Among the various natural disasters that take place around the world, flood is considered to be the most extensive. There have been several floods in Buzău river basin, and as a result of this, the area has been chosen as the study area. For the purpose of this research, we applied deep learning and machine learning benchmarks in order to prepare flood potential maps at the basin scale. In this regard 12 flood predictors, 205 flood and 205 non-flood locations were used as input data into the following 3 complex models: Deep Learning Neural Network-Harris Hawk Optimization-Index of Entropy (DLNN-HHO-IOE), Multilayer Perceptron-Harris Hawk Optimization-Index of Entropy (MLP-HHO-IOE) and Stacking ensemble-Harris Hawk Optimization-Index of Entropy (Stacking-HHO-IOE). The flood sample was divided into training (70%) and validating (30%) sample, meanwhile the prediction ability of flood conditioning factors was tested through the Correlation-based Feature Selection method. ROC Curve and statistical metrics were involved in the results validation. The modeling process through the stated algorithms showed that the most important flood predictors are represented by: slope (importance ≈ 20%), distance from river (importance ≈ 17.5%), land use (importance ≈ 12%) and TPI (importance ≈ 10%). The importance values were used to compute the flood susceptibility, while Natural Breaks method was used to classify the results. The high and very high flood susceptibility is spread on approximately 35–40% of the study zone. The ROC Curve, in terms of Success, Rate shows that the highest performance was achieved FPI_DLNN-HHO-IOE (AUC = 0.97), followed by FPI_{Stacking-HHO-IOE} (AUC = 0.966) and FPI_MLP-HHO-IOE (AUC = 0.953), while the Prediction Rate indicates the FPI_{Stacking-HHO-IOE} as being the most performant model with an AUC of 0.977, followed by FPI_DLNN-HHO-IOE (AUC = 0.97) and FPI_MLP-HHO-IOE (AUC = 0.924).

在世界各地发生的各种自然灾害中，洪水被认为是影响范围最广的。布泽乌河流域发生了几次洪水，因此该地区被选为研究区。为了本研究的目的，我们应用深度学习和机器学习基准来准备流域尺度的洪水潜力图。在这方面，12个洪水预测器、205个洪水和205个非洪水位置被用作以下3个复杂模型的输入数据：深度学习神经网络-Harris Hawk优化-熵指数（DLNN-HHO-IOE）、多层感知器- Harris Hawk 优化-熵指数 (MLP-HHO-IOE) 和堆叠集成-Harris Hawk 优化-熵指数 (Stacking-HHO-IOE)。将洪水样本分为训练样本（70%）和验证样本（30%），同时通过基于相关性的特征选择方法测试洪水调节因子的预测能力。结果验证涉及 ROC 曲线和统计指标。通过所述算法的建模过程表明，最重要的洪水预测因子由以下各项表示：坡度（重要性 ≈ 20%）、距河流的距离（重要性 ≈ 17.5%）、土地利用（重要性 ≈ 12%）和 TPI（重要性 ≈ 10） %）。采用重要性值计算洪水敏感性，并采用自然断裂法对结果进行分类。高洪水敏感性和极高洪水敏感性分布在研究区约 35-40% 的区域。ROC 曲线（就成功率而言）显示，FPI _DLNN-HHO-IOE (AUC = 0.97) 实现了最高性能，其次是 FPI _{Stacking-HHO-IOE} (AUC = 0.966) 和 FPI _MLP-HHO-IOE ( AUC = 0.953），而预测率表明 FPI _{Stacking-HHO-IOE}是性能最好的模型，AUC 为 0.977，其次是 FPI _DLNN-HHO-IOE（AUC = 0.97）和 FPI _MLP-HHO-IOE（曲线下面积 = 0.924）。