Combining Prior Knowledge and Self-Organising Feature Maps for Logging Data Stratification
Journal Of The Geological Society Of India · 01.08.2026 · 102 (8) · 1123-1131
DOI: 10.17491/jgsi.2026.174516 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal Of The Geological Society Of India, online erschienen am 01.08.2026. Verfasst von Jiaqi Chen und 2 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben.
Abstract (Originalsprache)
Well log stratification is crucial for geological interpretation, yet it faces challenges in balancing automation efficiency with geological interpretability. This study proposes a novel unsupervised method, PK-SOM (Prior Knowledge - Self Organising Maps), which integrates geological prior knowledge into Self-Organising Maps to overcome the “black box” limitations of data-driven models. The method employs Support Vector Data Description (SVDD) for anomaly detection, followed by a constrained SOM clustering process. Applied to borehole data from the Songliao Basin, PK-SOM achieved high stratigraphic consistency with expert interpretations, reducing boundary errors by ~5.6% compared to standard SOM. Furthermore, using PK-SOM stratified data as preprocessing significantly enhanced downstream lithology identification, improving model accuracy by over 11%. This demonstrates the method’s effectiveness in achieving automated, interpretable, and geologically reliable stratification without manual labelling.
Zitieren
APA
Chen, J., Zhang, X., & Weng, Z. (2026). Combining Prior Knowledge and Self-Organising Feature Maps for Logging Data Stratification. Journal Of The Geological Society Of India, 102(8), 1123-1131. https://doi.org/10.17491/jgsi.2026.174516
Vancouver
Chen J, Zhang X, Weng Z. Combining Prior Knowledge and Self-Organising Feature Maps for Logging Data Stratification. Journal Of The Geological Society Of India. 2026;102(8):1123-1131. doi:10.17491/jgsi.2026.174516
BibTeX
@article{Chen2026,
author = {Chen, Jiaqi and Zhang, Xialin and Weng, Zhengping},
title = {Combining Prior Knowledge and Self-Organising Feature Maps for Logging Data Stratification},
journal = {Journal Of The Geological Society Of India},
year = {2026},
volume = {102},
number = {8},
pages = {1123--1131},
doi = {10.17491/jgsi.2026.174516}
}
EUVIMED