Coastal forecast through coupling of Deep Learning and hydro-morphodynamical modelling
Coastal forecast through coupling of Deep Learning and hydro-morphodynamical modelling
复制标题
通过深度学习和水文形态动力学建模的耦合进行海岸预测
DOI：
10.1002/essoar.10512513.1
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Kumar P
中科院分区：
文献类型：
--
作者：
Kumar P
随着气候驱动的世界海岸线风险增加，了解和预测地貌变化以及开发有效的海岸预报系统，对于适应气候变化和作出明智的沿海管理选择至关重要。人工智能，特别是深度学习，是一项在过去几十年中迅速发展的强大技术，可以为沿海科学领域提供新的分析手段。然而，相对于其他科学领域，这些技术在沿海地貌学方面的潜力仍然相对未被发掘。本文研究了人工神经网络和贝叶斯网络与完全耦合的水动力和形态模型(Delft3D)相结合来预报海岸系统的形态变化和泥沙输移。测试了两套深度学习模型，一套依赖本地化建模输出或本地化数据源，另一套减少了对建模输出的依赖，一旦训练，只依赖边界条件和海岸线几何形状。第一组模型为训练和测试提供了大于0.95和0.86的回归值。第二组减少依赖模型提供大于0.84和0.76的回归值用于训练和测试。这两种模型都需要几分钟的运行时间，而流体动力模型需要几个小时的运行时间。我们的结果突出了深度学习和统计模型在沿海应用中的潜力。
As climate-driven risks for the world’s coastlines increase, understanding and predicting morphological changes as well as developing efficient systems for coastal forecast has become of the foremost importance for adaptation to climate change and informed coastal management choices. Artificial Intelligence, especially deep learning, is a powerful technology that has been rapidly evolving over the last couple of decades and can offer new means of analysis for the coastal science field. Yet, the potential of these technologies for coastal geomorphology remains relatively unexplored with respect to other scientific fields. This article investigates the use of Artificial Neural Networks and Bayesian Networks in combination with fully coupled hydrodynamics and morphological models (Delft3D) for predicting morphological changes and sediment transport along coastal systems. Two sets of deep learning models were tested, one set relying on localized modelling outputs or localized data sources and one set having reduced dependency from modeling outputs and, once trained, solely relying on boundary conditions and coastline geometry. The first set of models provides regression values greater than 0.95 and 0.86 for training and testing. The second set of reduced-dependency models provides regression values greater than 0.84 and 0.76 for training and testing. Both model types require a running time of the order of minutes, compared to the several hours of running times of the hydrodynamic models. Our results highlight the potential of deep learning and statistical models for coastal applications.
登录
查看更多内容
一种解决递归神经网络中过度拟合问题的方法，用于预测复杂系统的行为
DOI：
10.1109/ijcnn.2008.4634332
发表时间：
2008
期刊：
2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
影响因子：
--
作者：
K. Mahdaviani;Helga Mazyar;Saeed Majidi;Mohammad Saraee
通讯作者：
Mohammad Saraee
FVCOM的干湿点处理方法，第一部分：稳定性实验
影响因子：
2.9
作者：
Changsheng Chen;J. Qi;Hedong Liu;R. Beardsley;Huichan Lin;G. Cowles
通讯作者：
G. Cowles
影响因子：
25.2
作者：
Shriver, J.F.;Shum, C.K.;Taguchi, E.;Yi, Y.
通讯作者：
Yi, Y.
城市如何应对气候变化：比较汉堡和鹿特丹
影响因子：
6.7
作者：
Jo;J. Lovett
通讯作者：
J. Lovett
城市地区地下水溶解有机氮预测的机器学习技术和变量比较
DOI：
10.1016/j.proeng.2016.07.527
发表时间：
2016
期刊：
Procedia Engineering
影响因子：
--
作者：
Benya Wang;C. Oldham;M. Hipsey
通讯作者：
M. Hipsey