surrogate-modeling

Python Low-Code System Solutions

Official repo for "The impact of internal variability on benchmarking deep learning climate emulators" in JAMES25 (public)

A Genetic Algorithm (GA) / Discrete Particle Swarm Optimization/ Hybrid (GA-PSO) for nuclear fuel optimization using ML surrogates (DNN, KNN, Random Forest, Ridge) and OpenMC. Optimizes fuel loading patterns for a target k-eff and minimal Power Peaking Factor (PPF).

Modern OpenTURNS web workspace for reproducible uncertainty quantification, sensitivity analysis, reliability, surrogates, and traceable reports.

Performance Modeling of Data Storage Systems Using Generative Models, IEEE Access, vol. 13, pp. 49643-49658, 2025, doi: 10.1109/ACCESS.2025.3552409

ReservoirNeuralBench – A controlled benchmark of neural surrogates for 3D reservoir simulation on the Norne field.

This repository provides an implementation of algorithmic support for dynamic pricing based on surrogate ticket demand modeling for a passenger rail company on open data.

A novel neural network for effective learning of highly impulsive/oscillatory dynamic systems by jointly utilizing low-order derivatives

Space-filling Design of Experiments for Python: optimal sampling for discrete, continuous, integer and mixed parameter spaces

The last few solves you'll ever pay for: certified accelerator + identification layer over any black-box parametric solver, built on resona's effective-rank dial.

Curiosity → Perseverance rover wheel skin: Ansys FEA, analytical failure analysis, and a PCA–Gaussian-process surrogate model with a MATLAB GUI for instant stress/strain prediction.

G-PARC: physics-aware graph neural networks for spatiotemporal dynamics on unstructured meshes (Scientific Reports, 2026)

ProcGNN is a process-graph learning framework for stream-property prediction, developed at Network Science Lab @ CUK and implemented directly in PyTorch.

Uncertainty quantification, Bayesian inference, and scientific ML for physical/biological models

Global sensitivity analysis in JAX: Sobol, Morris, PCE, Shapley and ten more methods, vectorised and differentiable

基于实验数据标定的P2D电化学模型，结合机器学习代理模型（GPR）与 NSGA-II 遗传算法，对磷酸铁锂（LFP）电池的比能量（SE）—比功率（SP）进行多目标优化，求解 Pareto 前沿。

Physics-constrained TMM-SVR surrogate pipeline for PDMS thin-film infrared emissivity prediction

Python code for running the numerical experiments in the paper "Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods" by Brian Irwin, Eldad Haber, Raviv Gal, and Avi Ziv.

CARDIOKOOP - Control-aware Koopman deep learning framework for real-time hemodynamic forecasting and cardiovascular digital twin applications.

Uncertainty Quantification pipeline for reinforced-concrete FEM (Abaqus) using surrogate models (PCA+GPR, AE+GPR, Shape-Scale) for fast Monte Carlo propagation, sensitivity analysis, and reliability metrics.