The Effect of Different Optimization Strategies to Physics-Constrained Deep Learning for Soil Moisture Estimation

TL;DR

This paper investigates how different optimization algorithms affect the training of physics-constrained deep learning models for soil moisture estimation, demonstrating that Adam optimizer converges more effectively than RMSprop and GD.

Contribution

It introduces a physics-constrained deep learning framework for soil moisture modeling and compares the performance of three optimizers within this context.

Findings

Adam optimizer shows faster convergence.

Adam outperforms RMSprop and GD in training.

Physics-constrained models improve soil moisture estimation.

Abstract

Soil moisture is a key hydrological parameter that has significant importance to human society and the environment. Accurate modeling and monitoring of soil moisture in crop fields, especially in the root zone (top 100 cm of soil), is essential for improving agricultural production and crop yield with the help of precision irrigation and farming tools. Realizing the full sensor data potential depends greatly on advanced analytical and predictive domain-aware models. In this work, we propose a physics-constrained deep learning (P-DL) framework to integrate physics-based principles on water transport and water sensing signals for effective reconstruction of the soil moisture dynamics. We adopt three different optimizers, namely Adam, RMSprop, and GD, to minimize the loss function of P-DL during the training process. In the illustrative case study, we demonstrate the empirical convergence of Adam optimizers outperforms the other optimization methods in both mini-batch and full-batch training.