The Science & People Behind ExoMind

Meet the team and explore the essentials of our AI approach to exoplanet detection.

Who We Are

A small, focused team blending astrophysics and applied AI.

Sergio Navarro

Sergio Navarro

Full-Stack Developer

Full stack development, deployment and optimization. Focus on scalable web applications.

JavaScriptReactNode.js
Paula Lucas

Paula Lucas

Data Scientist

Data analysis, modeling and visualization. Focus on turning data into actionable insights.

PythonPandasMachine Learning
Mario Gallego

Mario Gallego

Backend & MLOps Engineer

Model deployment, automation and cloud integration. Focus on efficient backend pipelines.

FastAPIDockerCI/CD
Sergio Lozano

Sergio Lozano

Software Developer

Software design, testing and maintenance. Focus on clean, reliable and maintainable code.

JavaSpring BootGit
Javier Lorenzo

Javier Lorenzo

UI/UX Designer

User-centered design and prototyping. Focus on intuitive and aesthetic digital experiences.

FigmaPrototypingDesign Systems
María Toral

María Toral

Astrophysics Advisor

Research guidance and data interpretation. Focus on stellar modeling and exoplanet detection.

AstrophysicsData AnalysisScientific Research

Performance at a Glance

93%
chance to correctly confirm an exoplanet
High positive detection accuracy on KOI-like data.
1%
chance to miss a true exoplanet when filtering
Low false-negative rate when screening candidates.

Why Random Forest?

Short, practical reasons behind our choice.

Generalizes Well

Many shallow trees reduce overfitting across varied stellar systems.

Explainable Signals

Highlights depth, duration, period, SNR, and stellar context clearly.

Fast & Lightweight

Quick inference, easy retraining as new data arrives.

Want to try ExoMind?

Get early access and test your own light curves or spectra.