Rocks are an extremely important and indispensable part of the Earth's crust, with wide applications in various fields such as geology, environmental monitoring, and industry. Traditional methods often rely on a single analytical technique or visual inspection, but this may not achieve the accuracy required for thorough classification. Laser-induced breakdown spectroscopy (LIBS) technology mainly provides information on the composition and content of rock elements, while images can provide appearance information such as color and texture. The multilayer perceptron (MLP) and DenseNet121 models were selected for processing preprocessed LIBS and image data, respectively. When using LIBS and images separately for classification, the accuracy rates were 93.63% and 90.90%, respectively. However, after fusing the bimodal data using LIBS and images, we achieved a significant performance improvement of 97.27% in accuracy. This study indicates that advanced neural network models can effectively integrate LIBS and image data and improve the performance of rock classification.
LiS.SongW.FangL.ChenY.GhamisiP.BenediktssonJ.A.. “Deep Learning for Hyperspectral Image Classification: An Overview”. IEEE Trans. Geosci. Remote Sens. 2019. 57(9): 6690–6709. https://doi.org/10.1109/TGRS.2019.2907932
2.
JohnsenT.K.GulickV.C.. “Single and Multi-Mineral Classification Using Dual-Band Raman Spectroscopy for Planetary Surface Missions”. Am. Mineral. 2025. 110 (5): 685–698. https://doi.org/10.2138/am-2023-9072
3.
LvY.WangS.YangE.GeS.. “A Near-Infrared Spectroscopy Dataset of Coal and Coal-Measure Rock Under Diverse Conditions”. Sci. Data. 2024. 11. Article no. 628. 10.1038/s41597-024-03422-w
4.
SingtuenV.JansamutS.PongsaisriN.PhajuyB.. “Classification of Geologic Materials Used in the Sukhothai Historical Park of Thailand Using a Portable X-ray Fluorescence Analyzer and Petrographic Analysis”. Heritage Sci. 2024. 12. Article no. 134. https://doi.org/10.1186/s40494-024-01259-5
5.
AliA.ChiangY.W.SantosR.M.. “X-ray Diffraction Techniques for Mineral Characterization: A Review for Engineers of the Fundamentals, Applications, and Research Directions”. Minerals. 2022. 12(2): 205. https://doi.org/10.3390/min12020205
6.
SchulzB.KrauseJ.. “Electron Probe Petrochronology of Monazite-And Garnet-Bearing Metamorphic Rocks in the Saxothuringian Allochthonous Domains (Erzgebirge, Granulite and Münchberg Massifs)”. Geological Society, London, Special Publications. 2024. 537(1): 249–284. https://doi.org/10.1144/SP537-2022-195
7.
WangY.LiJ.XueG.PanK., et al. “Blank Sample Denoising Algorithm (BSDA): An Effective Spectral Noise Reduction in Water Sample LIBS Detection”. Talanta. 2024. 275: 126086. https://doi.org/10.1016/j.talanta.2024.126086
8.
AdarshU.K.BankapurA.PaiA.K.KarthaV.B.UnnikrishnanV.K.. “Advanced Chemometric Methodologies on Single Shot Hyphenated LIBS Data for Rapid and Reliable Characterization of Plastic Classes”. Talanta. 2024. 277: 126393. https://doi.org/10.1016/j.talanta.2024.126393
9.
ZhaoS.ZhaoY.DaiY.LiuZ.GaoX.. “Methods for Optimization of the Original Signal in Laser Induced Breakdown Spectroscopy”. Spectrochim. Acta, Part B. 2024. 218: 106982. https://doi.org/10.1016/j.sab.2024.106982
10.
PopovA.M.ZaytsevS.M.SeliverstovaI.V.ZakuskinA.S.LabutinT.A.. “Matrix Effects on Laser-Induced Plasma Parameters for Soils and Ores”. Spectrochim. Acta, Part B. 2018. 148: 205–210. https://doi.org/10.1016/j.sab.2018.07.005
11.
HuangJ.ZhouW.ZhuJ.ZhangY.LiuY.. “Rapid Detection and Identification of Rocks and Minerals by Laser-Induced Breakdown Spectroscopy”. Microwave Opt. Technol. Lett. 2023. 65(5): 1439–1447. https://doi.org/10.1002/mop.33622
12.
ChenT.SunL.YuH.WangW., et al. “Deep Learning with Laser-Induced Breakdown Spectroscopy (LIBS) for the Classification of Rocks Based on Elemental Imaging”. Applied Geochemistry. 2022. 136: 105135. https://doi.org/10.1016/j.apgeochem.2021.105135
13.
DawsonH.L.DubruleO.JohnC.M.. “Impact of Dataset Size and Convolutional Neural Network Architecture on Transfer Learning for Carbonate Rock Classification”. Comput. Geosci. 2023. 171: 105284. https://doi.org/10.1016/j.cageo.2022.105284
14.
MaJ.LiT.YangG.DaiK., et al. “A Real-Time Intelligent Classification Model Using Machine Learning for Tunnel Surrounding Rock and Its Application”. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards. 2023. 17(1): 148–168. https://doi.org/10.1080/17499518.2023.2182891
15.
ChengX.TangH.WuZ.LiangD.XieY.. “BILSTM-Based Deep Neural Network for Rock-Mass Classification Prediction Using Depth-Sequence MWD Data: A Case Study of a Tunnel in Yunnan, China”. Appl. Sci. 2023. 13(10): 6050.
16.
QiqiZ.SaiW.ShunT.LiangbinY.KunlunQ.QingfengG.. “Rocks2net: Rock Image Classification via a Spatial Localization Siamese Network”. Comput. Geosci. 2024. 185: 105560. https://doi.org/10.1016/j.cageo.2024.105560
17.
ChenZ.YuanF.LiX.ZhangM.ZhengC.. “A Novel Few-Shot Learning Framework for Rock Images Dually Driven by Data and Knowledge”. Appl. Comput. Geosci. 2024. 21: 100155. https://doi.org/10.1016/j.acags.2024.10015
18.
ZhangY.YeY.-L.GuoD.-J.HuangT.. “PCA-VGG16 Model for Classification of Rock Types”. Earth Sci. Inform. 2024. 17(2): 1553–1567. https://doi.org/10.1007/S12145-023-01217-y
19.
ZhouZ.GaoW.JamaliS.YuC.LiuY.. “Rapid Identification and Classification of Metal Waste by Laser-Induced Breakdown Spectroscopy”. J. Appl. Spectrosc. 2024. 91(2): 397–404. https://doi.org/10.1007/S10812-024-01733-9
20.
ShatwellD.G.MurrayV.BartonA.. “Real-Time Ore Sorting Using Color and Texture Analysis”. Int. J. Min. Sci. Technol. 2023. 33(6): 659–674.
21.
GongA.GuoL.YuY.XiaY., et al. “Spectrum-Image Dual-Modality Fusion Empowered Accurate and Efficient Classification System for Traditional Chinese Medicine”. Inform. Fusion. 2024. 101: 101981. https://doi.org/10.1016/j.inffus.2023.101981
22.
Díaz-RomeroD.Van Den EyndeS.ZaplanaI.ZhouC., et al. “Classification of Aluminum Scrap by Laser Induced Breakdown Spectroscopy (LIBS) and RGB + D Image Fusion Using Deep Learning Approaches”. Resour., Conserv. Recycl.2023. 190: 106865. https://doi.org/10.1016/j.resconrec.2023.106865
23.
PengJ.LinM.XieW.YeL., et al. “Fast Identification of Geographical Origins of Baishao (Radix Paeoniae Alba) Using the Deep Fusion of LIBS Spectrum and Ablation Image”. Microchem. J. 2023. 194: 109337. https://doi.org/10.1016/j.microc.2023.109337
24.
ZhouJ.GuoL.ZhangM.HuangW., et al. “Enhancement of Spectral Model Transferability in LIBS Systems Through LIBS-LIPAS Fusion Technique”. Anal. Chim. Acta. 2024. 1309: 342674. https://doi.org/10.1016/j.aca.2024.342674
25.
ZhangM.FuH.WangH.WuB., et al. “Improving Signal Stability and Analysis Accuracy in Laser-Induced Breakdown Spectroscopy by Multi-Directional Collection”. Spectrochim. Acta, Part B. 2023. 210: 106818.https://doi.org/10.1016/j.sab.2023.106818
26.
MishraP.KaramiA.NordonA.RutledgeD.N.RogerJ.-M.. “Automatic De-Noising of Close-Range Hyperspectral Images with a Wavelength-Specific Shearlet-Based Image Noise Reduction Method”. Sens. Actuators, B. 2019. 281: 1034–1044. https://doi.org/10.1016/j.snb.2018.11.034
27.
JayaganthanS.BabuM.S.VasaN.J.SarathiR.ImaiT.. “Classification of Coal Deposited Epoxy Micro-Nanocomposites by Adopting Machine Learning Techniques to LIBS Analysis”. J. Phys. Commun. 2021. 5(10): 105006. https://doi.org/10.1088/2399-6528/ac2b5d
28.
HaoL.KaiH.WeiqiangY.MinsunC.. “Recent Advances in Machine Learning Methodologies for LIBS Quantitative Analysis”. In: Y. Dongfang and G. Katherine, editors. Pulsed Laser Processing of Materials. Rijeka: IntechOpen, 2024. Pp. Ch. 7. https://doi.org/10.5772/intechopen.1004414
