physics-based-modeling

A physics-informed neural network approach is proposed for control-oriented building thermal modeling, combining data with physical laws to improve accuracy and reduce training data needs. The method predicts room temperature, power use, and hidden thermal states more reliably than standard neural networks.

Codex skill and open workflow for deriving, auditing, falsifying, and validating physics-based analytical models in thermal fluids, boiling, and CHF.

Physics-based electrochemical modeling of lithium-ion cells in Python: a from-scratch DFN/SPM solver, parameter estimation, and thermal, degradation, and design studies, validated against PyBaMM.

UnIvErZe is a comprehensive artificial life simulation platform that models biological evolution from first principles, implementing sophisticated genetic regulatory networks, developmental embryogeny, and multi-level selection pressures within a physics-based cellular automaton environment.

Physics-informed neural inverse solver for recovering hidden electrostatic sources from boundary potential measurements.

Breathe Battery Technologies is a UK battery software company, spun out of Imperial College London in 2019, that builds physics-based battery simulation, cell design, and adaptive charging software for OEM and cell engineering teams.

Schrödinger is a New York-headquartered (NASDAQ: SDGR) computational science company that develops a physics-based and AI-driven molecular simulation platform used across drug discovery and materials science.