Self-directed project
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · AI / ML · August 2026
A ProoV case study · educational project, not employment
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.
Graded against
- Build and validate the model correctly35%
- Optimize and evaluate honestly25%
- Write the Model Card (clarity + honesty)25%
- Explain it to a non-expert15%
Passed · pass mark 60/100
What stood out6
- Correctly excluded CO and NOx as downstream emissions that would not be available at prediction time
- Used a time-based split with earlier years for training and later years for testing
- Reported held-out MAE, RMSE, and R² and interpreted residual behavior instead of only quoting a headline score
- Wrote a model card that clearly states intended use, limitations, and a concrete monitoring plan
- Leakage-Free Feature Selection
- Chronological Hold-Out Evaluation
The work I submitted20 tasks
12 tasks · 13 lines · Python, JavaScript · 8 written answers · 501 words
- Problem Frame195 characters
- Leakage Flags113 characters
- Train Validate BaselinePython · 1.4k characters
- Train Validate Forest944 characters
- Tune Evaluate ResidualsPython · 2 lines
- Residual Read455 characters
- Train Validate124 characters
- Tune Evaluate SetupPython · 1.5k characters
- Tune Evaluate132 characters
- Drift Monitor94 characters
- Model Card2.5k characters
- Teach BackJavaScript · 816 characters
- Problem Frame14 words
- Leakage Flags1 word
- Train Validate Baseline141 words
- Train Validate Forest76 words
- Tune Evaluate Residuals92 words
- Residual Read66 words
- Train Validate1 word
- Tune Evaluate Setup110 words
Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.