Dheeraj Kumar completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware turbine yield predictor using the 8 legitimate ambient and sensor features, explicitly excluding downstream CO and NOx emissions. Trained and compared a LinearRegression baseline with a RandomForest on an earlier-years train / later-years test split, then evaluated the final model with held-out MAE, RMSE, R2, and residual analysis. Also authored a model card that explains intended use, limitations, and a practical monitoring plan.

• Leakage-Free Feature Selection
• Time-Based Holdout Evaluation
• Baseline-to-Ensemble Comparison
• Residual-Based Error Checking