A sequential deep learning surrogate framework integrating CNN and BiLSTM for DEM-based porosity prediction in heterogeneous granular assemblies
Computational Geosciences · 2026-12 · 30 (6)
DOI: 10.1007/s10596-026-10485-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Geosciences, online erschienen am 16.11.2026. Verfasst von Phong Nguyen Thanh und 7 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Zitieren
APA
Thanh, P. N., Anh, D. T., Truong, P., Son, M. T., Tran, B., Dang, N. M., Duy, H. P., & Bui, V. H. (2026). A sequential deep learning surrogate framework integrating CNN and BiLSTM for DEM-based porosity prediction in heterogeneous granular assemblies. Computational Geosciences, 30(6). https://doi.org/10.1007/s10596-026-10485-8
Vancouver
Thanh PN, Anh DT, Truong P, Son MT, Tran B, Dang NM, et al. A sequential deep learning surrogate framework integrating CNN and BiLSTM for DEM-based porosity prediction in heterogeneous granular assemblies. Computational Geosciences. 2026;30(6). doi:10.1007/s10596-026-10485-8
BibTeX
@article{Thanh2026,
author = {Thanh, Phong Nguyen and Anh, Duong Tran and Truong, Pham and Son, Mai Thai and Tran, Bang and Dang, Nguyen Mai and Duy, Hung Phan and Bui, Van Hieu},
title = {A sequential deep learning surrogate framework integrating CNN and BiLSTM for DEM-based porosity prediction in heterogeneous granular assemblies},
journal = {Computational Geosciences},
year = {2026},
volume = {30},
number = {6},
doi = {10.1007/s10596-026-10485-8}
}
EUVIMED