The Effect of Different Optimization Strategies to Physics-Constrained Deep Learning for Soil Moisture Estimation
This work addresses soil moisture modeling for agricultural applications, but it is incremental as it focuses on optimizer comparisons within an existing framework.
The study tackled soil moisture estimation in crop fields by proposing a physics-constrained deep learning framework and comparing optimizers, finding that Adam outperformed RMSprop and GD in convergence during training.
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.