Nihma Shareef completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware gas-turbine TEY predictor using the eight legitimate ambient/turbine sensors, excluded downstream CO/NOx emissions, and validated on a held-out later period rather than a random shuffle. Compared a linear baseline with a tuned RandomForestRegressor, reported held-out MAE/RMSE/R2, and documented limitations, drift risks, and monitoring steps in a model card written for operational use.

• Leakage-Free Feature Selection
• Time-Based Model Validation
• Honest Held-Out Evaluation
• Plain-Language Model Communication