# Jonas Ferrao | Intelligence Engineer

> Portfolio of Jonas Chris Ferrao, an AI ML Engineer specializing in machine learning, data science, and software engineering. Explore innovative projects in neural networks, computer vision, and production-grade ML systems.

Return to GridAstrophysicsPyTorchPhysics-Guided NNResearch

# PREML

Photometric Redshift Estimation using Machine Learning

Project Dossier

My Final Year Project applying deep learning to redshift estimation. Redshift estimation is key in astrophysics to measure cosmic distances and understand the universe’s expansion. Traditional spectroscopic methods are accurate but not scalable. Our project tackles this using machine learning.

####  Technical Architecture

We developed a **Physics-Guided Neural Network (PGNN)** that processes both photometric magnitudes and galaxy images. The architecture consists of:

- **MLP Head:** Processes tabular photometric inputs.
- **CNN Head:** Extracts features from galaxy imagery.
- **Cross-Attention:** Fuses features from both heads for robust representation.
- **Bayesian NN:** Provides uncertainty estimation alongside predictions.
- **Physics Loss:** Incorporates SED template fitting constraints.

[REF_IMG]: PREML Architecture

####  Impact

- Achieved SOTA accuracy, outperforming traditional methods.
- Satisfies two out of three LSST requirements up to z < 3.
- Created the PREML dataset (~400k samples), one of the largest public benchmarks.

Key Stats~400kDataset SizeSOTAAccuracyz < 3RedshiftActions[Live System](https://preml-e3bfevh8abfgenc8.centralindia-01.azurewebsites.net/)[Source Code](https://github.com/projectultra/PREML)[Official Article](https://doi.org/10.1007/s12036-026-10144-5)[Preprint](https://arxiv.org/abs/2507.00866)

## Reach out to me

[EMAIL](mailto:jonasferrao21@gmail.com)[PHONE](tel:+918805513038)[LINKEDIN](https://www.linkedin.com/in/jonas-ferrao/)

© 2026 JONAS FERRAO

@PROJECTULTRA