The rise in hydrological and physiographic spatiotemporal data has boosted machine learning's role in rapid flood mapping. Yet, data scarcity, especially high-resolution DEMs, challenges regions with limited resources. This paper examines how DEM type and resolution affect flood prediction accuracy, utilizing a cutting-edge deep learning (DL) method called 1D convolutional neural network (CNN). It utilizes synthetic hydrographs for training input and water depth data from LISFLOOD-FP, a 2D hydrodynamic model, for target data. This study investigates digital surface models (DSMs) and digital terrain models (DTMs) derived from a 1 m LIDAR-based DTM, with resolutions from 15 to 30 m. The methodology is applied and assessed in the established benchmark site of Carlisle, UK. The models' performance is then evaluated and compared against an observed flood event using RMSE, Bias, and Fit indices. Leveraging the insights gained from this region, the paper discusses the applicability of the methodology to address the challenges encountered in a data-scarce flood-prone region, exemplified by Pakistan. Results indicated that utilizing a 30 m DTM improved flood depth prediction accuracy by about 21% during the flood peak stage compared to a 30 m DSM, highlighting the superior performance of DTM at lower resolutions. Increasing the resolution of DTM to 15 m resulted in a minimum 50% increase in RMSE and a 20% increase in fit index across all flood phases. The findings emphasize that while a coarser resolution DEM may impact the accuracy of machine learning models, it remains a viable option for rapid flood prediction. Any attempts to improve data resolution in data-scarce regions would provide significant added value, ultimately enhancing flood risk management.

翻译：水文与地貌时空数据的增长推动了机器学习在快速洪水制图中的应用。然而，数据稀缺（尤其是高分辨率DEM）对资源有限地区构成挑战。本文通过采用一种名为一维卷积神经网络（CNN）的前沿深度学习方法，考察了DEM类型与分辨率对洪水预测精度的影响。该方法使用合成水文过程线作为训练输入，并以二维水动力学模型LISFLOOD-FP输出的水深数据为目标数据。研究基于1米激光雷达DTM导出的数字表面模型（DSM）和数字地形模型（DTM），分辨率范围为15至30米。该方法的有效性在英国卡莱尔市标准基准场地进行了验证与评估。随后，利用均方根误差（RMSE）、偏差（Bias）和拟合指数（Fit）指标，将模型性能与实际洪灾事件进行对比评估。基于该区域的研究发现，本文探讨了该方法在面临数据稀缺的洪灾频发地区（以巴基斯坦为例）的适用性。结果表明：在洪峰阶段，使用30米DTM相较于30米DSM可将洪水深度预测精度提升约21%，突显了低分辨率下DTM的优越性。将DTM分辨率提升至15米时，各洪水阶段RMSE至少降低50%，拟合指数提升20%。研究强调，尽管粗分辨率DEM可能影响机器学习模型精度，但仍可作为快速洪水预测的可行方案。在数据稀缺区域，任何提升数据分辨率的努力都将提供显著附加值，最终增强洪水风险管理能力。