Himani Pandey completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware turbine yield predictor using the correct sensor inputs and excluding downstream CO/NOx emissions. Compared a LinearRegression baseline against a RandomForest on a later held-out period, showing the forest improved held-out MAE from 2.90 to 1.53 MWh and R² from 0.957 to 0.983. Documented the model’s intended use, limits, and a practical monitoring trigger for retraining.

• Leakage-Free Feature Selection
• Time-Based Holdout Validation
• Baseline-to-Ensemble Comparison
• Plain-Language Model Communication