst, M., Huisman, J.A., Peterson, T.J., Weuthen, A., Western, A.W., Vereecken, H., 2012. Seasonal and event dynamics of spatial soil moisture patterns at the small catchment scale. Water Resour. Res. 48, 2011WR011518. https://doi.org/10.1029/2011WR011518
Sanchez, P.A., Ahamed, S., Carré, F., Hartemink, A.E., Hempel, J., Huising, J., Lagacherie, P., McBratney, A.B., McKenzie, N.J., Mendonça-Santos, M.D.L., Minasny, B., Montanarella, L., Okoth, P., Palm, C.A., Sachs, J.D., Shepherd, K.D., Vågen, T.-G., Vanlauwe, B., Walsh, M.G., Winowiecki, L.A., Zhang, G.-L., 2009. Digital Soil Map of the World. Science 325, 680-681. https://doi.org/10.1126/science.1175084
Togneri, R., Felipe Dos Santos, D., Camponogara, G., Nagano, H., Custódio, G., Prati, R., Fernandes, S., Kamienski, C., 2022. Soil moisture forecast for smart irrigation: The primetime for machine learning. Expert Syst. Appl. 207, 117653. https://doi.org/10.1016/j.eswa.2022.117653
Tucker, C.J., 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens. Environ. 8, 127-150. https://doi.org/10.1016/0034-4257(79)90013-0
Wu, Y., Zhong, Y., Liu, S., Xu, G., Xiao, C., Wu, X., Xie, B., Li, Z., Shum, C.K., 2025. Hydrogeodesy Facilitates the Accurate Assessment of Extreme Drought Events. J. Earth Sci. 36, 347-350. https://doi.org/10.1007/s12583-024-0123-z
Wu, Z., Feng, H., He, H., Zhou, J., Zhang, Y., 2021. Evaluation of Soil Moisture Climatology and Anomaly Components Derived From ERA5-Land and GLDAS-2.1 in China. Water Resour. Manag. 35, 629-643. https://doi.org/10.1007/s11269-020-02743-w
Yue, J., Tian, J., Tian, Q., Xu, K., Xu, N., 2019. Development of soil moisture indices from differences in water absorption between shortwave-infrared bands. ISPRS J. Photogramm. Remote Sens. 154, 216-230. https://doi.org/10.1016/j.isprsjprs.2019.06.012
Zhang, Y., Liang, S., Ma, H., He, T., Wang, Q., Li, B., Xu, J., Zhang, G., Liu, X., Xiong, C., 2023. Generation of global 1 km daily soil moisture product from 2000 to 2020 using ensemble learning. Earth Syst. Sci. Data 15, 2055-2079. https://doi.org/10.5194/essd-15-2055-2023
Zhang, Y., Liang, S., Zhu, Z., Ma, H., He, T., 2022. Soil moisture content retrieval from Landsat 8 data using ensemble learning. ISPRS J. Photogramm. Remote Sens. 185, 32-47. https://doi.org/10.1016/j.isprsjprs.2022.01.005
Zhang, Y., Schaap, M.G., 2017. Weighted recalibration of the Rosetta pedotransfer model with improved estimates of hydraulic parameter distributions and summary statistics (Rosetta3). J. Hydrol. 547, 39-53. https://doi.org/10.1016/j.jhydrol.2017.01.004
Zhang, Y.-R., Shang, G.-F., Leng, P., Ma, C., Ma, J., Zhang, X., Li, Z.-L., 2023. Estimation of quasi-full spatial coverage soil moisture with fine resolution in China from the combined use of ERA5-Land reanalysis and TRIMS land surface temperature product. Agric. Water Manag. 275, 107990. https://doi.org/10.1016/j.agwat.2022.107990
Zhao, T., Shi, J., Lv, L., Xu, H., Chen, D., Cui, Q., Jackson, T.J., Yan, G., Jia, L., Chen, L., Zhao, K., Zheng, X., Zhao, L., Zheng, C., Ji, D., Xiong, C., Wang, T., Li, R., Pan, J., Wen, J., Yu, C., Zheng, Y., Jiang, L., Chai, L., Lu, H., Yao, P., Ma, J., Lv, H., Wu, J., Zhao, W., Yang, N., Guo, P., Li, Y., Hu, L., Geng, D., Zhang, Z., 2020. Soil moisture experiment in the Luan River supporting new satellite mission opportunities. Remote Sens. Environ. 240, 111680. https://doi.org/10.1016/j.rse.2020.111680
Zheng, J., Zhao, T., Lü, H., Shi, J., Cosh, M.H., Ji, D., Jiang, L., Cui, Q., Lu, H., Yang, K., Wigneron, J.-P., Li, X., Zhu, Y., Hu, L., Peng, Z., Zeng, Y., Wang, X., Kang, C.S., 2022. Assessment of 24 soil moisture datasets using a new in situ network in the Shandian River Basin of China. Remote Sens. Environ. 271, 112891. https://doi.org/10.1016/j.rse.2022.112891
Zhu, X., Chen, J., Gao, F., Chen, X., Masek, J.G., 2010. An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions. Remote Sens. Environ. 114, 2610-2623. https://doi.org/10.1016/j.rse.2010.05.032
戴磊, 王贵玲, 何雨江, 2021. 基于分形理论研究土壤结构及其水分特征关系. 地球科学 46.
杨丽娜, 贾德彬, 高瑞忠, 苏文旭, 卢方园, 郝玉胜, 2023. 闪电河流域“三水”氢氧同位素特征及水体转换分析. 环境科学 44. https://doi.org/10.13227/j.hjkx.202207230
索瑞厅, 张绍兴, 姜德强, 李铱, 李旭峰, 2022. 多伦县地下水资源评价与可开采潜力分析. 湖南师范大学自然科学学报 45.
黄德华, 陈佐忠, 1986. 内蒙古锡林郭勒沙地草场49种植物根系分布深度的初步观察. 中国草原.