Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 4; p. 554
• Main Authors: Ahmed, A. A. Masrur, Deo, Ravinesh C, Raj, Nawin, Ghahramani, Afshin, Feng, Qi, Yin, Zhenliang, Yang, Linshan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 04.02.2021
• Subjects: Agricultural management; Agricultural practices; Algorithms; Artificial neural networks; climate; Climate models; Data collection; Decomposition; Deep learning; deep learning algorithm; El Nino; Farm buildings; Forecasting; gated recurrent unit; hybrids; Hydrology; Model testing; MODIS; Neural networks; Precipitation; Rain; Remote sensing; Remote sensors; satellite models of soil moisture; Satellite observation; satellites; Soil moisture; Soil surfaces; soil water; Stream flow; Sustainable agriculture; Sustainable practices; Teaching methods; Temporal resolution; Time series; Variables; viability; Water management; Water resources; Water resources management; Wavelet transforms; Australia

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU...