1
Frame and validate a model the honest way
Turn a real prediction problem into leakage-free features and validate on a genuinely held-out, time-based split, the discipline German ML-engineer roles actually test for.
Explore
Energy and Renewable: Machine Learning for the Power Grid
ProoV
4.6· 26 ratings
About this project
Step into a Junior Machine Learning Engineer role and build a model that predicts a gas turbine's energy yield from real sensor data. You will frame the problem, engineer leakage-free features, train and honestly validate a model, tune it, and write a model card a hiring manager would trust. A case study on public data, not affiliated with Siemens Energy.
Ideal for entry-level careers in
Add this to your LinkedIn profile
Projects
inEnergy and Renewable: Machine Learning for the Power Grid
Just completed
Associated with ProoV
A graded ProoV project, completed step by step and marked against a published rubric.
❖Python, scikit-learn and more skills
What you'll do
1
Night shift: the turbine-service problem
Meet the case, the real open dataset, and the deliverable you will build.
2
Frame the problem and engineer leakage-free features
Define the target, task and metric, then choose the eight legitimate sensors and exclude the leakage columns.
3
Select, train and validate the model
Train a baseline and a random forest on an honest time-based split in the scikit-learn lab.
4
Optimize and evaluate honestly
Tune on the held-out score, report MAE / RMSE / R2, and read your own residuals.
5
Monitor for drift and write the model card
Simulate silent drift, then author the one-page model card and explain it plainly.
6
Review and hand in
Review your trained model and model card, then submit the graded deliverable.
What you'll learn
2
Build it in scikit-learn, then read it truthfully
Train a baseline and a tree ensemble on real gas-turbine sensor data, tune on the held-out score, and report MAE, RMSE, R2 and residuals without over-claiming.
3
Write a model card a hiring manager trusts
Author the one-page model card, intended use, accuracy, limitations, failure mode and monitoring plan, and explain it in plain language to a non-expert.
What students say
Turn it more active by doing the code more complex, and also the process of create the pipeline from data until reach the vizualization/dashboard.
About what actually gas companies do and how machine learning can help in it.I learn how the limittion play a major role on companies as optimizing always is not the best solution.
It was fun doing this project but also felt a lot of left out as everything was given and it was just like a spoonfed project So i think this is ok to kill the time but the system needs more improvement to actaully hire engineers
The model predicts how much energy the turbine will produce. It is usually off by about 1.5 MWh. I trust this estimate because it was tested on turbine data it had not seen during training. It could let us down when conditions, especially temperature, move outside the range it w…
Learning about the difference between instinct and fact. How an engineer must validate his instinct before coming to decision
I learned how machine learning can be used to predict turbine energy output and how to evaluate model accuracy, limitations, and reliability using real-world data.