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.