Sam Dcruze completed Energy and Renewable: Machine Learning for the Power Grid

Built a leakage-aware gas-turbine TEY predictor using the eight pre-combustion sensors, with CO and NOx excluded because they are downstream emissions. Validated on a chronological holdout, compared Linear Regression against a Random Forest, and reported honest held-out performance (about 1.5 MWh MAE, ~0.98 R2) alongside residual analysis and a practical monitoring plan.

• Leakage-Free Feature Selection
• Chronological Holdout Validation
• Honest Held-Out Evaluation
• Model Risk Communication