针对沟壑发育地表无地面控制点（Ground Control points，GCPs）条件下卫星遥感立体影像地形三维重建精度较低、大面积GCPs采集困难或成本高等问题，本文提出融合卫星激光测高数据的高分七号（GF-7）卫星影像数字表面模型（Digital Surface Model，DSM）BP神经网络方法。该方法通过建立无控条件下GF-7卫星立体影像生成的DSM、地理位置经度与纬度、地形坡度、地形误差等多因子与激光测高点GEDI之间的关系，获取融合结果以改进无控条件下地形DSM精度。实验结果表明，沟壑发育地表矿区无控条件下GF-7卫星立体影像生成的DSM高程精度可高达20.49米，而本文融合生成的DSM平均高程精度为1.63米，与有控制点条件下地形DSM 1.44 米的高程精度基本相当。本文方法有效改善了沟壑发育地表矿区无控条件下卫星立体影像生成DSM高程精度质量低的问题，为国产高分影像推广应用与高精度地形建模提供新思路。

The accuracy of Digital Surface Model (DSM) reconstructed from satellite stereo imagery is generally lower in rugged gully-dominated landscapes than in flat areas, especially in the absence of ground control points (GCPs). Moreover, collecting GCPs in large and rugged areas is often operationally challenging or costly. In order to improve the accuracy of DSM derived from satellite stereo imagery, this study proposes a method that integrates laser altimetry data with the DSM generated from Gaofen-7 (GF-7) satellite stereo imagery using a Backpropagation (BP) neural network. The method seeks to improve terrain DSM accuracy in areas where GCPs are either scarce or costly to obtain, providing a more efficient solution for terrain modeling in such regions. Considering the high-precision elevation accuracy of laser altimetry data, the method improves the DSM accura-cy without GCPs through establishing relationships between multiple factors and elevation data from GEDI(Global Ecosystem Dynamics Investigation) mission. These factors include the DSM generated from GF-7 satellite stereo im-agery without GCPs, geographic coordinates (longitude and latitude), terrain slope, and terrain errors. This fusion is achieved through the use of a BP neural network, which is trained to model and enhance the accuracy of the DSM un-der uncontrolled conditions. The study area is located in the Loess Plateau region spanning Shaanxi Province and Inner Mongolia Autonomous Region, China. The terrain is severely eroded loess gullies, intensive mining activities, and dra-matic terrain undulations. The method is tested across regions covered with different numbers of images, and its per-formance is validated through comparisons with ground-truth data measured by RTK. The experimental results show that the elevation error of GF-7 stereo-derived DSM in gully-developed mining are-as without GCPs can reach up to 20.49 meters. In contrast, the average elevation accuracy of the fused DSM is signif-icantly improved to 1.63 meters after applying the fusion technique using the BP neural network, which is comparable to the accuracy of DSM generated with GCPs (1.44 meters). Furthermore, when utilizing quality-filtered laser altimetry points as substitute GCPs directly, the elevation accuracy of DSM can also be refined to 2.40 meters. However, the proposed comprehensive multi-factor fusion method yields better performance (1.63 meters vs 2.40 meters), confirm-ing the advantage of the fusion approaches. The improvement in elevation accuracy demonstrates that, whether used directly as GCP substitutes or through data fusion approaches, incorporating laser altimetry data can effectively en-hance the vertical accuracy of DSMs derived from GF-7 satellite stereo imagery without GCPs. The findings of this study show that the proposed BP neural network-based fusion method significantly enhances the accuracy of DSMs generated from GF-7 satellite stereo imagery in areas without GCPs. This approach effectively solves the problem of low elevation accuracy in regions with complex topography, such as gully-developed mining ar-eas. The study not only provides an innovative solution for terrain modeling in areas lacking GCPs but also offers a new way to utilize domestic high-resolution satellite imagery for high-precision terrain reconstruction. This method con-tributes to the advancement of terrain modeling techniques, especially in regions where obtaining GCPs is difficult or impossible, and provides a viable solution for reducing labor costs, improving operational efficiency, and reconstructing high-quality terrain DSMs.