Soil moisture forecast for smart irrigation: The primetime for machine learning

Abstract

The rise of the Internet of Things allowed higher spatial–temporal resolution soil moisture data captured through in situ sensing. Such abundance of data enables machine learning-based soil moisture forecast as an alternative to traditional mechanistic approaches for irrigation water need estimation. This paper develops a guideline for soil moisture forecast modeling based on machine learning, tested in a real case analysis comprehending eight crop types in twelve fields from four farms distributed over diverse climatic scenarios in Brazil. Instead of a single value, we predict the following days' minimum and maximum values as targets to monitor risks of extreme soil moisture values. Furthermore, modeling soil moisture directly in volumetric water content (VWC) is better than modeling soil matric potential (SMP) to later convert in soil moisture VWC. We test several algorithms and find out that LightGBM outperforms linear regression, decision tree, random forest, multilayer perceptron, LSTM, and StemGNN. Also, blending predictions via algorithm ensemble provides an additional accuracy gain. For model training and accuracy measurement, we use weighted datasets to privilege rare but critical data points. We show that soil moisture forecast reaches its maximum performance considering only past soil moisture, a context-aware index, and a precipitation forecast. Finally, we demonstrate that traditional domain-knowledge features - such as evapotranspiration, crop phenology, and soil hydraulic behavior - are not relevant to improving SM forecast performance. Consequently, our paper suggests full data-driven approaches for irrigation water need estimation, observed some care regarding data quality.