Amazon Archeological Site Discovery - a Deep Learning Approach
-
Updated
Sep 9, 2025 - Python
Amazon Archeological Site Discovery - a Deep Learning Approach
Satellite image classifier that identifies signs of deforestation and pollution using transfer learning with a pre-trained ResNet50 Convolutional Neural Network (CNN) model.
A cost-efficient, AI-powered tool for discovering archaeological sites in the Amazon basin using satellite imagery, LiDAR data, and historical records. Built for the OpenAI to Z Challenge.
COMP 590 - Data Science for Earth @ UNC-CH Final Project, Google Earth Engine, Amazon Rainforest Classification
A data science project exploring links between Amazon environmental events and disease-related mortality.
This project uses Google Earth Engine's (GEE) platform to analyze deforestation in the Amazon rainforest. The analysis is based on the Hansen Global Forest Change dataset.
Co-authored workshops on Machine Learning for Geospatial data at the University of Waterloo
A machine learning project developed in the context of COP30 to assess socio-environmental risk in Amazonian development projects using environmental indicators.
Aplicação de Data Science para previsão de desmatamento na Amazônia utilizando Random Forest. Inclui pipeline de engenharia de dados, validação temporal e dashboard interativo em Streamlit.
Machine Learning Engineer Capstone Project. Multi-Class Deep Learning Classification (CNN) to classify images in the Amazon Rainforest. Kaggle Competition.
Effects of drought and habitat fragmentation on Heliconia acuminata.
Historical analysis of Funai negative certificates and Indigenous lands rights in Brazil (1968-1990)
Scripts for the MA research about Brazil’s parliamentary discourses dynamics on the Amazon rainforest.
Windows adaptation of the PyEO forest change detection workflow for Sentinel-2 monitoring in the Amazon BR-163 corridor.
Fourier Domain Adaptation + Evidential Deep Learning for source-free cross-domain deforestation detection in the Brazilian Amazon using Landsat-8 satellite imagery. ConvNeXt encoder (9.5M params) with per-pixel uncertainty estimation. PyTorch implementation.
Detecting deforestation in the Brazilian Amazon by using NDVI and Woodiness index
End-to-end bioacoustic search for animal vocalizations in Amazonian forest recordings using SurfPerch, Qdrant, and an interactive review UI.
Add a description, image, and links to the amazon-rainforest topic page so that developers can more easily learn about it.
To associate your repository with the amazon-rainforest topic, visit your repo's landing page and select "manage topics."