VEDARSHMISHRA

2026 · Planetary science · Image processing

Jupiter

Looking for lightning on Jupiter in Cassini images, and being careful about what counts as found.

Explore the engineering ↓
Jupiter project cover
JUPITER
My role
Built the detector, ranking and review workflow
Status
All 6 known flashes recovered · no new ones confirmed
Focus
Scientific imaging · computer vision · validation

Result

Across 221 images from nine date windows, the detector found all six published lightning flashes within 8 px. It also flagged 106 candidates for review. Those are a to-do list, not discoveries.

  1. 01

    Detect

    Normalize each image and subtract the planet’s smooth glow.

  2. 02

    Filter

    Measure bright spots and flag the ones that look like artifacts.

  3. 03

    Rank

    Link spots across nearby frames and rank them for review.

  4. 04

    Review

    Check against known flashes and record a human decision.

The search

Inside the work.

Six reference events
01 / 10
Six known flashes

The six published lightning flashes I used to check the detector.

Classical detector pipeline
02 / 10
The detector

Image processing and region measurements. No neural network.

Search to review
03 / 10
Search to review

Raw spots, filtered candidates and review rows are different stages, so they get different counts.

Validation and geometry
04 / 10
Validation and geometry

Localization checks and geometry work constrain the scientific interpretation.

Review examples
05 / 10
Candidates and artifacts

Candidates that didn’t match anything known, plus some artifacts. None of them is a discovery yet.

Human review interface
06 / 10
The review tool

Where each candidate gets a human decision. No labels have been accepted yet.

From review to future training
07 / 10
Toward a trained model

Labels and a frozen benchmark have to exist before a learned model is worth comparing.

Published marks in full frames
08 / 10
Published marks in full frames

Full-frame context shows where the six published validation marks occur.

All 221 analyzed frames
09 / 10
All 221 images

Every image I analyzed, not just the good ones.

Candidate contact sheets
10 / 10
Candidates by date

Grouped by date, to show how much ends up in review.

From 196,233 bright spots to 106 worth a look
StageCountMeaning
Calibrated images221Nine date windows
Bright regions196,233Broad first-pass detections
Filtered candidates12,611Passed artifact filters
Prioritized rows106Human review packet
Known marks recovered6 / 6Within 8 px; not overall accuracy

How the detector works

It runs on calibrated Cassini ISS images in Python with NumPy and Pillow. Each image is scaled between its 2nd and 99.8th percentile, then a Gaussian blur (radius 18) is subtracted to take out the planet’s smooth glow and leave only small bright spots.

Noise is estimated as 1.4826 × the median absolute deviation. Unlike a standard deviation, that isn’t dragged up by the bright spots you’re looking for. Pixels 7× above the noise are grouped into connected regions, and each region gets measured: position, area, peak and total signal, sharpness and elongation. To become a candidate, a region needs at least 3 pixels, a peak above 8× the noise, and no artifact flags.

From 196,233 to 106

The first pass found 196,233 bright regions. Artifact filters cut that to 12,611. Detections within 85 px and 12 minutes of each other are then linked, since a real flash can show up in more than one frame, and each one is scored on persistence, motion, diffuse shape, signal and an artifact penalty.

That score only sets the review order. It isn’t a probability that something is lightning.

Checking against known flashes

All six published flashes were recovered within 8 px, with offsets between 1.54 and 5.56 px. That shows the detector can find real lightning. It doesn’t measure how often it’s wrong across all 221 images.

Why nothing is a discovery yet

A candidate that matches nothing known still needs a person to look at it, evidence in more than one frame, and a geometry check. Only 42 of the 106 have a computed position on Jupiter; for the other 64 the line of sight misses the planet, and I left them without made-up coordinates. No human labels have been accepted yet.

Next

There’s no neural network here, on purpose. Training one would need accepted positive and negative labels, a frozen benchmark and versioned data, and then it would have to beat this simple detector to be worth it.

Explore the code on GitHub ↗

Sources

Technical records.

Continue exploring.

← Back to Selected Builds