Prediction studio

Build the next exoplanet insights

Prepare candidate objects, import datasets of matching structure, and trigger the pipeline when everything looks ready. This space will host the full workflow.

Review data objects Skip to prediction

Exoplanet Candidates

Each card represents a potential exoplanet signal from telescope observations. Data includes transit characteristics, orbital parameters, and host star properties. Configure candidate objects to prepare them for machine learning classification.

Required Features

Feature Description Units
Orbital Period Time for one orbit Days
Stellar Radius Host star radius Solar radii
Rate of Ascension Right ascension Degrees
Declination Declination coordinate Degrees
Transit Duration Duration of transit Hours
Transit Depth Depth of light curve dip PPM
Planet Radius Estimated planet radius Earth radii
Planet Temperature Estimated equilibrium temperature Kelvin
Insolation Flux Stellar flux received Earth flux
Stellar Temperature Host star temperature Kelvin

Kepler-227 b

K00752.01 - CONFIRMED

Ready
Orbital Period
9.48803557
Stellar Radius
0.927
Rate of Ascension
291.934230
Declination
48.141651
Transit Duration
2.9575
Transit Depth
615.8
Planet Radius
2.26
Planet Temperature
793
Insolation Flux
93.59
Stellar Temperature
5455

Kepler-228 c

K00756.02 - CANDIDATE

Processing
Orbital Period
4.13443512
Stellar Radius
0.972
Rate of Ascension
296.286130
Declination
48.224670
Transit Duration
3.1402
Transit Depth
686
Planet Radius
2.77
Planet Temperature
1160
Insolation Flux
427.65
Stellar Temperature
6046

KepID 10419211

K00742.01 - FALSE POSITIVE

Draft
Orbital Period
11.521446064
Stellar Radius
0.848
Rate of Ascension
297.079930
Declination
47.597401
Transit Duration
3.6399
Transit Depth
17984.3
Planet Radius
150.51
Planet Temperature
753
Insolation Flux
75.88
Stellar Temperature
5795

Exoplanet Classification

Run machine learning models on individual candidates or bulk datasets. Upload transit light curves, stellar parameters, or preprocessed feature sets. The model will classify signals as confirmed planets, false positives, or candidates requiring further observation.

Single Candidate

Analyze one exoplanet candidate at a time for detailed classification and confidence scoring.

Single candidate: no selection yet.

    Bulk Dataset

    Process large catalogs of transit signals for automated screening and candidate identification.

      Choose Single for individual objects or Bulk for uploaded datasets. Classification results, confidence scores, and transit visualizations will appear below once processing is complete.

      Classification Results

      View model predictions, confidence scores, and explanatory visualizations. Export results for further analysis or integration with astronomical databases.

      Ready for exoplanet classification. Select candidates above and run the machine learning model.