Rumaisa Sabi completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware gas-turbine TEY predictor end to end: framed the regression target correctly, excluded downstream CO/NOx emissions from the feature set, and benchmarked a LinearRegression baseline against a tuned RandomForest on a locked-away later-year test split. The final model achieved 1.53 MWh MAE and 0.983 R² on held-out data, with a model card that clearly states intended use, limitations, and a retraining trigger based on rolling error and drift.

• Leakage-Free Feature Selection
• Honest Held-Out Evaluation
• Residual-Based Error Analysis
• Plain-Language Model Communication