Tejas Maske 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, used only the eight legitimate ambient and turbine sensor inputs, and excluded CO/NOx because they are downstream emissions not available at prediction time. Compared a LinearRegression baseline with a RandomForest on a chronological hold-out set, reported held-out MAE/RMSE/R², and documented limitations, drift monitoring, and deployment use in a concise model card.

• Leakage-Free Feature Selection
• Chronological Hold-Out Evaluation
• Baseline-to-Ensemble Comparison
• Plain-Language Model Communication