论文标题
Hydrodeep-知识引导的深神经网络，用于地理时空数据分析
HydroDeep -- A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis
论文作者
论文摘要
由于证据有限和区域气候变化的复杂原因，预测河流洪水的信心仍然很低。了解GEO-Spatiotemporal信息固有的基本机制对于提高预测准确性至关重要。本文展示了混合神经网络体系结构 - Hydrodeep，该结构将基于过程的水力生态模型与深度卷积神经网络（CNN）和长短期记忆（LSTM）网络的结合结合在一起。 Nash-Sutcliffe效率的HydroDep的表现分别优于独立的CNN和LSTM的性能。另外，我们表明，通过独特的转移学习方法将其知识传递到遥远的地方，通过学习新区域的训练持续时间，通过学习其区域地理型跨阶段特征，以减少的迭代数量减少了Hydrodeep的训练持续时间。
Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low. Understanding the fundamental mechanisms intrinsic to geo-spatiotemporal information is crucial to improve the prediction accuracy. This paper demonstrates a hybrid neural network architecture - HydroDeep, that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network. HydroDeep outperforms the independent CNN's and LSTM's performance by 1.6% and 10.5% respectively in Nash-Sutcliffe efficiency. Also, we show that HydroDeep pre-trained in one region is adept at passing on its knowledge to distant places via unique transfer learning approaches that minimize HydroDeep's training duration for a new region by learning its regional geo-spatiotemporal features in a reduced number of iterations.
