Fruit orchard monitoring through satellite imagery

This project focuses on the collection of satellite images to extract vegetation indices for the construction of a dataset aimed at predicting flowering dates. The pipeline includes remote sensing data acquisition, feature engineering, and the implementation of tree-based machine learning models such as Random Forest and XGBoost for regression tasks.

Stack: Sentinel-2 QGIS Python XGBoost Scikit-learn

Image 1 Image 2

Dashboard Mujeres en Tecnología

Dashboard built by validating and cleaning non-relational data, implementing exploratory queries, and uncovering key insights.

Stack: Python Pandas Numpy Dash Plotly

Image 1 Image 2

ExploraML

ExploraML is my degree thesis. It is a web platform designed to introduce basic machine learning concepts, allowing users to interact with a churn prediction dataset and run different supervised learning techniques such as Logistic Regression, Stochastic Gradient Descent, Random Forest, Decision tree and compare their performance.

🔗View on github

Stack: Python Pandas Numpy Plotly Scikit-learn Flask SQLite Gunicorn

Image 1 Image 2

Soil Moisture Prediction

Visualizations built from satellite data collected from the Global Land Data Assimilation System (GLDAS).

🔗View on github

Stack: Python Numpy netCDF4 Matplotlib PIL