Microplastics (MPs) represent a novel class of environmental pollutants. Their varied shapes, small size, complex composition, low concentration, and wide distribution make their identification and quantification particularly challenging. Combination optical microscopic imaging techniques and artificial intelligence (AI) methods offer unique advantages in analyzing MPs. This review briefly introduces optical microscopic imaging technologies for microplastic detection (such as optical microscopy, fluorescence microscopy, digital cameras, smartphones, hyperspectral imaging, etc.) and artificial neural network-based AI approaches (including convolutional neural networks, encoder-decoder segmentation network, object detection and instance segmentation networks, hybrid architectures incorporating sequence modeling and attention mechanisms, etc.) It focuses on summarizing the research advances in the identification, classification, and quantification of microplastics using AI-assisted optical imaging technologies (such as machine learning and deep learning). Additionally, the challenges and future development prospects of AI-enabled optical microscopic imaging for microplastic detection are discussed.
THOMPSONR C, OLSENY, MITCHELLR P,et al. Lost at sea:Where is all the plastic?[J]. Science,2004,304(5672):838.
[2]
JAMBECKJ R, GEYERR, WILCOXC,et al. Plastic waste inputs from land into the ocean[J]. Science,2015,347(6223):768-771.
[3]
DIANAZ T, ROCHMANC M, MallosN. UN plastic pollution treaty must not ignore the scourge of microplastics[J]. Nature, 2024, 634(8034): 545.
[4]
WUN, GRIEVES W D, MANNINGA J,et al. Flocs as vectors for microplastics in the aquatic environment[J]. Nature Water,2024,2(11):1082-1090.
[5]
PARRELLAF, BRIZZOLARAS, HOLZNERM,et al. Impact of heteroaggregation between microplastics and algae on particle vertical transport[J]. Nature Water,2024,2(6):541-552.
[6]
DONGH K, WANGX P, NIUX R,et al. Overview of analytical methods for the determination of microplastics:Current status and trends[J]. TrAC Trends in Analytical Chemistry,2023,167:117261.
[7]
PRATAJ C, COSTA J PDA, DUARTEA C,et al. Methods for sampling and detection of microplastics in water and sediment:A critical review[J]. TrAC Trends in Analytical Chemistry,2019,110:150-159.
[8]
QIANN X, GAOX, LANGX Q,et al. Rapid single-particle chemical imaging of nanoplastics by SRS microscopy[J]. Proceedings of the National Academy of Sciences of the United States of America,2024,121(3):e2300582121.
[9]
HUANGQ, WUX Y, CAOG D,et al. Mass spectrometry-based techniques for determination of microplastics in terrestrial ecosystems[J]. TrAC Trends in Analytical Chemistry,2024,178:117853.
[10]
SHIMW J, HONGS H, EOS E. Identification methods in microplastic analysis:A review[J]. Analytical Methods,2017,9(9):1384-1391.
[11]
LIUS D, SHANGE X, LIUJ N,et al. What have we known so far for fluorescence staining and quantification of microplastics:A tutorial review[J]. Frontiers of Environmental Science & Engineering,2021,16(1):8.
ZHANGY, ZHANGD, ZHANGZ C. A critical review on artificial intelligence-based microplastics imaging technology:Recent advances,hot-spots and challenges[J]. International Journal of Environmental Research and Public Health,2023,20(2):1150.
[14]
JINH, KONGF H, LIX Y,et al. Artificial intelligence in microplastic detection and pollution control[J]. Environmental Research,2024,262:119812.
[15]
HUB B, DAIY D, ZHOUH,et al. Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors[J]. Journal of Hazardous Materials,2024,474:134865.
[16]
GUOP W, WANGY H, MOGHADDAMFARDP,et al. Artificial intelligence-empowered collection and characterization of microplastics:A review[J]. Journal of Hazardous Materials,2024,471:134405.
[17]
LATWALM, ARORAS, MURTHYK R. Data driven AI (artificial intelligence) detection furnish economic pathways for microplastics[J]. Journal of Contaminant Hydrology,2024,264:104365.
[18]
THANGAGIRIB, SIVAKUMARR. Prospective application of artificial intelligence towards the detection,and classifications of microplastics with bibliometric analysis[J]. Water,Air,& Soil Pollution,2024,235(6):362.
[19]
NAGPALM, GUPTAK, GUPTAT,et al. Advancing microplastic pollution management in aquatic environments through artificial intelligence[J]. Journal of Environmental Health Science & Engineering,2025,23(2):33.
[20]
RAWATH, GAURA, SINGHN,et al. Artificial intelligence-driven detection of microplastics in food:A comprehensive review of sources,health risks,detection techniques,and emerging artificial intelligence solutions[J]. Food Chemistry:X,2025,29:102687.
[21]
ZHANGJ, ZHOUW S, QIH L,et al. Deep-learning-assisted digital fluorescence immunoassay on magnetic beads for ultrasensitive determination of protein biomarkers[J]. Analytical Chemistry,2025,97(4):2393-2401.
[22]
WANGZ M, WAGNERJ, GHOSALS,et al. SEM/EDS and optical microscopy analyses of microplastics in ocean trawl and fish guts[J]. The Science of the Total Environment,2017,603/604:616-626.
[23]
KARAKOLISE G, NGUYENB, YOUJ B,et al. Fluorescent dyes for visualizing microplastic particles and fibers in laboratory-based studies[J]. Environmental Science & Technology Letters,2019,6(6):334-340.
[24]
MACAIRANJ R, NGUYENB, LIF,et al. Tissue clearing to localize microplastics via three-dimensional imaging of whole organisms[J]. Environmental Science & Technology,2023,57(23):8476-8483.
[25]
WAHYUDIA, SETYOBUDIR H, ISWAHYUDII,et al. Determination and quantification of microplastics in goat farms[J]. Bioresource Technology Reports,2025,31:102199.
[26]
FRIESE, DEKIFFJ H, WILLMEYERJ,et al. Identification of polymer types and additives in marine microplastic particles using pyrolysis-GC/MS and scanning electron microscopy[J]. Environmental Science. Processes & Impacts,2013,15(10):1949-1956.
[27]
LUOH W, XIANGY H, ZHAOY Y,et al. Nanoscale infrared,thermal and mechanical properties of aged microplastics revealed by an atomic force microscopy coupled with infrared spectroscopy (AFM-IR) technique[J]. Science of the Total Environment,2020,744:140944.
[28]
MOLINA-MILLÁNL, CUYPERSE, NAVARRO-MARTÍNL,et al. Mass spectrometry imaging enables detection of MPs and their effects in Daphnia magna following acute exposure[J]. Aquatic Toxicology,2025,280:107253.
[29]
PRATAJ C, ALVESJ R, COSTA J PDA,et al. Major factors influencing the quantification of Nile Red stained microplastics and improved automatic quantification (MP-VAT 2.0)[J]. Science of the Total Environment,2020,719:137498.
[30]
SIMMERMANC B, COLEMAN WASIKJ K. The effect of urban point source contamination on microplastic levels in water and organisms in a cold-water stream[J]. Limnology and Oceanography Letters,2020,5(1):137-146.
[31]
LORENZO-NAVARROJ, CASTRILLÓN-SANTANAM, SÁNCHEZ-NIELSENE,et al. Deep learning approach for automatic microplastics counting and classification[J]. Science of the Total Environment,2021,765:142728.
[32]
CAPONETTIV, MAVRIDI-PRINTEZIA, CINGOLANIM,et al. A selective ratiometric fluorescent probe for No-wash detection of PVC microplastic[J]. Polymers,2021,13(10):1588.
[33]
LEONARDJ, KOYDEMIRH C, KOUTNIKV S,et al. Smartphone-enabled rapid quantification of microplastics[J]. Journal of Hazardous Materials Letters,2022,3:100052.
[34]
KARKIA, THAIBAB M, SHISHIR ACHARYAK C,et al. Smartphone microscopic method for imaging and quantification of microplastics in drinking water[J]. Microscopy Research and Technique,2024,87(10):2266-2274.
[35]
LEEJ J, KANGJ Y, KIMC. A low-cost TICT-based staining agent for identification of microplastics:Theoretical studies and simple,cost-effective smartphone-based fluorescence microscope application[J]. Journal of Hazardous Materials,2024,465:133168.
[36]
MARCOTTC, KANSIZM, DILLONE,et al. Two-dimensional correlation analysis of highly spatially resolved simultaneous IR and Raman spectral imaging of bioplastics composite using optical photothermal Infrared and Raman spectroscopy[J]. Journal of Molecular Structure,2020,1210:128045.
[37]
FALTYNKOVAA, JOHNSENG, WAGNERM. Hyperspectral imaging as an emerging tool to analyze microplastics:A systematic review and recommendations for future development[J]. Microplastics and Nanoplastics,2021,1(1):13.
[38]
ALAMG, IHSANULLAHI, NAUSHADM,et al. Applications of artificial intelligence in water treatment for optimization and automation of adsorption processes:Recent advances and prospects[J]. Chemical Engineering Journal,2022,427:130011.
[39]
SATINETC, FOUSSF. A supervised machine learning classification framework for clothing products’ sustainability[J]. Sustainability,2022,14(3):1334.
[40]
JUNIORR F R, DOS SANTOS AREIASI A, CAMPOSM M,et al. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals[J]. Measurement,2022,190:110759.
[41]
KAVITHAM, GAYATHRIR, POLATK,et al. Performance evaluation of deep e-CNN with integrated spatial-spectral features in hyperspectral image classification[J]. Measurement,2022,191:110760.
[42]
CAOJ Z, LIJ C, HUX P,et al. Towards interpreting deep neural networks via layer behavior understanding[J]. Machine Learning,2022,111(3):1159-1179.
[43]
KUSUMAA I, HUANGY M. Product quality prediction in pulsed laser cutting of silicon steel sheet using vibration signals and deep neural network[J]. Journal of Intelligent Manufacturing,2023,34(4):1683-1699.
[44]
YUANX F, JIAZ Z, LIL,et al. A SIA-LSTM based virtual metrology for quality variables in irregular sampled time sequence of industrial processes[J]. Chemical Engineering Science,2022,249:117299.
[45]
WANGJ S, DONGJ H, TANGM R,et al. Identification and detection of microplastic particles in marine environment by using improved faster R-CNN model[J]. Journal of Environmental Management,2023,345:118802.
HAOY, WANGP, CUIM R,et al. Automatic localization and segmentation of adherent microplastics in optical micrographs based on improved YOLOv5 and adaptive perceptual UNET 3+++[J]. Biomedical Signal Processing and Control,2024,95:106399.
[48]
AKKAJITP, ALAHIM E E, SUKKUEAA. Enhanced detection and classification of microplastics in marine environments using deep learning[J]. Regional Studies in Marine Science,2024,80:103880.
[49]
HANX L, JIANGN J, HATAT,et al. Deep learning based approach for automated characterization of large marine microplastic particles[J]. Marine Environmental Research,2023,183:105829.
[50]
HUANGH, CAIH W, QURESHIJ U,et al. Proceeding the categorization of microplastics through deep learning-based image segmentation[J]. Science of the Total Environment,2023,896:165308.
[51]
TATAG, ROYERS J, POIRIONO, et al. A robotic approach towards quantifying epipelagic bound plastic using deep visual models[J/OL]. arXiv-CS-Artificial Intelligence,
[52]
THANGARAJR, ANANDAMURUGANS, KALIAPPANV K. Automated tomato leaf disease classification using transfer learning-based deep convolution neural network[J]. Journal of Plant Diseases and Protection,2021,128(1):73-86.
[53]
THAMMASANYAT, PATIAMS, RODCHAROENE,et al. A new approach to classifying polymer type of microplastics based on Faster-RCNN-FPN and spectroscopic imagery under ultraviolet light[J]. Scientific Reports,2024,14(1):3529.
[54]
KUTRALAM-MUNIASAMYG, PÉREZ-GUEVARAF, ELIZALDE-MARTÍNEZI,et al. How well-protected are protected areas from anthropogenic microplastic contamination?Review of analytical methods,current trends,and prospects[J]. Trends in Environmental Analytical Chemistry,2021,32:e00147.
[55]
ZHUZ A, PARKERW, WONGA. Leveraging deep learning for automatic recognition of microplastics (MPs) via focal plane array (FPA) micro-FT-IR imaging[J]. Environmental Pollution,2023,337:122548.
[56]
LEIB, BISSONNETTEJ R, HOGANÚ E,et al. Customizable machine-learning models for rapid microplastic identification using Raman microscopy[J]. Analytical Chemistry,2022,94(49):17011-17019.
[57]
AIW J, LIUS L, LIAOH P,et al. Application of hyperspectral imaging technology in the rapid identification of microplastics in farmland soil[J]. Science of the Total Environment,2022,807:151030.
[58]
SHIB, PATELM, YUD,et al. Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning[J]. Science of the Total Environment,2022,825:153903.
[59]
TIANX, BEÉNF, BÄUERLEINP S. Quantum cascade laser imaging (LDIR) and machine learning for the identification of environmentally exposed microplastics and polymers[J]. Environmental Research,2022,212(Pt D):113569.
[60]
XUJ J, WANGZ L. Efficient and accurate microplastics identification and segmentation in urban waters using convolutional neural networks[J]. The Science of the Total Environment,2024,911:168696.
[61]
PARKH M, PARKS, DE GUZMANM K,et al. MP-Net:Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams[J]. PLoS One,2022,17(6):e0269449.
[62]
MEYERSN, DE WITTEB, SCHMIDTN,et al. From microplastics to pixels:Testing the robustness of two machine learning approaches for automated,Nile red-based marine microplastic identification[J]. Environmental Science and Pollution Research International,2024,31(52):61860-61875.
[63]
VITALIC, PETERSR J B, JANSSENH G,et al. Quantitative image analysis of microplastics in bottled water using artificial intelligence[J]. Talanta,2024,266:124965.
[64]
CABANEROSS M, CHAPMANE, HANSENM,et al. Automatic pre-screening of outdoor airborne microplastics in micrographs using deep learning[J]. Environmental Pollution,2025,372:125993.