portfolio

Forager | Full Stack Ecological Intelligence App

Forager identifying a wild mushroom: species, safety verdict, nutrition, and model heatmap

Forager identifies wild edible plants and fungi from a photo, then streams back species, safety, nutrition, and weather data while you're still on the trail.

A custom EfficientNet-B7 classifier (95.7% accuracy across 101 species, trained on ~177K iNaturalist images) runs on CPU as a dual-output ONNX model, returning predictions and CAM explainability heatmaps in a single forward pass with no PyTorch in production. Results stream to the frontend over Server-Sent Events and persist incrementally, so a downstream hiccup like a flaky weather API never wipes out the species ID you were waiting on. The safety layer pulls verdicts from a curated, citation-backed knowledge base instead of an LLM, and defaults to caution on low confidence or missing data, so a "safe" verdict is never returned without backing data.

Stack: React 19 / TypeScript (Zustand, Tailwind, shadcn/ui), FastAPI with async SQLAlchemy, PostgreSQL, deployed on a single AWS EC2 instance via Terraform and Docker Compose.

view forager live  ·  view codebase on GitHub

What's next: out-of-distribution detection so the model can say "I don't know" instead of guessing; an offline PWA running a distilled in-browser model; and RAG-powered chat for follow-up questions about an identified species.

Citizen Science App for Kids | OSU Capstone

For my capstone at Oregon State, our team of four built a citizen science platform that helps teachers bring real data collection into their classrooms. Students grab a project code, head outside, and start logging wildlife and plant observations from any device, no account required.

I was the sole backend engineer. I designed the full relational database schema in MySQL and built the Flask REST API with JWT authentication, role-based access control, session management, and input validation, serving both the mobile field app and the admin dashboard. On the admin side, I built interactive Chart.js visualizations so teachers could explore student submissions across their projects. Rounded it out with full API documentation and a Pytest test suite, deployed on Railway.

Stack: Python, Flask, MySQL, Chart.js, Pytest, Railway.

view backend codebase on GitHub

Contact: lindsayreneeschwartz@gmail.com