Back to research

Machine Learning Team Lead

AI For Search and Rescue (IntelliSAR)

San Luis Obispo, CA·Mar 2023 - May 2025

Led a 15-person ML team on IntelliSAR, training models on the ISRID historical missing-person dataset to narrow search areas. The wander-status model reached 86% recall against a 14% minority class. Presented twice at the National Missing and Unidentified Persons Conference.

What I worked on

  • Led a 15-person ML team on IntelliSAR, a Cal Poly research collaboration with experienced search and rescue leaders, under Dr. Franz Kurfess.
  • Trained K-means, K-Nearest Neighbors, and SVM models on the International Search and Rescue Incident Database (ISRID), Robert Koester's historical missing-person dataset, to surface behavioral patterns that narrow a search area.
  • Built a K-Nearest Neighbors wander-status prediction model reaching 86% recall and 75% precision on a heavily imbalanced dataset where only 14% of incidents were unsuccessful outcomes.
  • Identified predictive relationships between elevation, subject situation, and rescue outcome, and between age, gender, and time missing, confirming and extending published findings on dementia prevalence among missing persons.
  • Presented findings twice at the National Missing and Unidentified Persons Conference in Las Vegas, most recently in April 2025.
  • Coordinated with the supervising professor and implemented agile practices that reduced project turnaround time across the team.

Tools and techniques

PythonScikit-learnK-Nearest NeighborsK-meansSVMImbalanced ClassificationExplainable AITeam Leadership