IoT-Enabled Machine Learning Framework for Prediction of Eutrophication

This study presents an innovative predictive monitoring framework that integrates the Internet of Things (IoT) with advanced machine learning (ML) techniques to model the relationship between oxidized nitrate (NOX)—employed as the sole predictor—and chlorophyll a (CHLA), a key proxy for algal biomass. By utilising a single optimally selected parameter, the approach significantly reduces sensor deployment complexity and instrumentation costs, while minimising data acquisition and computational requirements. Logarithmic and Yeo-Johnson transformations were applied to the predictor and target variables, respectively, to address distributional skewness and enhance variance homogeneity. An optimised Random Forest model demonstrated strong predictive performance, achieving a coefficient of determination (R2) of 0.8392 and low error metrics (MSE = 0.1630; RMSE = 0.4037; MAE = 0.2774). These results highlight the framework's efficacy and scalability in delivering resource-efficient, data-light predictive systems capable of real-time, automated monitoring via an IoT-enabled architecture. The study underscores the potential of combining IoT infrastructures with machine learning to develop computationally efficient, scalable solutions for the intelligent management of complex dynamic systems.