Landslide failure time prediction is considered a challenging issue in landslide research. A significant goal of landslide research is to provide scientific and accurate prediction methods. In this paper, the short-term forecasting of landslides (STFL) model is proposed by analyzing landslide deformation characteristics in a known evolution process. The landslides on the southern slope of the West open pit mine (SSWOPM) in Liaoning province, northeast China, and Huangci in Gansu province, northwest China, were selected as the study cases. After pre-processing, which include eliminating abnormal data (t test), adding missing data (cubic spline interpolation), and smoothing noisy data (Savitzky–Golay filters), the displacement data are assembled to serve as the model’s input parameters. The parameters of STFL can be obtained through the Levenberg–Marquardt (LM) algorithm. Using the forecasting criterion, the time of failure of landslides can be predicted and determined. Forecasting results provide evidence that the STFL model can achieve an accurate prediction of landslide displacement (correlation coefficient R² > 0.99). The forecasting results of the SSWOPM and Huangci landslides indicate that the forecasting failure time of the STFL model is March 10, 2014 and January 31, 1995, respectively, which are near the actual failure time compared with those obtained using the Verhulst model. This finding indicates that the new method has excellent reliability and accuracy in landslide prediction and a robust description of the landslide movement.

滑坡破坏时间的预测被认为是滑坡研究中一个具有挑战性的问题。滑坡研究的一个重要目标是提供科学而准确的预测方法。本文通过分析已知演化过程中的滑坡变形特征，提出了滑坡的短期预测模型。选择了辽宁省西部露天矿（SSWOPM）南坡和西北甘肃省黄ci县的滑坡作为研究案例。经过预处理后，其中包括消除异常数据（t测试），添加缺失数据（三次样条插值）和平滑噪声数据（Savitzky-Golay滤波器），将位移数据组合起来作为模型的输入参数。STFL的参数可以通过Levenberg-Marquardt（LM）算法获得。使用预测标准，可以预测并确定滑坡的破坏时间。预测结果提供了证据，表明STFL模型可以实现对滑坡位移的准确预测（相关系数R ²> 0.99）。SSWOPM和黄ci滑坡的预测结果表明，STFL模型的预测失效时间分别为2014年3月10日和1995年1月31日，与使用Verhulst模型获得的预测失效时间相近。这一发现表明，该新方法在滑坡预测和滑坡运动的可靠描述方面具有出色的可靠性和准确性。