The accurate modeling of landslide risk is essential pre-requisite for the development of reliable landslide control and mitigation strategies. However, landslide risk depends on the poorly known environmental and socio-economic factors for regional patterns of landslide occurrence probability and vulnerability, which constitute still a matter of research. Here, a hybrid model is described that couples data mining and multi-criteria decision-making methods for hazard and vulnerability mapping and presents its application to landslide risk assessment in Golestan Province, Northeastern Iran. To this end, landslide probability is mapped using three state-of-the-art machine learning (ML) algorithms—Maximum Entropy, Support Vector Machine and Genetic Algorithm for Rule Set Production—and combine the results with Fuzzy Analytical Hierarchy Process computations of vulnerability to obtain the landslide risk map. Based on obtained results, a discussion is presented on landslide probability as a function of the main relevant human-environmental conditioning factors in Golestan Province. In particular, from the response curves of the machine learning algorithms, it can be found that the probability p of landslide occurrence decreases nearly exponentially with the distance x to the next road, fault, or river. Specifically, the results indicated that \(p \approx \exp \left( { - \lambda x} \right)\) where the length scale λ is about \(0.0797\) km⁻¹ for road, \(0.108\) km⁻¹ for fault, and \(0.734\) km⁻¹ 0.734 km⁻¹ for river. Furthermore, according to the results, p follows, approximately, a lognormal function of elevation, while the equation \(p = p_{0} - K\left( {\theta - \theta_{0} } \right)^{2}\) fits well the dependence of landslide modeling on the slope-angle θ, with \(p_{0} \approx 0.64,\;\theta_{0} \approx 25.6^{ \circ } \;{\text{and}}\;\left| K \right| \approx 6.6 \times 10^{ - 4}\). However, the highest predicted landslide risk levels in Golestan Province are located in the south and southwest areas surrounding Gorgan City, owing to the combined effect of dense local human occupation and strongly landslide-prone environmental conditions. Obtained results provide insights for quantitative modeling of landslide risk, as well as for priority planning in landslide risk management.

滑坡风险的准确建模是制定可靠的滑坡控制和缓解策略的必要先决条件。然而，滑坡风险取决于对滑坡发生概率和脆弱性的区域模式知之甚少的环境和社会经济因素，这仍然是一个研究问题。在这里，描述了一种混合模型，该模型将数据挖掘和多标准决策方法结合起来用于灾害和脆弱性测绘，并将其应用于伊朗东北部 Golestan 省的滑坡风险评估。为此，使用三种最先进的机器学习 (ML) 算法——最大熵、用于规则集生成的支持向量机和遗传算法——并将结果与​​脆弱性的模糊分析层次过程计算相结合，以获得滑坡风险图。根据获得的结果，讨论了作为 Golestan 省主要相关人类环境条件因素函数的滑坡概率。特别是，从机器学习算法的响应曲线可以发现，概率滑坡发生的p几乎随着到下一条道路、断层或河流的距离x呈指数下降。具体来说，结果表明\(p \approx \exp \left( { - \lambda x} \right)\)其中长度尺度λ大约为\(0.0797\) km ^-1对于道路，\(0.108\) km ^-1为断层，\(0.734\) km ^-1 0.734 km ^-1为河流。此外，根据结果，p近似遵循高程的对数正态函数，而方程\(p = p_{0} - K\left( {\theta - \theta_{0} } \right)^{2 }\)很好地拟合了滑坡建模对坡度角 θ 的依赖性，其中\(p_{0} \approx 0.64,\;\theta_{0} \approx 25.6^{ \circ } \;{\text{and}}\ ;\left| K \right| \approx 6.6 \times 10^{ - 4}\)。然而，由于当地人口密集和易发生滑坡的环境条件的综合影响，戈勒斯坦省预测的最高滑坡风险水平位于戈尔甘市周围的南部和西南部地区。获得的结果为滑坡风险的定量建模以及滑坡风险管理的优先规划提供了见解。