Long-horizon forecasting of electrolysis stability from early-stage operating data through temporal learning

Electrochemical devices such as electrolyzers are central to a sustainable, electrified future, and the ability to predict device-level stability from early-stage operation can substantially accelerate technology development. Data-driven stability forecasting offers a promising route toward this goal but remains challenged by the complexity of open, dynamic electrochemical systems and the limited availability of high-quality training data. Here, we develop ElectroTS, a data-driven electrolysis prognostic framework that integrates data-adaptive rectification with temporal sequence modeling to enable robust prediction of lifetime, degradation rates, and uncertainty in electrolytic systems. We first construct well-structured stability datasets for anionexchange membrane water electrolysis (AEMWE) and CO2 solid oxide electrolyzer cells (SOEC), explicitly designed for long-horizon forecasting. Using only early-stage operating data, ElectroTS enables forecasting over operating durations exceeding tenfold the input window and beyond 1,000 hours, providing actionable guidance for rapid screening of materials and operating conditions. Moreover, few-shot transfer learning enables efficient cross-platform generalization, as demonstrated across low-temperature aqueous and high-temperature solid-state electrolysis systems. This work establishes a generalizable, long-horizon forecasting framework for data-driven stability prediction across electrochemical energy technologies. Posted on 30 April 2026-CC-BY-NC-ND 4.0-This is a preprint and has not been peer reviewed. Data may be preliminary.