This core technical module equips students to transform complex real-world data into actionable insights for environmental and social impact. Learners explore the mathematical foundations of probability, statistical inference, and quantitative research methods to drive evidence-based decision-making. Through robust data wrangling, scalable engineering pipelines, and exploratory visualisation, students effectively process large-scale environmental datasets. The curriculum covers advanced predictive analytics, supervised and unsupervised machine learning, Bayesian networks, and time-series analysis for climate forecasting. Emphasising rigorous model evaluation, bias, variance, and generalisation in scientific AI, this module provides the essential computational toolkit to monitor and predict ecological trends whilst addressing urgent global sustainability challenges.