滑坡具有区域性、群发性、多发性及灾害严重的特点，开展大范围的区域滑坡空间预测评价是实现防灾减灾的有效途径。在区域滑坡空间预测研究方面，还存在预测指标体系的确定方法、预测指标的权重取值及连续数据离散化处理过程中造成的图层信息损失等问题，需要进一步研究解决。分别综述了确定性模型和非确定性模型在滑坡空间预测评价中的应用情况，重点介绍了非确定性模型中的知识驱动模型和数据驱动模型的应用情况及适用条件；并展望了区域滑坡空间预测方法的发展趋势。

Landslide is regional, group-occurring, frequent and harmful. It’s useful and effective to carry out research on regional landslide susceptibility mapping to prevent and reduce losses caused by landslides. We summarized the application of regional landslide susceptibility mapping models which include deterministic model and nondeterministic model, especially the knowledge-driven model and the data-driven model in the nondeterministic model. Moreover, we looked forward to the development tendency of these models. More researches should be carried out to select the predictors and determine the index weights of predictor objectively and quantitatively, and to avoid  the loss of useful information during the discretization of geological variables.