To date, various methods of flood prediction using numerical analysis or machine learning have been studied. However, a methodology for simultaneously predicting the rainfall return period and an inundation map for observed rainfall has not been presented. Simultaneous prediction of the return period and inundation map would be a useful technique for responding to floods in real-time and could provide an expected inundation area by return period. In this study, return period estimation for observed rainfall was performed via PNN (probabilistic neural network). SVR (support vector regression) and a SOM (self-organizing map) were used to predict flood volume and inundation maps. The study area was the Gangnam area, which has experienced extensive urbanization. The database for training SVR and SOM was constructed by one- and two-dimensional flood analysis with consideration of 120 probable rainfall events. The probable rainfall events were composed with 2–100 year return periods and 1–3 hour durations. The SVR technique was used to predict flood volume according to the rainfall return period, and the SOM was used to cluster various expected flood patterns to be used for predicting inundation maps. The prediction results were compared with the simulation results of a two-dimensional flood analysis model. The highest fitness of the predicted flood maps in the study area was calculated at 85.94%. The proposed method was found to constitute a practical methodology that could be helpful in improving urban flood response capabilities.

中文翻译：

---

具有降雨重现期和机器学习的洪水地图预测

迄今为止，已经研究了使用数值分析或机器学习的各种洪水预测方法。然而，尚未提出同时预测降雨重现期和观测降雨的淹没图的方法。同时预测重现期和淹没地图将是实时响应洪水的有用技术，并可以按重现期提供预期的淹没区域。在本研究中，观测降雨的重现期估计是通过 PNN（概率神经网络）进行的。SVR（支持向量回归）和 SOM（自组织图）用于预测洪水量和淹没图。研究区域是江南地区，该地区经历了广泛的城市化。训练SVR和SOM的数据库是通过考虑120个可能的降雨事件的一维和二维洪水分析构建的。可能的降雨事件由 2-100 年重现期和 1-3 小时持续时间组成。SVR技术用于根据降雨重现期预测洪水量，SOM用于聚类各种预期洪水模式，用于预测洪水图。预测结果与二维洪水分析模型的模拟结果进行了比较。研究区预测洪水图的最高适应度为85.94%。发现所提出的方法构成了一种有助于提高城市洪水响应能力的实用方法。可能的降雨事件由 2-100 年重现期和 1-3 小时持续时间组成。SVR技术用于根据降雨重现期预测洪水量，SOM用于聚类各种预期洪水模式，用于预测洪水图。预测结果与二维洪水分析模型的模拟结果进行了比较。研究区预测洪水图的最高适应度为85.94%。发现所提出的方法构成了一种有助于提高城市洪水响应能力的实用方法。可能的降雨事件由 2-100 年重现期和 1-3 小时持续时间组成。SVR技术用于根据降雨重现期预测洪水量，SOM用于聚类各种预期洪水模式，用于预测洪水图。预测结果与二维洪水分析模型的模拟结果进行了比较。研究区预测洪水图的最高适应度为85.94%。发现所提出的方法构成了一种有助于提高城市洪水响应能力的实用方法。SOM 用于聚类各种预期的洪水模式，用于预测洪水图。预测结果与二维洪水分析模型的模拟结果进行了比较。研究区预测洪水图的最高适应度为85.94%。发现所提出的方法构成了一种有助于提高城市洪水响应能力的实用方法。SOM 用于聚类各种预期的洪水模式，用于预测洪水图。预测结果与二维洪水分析模型的模拟结果进行了比较。研究区预测洪水图的最高适应度为85.94%。发现所提出的方法构成了一种有助于提高城市洪水响应能力的实用方法。