Mineral identification based on data augmentation and ensemble learning

doi:10.13745/j.esf.sf.2024.5.6

Abstract

Abstract:

Mineral identification as a crucial aspect of geosciences is of great importance to resource exploration, rock classification, and geological monitoring. However, traditional methods are inefficient as they often rely on human experience and subjective judgment. In recent years deep learning-based image classification has been used for accurate and rapid mineral identification. While these studies have achieved certain results, the number of identifiable mineral types are limited and the identification accuracy need to be further improved. This paper aims to address the issue of uneven distribution of mineral image samples in a mineral dataset on 36 common minerals. DCGAN is first used to generate images for data augmentation focusing on the 11 minerals with low sample counts, and the best set of images is selected, by comparison, to expand the dataset. Next, to obtain a more reliable and precise identification model, ResNet, RegNet, EfficientNet, and Vision Transformer models with better performance on ImageNet are transferred to the mineral dataset. Based on the permutations of the trained base models, 11 ensemble models are obtained, with which 24 identification results are obtained using two voting methods, average and weighted soft voting. These results are then compared to select the one with the highest accuracy. The experimental results demonstrated that data augmentation using DCGAN improved the model accuracy by 3.12% averaged over all models. Among the ensemble models, weighted soft voting performed better and achieved the highest accuracy of 87.47% on the augmented dataset.

Key words: mineral identification, deep convolutional generative adversarial networks, data augmentation, ensemble learning

CLC Number:

TP391.4
P57

WANG Lin, JI Xiaohui, YANG Mei, HE Mingyue, ZHANG Zhaochong, ZENG Shan, WANG Yuzhu. Mineral identification based on data augmentation and ensemble learning[J]. Earth Science Frontiers, 2024, 31(4): 87-94.

Figures/Tables 12

References 29

[1]	郝慧珍, 顾庆, 胡修棉. 基于机器学习的矿物智能识别方法研究进展与展望[J]. 地球科学, 2021, 46(9): 3091-3106.
[2]	周永章, 左仁广, 刘刚, 等. 数学地球科学跨越发展的十年: 大数据、人工智能算法正在改变地质学[J]. 矿物岩石地球化学通报, 2021, 40(3): 556-573, 777.
[3]	徐述腾, 周永章. 基于深度学习的镜下矿石矿物的智能识别实验研究[J]. 岩石学报, 2018, 34(11): 3244-3252.
[4]	彭伟航, 白林, 商世为, 等. 基于改进InceptionV3模型的常见矿物智能识别[J]. 地质通报, 2019, 38(12): 2059-2066.
[5]	郭艳军, 周哲, 林贺洵, 等. 基于深度学习的智能矿物识别方法研究[J]. 地学前缘, 2020, 27(5): 39-47. DOI
[6]	LIU C Z, LI M C, ZHANG Y, et al. An enhanced rock mineral recognition method integrating a deep learning model and clustering algorithm[J]. Minerals, 2019, 9(9): 516.
[7]	李明超, 刘承照, 张野, 等. 耦合颜色和纹理特征的矿物图像数据深度学习模型与智能识别方法[J]. 大地构造与成矿学, 2020, 44(2): 203-211.
[8]	杨彪, 马亦骥, 倪瑞璞, 等. 基于多尺度密集连接网络的矿物图像智能识别[J]. 云南大学学报(自然科学版), 2022, 44(6): 1118-1126.
[9]	杨彪, 倪瑞璞, 高皓, 等. 基于多分辨率图像的矿物特征自动提取与矿物智能识别模型[J]. 有色金属工程, 2022, 12(5): 84-93.
[10]	ZHOU W Y, WANG H, WAN Z B. Oreimage classification based on improved CNN[J]. Computers and Electrical Engineering, 2022, 99: 107819.
[11]	李雷, 卢才武, 江松, 等. 基于改进ConvNeXt网络的矿物图像智能识别[J/OL]. 地质通报: 1-11[2023-08-16]. http://kns.cnki.net/kcms/detail/11.4648.P.20230331.1254.002.html.
[12]	ZENG X, XIAO Y C, JI X H, et al. Mineral identification based on deep learning that combines image and mohs hardness[J]. Minerals, 2021, 11(5): 506.
[13]	WU B K, JI X H, HE M Y, et al. Mineral identification based on multi-label image classification[J]. Minerals, 2022, 12(11): 1338.
[14]	ANTONIOU A, STORKEY A, EDWARDS H. Data augmentation generative adversarial networks[EB/OL]. (2018-03-21)[2023-07-29]. https://arxiv.org/abs/1711.04340v2.
[15]	CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65.
[16]	BUSHRA S N, SHOBANA G. A survey on deep convolutional generative adversarial neural network (dcgan) for detection of Covid-19 using chest X-ray/CT-Scan[C]// Proceedings of the 3rd international conference on intelligent sustainable systems (ICISS), Thoothukudi. New York: IEEE, 2020: 702-708.
[17]	姜霞, 邱波, 王林倩, 等. 基于半监督模式的恒星光谱自动分类方法[J]. 光谱学与光谱分析, 2023, 43(6): 1875-1880.
[18]	甘岚, 沈鸿飞, 王瑶, 等. 基于改进DCGAN的数据增强方法[J]. 计算机应用, 2021, 41(5): 1305-1313. DOI
[19]	DONG X B, YU Z W, CAO W M, et al. A survey on ensemble learning[J]. Frontiers of Computer Science, 2020, 14(2): 241-258. DOI
[20]	SAQLAIN M, JARGALSAIKHAN B, LEE J Y. A voting ensemble classifier for wafer map defect patterns identification in semiconductor manufacturing[J]. IEEE Transactions on Semiconductor Manufacturing, 2019, 32(2): 171-182.
[21]	崔阳阳, 邓念东, 曹晓凡, 等. 基于集成学习的地质灾害危险性评价[J]. 水力发电, 2020, 46(10): 36-41.
[22]	李艳霞, 柴毅, 胡友强, 等. 不平衡数据分类方法综述[J]. 控制与决策, 2019, 34(4): 673-688.
[23]	LI J, JIA J J, XU D L. Unsupervised representation learning of image-based plant disease with deep convolutional generative adversarial networks[C]// Proceedings of the 37th Chinese control conference (CCC). New York: IEEE, 2018: 9159-9163.
[24]	蔡晓龙. 基于DCGAN算法的图像生成技术研究[D]. 青岛: 青岛理工大学, 2018.
[25]	ROKACH L. Ensemble learning: a survey[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2018, 8(5): e1249.
[26]	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. New York: IEEE, 2016: 770-778.
[27]	RADOSAVOVIC I, KOSARAJU R P, GIRSHICK R, et al. Designing network design spaces[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. New York: IEEE, 2020: 10428-10436.
[28]	TAN M X, LE Q V. Efficientnet: rethinking model scaling for convolutional neural networks[EB/OL]. (2020-09-11)[2023-07-02]. https://arxiv.org/abs/1905.11946.
[29]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. (2021-06-03)[2023-07-16]. https://arxiv.org/abs/2010.11929.

序号	矿物名称	数量	序号	矿物名称	数量	序号
1	玛瑙	3 225	13	锂电气石	5 439	25	黄铁矿	8 769
2	钠长石	1 775	14	绿帘石	3 720	26	石英	34 883
3	铁铝榴石	2 018	15	萤石	26 336	27	菱锰矿	4 276
4	硫酸铅矿	1 797	16	方铅矿	6 188	28	红宝石	820
5	蓝铜矿	7 924	17	自然金	4 545	29	蓝宝石	996
6	绿柱石	8 957	18	盐岩	756	30	黑电气石	2 099
7	锡石	3 205	19	赤铁矿	5 728	31	闪锌矿	6 354
8	黄铜矿	3 253	20	磁铁矿	2 445	32	辉锑矿	2 475
9	辰砂	1 605	21	孔雀石	6 796	33	硫黄	1 890
10	自然铜	5 288	22	白铁矿	1 608	34	黄玉	3 577
11	钙铁榴石	755	23	蛋白石	3 197	35	铜铀云母	1 100
12	透辉石	1 586	24	雌黄	720	36	钼铅矿	7 583

序号	矿物名称	数量	序号	矿物名称	数量	序号
1	玛瑙	3 225	13	锂电气石	5 439	25	黄铁矿	8 769
2	钠长石	1 775	14	绿帘石	3 720	26	石英	34 883
3	铁铝榴石	2 018	15	萤石	26 336	27	菱锰矿	4 276
4	硫酸铅矿	1 797	16	方铅矿	6 188	28	红宝石	820
5	蓝铜矿	7 924	17	自然金	4 545	29	蓝宝石	996
6	绿柱石	8 957	18	盐岩	756	30	黑电气石	2 099
7	锡石	3 205	19	赤铁矿	5 728	31	闪锌矿	6 354
8	黄铜矿	3 253	20	磁铁矿	2 445	32	辉锑矿	2 475
9	辰砂	1 605	21	孔雀石	6 796	33	硫黄	1 890
10	自然铜	5 288	22	白铁矿	1 608	34	黄玉	3 577
11	钙铁榴石	755	23	蛋白石	3 197	35	铜铀云母	1 100
12	透辉石	1 586	24	雌黄	720	36	钼铅矿	7 583

生成器	鉴别器
(deConv2d,LReLU,Dropout)	(FullConnect,BN,LReLU)
(deConv2d,BN,LReLU,Dropout)	(FullConnect,BN,LReLU)
(deConv2d,BN,LReLU,Dropout)	(deConv2d,BN,LReLU)
(deConv2d,BN,tanh,Dropout)	(deConv2d,sigmoid)

生成器	鉴别器
(deConv2d,LReLU,Dropout)	(FullConnect,BN,LReLU)
(deConv2d,BN,LReLU,Dropout)	(FullConnect,BN,LReLU)
(deConv2d,BN,LReLU,Dropout)	(deConv2d,BN,LReLU)
(deConv2d,BN,tanh,Dropout)	(deConv2d,sigmoid)

实验环境	规格参数
GPU	NVIDIA Tesla P100-PCIE
显存	12 GB
操作系统	CentOS Linux 7 (Core)
编程语言	Python 3.9.13
深度学习框架	Pytorch 2.0.1
CUDA版本	11.7