基于人工智能的危险废物(医疗废物)智能识别:多源数据驱动的研究进展与未来方向

邹惠煌; 何品晶; 吕凡; 彭伟; 章骅

PDF(457 KB)

中国环境科学 ›› 2025, Vol. 45 ›› Issue (12) : 6717-6725.

固体废物

基于人工智能的危险废物(医疗废物)智能识别:多源数据驱动的研究进展与未来方向

邹惠煌¹, 何品晶^1,2, 吕凡^1,2, 彭伟^1,2, 章骅^1,2

作者信息 +

Artificial intelligence-enabled identification of hazardous waste (medical waste): Advances and future directions based on multi-source data

ZOU Hui-huang¹, HE Pin-jing^1,2, LYU Fan^1,2, PENG Wei^1,2, ZHANG Hua^1,2

Author information +

文章历史 +

摘要

系统综述了数据驱动下的危险废物(医疗废物)智能识别技术, 涵盖基于人工智能和光谱数据建模的一般准则, 解析了数据采集、标签不平衡、模型泛化与可解释性等关键挑战.提出了未来研究的方向, 包括人工智能辅助光谱建模、迁移学习、多模态融合方法、以及基于机器学习的光谱-结构-性质关系建模等.旨在为危险废物(医疗废物)的智能识别与管理提供系统性参考, 推动其在处理处置、资源化利用和智能监测中的实用化进程.

Abstract

Data-driven intelligent identification technologies for hazardous waste (medical waste) were systematically reviewed. General principles for modeling based on artificial intelligence and spectroscopy were summarized. Key challenges, including data acquisition, class imbalance, model generalization, and interpretability, were analyzed. Future research directions were proposed, including AI-assisted spectroscopic modeling, transfer learning, multimodal data fusion, and machine-learning-based modeling of relationships among spectra, structures, and properties. A systematic reference for the intelligent identification and management of hazardous (medical) waste was provided, and guidance to accelerate practical deployment in treatment and disposal, resource recovery, and intelligent monitoring was offered.

导出引用

邹惠煌, 何品晶, 吕凡, 彭伟, 章骅. 基于人工智能的危险废物(医疗废物)智能识别:多源数据驱动的研究进展与未来方向[J]. 中国环境科学. 2025, 45(12): 6717-6725

ZOU Hui-huang, HE Pin-jing, LYU Fan, PENG Wei, ZHANG Hua. Artificial intelligence-enabled identification of hazardous waste (medical waste): Advances and future directions based on multi-source data[J]. China Environmental Science. 2025, 45(12): 6717-6725

中图分类号： X705

参考文献

[1] 中华人民共和国生态环境部.2023年中国生态环境统计年报 [R]. 北京:中华人民共和国生态环境部, 2024. Ministry of Ecology and Environment of the People’s Republic of China. 2023 statistical report on ecological environment in China [R]. Beijing: MEE, 2024.
[2] Huber F, Blasenbauer D, Mallow O, et al. Thermal co-treatment of combustible hazardous waste and waste incineration fly ash in a rotary kiln [J]. Waste Management, 2016,58:181-190.
[3] Vrancken C, Longhurst P J, Wagland S T. Critical review of real-time methods for solid waste characterisation: Informing material recovery and fuel production [J]. Waste Management, 2017,61:40-57.
[4] Jia Y X, Chen X, Wang M, et al. A win-win strategy for the reclamation of waste acid and conversion of organic acid by a modified electrodialysis [J]. Separation and Purification Technology, 2016,171:11-16.
[5] Sterkens W, Diaz Romero D, Goedemé T, et al. Detection and recognition of batteries on X-Ray images of waste electrical and electronic equipment using deep learning [J]. Resources, Conservation and Recycling, 2021,168:105246.
[6] Lan D Y, Zhang H, Wu T W, et al. Repercussions of clinical waste co-incineration in municipal solid waste incinerator during COVID-19pandemic [J]. Journal of Hazardous Materials, 2022,423:127144.
[7] Neuwahl F C G, Gómez Benavides J, Holbrook S, et al. Best Available Techniques (BAT) reference document for waste incineration: industrial emissions directive 2010/75/EU (Integrated Pollution Prevention and Control) [R]. EUR 29971EN, 2019.
[8] Long Y Y, Hu Y, Wang H Y, et al. Effective disposal of hazardous waste from non-ferrous waste recycling through thermal treatment [J]. Journal of Cleaner Production, 2024,434:140004.
[9] Teng J, Shi Y, Liu Z H, et al. Rapid identification of hazardous heavy metal-containing waste by combining EDXRF with machine learning: Taking zinc smelting waste as an example [J]. Resources, Conservation and Recycling, 2023,198:107155.
[10] Yang J, Xu Y P, Chen P, et al. Combining spectroscopy and machine learning for rapid identification of plastic waste: Recent developments and future prospects [J]. Journal of Cleaner Production, 2023,431: 139771.
[11] Mishra P, Passos D, Marini F, et al. Deep learning for near-infrared spectral data modelling: Hypes and benefits [J]. TrAC Trends in Analytical Chemistry, 2022,157:116804.
[12] Ren T, Li Y, Wang X, et al. Portable pyrolysis-point discharge optical spectrometer for in situ plastic polymer identification by coupling with machine learning [J]. Environmental Science & Technology, 2024,58 (5):2554-2563.
[13] Lan D Y, He P J, Qi Y P, et al. Optimizing the Quality of Machine Learning for Identifying the Share of Biogenic and Fossil Carbon in Solid Waste [J]. Analytical Chemistry, 2023,95(9):4412-4420.
[14] Wu T W, Zhang H, Peng W, et al. Applications of convolutional neural networks for intelligent waste identification and recycling: A review [J]. Resources, Conservation and Recycling, 2023,190:106813.
[15] Zou H H, He P J, Peng W, et al. Rapid detection of colored and colorless macro-and micro-plastics in complex environment via near-infrared spectroscopy and machine learning [J]. Journal of Environmental Sciences, 2025,147:512-522.
[16] Jayaprakash V, You J B, Kanike C, et al. Determination of trace organic contaminant concentration via machine classification of surface-enhanced raman spectra [J]. Environmental Science & Technology, 2024,58(35):15619-15628.
[17] Mäkelä M, Rissanen M, Sixta H. Machine vision estimates the polyester content in recyclable waste textiles [J]. Resources, Conservation and Recycling, 2020,161:105007.
[18] Michel A P M, Morrison A E, Preston V L, et al. Rapid identification of marine plastic debris via spectroscopic techniques and machine learning classifiers [J]. Environmental Science & Technology, 2020, 54(17):10630-10637.
[19] Zhao Y, Li J. Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions [J]. Environmental Science & Technology, 2022,56(24): 17531-17544.
[20] Qiao Y B, Zhang Q, Qi Y, et al. A Waste Classification model in Low-illumination scenes based on ConvNeXt [J]. Resources, Conservation and Recycling, 2023,199:107274.
[21] Lu W S, Chen J J, Xue F. Using computer vision to recognize composition of construction waste mixtures: A semantic segmentation approach [J]. Resources, Conservation and Recycling, 2022,178: 106022.
[22] Zhou H Y, Yu X Y, Alhaskawi A, et al. A deep learning approach for medical waste classification [J]. Scientific Reports, 2022,12(1):2159.
[23] Verma M, Kumar A, Kumar S. Medical Waste Classification using Deep Learning and Convolutional Neural Networks; proceedings of the 2022IEEE Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), F 21-23Dec. 2022,2022 [C].
[24] Nowakowski P, Pamuła T. Application of deep learning object classifier to improve e-waste collection planning [J]. Waste Management, 2020,109:1-9.
[25] Rawat W, Wang Z. Deep convolutional neural networks for image classification: A comprehensive review [J]. Neural Computation, 2017,29(9):2352-2449.
[26] Adarsh U K, Bhoje Gowd E, Bankapur A, et al. Development of an inter-confirmatory plastic characterization system using spectroscopic techniques for waste management [J]. Waste Management, 2022,150: 339-351.
[27] Kotula A P, Orski S V, Brignac K C, et al. Time-gated Raman spectroscopy of recovered plastics [J]. Marine Pollution Bulletin, 2022,181:113894.
[28] Li Y H, Yao J J, Nie P C, et al. An effective method for the rapid detection of microplastics in soil [J]. Chemosphere, 2021,276:128696.
[29] Qi Y P, He P J, Lan D Y, et al. Rapid determination of moisture content of multi-source solid waste using ATR-FTIR and multiple machine learning methods [J]. Waste Management, 2022,153:20-30.
[30] Neo E R K, Low J S C, Goodship V, et al. Deep learning for chemometric analysis of plastic spectral data from infrared and Raman databases [J]. Resources, Conservation and Recycling, 2023,188: 106718.
[31] Pocheville A, Uria I, España P, et al. Raman spectroscopy integrated with machine learning techniques to improve industrial sorting of Waste Electric and Electronic Equipment (WEEE) plastics [J]. Journal of Environmental Management, 2025,373:123897.
[32] Liu J, Zhang X, Du Z F, et al. Application of confocal laser Raman spectroscopy on marine sediment microplastics [J]. Journal of Oceanology and Limnology, 2020,38(5):1502-1516.
[33] 袁和财.基于拉曼光谱技术和深度学习网络的有害物快速检测分析 [D]. 合肥:安徽大学, 2021. Yuan H C. Rapid detection and analysis of hazardous substances based on Raman spectroscopy technology and deep learning network [D]. Hefei: Anhui University, 2021.
[34] Costa V C, de Mello M L, Babos D V, et al. Calibration strategies for determination of Pb content in recycled polypropylene from car batteries using laser-induced breakdown spectroscopy (LIBS) [J]. Microchemical Journal, 2020,159:105558.
[35] Costa V C, Aquino F W B, Paranhos C M, et al. Use of laser-induced breakdown spectroscopy for the determination of polycarbonate (PC) and acrylonitrile-butadiene-styrene (ABS) concentrations in PC/ABS plastics from e-waste [J]. Waste Management, 2017,70:212-221.
[36] Neo E R K, Yeo Z, Low J S C, et al. A review on chemometric techniques with infrared, Raman and laser-induced breakdown spectroscopy for sorting plastic waste in the recycling industry [J]. Resources, Conservation and Recycling, 2022,180:106217.
[37] Abina A, Puc U, Zidanšek A. Challenges and opportunities of terahertz technology in construction and demolition waste management [J]. Journal of Environmental Management, 2022,315:115118.
[38] Amigo J M, Babamoradi H, Elcoroaristizabal S. Hyperspectral image analysis. A tutorial [J]. Analytica Chimica Acta, 2015,896:34-51.
[39] Bell T W, Siegel D A. Nutrient availability and senescence spatially structure the dynamics of a foundation species [J]. Proceedings of the National Academy of Sciences, 2022,119(1):e2105135118.
[40] Yoon J, Joseph J, Waterhouse D J, et al. A clinically translatable hyperspectral endoscopy (HySE) system for imaging the gastrointestinal tract [J]. Nature Communications, 2019,10(1):1902.
[41] He H J, Chen Y, Li G, et al. Hyperspectral imaging combined with chemometrics for rapid detection of talcum powder adulterated in wheat flour [J]. Food Control, 2023,144:109378.
[42] Ge Y F, Song S Z, Yu S, et al. Rice seed classification by hyperspectral imaging system: A real-world dataset and a credible algorithm [J]. Computers and Electronics in Agriculture, 2024,219:108776.
[43] Tan W J, Duan Q Y, Yao L P, et al. A sensor combination based automatic sorting system for waste washing machine parts [J]. Resources, Conservation and Recycling, 2022,181:106270.
[44] Wu T W, He P J, Lan D Y, et al. Application of XGBoost for Fast Identification of Typical Industrial Organic Waste Samples with Near-Infrared Hyperspectral Imaging [J]. ACS ES&T Engineering, 2023,3(6):841-850.
[45] Xiao W, Yang J H, Fang H Y, et al. A robust classification algorithm for separation of construction waste using NIR hyperspectral system [J]. Waste Management, 2019,90:1-9.
[46] Wu X Y, Li J, Yao L P, et al. Auto-sorting commonly recovered plastics from waste household appliances and electronics using near-infrared spectroscopy [J]. Journal of Cleaner Production, 2020, 246:118732.
[47] Ai W J, Chen G L, Yue X J, et al. Application of hyperspectral and deep learning in farmland soil microplastic detection [J]. Journal of Hazardous Materials, 2023,445:130568.
[48] Amariei G, Henriksen M L, Friis J B, et al. In-line identification of Pb-based pigments in fishing nets and ropes based on hyperspectral imaging and machine learning [J]. Marine Pollution Bulletin, 2023, 191:114910.
[49] 韩英越.工业固废谁填场地污染识别迁移及健康风险评估研究 [D]. 杭州:浙江大学, 2022. Han Y Y. Study on pollution identification, migration and health risk assessment of industrial solid waste landfill sites [D]. Hangzhou: Zhejiang University, 2022.
[50] 滕婧.基于XRF与机器学习的电镀污泥成分定量分析及应用研究 [D]. 重庆:重庆大学, 2023. Teng J. Quantitative analysis and application research of electroplating sludge components based on XRF and machine learning [D]. Chongqing: Chongqing University, 2023.
[51] 杨婉琪.基于XRF的土壤重金属元素智能分析算法研究及应用 [D]. 西安:电子科技大学, 2024. Yang W Q. Research and application of intelligent analysis algorithm for soil heavy metal elements based on XRF [D]. Xi'an: University of Electronic Science and Technology of China, 2024.
[52] 黄瑞潇,卢永琦,郑志敏,等.典型固体废物的XRF-XRD耦合光谱指纹特征识别 [J]. 中国环境科学, 2025,45(10):5585-5595. Huang R X, Lu Y Q, Zheng Z M, et al. Identification of coupled spectral fingerprint characteristics of typical solid waste by XRF-XRD [J]. China Environmental Science, 2025,45(10):5585-5595.
[53] Li Y K, Zhang X M. Intelligent X-ray waste detection and classification via X-ray characteristic enhancement and deep learning [J]. Journal of Cleaner Production, 2024,435:140573.
[54] Ueda T, Koyanaka S, Oki T. In-line sorting system with battery detection capabilities in e-waste using combination of X-ray transmission scanning and deep learning [J]. Resources, Conservation and Recycling, 2024,201:107345.
[55] Wang Z W, Zhou H, Li Y, et al. Experimental Study of the Pore Structure during Coal and Biomass Ash Sintering Based on X-ray CT Technology [J]. Energy & Fuels, 2021,35(3):2098-2109.
[56] Liu X Y, Zhang L Y, Wu S, et al. Changes in municipal solid waste pore structure during degradation: Analysis of synthetic waste using X-ray computed microtomography [J]. Science of the Total Environment, 2020,708:135089.
[57] Trusler M M, Sturrock C J, Vane C H, et al. X-ray computed tomography: A novel non-invasive approach for the detection of microplastics in sediments? [J]. Marine Pollution Bulletin, 2023, 194:115350.
[58] Sterkens W, Diaz-Romero D, Goedemé T, et al. Detection and recognition of batteries on X-Ray images of waste electrical and electronic equipment using deep learning [J]. Resources, Conservation and Recycling, 2021,168:105246.
[59] Mishra P, Biancolillo A, Roger J M, et al. New data preprocessing trends based on ensemble of multiple preprocessing techniques [J]. TrAC Trends in Analytical Chemistry, 2020,132:116045.
[60] Liang R, Chen C, Sun T, et al. Interpretable machine learning assisted spectroscopy for fast characterization of biomass and waste [J]. Waste Management, 2023,160:90-100.
[61] He B, Zhu X, Cang Z, et al. Interpretation and Prediction of the CO2Sequestration of Steel Slag by Machine Learning [J]. Environmental Science & Technology, 2023,57(46):17940-17949.
[62] 闫红宇.激光诱导击穿光谱的分类策略及其应用 [D]. 太原:中北大学, 2024. Yan H Y. Classification strategies of laser-induced breakdown spectroscopy and their applications [D]. Taiyuan: North University of China, 2024.
[63] 赵紫嫣.基于深度学习的混合物拉曼光谱解析技术研究 [D]. 无锡:江南大学, 2024. Zhao Z Y. Research on Raman spectroscopy analysis technology of mixtures based on deep learning [D]. Wuxi: Jiangnan University, 2024.
[64] Teng J, Shi Y, Liu Z H, et al. Rapid identification of hazardous heavy metal-containing waste by combining EDXRF with machine learning: Taking zinc smelting waste as an example [J]. Resources, Conservation and Recycling, 2023,198:107155.
[65] Shen Y L, Lan D Y, He P J, et al. Nondestructive optical and spectroscopic techniques combined with machine learning for identifying solid waste: A review [J]. TrAC Trends in Analytical Chemistry, 2025,186:118195.
[66] Murdoch W J, Singh C, Kumbier K, et al. Definitions, methods, and applications in interpretable machine learning [J]. Proceedings of the National Academy of Sciences, 2019,116(44):22071-22080.
[67] Kucheryavskiy S. Analysis of NIR spectroscopic data using decision trees and their ensembles [J]. Journal of Analysis and Testing, 2018, 2(3):274-289.
[68] Beć K B, Grabska J, Huck C W. Interpretability in near-infrared (NIR) spectroscopy: Current pathways to the long-standing challenge [J]. TrAC Trends in Analytical Chemistry, 2025,189:118254.
[69] Langley A, Lonergan M, Huang T, et al. Analyzing mixed construction and demolition waste in material recovery facilities: Evolution, challenges, and applications of computer vision and deep learning [J]. Resources, Conservation and Recycling, 2025,217:108218.
[70] Zhu J J, Yang M, Ren Z J. Machine learning in environmental research: Common pitfalls and best practices [J]. Environmental Science & Technology, 2023,57(46):17671-17689.
[71] Noto N, Kunisada R, Rohlfs T, et al. Transfer learning across different photocatalytic organic reactions [J]. Nature Communications, 2025, 16(1):3388.
[72] Liu X, An H, Cai W, et al. Deep learning in spectral analysis: Modeling and imaging [J]. TrAC Trends in Analytical Chemistry, 2024,172:117612.
[73] Chen C, Liang R, Song M, et al. Noise-assisted data enhancement promoting image classification of municipal solid waste [J]. Resources, Conservation and Recycling, 2024,209:107790.
[74] Adarsh U K, Kartha V B, Santhosh C, et al. Spectroscopy: A promising tool for plastic waste management [J]. TrAC Trends in Analytical Chemistry, 2022,149:116534.
[75] Yao S, Yu Z, Hou Z, et al. Development of laser-induced breakdown spectroscopy based spectral tandem technology: A topical review [J]. TrAC Trends in Analytical Chemistry, 2024,177:117795.
[76] Azcarate S M, Ríos-Reina R, Amigo J M, et al. Data handling in data fusion: Methodologies and applications [J]. TrAC Trends in Analytical Chemistry, 2021,143:116355.
[77] Wang H P, Chen P, Dai J W, et al. Recent advances of chemometric calibration methods in modern spectroscopy: Algorithms, strategy, and related issues [J]. TrAC Trends in Analytical Chemistry, 2022,153: 116648.
[78] Daghighi A, Casanola Martin G M, Iduoku K, et al. Multi-endpoint acute toxicity assessment of organic compounds using large-scale machine learning modeling [J]. Environmental Science & Technology, 2024,58(23):10116-10127.
[79] Zhang C Y, Li X, Keil Stietz K P, et al. Machine Learning-Assisted Identification and Quantification of Hydroxylated Metabolites of Polychlorinated Biphenyls in Animal Samples [J]. Environmental Science & Technology, 2022,56(18):13169-13178.
[80] Corso G, Stark H, Jegelka S, et al. Graph neural networks [J]. Nature Reviews Methods Primers, 2024,4(1):17.
[81] Wu Z, Wang J, Du H, et al. Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking [J]. Nature Communications, 2023,14(1):2585.