arrow
Return

Explainable deep learning for automatic rock classification

delete2024-02-01
delete11
PRE
AI
郑栋宇 cover
郑栋宇 (Dongyu Zheng)
钟
钟瀚霆 (Hanting Zhong) *
G
Gustau Camps‐Valls
Z
Zhisong Cao
X
Xiaogang Ma
B
Benjamin Mills
X
Xiumian Hu
侯明才 cover
侯明才 (Mingcai Hou)
C
Chao Ma
DOI:10.1016/j.cageo.2023.105511delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
As deep learning (DL) gains popularity for its ability to make accurate predictions in various fields, its applications in geosciences are also on the rise. Many studies focus on achieving high accuracy in DL models by selecting models, developing more complex architectures, and tuning hyperparameters. However, the interpretability of these models, or the ability to understand how they make their predictions, is less frequently discussed. To address the challenge of high accuracy but low interpretability of DL models in geosciences, we study rock classification from thin-section photomicrographs of six types of sedimentary rocks, including quartz arenite, feldspathic arenite, lithic arenite, siltstone, oolitic packstone, and dolomite. These rocks' characteristic framework grains and grain textures are their distinguishing features, such as the rounded or oval ooids in oolitic packstone. We first train regular DL models, such as ResNet-50, on these photomicrographs and achieve an accuracy of over 0.94. However, these models make classifications based on features like cracks, cements, and scale bars, which are irrelevant for distinguishing sedimentary rocks in real-world applications. We then propose an attention-based dual network incorporating both global (overall photomicrograph) and local (distinguishing framework grains) features to address this issue. Our proposed model achieves not only high accuracy (0.99) but also provides interpretable feature extractions. Our study highlights the need to consider interpretability and geological knowledge in developing DL models, in addition to aiming for high accuracy.
Keywords:
Explainable deep learning
Knowledge-infused machine learning
Model interpretability
Attention-based modal network
Rock classification

Journal

C
Computers and Geosciences
IF:
4.4
Papers:
5.0K
Citations:
2.0W

Organization

cheng du university of technology cover
cheng du university of technology
Scholars:
119
Papers: 28
Citations: 5.3K
U
university of valenci a
Scholars:
27
Papers: 12
Citations: 1.3W
U
University of Idaho
Scholars:
294
Papers: 152
Citations: 3.4K
Nanjing University cover
Nanjing University
Scholars:
6.4K
Papers: 1.8K
Citations: 4.4W
U
University of Leeds
Scholars:
2.2K
Papers: 902
Citations: 2.5W
researcher View more organizations
Cited Papers

Cited Papers

IDO as a drug target for cancer immunotherapy: recent developments in IDO inhibitors discovery
err2016-01-01
err0
PREAI
errShan Qian; Man Zhang; Quanlong Chen; Yanying He; Wei Wang; Zhouyu Wang
errShare
errSave
Application of deep learning for semantic segmentation of sandstone thin sections
err2021-07-01
err50
PREAI
errSaxena, Nishank; Day-Stirrat, Ruarri J.; Hows, Amie; Hofmann, Ronny
errShare
errSave
Postshock Arrhythmogenesis in a Slice of the Canine Heart
err2003-10-20
err0
PREAI
errMATTHEW G. HILLEBRENNER; JAMES C. EASON; CRAIG A. CAMPBELL; NATALIA A. TRAYANOVA
errShare
errSave
errShare
errSave
Dual-input attention network for automatic identification of detritus from river sands
err2021-06-01
err5
PREAI
errGe, Shiping; Wang, Cong; Jiang, Zhiwei; Hao, Huizhen; Gu, Qing
errShare
errSave
Sensing prior constraints in deep neural networks for solving exploration geophysical problems
err2023-06-01
err35
errOAAI
errWu, Xinming; Ma, Jianwei; Si, Xu; Bi, Zhengfa; Yang, Jiarun; Gao, Hui; Xie, Dongzi; Guo, Zhixiang; Zhang, Jie
errShare
errSave
Fully automated carbonate petrography using deep convolutional neural networks
err2020-12-01
err68
errOAAI
errKoeshidayatullah, Ardiansyah; Morsilli, Michele; Lehrmann, Daniel J.; Al-Ramadan, Khalid; Payne, Jonathan L.
errShare
errSave
researcher View more