Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
复制标题
DOI：
10.1002/2017gl075619
复制
发表时间：
2017-11-16
影响因子：
5.2
通讯作者：
Yang, Xiao
中科院分区：
文献类型：
--
作者：
Fang, Kuai;Shen, Chaopeng;Yang, Xiao
自2015年以来，土壤水分主动被动（SMAP）使命已经提供了有价值的地表土壤水分传感。然而，它的时间跨度很短，重访时间表不定期。利用最先进的时间序列深度学习神经网络，长短期记忆（LSTM），我们创建了一个系统，预测SMAP 3级水分产品，其中大气强迫，模型模拟水分和静态地文属性作为输入。该系统通过模型模拟消除了大部分偏差，并改善了预测的湿度气候学，实现了较小的测试均方根误差（美国大陆75%以上的地区，包括森林覆盖的东南部，为0.87）。作为LSTM在水文学中的首次应用，我们证明了所提出的网络避免了过拟合，并且对于时间和空间外推测试都是鲁棒的。LSTM可以很好地推广到具有不同气候和环境设置的地区。由于对SMAP的高保真度，LSTM在后报、数据同化和天气预报方面显示出巨大的潜力。
The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedules. Utilizing a state-of-the-art time series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 moisture product with atmospheric forcings, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-square errors (0.87 for over 75% of Continental United States, including the forested southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and environmental settings. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.