---
title: Api Transpetro Hackathon
emoji: 🏆
colorFrom: yellow
colorTo: blue
sdk: docker
pinned: false
license: mit
short_description: API for predicting naval biofouling.
---
Artificial Intelligence API for predicting naval biofouling, performance loss, 
and financial risk in real-time. Developed based on naval physics, fuel chemistry, 
and machine learning models (Random Forest + XGBoost).

The API is running in production on Hugging Face Spaces.

- Base Endpoint: https://carpenterbb-api-transpetro-hackathon.hf.space
- Interactive Documentation (Swagger): https://carpenterbb-api-transpetro-hackathon.hf.space/docs

- All requests must include the following: access_token = hackathon_transpetro_2025

🔮 Prediction Route
- POST /predict

Author:
- Gabrielly Gomes (Machine Learning Engineer)

Attention:
This model was developed for Transpetro(Petrobras) Hackathon.

My team: 
- Gabrielly Gomes - ML Engineer
- Patrick Passos - Developer (full stack)
- Lucas Fernandes - Designer/Business