Prototype a Normalizing Flow for Anomaly Scoring in Climate Sensor Data
Overview
What this challenge is about.
Train a normalizing flow to score anomalies in climate sensor data, compare to a baseline, and report ROC-AUC. Earn a verifiable certificate.
The scenario
The startup (around 35 staff, Icelandic geothermal monitoring, expanding to Pamplona-region wind soon) treats its calibration story as a sales advantage with industrial customers.
The Brief
What you'll do, and what you'll demonstrate.
Show whether a Normalizing Flow produces better-calibrated anomaly scores than the current Z-score detector on hand-labeled geothermal sensor data.
Earning criteria — what you'll demonstrate
- Implement and train normalizing flows on multivariate sensor data
- Use density estimates as anomaly scores defensibly
- Evaluate calibration formally (reliability, ECE, risk-coverage)
- Communicate research results to a domain-scientific audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Normalizing Flows
Apply normalizing flows to solve real industry problems and demonstrate production-level capability.
- Density Estimation
Apply density estimation to solve real industry problems and demonstrate production-level capability.
- Anomaly Detection
Apply anomaly detection to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Calibration
Apply calibration to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Normalizing flows for anomaly scoring is an active research thread; this challenge produces a credible first artifact.
This challenge sharpens
- normalizing-flows
- density-estimation
- anomaly-detection
Research Scientist
Formal calibration analysis on industrial sensor data is the kind of rigor expected from a junior research scientist.
This challenge sharpens
- normalizing-flows
- calibration
- evaluation
Applied AI Scientist
Beating a deployed Z-score detector with a research method is exactly the bridge applied AI scientists build between research and product.
This challenge sharpens
- density-estimation
- anomaly-detection
- calibration