Kokku Shivank completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware turbine yield predictor end to end: selected the eight valid sensor features, excluded downstream CO/NOx emissions, trained and compared a LinearRegression baseline with a RandomForest, and evaluated on a locked-away later-year test split. Reported honest held-out performance (MAE 1.502 MWh, RMSE 1.908 MWh, R² 0.9838), documented residual behavior, and wrote a concise model card with intended use, limits, and drift monitoring.

• Leakage-Free Feature Selection
• Honest Held-Out Evaluation
• Model Comparison and Tuning
• Plain-Language Model Communication