Rainfall-induced shallow landslides are expected to increase due to more intense precipitation linked to climate change. This study aims to develop an effective pixel-based tool for the space-time prediction of soil slips by combining a FeedForward Neural Network (FFN) with insights from the physically-based model SLIP (Shallow Landslide Instability Prediction). The FFN model was developed based on past events in four towns of the Emilia Apennines (Italy) from 2004 to 2014 under varying rainfall conditions. Among the key aspects analysed were the inclusion of both landslide and non-landslide days, the evaluation of two different cumulative rainfall periods (10 and 30 days), and various technical elements related to machine learning, including training approach, network topology, and activation function. A 2:1 imbalance in non-landslide/landslide pixels was implemented to enhance prediction performance. Prediction accuracy was measured using the Quality Combined Index (QCI), which combines AUROC, AUPRC, and F1-score. The best FFN model achieved a QCI of 0.85, accurately predicting non-landslides and minimizing false alarms. A comparison with SLIP showed that SLIP better captured the progressive destabilization in areas nearing instability, while the FFN provided a clearer distinction between stable and unstable zones. A successful blind prediction was demonstrated for a landslide in Compiano (November 2019), validating the model's applicability. SLIP also contributed to understanding the initial soil saturation and rainfall conditions, highlighting its potential to enhance FFN predictions in different meteorological scenarios. Although the developed pixel-based model could be utilized as is, further research is needed to enhance its application for early warning purposes in varying meteorological conditions.

中文翻译：

---

人工神经网络与 SLIP 模型相比，通过人工神经网络对降雨诱发的浅层滑坡进行时空预测


由于与气候变化相关的更强降水，预计降雨引起的浅层滑坡将增加。本研究旨在通过将前馈神经网络 （FFN） 与基于物理的模型 SLIP（浅层滑坡不稳定性预测）的见解相结合，开发一种有效的基于像素的工具，用于土壤滑坡的时空预测。FFN 模型是根据 2004 年至 2014 年在不同降雨条件下在艾米利亚亚平宁山脉（意大利）四个城镇发生的过去事件开发的。分析的关键方面包括包括滑坡和非滑坡天数、两个不同的累积降雨期（10 天和 30 天）的评估，以及与机器学习相关的各种技术元素，包括训练方法、网络拓扑和激活函数。在非滑坡/滑坡像素中实施了 2：1 的不平衡，以提高预测性能。使用质量综合指数 （QCI） 测量预测准确性，该指数结合了 AUROC、AUPRC 和 F1 分数。最佳 FFN 模型实现了 0.85 的 QCI，准确预测了非滑坡并最大限度地减少了误报。与 SLIP 的比较表明，SLIP 更好地捕捉了接近不稳定区域的渐进性不稳定，而 FFN 更清楚地区分了稳定区和不稳定区。对 Compiano 的山体滑坡（2019 年 11 月）进行了成功的盲预测，验证了该模型的适用性。SLIP 还有助于了解初始土壤饱和度和降雨条件，突出了其在不同气象情景下增强 FFN 预测的潜力。 尽管开发的基于像素的模型可以按原样使用，但需要进一步研究以增强其在不同气象条件下的早期预警目的的应用。