ML / Optimization

Machine learning, deep learning, and optimization:

1. Building Footprints Comparison: SAM 3 vs ESRI

   Professional work. Extracted building outlines across Lewisville, Texas, from 21.1 gigapixels of 10 cm Nearmap imagery with Meta’s SAM 3 and Esri’s pretrained Mask R-CNN, then compared them with identical cleanup and scoring, a tuning protocol written in advance, and a test area scored once.

2. Income Level Prediction Using R

   Learning project. Comparing R models for predicting income categories.

3. Water Conservation Routes

   Professional work. Shorter routes for inspecting commercial, industrial, and multifamily water meters.

4. Lead Service Line Evidence Workbench

   Synthetic-data demonstration. A local Python workflow that connects document evidence, material predictions, and traceable human review.

5. Lead Pipe Prediction Prototype

   Synthetic-data demonstration. A synthetic-data prototype for predicting pipe materials and organizing human review.

6. Traveling Salesman

   Public code. A Python TSP solver with exact methods, local search, metaheuristics, a command-line interface, and reproducible TSPLIB comparisons.

← Back to projects