Research Notes

Short notes on methodology, deployment, and research direction. Updated occasionally.

May 2026 · Methodology

Why Physics-Informed Loss Terms Are Hard to Get Right

The trade-off between physical plausibility and raw accuracy, and why adaptive penalty design matters.

April 2026 · Deployment

Running ML Inference on a Jetson at the Turbine: What Actually Matters

Lessons from deploying wind forecasting models on edge hardware with strict latency and memory budgets.

March 2026 · Direction

From SDG Language to Resilience Language

Why the global research funding vocabulary is shifting, and what it means for physics-informed AI.