Abdullah completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware gas-turbine TEY predictor using the correct 8 operating sensors, excluding downstream CO/NOx emissions. Trained and compared a LinearRegression baseline with a tuned RandomForest on an earlier-vs-later time split, then evaluated honestly on held-out data with MAE, RMSE, R², and residual analysis. Also authored a model card that explains intended use, limitations, and monitoring in manager-friendly language.

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