eprintid: 10185732 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/18/57/32 datestamp: 2024-01-18 11:03:50 lastmod: 2024-01-18 11:03:50 status_changed: 2024-01-18 11:03:50 type: article metadata_visibility: show sword_depositor: 699 creators_name: Wu, Sipei creators_name: Wang, Haiou creators_name: Luo, Kai Hong title: A robust autoregressive long-term spatiotemporal forecasting framework for surrogate-based turbulent combustion modeling via deep learning ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F45 keywords: Turbulent combustion; Detailed reaction mechanism; Transient simulation; Deep neural network; Spatiotemporal series prediction; Long-term forecast stability note: Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). abstract: This paper systematically develops a high-fidelity turbulent combustion surrogate model using deep learning. We construct a surrogate model to simulate the turbulent combustion process in real time, based on a state-of-the-art spatiotemporal forecasting neural network. To address the issue of shifted distribution in autoregressive long-term prediction, two training techniques are proposed: unrolled training and injecting noise training. These techniques significantly improve the stability and robustness of the model. Two datasets of turbulent combustion in a combustor with cavity and a vitiated co-flow burner (Cabra burner) have been generated for model validation. The effects of model architecture, unrolled time, noise amplitude, and training dataset size on the long-term predictive performance are explored. The well-trained model can be applicable to new cases by extrapolation and give spatially and temporally consistent results in long-term predictions for turbulent reacting flows that are highly unsteady. date: 2024-01 date_type: published publisher: Elsevier BV official_url: http://dx.doi.org/10.1016/j.egyai.2023.100333 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2140128 doi: 10.1016/j.egyai.2023.100333 lyricists_name: Luo, Kai lyricists_id: KLUOX54 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public publication: Energy and AI volume: 15 article_number: 100333 issn: 2666-5468 citation: Wu, Sipei; Wang, Haiou; Luo, Kai Hong; (2024) A robust autoregressive long-term spatiotemporal forecasting framework for surrogate-based turbulent combustion modeling via deep learning. Energy and AI , 15 , Article 100333. 10.1016/j.egyai.2023.100333 <https://doi.org/10.1016/j.egyai.2023.100333>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10185732/1/1-s2.0-S2666546823001052-main.pdf