3-D Bi-directional LSTM for Satellite Soil Moisture Downscaling

Madhukumar, Neethu, Wang, Eric, Fookes, Clinton, and Xiang, Wei (2022) 3-D Bi-directional LSTM for Satellite Soil Moisture Downscaling. IEEE Transactions on Geoscience and Remote Sensing, 60. 5414018.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/TGRS.2022.322710...
 
2


Abstract

Soil moisture (SM) is a crucial parameter of hydrological processes as it affects the exchange of water and heat at the land/atmosphere interface. Regional hydrological applications (floods and modeling of small basins) and agricultural applications (irrigation and agricultural land mapping) require daily SM values having a spatial resolution of at least 1-km. This requirement is currently unmet by existing satellite missions. Notably, SM has variability over three dimensions. As such, accurate prediction of satellite SM requires multiple bidirectional spectra-spatiotemporal analyses. However, current state-of-the-art SM downscaling models cannot yet fulfill this requirement. This article proposes a new bidirectional long short-term memory (LSTM) model dubbed the 3-D bidirectional LSTM (3D-Bi-LSTM), which downscales the soil moisture active passive (SMAP) global daily 9-km SM to daily 1-km SM. In the proposed downscaling model, the region-specific soil moisture indices (SMIs) are first extracted using a covariance-adaptive convolutional neural network (CNN) to support the extraction of important distinctive information from multispectral data. Next, the CNN output is provided to the 3D-Bi-LSTM to perform the bidirectional analysis of spatial correlation within a feature and spectral correlation between features over multiple time instants. Experimental results demonstrate the proposed model outperforms the state-of-the-art networks. An ablation study, transferability assessment, and feature importance study further demonstrate the proposed 3D-Bi-LSTM’s efficiency.

Item ID: 77667
Item Type: Article (Research - C1)
ISSN: 1558-0644
Keywords: Bidirectional analysis, convolutional neural network (CNN), downscaling, long short-term memory (LSTM) network, soil moisture (SM)
Copyright Information: © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
Funders: Australian Research Council (ARC)
Projects and Grants: ARC DP220101634
Date Deposited: 31 Mar 2023 01:53
FoR Codes: 40 ENGINEERING > 4013 Geomatic engineering > 401304 Photogrammetry and remote sensing @ 100%
SEO Codes: 28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280110 Expanding knowledge in engineering @ 100%
Downloads: Total: 2
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page