arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.07903cs.LGphysics.ao-phstat.ML
收藏

NeuralHydrology --水文学中的LSTM解释

NeuralHydrology -- Interpreting LSTMs in Hydrology

Johannes Kepler University Linz(林茨约翰内斯·开普勒大学);University of Natural Resources and Life Sciences, Vienna(维也纳自然资源与生命科学大学)

Frederik Kratzert, Mathew Herrnegger, Daniel Klotz, Sepp Hochreiter, Günter Klambauer

摘要:

尽管长短期记忆网络取得了巨大的成功,但它们在环境科学中的应用却很少。我们认为,原因之一是难以解释训练网络的内部结构。在这项研究中,我们着眼于LSTM的应用,在水文学领域的中心任务之一,在该领域的河流流量预测气象观测。LSTM特别适合于这个问题,因为存储单元可以表示动态水库和存储,这是水文系统的状态空间建模方法中的重要组成部分。基于两个不同的集水区,一个有雪的影响,一个没有,我们演示了如何训练模型可以分析和解释。在这个过程中,我们表明,网络内部学习代表的模式,是符合我们的定性理解的水文系统。

英文摘要:

Despite the huge success of Long Short-Term Memory networks, their applications in environmental sciences are scarce. We argue that one reason is the difficulty to interpret the internals of trained networks. In this study, we look at the application of LSTMs for rainfall-runoff forecasting, one of the central tasks in the field of hydrology, in which the river discharge has to be predicted from meteorological observations. LSTMs are particularly well-suited for this problem since memory cells can represent dynamic reservoirs and storages, which are essential components in state-space modelling approaches of the hydrological system. On basis of two different catchments, one with snow influence and one without, we demonstrate how the trained model can be analyzed and interpreted. In the process, we show that the network internally learns to represent patterns that are consistent with our qualitative understanding of the hydrological system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑