Abstract

This thesis presents the development of the Chlorophyll-a Modeling and Monitoring Online System (CMMOS), an innovative Artificial Intelligence (AI)-based tool designed to enhance the monitoring and prediction of chlorophyll-a concentrations in lake ecosystems. Traditional methods of monitoring these concentrations face limitations in real-time data processing and the handling of complex environmental interactions. CMMOS addresses these challenges by integrating a sophisticated array of machine learning models, including Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Gradient Boosting Tree (GBDT), Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM), K Nearest Neighbors (KNN), Multiple Linear Regression (MLR), and Extreme Gradient Boosting (XGBoost). The system's efficacy was rigorously evaluated using comprehensive datasets from Lake Champlain and Lake Simcoe. Through these evaluations, the system demonstrated high predictive performance, particularly for models like RF, GBDT, and XGBoost, which excelled across various metrics. Data preprocessing techniques including Missing Value Imputation, Outlier Detection, and Feature Selection proved critical in enhancing the accuracy and reliability of these models. CMMOS contributes to the field of environmental science by offering a real-time, data-driven approach to lake water quality management. The system facilitates dynamic monitoring and predictive analysis, enabling stakeholders to make informed decisions promptly. It illustrates the substantial advantages of utilizing AI in ecological monitoring and management. Recommendations for future work include further optimization of machine learning models, exploration of ensemble techniques to refine predictive accuracy, expansion of the system to include more diverse environmental variables, and enhancements to the user interface to better serve various users. This thesis lays a robust foundation for future advancements in AI applications for environmental monitoring, aiming to improve the sustainability and effectiveness of lake management practices.