# A neural network machine-learning approach for characterising hydrogen trapping parameters from TDS experiments

arXiv: https://arxiv.org/abs/2508.03371 · HTML: https://mlsanity.com/paper/2508.03371/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 87 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review](https://mlsanity.com/paper/2303.07647/) (2023)
- [Progress and opportunities in modelling environmentally assisted cracking](https://mlsanity.com/paper/2108.00816/) (2021)
- [An electro-chemo-mechanical framework for predicting hydrogen uptake in metals due to aqueous electrolytes](https://mlsanity.com/paper/2209.08635/) (2022)
- [Multielement polynomial chaos Kriging-based metamodelling for Bayesian inference of non-smooth systems](https://mlsanity.com/paper/2212.02250/) (2022)
- [Stabilising effects of lumped integration schemes for the simulation of metal-electrolyte reactions](https://mlsanity.com/paper/2302.02678/) (2023)
- [A phase field-based framework for electro-chemo-mechanical fracture: crack-contained electrolytes, chemical reactions and stabilisation](https://mlsanity.com/paper/2307.01105/) (2023)
- [Computational predictions of weld structural integrity in hydrogen transport pipelines](https://mlsanity.com/paper/2401.11529/) (2024)
- [TDS Simulator: A MATLAB App to model temperature-programmed hydrogen desorption](https://mlsanity.com/paper/2411.01231/) (2024)
- [A computational framework to predict weld integrity and microstructural heterogeneity: application to hydrogen transmission](https://mlsanity.com/paper/2412.08217/) (2024)
- [A COMSOL framework for predicting hydrogen embrittlement -- Part I: coupled hydrogen transport](https://mlsanity.com/paper/2503.01736/) (2025)

## Abstract (arXiv)

The hydrogen trapping behaviour of metallic alloys is generally characterised using Thermal Desorption Spectroscopy (TDS). However, as an indirect method, extracting key parameters (trap binding energies and densities) remains a significant challenge. To address these limitations, this work introduces a machine learning-based scheme for parameter identification from TDS spectra. A multi-Neural Network (NN) model is developed and trained exclusively on synthetic data to predict trapping parameters directly from experimental data. The model comprises two multi-layer, fully connected, feed-forward NNs trained with backpropagation. The first network (classification model) predicts the number of distinct trap types. The second network (regression model) then predicts the corresponding trap densities and binding energies. The NN architectures, hyperparameters, and data pre-processing were optimised to minimise the amount of training data. The proposed model demonstrated strong predictive capabilities when applied to three tempered martensitic steels of different compositions. The code developed is freely provided.