Agricultural Sciences & Engineering · EARTH University
Agricultural Sciences professional specializing in precision & digital agriculture, remote sensing, and geospatial analysis. I build data-driven tools — from UAV imagery to machine learning models — to advance sustainable food systems and global agricultural resilience.
I am a highly motivated final-year Agricultural Sciences & Engineering student at EARTH University, Costa Rica, specializing in precision and digital agriculture, remote sensing, and geospatial analysis.
I am experienced in UAV data acquisition and processing using Pix4D, Agisoft Metashape, QGIS, and Google Earth Engine, and proficient in Python and R for spatial modeling, statistical analysis, and machine learning. My work focuses on developing data-driven tools for biomass estimation and precision farm management.
I am passionate about applying geospatial intelligence and AgriTech innovation to advance sustainable food systems and global agricultural resilience — bridging field-scale agronomy with modern data science.
My full Statement of Purpose — covering my research interests across data science, agricultural systems, and food quality, my technical background, and my long-term goals — is available as a PDF.
📄 Read my Statement of Purpose (PDF)Seeking funded MSc opportunities in data-driven agricultural and food systems, remote sensing, or food quality & nutrition.
AvailableOpen to PhD projects bridging machine learning, remote sensing, and crop/food systems for real-world impact.
AvailableAvailable for AgriTech, precision-agriculture, UAV/remote-sensing, and data-science roles, plus research collaborations.
AvailableI design and execute UAV data-collection campaigns, preprocess high-resolution multispectral and RGB imagery, perform image segmentation and feature extraction, and develop machine learning regression models validated against ground-truth field measurements collected in Denmark.
The full pipeline runs in Python (Google Colab), with orthomosaics and vegetation indices generated in Pix4D and QGIS.
UAV multispectral & RGB flights plus ground-truth biomass sampling (Aarhus, Denmark).
Orthomosaics & vegetation indices generated in Pix4D and QGIS.
Spectral and index features extracted and prepared in Python (Google Colab).
Regression models — Random Forest, SVM, and XGBoost — trained on the feature set.
Predictions validated against ground-truth field measurements; biomass mapped.
Drone flights, Kernza campaigns, root imaging, and presentations — organized by theme. Hover to pause · click to enlarge.
CV, statement of purpose, and certificates are free to download. 🔒 The academic transcript is private — request access by email and I'll share it directly.



