Efficient Ml Degradation Forecasting Aem

---
name: efficient-ml-degradation-forecasting-aem
description: Data-driven machine learning approach for medium-term degradation forecasting in Anion Exchange Membrane water electrolyzers using LSTMs and CNNs
version: 1.0.0
tags: [cs.LG, eess.SY, physics.app-ph, degradation-forecasting, water-electrolysis, lstm, cnn, time-series]
source: arxiv
arxiv_id: 2609.37941v1
utility: 0.85
---

# An Efficient Machine Learning Approach for Degradation Forecasting in AEM Water Electrolysis

**Authors:** Marco Veneriano, Ani Gjergji, Sebastiano Bellani
**Published:** 2026-09-29
**Categories:** cs.LG, eess.SY, physics.app-ph
**arXiv:** https://arxiv.org/abs/2609.37941v1

## Summary

This study provides a data-driven analysis of a novel dataset of single-cell Anion Exchange Membrane water electrolyzers (AEMWE), operated under constant current load across multiple heterogeneous experimental campaigns. We train and evaluate a range of machine learning models with different complexity, including linear baselines, LSTMs and CNNs, to perform medium-term forecasting of the cell voltage degradation curve. The models are assessed within a rigorous training and evaluation framework that accounts for the heterogeneous nature of the experimental data. This work demonstrates that machine learning approaches can effectively predict degradation patterns in water electrolysis systems, enabling better maintenance planning and system optimization for green hydrogen production.

## Key Contributions

- Provides data-driven analysis of a novel dataset of Anion Exchange Membrane water electrolyzers
- Trains and evaluates multiple ML models (linear baselines, LSTMs, CNNs) for degradation forecasting
- Implements rigorous training and evaluation framework for heterogeneous experimental data
- Demonstrates effective medium-term forecasting of cell voltage degradation curves
- Supports better maintenance planning and optimization for green hydrogen production systems

## Relevance

This paper is valuable for researchers and practitioners working on green hydrogen production, fuel cell technology, and predictive maintenance in energy systems. The machine learning approaches for degradation forecasting can help optimize the operation and maintenance of water electrolysis systems, reducing costs and improving efficiency. The rigorous evaluation framework provides a template for similar predictive modeling tasks in other energy conversion technologies.