热红外遥感技术能够快速获取区域及全球尺度的地表温度，但无法有效反映有云条件下的地表热环境。针对风云四号 B 星（FY-4B）地表温度遥感产品在云层覆盖区域数据缺失的问题，提出基于 XG‐Boost （eXtreme Gradient Boosting）机器学习算法的多源数据融合方法，结合CLDAS（CMA Land Data As‐similation System）地表温度分析产品、气象站点观测数据、地形和植被等辅助数据，对陕西省典型日期的云下地表温度进行了重建与融合试验。结果表明：（1）典型日期融合后的云下地表温度与 CLDAS地表温度的相关系数超过0. 91，平均绝对误差与均方根误差稳定在2~4 ℃。（2）融合结果在保留原始FY-4B晴空数据空间特征的同时，与CLDAS 地表温度在陕北黄土高原、关中平原及复杂地形区域的空间分布一致性较高。（3）SHAP（SHapley Additive exPlanations）值分析显示，CLDAS地表温度、纬度和归一化植被指数（Normalized Difference Vegetation Index，NDVI）是影响融合结果的关键特征变量，其中，高纬度、低植被覆盖对地表温度模拟值具有显著的正向贡献，尤其是当纬度高于 35°N-36°N 和 NDVI低于0. 2时。（4）不同区域云下及全天候条件下的地表温度融合结果与相同条件下的CLDAS 地表温度检验效果相似，关中和陕南地区表现较为接近且相对更好。本研究提出的方法可为地表温度的卫星遥感全天候监测业务服务提供技术支持。

Thermal infrared remote sensing technology enables the rapid acquisition of land surface temperature （LST）data at both regional and global scales. However，its effectiveness is substantially diminished under cloudy conditions，where it fails to reliably characterize the underlying surface thermal environment. To address‐ ing the issue of data gaps in the Fengyun-4B（FY-4B）satellite LST remote sensing products in cloud-covered ar‐ eas，we proposed a multi-source data fusion method based on the eXtreme Gradient Boosting（XGBoost）ma‐ chine learning algorithm. The method integrated FY-4B LST products with auxiliary datasets，including the CMA Land Data Assimilation System（CLDAS）LST products，meteorological station observations，as well as topographic data and vegetation index，to reconstruct and fuse cloud-covered LST in Shaanxi Province on differ‐ ent typical dates. The results showed that，（1）for selected typical dates，the correlation coefficients between the fused cloud-coverd LST and CLDAS LST exceeded 0. 91，with both mean absolute errors（MAE）and root mean square errors（RMSE）stable between 2 ℃ and 4 ℃，or reduced by more than 0. 5 ℃ compared to clearsky areas.（2）The fusion method effectively addressed data gaps in cloud-covered areas，while preserving the spatial characteristics of the original FY-4B clear-sky LST. Moreover，the fused results exhibited high spatial con‐ sistency with the CLDAS LST across diverse terrains，including the Loess Plateau in Northern Shaanxi，the Guanzhong Plain，and regions characterized by complex topography. （3） Shapley Additive exPlanations （SHAP）analysis revealed that CLDAS LST，latitude and the normalized difference vegetation index emerged as the key feature variables influencing the fusion outcomes，with higher latitudes and areas with sparse vegetation exhibiting pronounced positive contributions to the simulated LST values. For areas situated north of 35° N - 36°N，increased latitude correlated with higher simulated LST values. Conversely，lower normalized difference vegetation index（NDVI）values facilitated higher LST outputs，while NDVI values exceeding 0. 2 reverse this contribution direction.（4）Comparative validation across different regions under both cloud-covered and allweather conditions indicated that the fused LST results were closely aligned with CLDAS LST，with perfor‐ mance in Northern Shaanxi slightly inferior to that in the Guanzhong and Southern Shaanxi regions，the latter two exhibiting comparable and relatively superior accuracy. These regional discrepancies may arise from the com‐ bined effects of cloud distribution patterns，topographic complexity，and the model’s sensitivity to local feature variables. The method proposed in this study can provide technical support for operational all-weather land sur‐ face temperature monitoring using satellite remote sensing，thereby enhancing the reliability and applicability of satellite-based thermal observations.