Devang Rathi completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-free gas-turbine TEY predictor end to end using the 8 operational sensor features, excluding downstream CO/NOx emissions to avoid target leakage. Trained and compared a LinearRegression baseline and a tuned RandomForest on a genuine time-based holdout, then reported held-out MAE, RMSE, R2, residual behavior, and a concise model card with monitoring and limitations.

• Leakage-Free Feature Selection
• Time-Based Validation Discipline
• Honest Held-Out Evaluation
• Practical Model Communication