Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
This provides spatio-temporally seamless soil moisture coverage for hydrology applications, but it is an incremental application of an existing method to a new domain.
The researchers tackled the problem of SMAP's short time span and irregular revisit schedule by using an LSTM neural network to predict soil moisture data, achieving a test root-mean-squared error <0.035 and correlation coefficient >0.87 for over 75% of the Continental US.
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 schedule. 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 soil moisture data with atmospheric forcing, 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-squared error (<0.035) and high correlation coefficient >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 physiography. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.