Hybrid Architecture for Tight Sandstone: Automated Mineral Identification and Quantitative Petrology
Minerals · 11.09.2025 · 15 (9) · 962
DOI: 10.3390/min15090962 ↗Kurz gefasst
Fachartikel in der Zeitschrift Minerals, online erschienen am 11.09.2025. Verfasst von Lanfang Dong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SINOPEC Key Laboratory of Petroleum Accumulation Mechanisms’ Microscopic Panoramic Segmentation of Dense Sandstone Open Fund, SINOPEC Excellent Youth Technology Innovation Fund.
Abstract (Originalsprache)
This study proposes an integrated computer vision system for automated petrological analysis of tight sandstone micro-structures. The system combines Zero-Shot Segmentation SAM (Segment Anything Model), Mask R-CNN (Region-Based Convolutional Neural Networks) instance segmentation, and an improved MetaFormer architecture with Cascaded Group Attention (CGA) attention mechanism, together with a parameter analysis module to form a hybrid deep learning system. This enables end-to-end mineral identification and multi-scale structural quantification of granulometric properties, grain contact relationships, and pore networks. The system is validated on proprietary tight sandstone datasets, SMISD (Sandstone Microscopic Image Segmentation Dataset)/SMIRD (Sandstone Microscopic Image Recognition Dataset). It achieves 92.1% mIoU segmentation accuracy and 90.7% mineral recognition accuracy while reducing processing time from more than 30 min to less than 2 min per sample. The system provides standardized reservoir characterization through automated generation of quantitative reports (Excel), analytical images (JPG), and structured data (JSON), demonstrating production-ready efficiency for tight sandstone evaluation.
Förderung
- SINOPEC Key Laboratory of Petroleum Accumulation Mechanisms’ Microscopic Panoramic Segmentation of Dense Sandstone Open Fund
- SINOPEC Excellent Youth Technology Innovation Fund
Zitieren
APA
Dong, L., Sun, C., Yu, X., Zhang, X., Chen, M., & Xu, M. (2025). Hybrid Architecture for Tight Sandstone: Automated Mineral Identification and Quantitative Petrology. Minerals, 15(9), 962. https://doi.org/10.3390/min15090962
Vancouver
Dong L, Sun C, Yu X, Zhang X, Chen M, Xu M. Hybrid Architecture for Tight Sandstone: Automated Mineral Identification and Quantitative Petrology. Minerals. 2025;15(9):962. doi:10.3390/min15090962
BibTeX
@article{Dong2025,
author = {Dong, Lanfang and Sun, Chenxu and Yu, Xiaolu and Zhang, Xinming and Chen, Menglian and Xu, Mingyang},
title = {Hybrid Architecture for Tight Sandstone: Automated Mineral Identification and Quantitative Petrology},
journal = {Minerals},
year = {2025},
volume = {15},
number = {9},
pages = {962},
doi = {10.3390/min15090962}
}
EUVIMED