{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:44:56Z","timestamp":1782841496152,"version":"3.54.5"},"reference-count":0,"publisher":"ECMS","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,23]]},"abstract":"<jats:p>Battery formation step is a critical and cost-intensive process in lithium-ion battery manufacturing, primarily responsible for establishing the Solid\u2013Electrolyte Interphase (SEI), which governs long-term performance and stability. High-fidelity electrochemical simulations, such as the Doyle\u2013Fuller\u2013Newman (DFN) model with SEI kinetics, provide detailed insight into SEI growth and thermal behaviour during formation. However, exploring diverse formation protocols using such models is computationally expensive, limiting their use in large-scale optimization studies. This work explores a novel cross-formation surrogate modelling framework to accelerate formation analysis. Using DFN-based simulations, we generate multiple distinct formation protocols, including Multi-stage, Slow single-cycle, and Fast single-cycle regimes. Deep learning models are trained under four strategies--Mixed, Multi-stage, Slow, and Fast training, and evaluated for their ability to generalize across unseen formation protocols in predicting SEI growth rate and cell temperature. Results show that cross-training between Multi-stage and Slow protocols achieves high predictive accuracy, whereas Fast formation behaviour cannot be reliably extrapolated without similar high-rate data in training. Additionally, incorporating a physically motivated feature--the square root of cumulative current--significantly enhances model performance. The proposed framework enables efficient cross-protocol generalization and provides a foundation for data-driven optimization of battery formation processes.<\/jats:p>","DOI":"10.7148\/2026-0433","type":"proceedings-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:55:14Z","timestamp":1782838514000},"page":"433-442","source":"Crossref","is-referenced-by-count":0,"title":["Learning across formation regimes: surrogate modelling for solid\u2013electrolyte\u2013interphase growth and battery thermal optimisation"],"prefix":"10.7148","author":[{"given":"Aditya","family":"Dey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyanapathiranage Sudeepika W.","family":"Samarathunga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fadi","family":"Al Machot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bikesh","family":"Shrestha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4144","published-online":{"date-parts":[[2026,6,23]]},"event":{"name":"40th ECMS International Conference on Modelling and Simulation"},"container-title":["ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina"],"original-title":[],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:55:17Z","timestamp":1782838517000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.scs-europe.net\/dlib\/2026\/ecms2026acceptedpapers\/0433_simai_ecms2026_0097.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":0,"URL":"https:\/\/doi.org\/10.7148\/2026-0433","relation":{},"subject":[],"published":{"date-parts":[[2026,6,23]]}}}