Decision support prototype for farmers based on environmental parameter modelling through supervised machine learning

Supervised machine learning models are increasingly prevalent across a wide range of domains. Farming, a fundamental means of subsistence throughout human history, is no exception. Consequently, machine learning algorithms have emerged as valuable tools for the monitoring and management of crops. This paper provides a comparative analysis of predicting soil temperature based on air parameters using various supervised machine learning techniques, including Linear Regression, Decision Trees and Ensemble Learning. Using this, farmers can extract accurate soil temperature forecasts through a newly developed intuitive graphical user interface (GUI), enhancing their ability to make informed agricultural decisions.