ABOUT ME

I'm a Forestry Engineer completing my M.S. in GIS at the University of Maryland this spring. My career has taken me from forest inventory work to modeling public health indicators across Sub-Saharan Africa—always with one constant: using spatial data to solve problems that matter.

I've worked with multidisciplinary teams across continents, turning messy GPS datasets and survey data into clear insights that inform real decisions. Whether it's mapping health outcomes for local governments or managing geospatial databases for development programs, I'm drawn to work where precision meets purpose.

Currently expanding into cloud infrastructure (training for AWS Solutions Architect certification) to build more scalable geospatial solutions. I'm looking for my next role with organizations that use data and technology to create measurable impact—where the mission is as important as the method.

Featured Work

Machine Learning / GEE / Wildfires

Wildfire Risk Prediction: Paraguayan Chaco

A predictive modeling project utilizing Random Forest to estimate daily wildfire likelihood. By integrating 24 years of FIRMS data with climate and topographic variables, this tool provides a robust framework for early-warning systems.

Python Scikit-Learn Google Earth Engine

View Full Case Study

Remote Sensing / Conservation

Mbaracayú Reserve Forest Loss Assessment

An analysis of illegal logging and wildfire impacts using Sentinel-2A multispectral data. This study quantified over 19,000 hectares of forest disturbance using NDVI and NBR indices to identify land-cover transitions.

ArcGIS Pro Remote Sensing Change Detection

Explore Methodology

Wildfires / Spatial Stats

Spatial and temporal analysis of wildfires in the Paraguayan Chaco

An overview of spatio-temporal patterns of wildfires in the Paraguayan Chaco. The analysis took historical fire data from MODIS and analyzed clustering, covariance, and emerging hotspots.

Python (Geopandas) Spatial Statistics ArcGIS Pro

Story Map

Automation / Spatial Stats

Road Accident Hotspot Analysis Tool

An automated ArcPy toolbox designed for urban safety engineering. It streamlines the identification of statistically significant (Getis-Ord Gi*) crash clusters, reducing data preparation time by 80%.

Python (ArcPy) Spatial Statistics HTML Reporting

GitHub Repository

Projects

Tree Planting & Carbon Tracking

An ArcGIS Dashboard monitoring urban reforestation with automated carbon capture estimation.

Python-driven environmental impact metrics.
Real-time spatial tracking of municipal planting.

Explore Dashboard

North Carolina Infant Mortality: Autocorrelation Study

A rigorous statistical analysis of infant mortality patterns across North Carolina. This project moves beyond simple heatmaps to prove statistical significance using global and local spatial autocorrelation metrics.

Methodology: Comparative analysis using Global Moran’s I and Getis-Ord G* to identify validated high-rate clusters (Hotspots) in the NE and SE regions.
Spatial Insights: Differentiated between "count" vs. "rate" patterns to identify socioeconomic outliers and statistically significant "Low-High" coastal anomalies.
Validation: Rejecting null hypotheses via Z-scores and P-value assessment to ensure data-driven public health conclusions.

Lincoln City: Spatio-Temporal Crime Pattern Analysis

A multi-methodological study of auto-theft patterns in Lincoln City, Oregon. This project utilizes hierarchical clustering and moving averages to provide actionable intelligence for law enforcement resource allocation.

Clustering: Applied Nearest Neighbor Hierarchical (NNH) spatial clustering across multiple radii to identify 1st and 2nd order crime hotspots.
Temporal Modeling: Developed a Spatio-Temporal Moving Average (STMA) to track the geographic "drift" of incidents over time.
Comparison: Evaluated NNA vs. NNH to prove why hierarchical structures provide superior operational insights over simple distribution measures.

Web GIS / ArcGIS Experience Builder

A resident-facing web application designed for the City of College Park to promote outdoor engagement. This portal aggregates municipal spatial data into a user-friendly interface, allowing residents to discover parks, trails, and recreational facilities in real-time.

Key Features: Interactive filtering by activity type, mobile-responsive design, and integrated routing.
Platform: ArcGIS Experience Builder / ArcGIS Online. Impact: Streamlined public access to city amenities and improved digital engagement for the Parks & Recreation department.

Paraguayan National budget 2024

A comprehensive visualization of the 2024 Paraguayan national budget. This dashboard deconstructs complex governmental fiscal data into digestible hierarchies, allowing for transparency in public spending and departmental allocations.

Visualizations: Treemaps of institutional spending, year-over-year allocation shifts, and categorical breakdowns.
Data Engineering: Cleaned and structured raw public accounting datasets for interactive exploration.
Value: Demonstrates the ability to apply data engineering principles to non-spatial financial sectors, emphasizing transparency and civic tech.

View Dashboard

Health Workforce Logistics

Visualizing healthcare coverage across Paraguay to identify regional disparities in medical professional density.

Interactive Tableau dashboard for policy planning.
Analyzed urban vs. rural specialist distribution.