Atharva Pardeshi completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware turbine yield predictor end to end: framed TEY as the target, excluded downstream CO/NOx emissions, trained a LinearRegression baseline and a RandomForest on an earlier-years/later-years split, and evaluated on locked-away held-out data. Reported honest held-out performance (MAE 1.508 MWh, RMSE 1.910, R2 0.9838) and documented intended use, limitations, and monitoring in a model card.

• Leakage-Free Feature Selection
• Time-Based Holdout Evaluation
• Honest Metric Reporting
• Basic Drift Monitoring Design