Marine Scientist · Environmental Steward · Computational Biologist
Part of SCMTS's volunteer trail crews building and maintaining trails at Wilder Ranch State Park and Henry Cowell Redwoods State Park — contributing to new public trail access in the Santa Cruz Mountains.
As Trail Committee Chair for Advocates for Nisene Marks State Park, I lead conservation stewardship initiatives combining field leadership with geospatial technology to protect old-growth redwood ecosystems.
Trail stewardship and habitat restoration at Elkhorn Slough National Estuarine Research Reserve — maintaining visitor access through coastal wetland environments while supporting the reserve's ecological mission.
Volunteer with the Stewardship Trails & Access Crew, maintaining roads, trails, and ecological integrity across Big Sur Land Trust's protected coastal and mountain landscapes.
Conservation volunteer on the 20,000-acre Santa Lucia Preserve in Carmel, working alongside the Conservancy to maintain trails and support science-guided land management on permanently protected wildlands.
Pick a card, any card
Each card represents a research or presentation topic
Real-time HAB monitoring combining NOAA VIIRS satellite data, buoy measurements, and ensemble ML. Built 3 custom REST APIs, dual dashboards for farmers and public safety, and automated alert system.
Custom-built edge station: Raspberry Pi 5 + RTL-SDR Blog V4 + SIM7028 NB-IoT HAT. Each unit operates autonomously in the field for weeks, detecting VHF wildlife tags across the 151 MHz band.
927-line multi-channel FFT-based detection engine. Processes 256K IQ samples through adaptive baseline tracking, pattern validation with ghost filtering, and coefficient-of-variation analysis to distinguish true repeating tags (CV < 0.15) from noise.
Dual dashboard architecture: local Flask station dashboard for real-time tag detection and system health, plus a centralized FastAPI server with 35+ REST endpoints, 8-table SQLite schema, HMAC auth, and Leaflet geographic mapping for multi-station fleet monitoring.
Automatic WiFi-to-NB-IoT failover for network resilience. SQLite-backed offline queue buffers detections during connectivity gaps. Batched events use single-letter JSON keys to achieve ~650 bytes per cellular alert. Exponential backoff (2s→60s) with connection state machine tracking wifi/nbiot/offline states.
Field-tested at Monterey Bay coastal sites. Yagi directional antenna achieves 1,700+ ft max range with 62% detection rate. Auto-calibration sweep optimizes SDR gain (15–45 dB) on boot. Watchdog daemon monitors system health every 60s with 3-strike escalation policy.
Shown: first-generation 5-keypoint model. Current pipeline uses the 16-keypoint schema described below.
YOLOv8-pose model trained on 16 anatomical keypoints—9 Tier 1 body-axis landmarks (snout, eye, gill slits, pectoral base, dorsal base, caudal) and 7 Tier 2 fin tips—for white shark body condition assessment from underwater video. Extracts angle-tolerant morphometric ratios including total length, fork length, head-to-total ratio, and body condition index across 4 California research sites.
Semi-supervised 8-stage pipeline: video cataloging → frame extraction → seed annotation → model training → active learning selection → human correction → pseudo-label amplification → refinement. Processes 4,850 videos (661 GB) spanning 2012–2026 across Año Nuevo, Aptos, Farallon Islands, and Point Reyes. Uncertainty + k-center diversity scoring selects the most informative frames for annotation, with pre-annotation from the current best model to accelerate human review.
Presented research at multiple conferences including the CSUMB Summer Symposium on ML-based dorsal fin morphometrics for white shark identification and health assessment.
Automated harbor porpoise individual identification from dorsal fin photos. SAM 2 segments the body, protrusion geometry extracts the fin, MegaDescriptor-L-384 embeds the crop through an ArcFace head, and cosine similarity ranks the 198-individual catalog.
Leave-one-out evaluation on individuals with ≥5 sightings yields 93.0% rank-1 and 98.3% rank-5 accuracy. Temporal split (train ≤2022, test 2023+) gives 30.5% rank-1 — reflecting the real-world challenge of fin shape change over years. Gallery size experiments confirm more photos per individual directly improve re-ID accuracy.
Gradio web interface for field researchers to upload dorsal fin photos and receive ranked identity matches. Includes catalog browsing with individual sighting histories, Dropbox integration for photo ingestion, and batch processing. Deployed on an 8-node Raspberry Pi Kubernetes cluster processing 360 images/hour.
Full-stack Flask annotation platform for shark scar and morphometric data. SAM2 AI segmentation for body and scar detection, 15-point keypoint skeleton with auto-generation (click snout + caudal, remaining 13 points placed automatically), and 12-zone body diagram with 11 scar types. Multi-annotator consensus scoring with weighted voting by experience, proficiency, and confidence tiers.
Interactive 12-zone SVG body diagram for precise anatomical scar placement. Each zone is clickable and color-coded. Scar annotations include type classification, confidence rating (1–5 stars), side (left/right/dorsal/ventral), and free-text notes. Auto-save triggers every 5 minutes with unsaved-changes browser guard.
Export pipeline supporting COCO JSON, Google Forms CSV, Keypoint CSV (wide format), and Google Sheets (3-tab: Scars, Keypoints, Admin Flags) with auto-sync on every annotation save. Google Drive integration auto-resolves video IDs with 3-tier resolution (local → cached → Drive). Deployed at annotate.shark-id.org on AWS EC2 with Docker Compose and nginx reverse proxy.
LlamaIndex RAG pipeline with LanceDB vector store for citation-aware Q&A across shark research papers. Every answer includes [Author et al., Year, p.X] citations traced to source documents. Supports PDF, DOCX, HTML, EPUB, and Markdown ingestion with Docling section-aware parsing and PyMuPDF fallback.
Automated literature discovery via OpenAlex API with Unpaywall PDF downloading. Pre-configured for 20 shark research domains—morphometrics, telemetry, ecology, machine learning, genetics, behavior, conservation, and more—targeting white sharks, leopard sharks, and orcas. Gradio UI with 7 tabs for chat, upload, library management, summarization, and settings.
Performed CFD analysis using OpenFOAM to model hydrodynamic drag around acoustic tags on shark dorsal fins. Iterative simulations refined tag geometry to minimize swimming resistance.
End-to-end pipeline for TECAN plate reader growth curve analysis on bacteria remediation strains. Automates the full workflow from raw data to publication-ready figures.
Multi-DOF robotic arm exploring kinematics, servo control, and mechanical design.
Custom monitoring devices measuring pH, temperature, DO, and salinity in real-time.
Research platform and learning opportunity for avionics. Custom-built FPV drone serving as a hands-on testbed for flight controller programming, PID tuning, ESC protocols, and radio telemetry systems.
The story behind the science — seven chapters, one thread
"The frontier in marine science is not just about reaching new places, but about seeing what is already there in radically new ways."
Chapter I
1
The first time I saw ROV footage of a hydrothermal vent, the shimmering fluid and tube worms crowding a chimney in complete darkness, something shifted. It was during a thesis defense I'd stumbled into, a graduate student describing species that had never been cataloged, ecosystems sustained by chemistry instead of sunlight, DNA analysis revealing evolutionary histories that rewrote textbooks.
That experience showed me that entire ecosystems on our own planet remain unknown, and that the tools we build to observe them determine what we can discover. It is the reason I now build those tools.
Chapter II
3
California State University, Monterey Bay became the place where curiosity found structure. A B.S. in Marine Science with a Biology minor gave me the foundation, but the coursework that actually shaped my thinking went deeper: Marine Ecology, Scientific Diving, Statistics, GIS, and Python Programming.
Each course added a new lens. Statistics taught me to question what I thought I saw. GIS taught me to think spatially. Python taught me that the bottleneck in science is rarely data, it's the tools to make sense of it. Beyond the classroom, volunteer work is where I found my love for conservation and teaching. Guiding kids through the mudflats and channels of Elkhorn Slough, watching them discover crabs and birds for the first time, reminded me why this work matters beyond the lab.
Chapter III
5
Spring 2024 was when research stopped being theoretical. At Moss Landing Marine Labs, I was elbow-deep in urchin conditioning tanks. In the Ocean Predator Ecology Lab, I was reviewing hours of white shark footage, learning to read injury patterns the way a doctor reads an X-ray. Every kelp canopy dive at San Carlos Beach taught me that the ocean doesn't wait for you to be ready.
After earning my NAUI Divemaster, South Africa changed everything. The research diving program threw me into conditions I wasn't ready for, surge, cold water, unfamiliar species, boats that never stopped moving. What I gained was the understanding that fieldwork is where science becomes honest.
Chapter IV
7
Being selected as a UROC Innovation Scholar, funded by CSUN's HSI Equity Innovation Hub and Apple, gave me the resources to think bigger. I wasn't just collecting data anymore; I was building systems to process it. Marine ecology research on latitudinal biodiversity gradients using PISCO and NOAA CUTI datasets taught me to think at scale.
Outside the lab, I took on leadership roles in conservation and education, roles that reminded me that science without community is just data. And in the lab, the SharkHealthApp was taking shape: dual YOLO models achieving 96% pose accuracy, semi-supervised learning, automated keypoint tracking from archival footage.
Chapter V
9
A week-long hackathon, inspired by my work in aquaculture and the colleges and communities that need these tools most. We built a real-time harmful algal bloom monitoring system for Monterey Bay, fusing NOAA VIIRS satellite imagery with NDBC buoy observations and CalHABMAP toxin records. A 47-feature XGBoost model generating 8-day HAB forecasts.
The full stack came together under pressure: Python data pipeline, Flask REST API, Docker deployment, three React/TypeScript dashboards serving aquaculture farmers, beachgoers, and marine mammal researchers. When they announced first place, it was proof that the tools I'd been building actually worked when it mattered.
Chapter VI
11
VHF wildlife tag relay stations, Raspberry Pi, RTL-SDR, and NB-IoT cellular, deployed off-grid at Elkhorn Slough. Solar-powered and bridging MQTT to AWS EC2, the kind of system where failure means losing data that took months of fieldwork to create.
Alongside the stations, I'm developing a custom aerial platform for automated white shark population assessments and a CNN-based pipeline for behavior classification from dorsal-mounted camera footage fused with accelerometer and magnetometer data. A multi-task deep learning framework for angle-tolerant morphometric extraction, presented at NEPSS 2026 in February.
Chapter VII
13
Continuing as researcher and steward. Everything I've worked toward, from field ecology to computer vision to hardware deployments, converges on the same goal: building tools that let us observe what we couldn't before and making that knowledge accessible to the people and communities who need it.
Whether it's conservation monitoring, marine health assessment, or education outreach, the thread is the same. Science should serve the places and people it studies.
