Analysis and discrimination of tectonic settings based on stacking quantum neural networks

doi:10.13745/j.esf.sf.2023.3.3

Abstract

Abstract:

Quantum geoscience represents a cutting-edge interdisciplinary field that leverages quantum computing and quantum machine learning algorithms to revolutionize the analysis of geological data. Among these advancements, the quantum neural network stands out for its efficiency and accuracy in processing complex multi-source data. This study focuses on addressing the challenge of discriminating tectonic settings, enhancing the quantum neural network (S-QNN) with an ensemble strategy to differentiate between basalt, gabbro, and spinel settings. Comparative analyses are conducted with four traditional algorithms (SVM, RF, KNN, NB), artificial neural network (ANN), and traditional quantum neural network (QNN). Results demonstrate that the S-QNN model outperforms the optimal traditional algorithm by 5.67%, 6.19%, and 13.34% in the respective cases, and surpasses the QNN by 3.11%, 4.99%, and 3.84%. The S-QNN model exhibits robustness and versatility, highlighting its superiority in data processing. This study underscores the potential of quantum machine learning algorithms in geoscience research, showcasing the advantages of S-QNN and paving the way for innovative integration of quantum science and geoscience.

Key words: quantum geoscience, tectonic settings discrimination, rock and mineral, geochemistry, stack integration algorithm, stacking quantum neural network (S-QNN)

CLC Number:

ZHANG Jiawen, LI Mingchao, HAN Shuai, ZHANG Jingyi. Analysis and discrimination of tectonic settings based on stacking quantum neural networks[J]. Earth Science Frontiers, 2024, 31(3): 511-519.

Figures/Tables 12

Fig.1 Schematic diagram of quantum neural network

Fig.2 Definitions and matrix representations of quantum gates

Fig.3 Construction of stacking quantum neural network

Fig.4 Correlation matrix of chemical composition of rocks and minerals (a) Basalt; (b) Gabbro; (c) Spinel.

Table 1 Test accuracy of traditional algorithm in basalt discrimination

类别	各传统算法的测试准确率/%
类别	SVM	RF	KNN	NB	MLP
IAB	83.02	83.02	69.81	88.68	84.91
MORB	88.89	88.89	74.07	74.07	81.48
OIB	83.02	90.57	62.26	33.96	90.57
总体	85.00	87.50	68.75	65.63	85.63

Table 2 Test accuracy of traditional algorithm in gabbro discrimination

类别	各传统算法的测试准确率/%
类别	SVM	RF	KNN	NB	MLP
IAG	63.16	80.70	52.63	68.42	73.68
MORG	100.00	100.00	100.00	100.00	100.00
OIG	68.12	66.67	78.26	44.93	69.57
总体	76.11	81.11	76.67	68.89	80.00

Table 3 Test accuracy of traditional algorithm in spinel discrimination

类别	各传统算法的测试准确率/%
类别	SVM	RF	KNN	NB	MLP
CMS	80.00	77.65	61.18	63.53	61.18
OIS	66.00	60.00	64.00	68.00	74.00
SCS	63.04	63.04	76.09	80.43	60.87
总体	71.82	69.06	65.75	69.06	64.64

Fig.5 Confusion matrix of discrimination results of QNN (a) Basalt; (b) Gabbro; (c) Spinel.

Fig.6 Training process QNN model (a) Basalt; (b) Gabbro; (c) Spinel.

Table 4 Parameters of base learners of S-QNN model

元学习机	网络层数	学习速率	批处理数目	迭代步数
QNN-1	6	0.005	10	90
QNN-2	6	0.012	32	90
QNN-3	7	0.008	16	120
QNN-4	8	0.005	20	150
QNN-5	10	0.004	30	150

Fig.7 Confusion matrix of discrimination results of S-QNN (a) Basalt; (b) Gabbro; (c) Spinel.

Fig.8 Comparison of discriminant accuracy among different algorithms

References 47

[1]	张旗, 朱月琴, 焦守涛. 论传统研究与大数据研究的关系(代序)[J]. 地质通报, 2019, 38(12): 1939-1942.
[2]	董少春, 齐浩, 胡欢. 地球科学大数据的现状与发展[J]. 科学技术与工程, 2019, 19(20): 1-11.
[3]	罗建民, 张旗. 大数据开创地学研究新途径: 查明相关关系, 增强研究可行性[J]. 地学前缘, 2019, 26(4): 6-12. DOI
[4]	冯军, 张琪, 罗建民. 深度挖掘数据潜在价值提高找矿靶区定量优选精度[J]. 地学前缘, 2022, 29(4): 403-411. DOI
[5]	周永章, 陈烁, 张旗, 等. 大数据与数学地球科学研究进展: 大数据与数学地球科学专题代序[J]. 岩石学报, 2018, 34(2): 255-263.
[6]	刘睿, 左蕾, 张鹏, 等. 纳米地质学: 量子科学走进地质学的桥梁[J]. 地学前缘, 2023, 30(3): 308-312. DOI
[7]	张旗, 焦守涛, 李明超, 等. 量子纠缠技术在地质学上应用的可能性[J]. 地学前缘, 2019, 26(4): 159-169. DOI
[8]	MONTANARO A. Quantum algorithms: an overview[J]. NPJ Quantum Information, 2016, 2(1): 15023.
[9]	BIAMONTE J. WITTEK P, PANCOTTI N, et al. Quantum machine learning[J]. Nature, 2017, 549(7671): 195-202.
[10]	CAMPBELL E T, TERHAL B M, VUILLOT C. Roads towards fault-tolerant universal quantum computation[J]. Nature, 2017, 549(7671): 172-179.
[11]	LUO Y H, ZHONG H S, ERHARD M, et al. Quantum teleportation in high dimensions[J]. Physical Review Letters, 2019, 123(7): 070505.
[12]	RAO K B. Computer systems architecture vs quantum computer[C]//Proceedings of International Conference on Intelligent Computing and Control Systems (ICICCS). Madurai: Vaigai College of Engineering, 2017, 8250619: 1018-1023.
[13]	CHAMBERLAND C, NOH K, ARRANGOIZ-ARRIOLA P, et al. Building a fault-tolerant quantum computer using concatenated cat codes[J]. PRX Quantum, 2022, 3(1): 010329.
[14]	PANET I, FLURY J, BIANCALE R, et al. Earth system mass transport mission (e.motion): a concept for future earth gravity field measurements from space[J]. Surveys in Geophysics, 2013, 34(2): 141-163.
[15]	JANVIER C, MÉNORET V, DESRUELLE B, et al. Compact differential gravimeter at the quantum projection-noise limit[J]. Physical Review A, 2022, 105(2): 022801.
[16]	LOPEZ CFA, LAMATA L, RETAMAL JC, et al. Multiqubit and multilevel quantum reinforcement learning with quantum technologies[J]. Plos One, 2018, 13(7): 1-25.
[17]	REBENTROST P, MOHSENI M, LLOYD S. Quantum support vector machine for big data classification[J]. Physical Review Letters, 2014, 113(13): 130503.
[18]	LI Z K, CHAI Z H, GUO Y H, et al. Resonant quantum principal component analysis[J]. Science Advances, 2021, 7(34): eabg2589.
[19]	KAK S C. Quantum neural computing[M]//HAWKES P W. Advances in imaging and electron physics. Amsterdam: Elsevier, 1995: 259-313.
[20]	王良玉, 张明林, 祝洪涛, 等. 人工神经网络及其在地学中的应用综述[J]. 世界核地质科学, 2021, 38(1): 15-26.
[21]	吕颜轩, 高庆, 吕金虎, 等. 面向近期量子处理器的量子神经网络研究进展[J]. 中国科学: 技术科学, 2022, 52(4): 547-564.
[22]	高骏, 何俊佳. 量子遗传神经网络在变压器油中溶解气体分析中的应用[J]. 中国电机工程学报, 2010, 30(30): 121-127.
[23]	HUANG R, TAN X Q, XU Q S. Variational quantum tensor networks classifiers[J]. Neurocomputing, 2021, 452: 89-98.
[24]	LLOYD S, WEEDBROOK C. Quantum generative adversarial learning[J]. Physical Review Letters, 2018, 121(4): 040502.
[25]	WEI S J, CHEN Y H, ZHOU Z R, et al. A quantum convolutional neural network on NISQ devices[J]. AAPPS Bulletin, 2022, 32(1): 1-11.
[26]	郭知鑫, 杨永太, 任祎, 等. 二连盆地吉尔嘎朗图凹陷南部基底花岗岩形成演化及其大地构造背景研究[J]. 地学前缘, 2023, 30(2): 259-271. DOI
[27]	PEARCE J A, CANN J R. Tectonic setting of basic volcanic rocks determined using trace element analyses[J]. Earth and Planetary Science Letters, 1973, 19(2): 290-300.
[28]	李曙光. 蛇绿岩生成构造环境的Ba-Th-Nb-La判别图[J]. 岩石学报, 1993, 9(2): 146-157.
[29]	张旗. 如何正确使用玄武岩判别图[J]. 岩石学报, 1990, 6(2): 87-94.
[30]	LI C S, ARNDT N T, TANG Q Y, et al. Trace element indiscrimination diagrams[J]. Lithos, 2015, 232: 76-83.
[31]	周永章, 张良均, 张澳多, 等. 地球科学大数据挖掘与机器学习[M]. 广州: 中山大学出版社, 2018.
[32]	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.
[33]	韩帅, 李明超, 刘承照, 等. 基于玄武岩大数据的大地构造环境智能挖掘判别与分析[J]. 岩石学报, 2018, 34(11): 3207-3216.
[34]	焦守涛, 周永章, 张旗, 等. 基于GEOROC数据库的全球辉长岩大数据的大地构造环境智能判别研究[J]. 岩石学报, 2018, 34(11): 3189-3194.
[35]	UEKI K, HINO H, KUWATANI T. Geochemical discrimination and characteristics of magmatic tectonic settings: a machine-learning-based approach[J]. Geochemistry, Geophysics, Geosystems, 2018, 19(4): 1327-1347.
[36]	HAN S, LI M C, REN Q B. Discriminating among tectonic settings of spinel based on multiple machine learning algorithms[J]. Big Earth Data, 2019, 3(1): 67-82.
[37]	REN Q B, LI M C, HAN S, et al. Basalt tectonic discrimination using combined machine learning approach[J]. Minerals, 2019, 9(6): 376.
[38]	朱紫怡, 周飞, 王瑀, 等. 基于机器学习的锆石成因分类研究[J]. 地学前缘, 2022, 29(5): 464-475. DOI
[39]	葛粲, 汪方跃, 顾海欧, 等. 基于卷积神经网络和火山岩大数据的构造源区判别[J]. 地学前缘, 2019, 26(4): 22-32. DOI
[40]	JENKINS B K, TANGUAY A R. Handbook of neural computing and neural networks[M]. Boston: MIT Press, 1995.
[41]	FREDRICK M. Artificial neural network-based decision support systems in manufacturing processes: a systematic literature review[J]. Computers and Industrial Engineering, 2022, 165: 107964.
[42]	TAKAHASHI K, KUROKAWA M, HASHIMOTO M. Multi-layer quantum neural network controller trained by real-coded genetic algorithm[J]. Neurocomputing, 2014, 134: 159-164.
[43]	JESWAL S K, CHAKRAVERTY S. Recent developments and applications in quantum neural network: a review[J]. Archives of Computational Methods in Engineering, 2019, 26(4): 793-807. DOI
[44]	KILLORAN N, BROMLEY T R, ARRAZOLA J M, et al. Continuous-variable quantum neural networks[J]. Physical Review Research, 2019, 1(3): 033063.
[45]	DIVINCENZO D P. Quantum gates and circuits[J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1969): 261-276.
[46]	NORDHAUSEN K. Ensemble methods: foundations and algorithms by Zhi-Hua Zhou[J]. International Statistical Review, 2013, 81(3): 470.
[47]	ZHANG J W, LI M C, HAN S, et al. Estimation of seismic wave incident angle using vibration response data and stacking ensemble algorithm[J]. Computers and Geotechnics, 2021, 137(5): 104255.