SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era
Not on the map. Why?
Abstract (arXiv)
Surrogate models are widely used to approximate complex systems across science and engineering to reduce computational costs. Despite their widespread adoption, the field lacks standardisation across key stages of the modelling pipeline, including data sampling, model selection, evaluation, and downstream analysis. This fragmentation limits reproducibility and cross-domain utility -- a challenge further exacerbated by the rapid proliferation of AI-driven surrogate models. We argue for the urgent need to establish a structured reporting standard, the Surrogate Model Reporting Standard (SMRS), that systematically captures essential design and evaluation choices while remaining agnostic to implementation specifics. By promoting a standardised yet flexible framework, we aim to improve the reliability of surrogate modelling, foster interdisciplinary knowledge transfer, and, as a result, accelerate scientific progress in the AI era.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 114 references that are in the map. First posted on arXiv 10 Feb 2025.
Builds on
46 of 114 references.
References · 46
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
- 2018Model Cards for Model Reportingcited by 1,068
- 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
- 2019The frontier of simulation-based inferencecited by 490
- 2015Variational Dropout and the Local Reparameterization Trickcited by 489
- 2017A Brief Survey of Deep Reinforcement Learningcited by 466
- 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
- 2013A General Framework for Updating Belief Distributionscited by 172
34 more
- 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 162
- 2020Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systemscited by 160
- 2021Benchmarking Simulation-Based Inferencecited by 160
- 2023Scalable Transformer for PDE Surrogate Modelingcited by 123
- 2018Validating Bayesian Inference Algorithms with Simulation-Based Calibrationcited by 118
- 2015Practical Bayesian model evaluation using leave-one-out cross-validation and WAICcited by 110
- 2019Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimizationcited by 70
- 2019Robust Bi-Tempered Logistic Loss Based on Bregman Divergencescited by 61
- 2023A Study of Bayesian Neural Network Surrogates for Bayesian Optimizationcited by 50
- 2022Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrapcited by 41
- 2023SMT 2.0: A Surrogate Modeling Toolbox with a focus on Hierarchical and Mixed Variables Gaussian Processescited by 27
- 2022Simulation-Based Calibration Checking for Bayesian Computation: The Choice of Test Quantities Shapes Sensitivitycited by 19
- 2023Multi-fidelity reduced-order surrogate modelingcited by 18
- 2020Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questionscited by 16
- 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
- 2024Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modelingcited by 13
- 2017Objective Bayesian inference with proper scoring rulescited by 12
- 2021PriorVAE: Encoding spatial priors with VAEs for small-area estimationcited by 11
- 2025Robust and Conjugate Spatio-Temporal Gaussian Processescited by 9
- 2019Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniquescited by 8
- 2021Toward a Taxonomy of Trust for Probabilistic Machine Learningcited by 8
- 2023A generative model for surrogates of spatial-temporal wildfire nowcastingcited by 8
- 2024Surrogate Modeling and Control of Medical Digital Twinscited by 8
- 2022Efficient Learning of Accurate Surrogates for Simulations of Complex Systemscited by 7
- 2023PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modellingcited by 6
- 2023Intelligent sampling for surrogate modeling, hyperparameter optimization, and data analysiscited by 6
- 2024Deep adaptive sampling for surrogate modeling without labeled datacited by 5
- 2023On the Stability of General Bayesian Inferencecited by 4
- 2023Uncertainty Quantification and Propagation in Surrogate-based Bayesian Inferencecited by 4
- 2025Posterior SBC: Simulation-Based Calibration Checking Conditional on Datacited by 3
- 2023Learning Efficient Surrogate Dynamic Models with Graph Spline Networkscited by 2
- 2022Seq2Seq Surrogates of Epidemic Models to Facilitate Bayesian Inferencecited by 1
- 2023Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applicationscited by 1
- 2023Surrogate Modelling for Sea Ice Concentration using Lightweight Neural Ensemblecited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.