Deep learning-powered efficient characterization and quantification of microplastics.

Characterizing and quantifying microplastics (MPs) are time-consuming and labor-intensive tasks traditionally. This paper presents an artificial intelligence (AI) framework aiming to automate these tasks by integrating computer vision and deep learning techniques. The approach leverages Fourier Transform Infrared (FTIR) spectra and visual images. Primary novelties of this research involve the development of: (1) an AI framework integrating efforts of data processing, analytics, visualization, and human-computer interaction; (2) a method for transforming FTIR data into contour images; (3) data augmentation strategies for resolving data scarcity and imbalance issues; (4) deep learning models for identifying MPs; (5) computer vision algorithms for quantifying MPs; and (6) an engineer-friendly graphic user interface (GUI) for enhancing data accessibility. The AI framework has been applied to polyethylene, polypropylene, polystyrene, polyamide, ethylene-vinyl acetate, and cellulose acetate. Results confirmed the efficacy of the framework, exhibiting high accuracy scores in classification (98 %), segmentation (99 %), and quantification (96 %) tasks. This research advances the capability of automatic assessment of MPs.

• Publication year

  2024

• Venue

  Journal of Hazardous Materials

• Publication date

  2024-10-01

• Fields of study

  Medicine, Materials Science, Computer Science, Engineering

• Identifiers
  DOI 10.1016/j.jhazmat.2024.136241PMID 39454332
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Deciphering the pathogenic risks of microplastics as emerging particulate organic matter in aquatic ecosystem.

  2024cited by this paper
• Artificial intelligence-empowered collection and characterization of microplastics: A review.

  2024cited by this paper
• Insights into the influence of polystyrene microplastics on the bio-degradation behavior of tetrabromobisphenol A in soil.

  2024cited by this paper
• Contribution of Road Vehicle Tyre Wear to Microplastics and Ambient Air Pollution

  2024cited by this paper
• Intelligent characterization of complex cracks in strain-hardening cementitious composites based on generative computer vision

  2024cited by this paper
• Automatic interpretation of strain distributions measured from distributed fiber optic sensors for crack monitoring

  2023cited by this paper
• Proceeding the categorization of microplastics through deep learning-based image segmentation.

  2023cited by this paper
• Development and implementation of information extraction techniques for AI-assisted design of low-carbon cost-effective ultra-high-performance concrete with self-updateability

  2023cited by this paper
• Vulnerability of microplastics on marine environment: A review

  2023cited by this paper
• Intelligent monitoring of spatially-distributed cracks using distributed fiber optic sensors assisted by deep learning

  2023cited by this paper
• A Complete Guide to Extraction Methods of Microplastics from Complex Environmental Matrices

  2023cited by this paper
• Raman spectroscopy for microplastic detection in water sources: a systematic review

  2022cited by this paper
• Characterization and identification of microplastics using Raman spectroscopy coupled with multivariate analysis.

  2022cited by this paper
• Machine learning may accelerate the recognition and control of microplastic pollution: Future prospects.

  2022cited by this paper
• An Ensemble Machine Learning Method for Microplastics Identification with Ftir Spectrum

  2022cited by this paper
• Deep learning and infrared thermography for asphalt pavement crack severity classification

  2022cited by this paper
• Monitoring and automatic characterization of cracks in strain-hardening cementitious composite (SHCC) through intelligent interpretation of photos

  2022cited by this paper
• The Raman spectroscopy and SEM/EDS investigation of the primary sources of microplastics from cosmetics available in Poland.

  2022cited by this paper
• Quantitative assessment of visual microscopy as a tool for microplastic research: Recommendations for improving methods and reporting.

  2022cited by this paper
• Contamination of sea surface water offshore the Tokai region and Tokyo Bay in Japan by small microplastics.

  2022cited by this paper
• Microplastics in human food chains: Food becoming a threat to health safety.

  2022cited by this paper
• Microplastics: An overview on separation, identification and characterization of microplastics.

  2021cited by this paper
• Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning

  2021cited by this paper
• The rise of artificial soil carbon inputs: Reviewing microplastic pollution effects in the soil environment.

  2021cited by this paper
• Training and evaluating machine learning algorithms for ocean microplastics classification through vibrational spectroscopy.

  2021cited by this paper
• Microplastic constituent identification from admixtures by Fourier-transform infrared (FTIR) spectroscopy: The use of polyethylene terephthalate (PET), polyethylene (PE), polypropylene (PP), polyvinyl chloride (PVC) and nylon (NY) as the model constituents

  2021cited by this paper
• Automatic identification and quantification of dense microcracks in high-performance fiber-reinforced cementitious composites through deep learning-based computer vision

  2021cited by this paper
• Rapid Identification of Marine Plastic Debris via Spectroscopic Techniques and Machine Learning Classifiers.

  2020cited by this paper
• Comparison of pyrolysis gas chromatography/mass spectrometry and hyperspectral FTIR imaging spectroscopy for the analysis of microplastics

  2020cited by this paper
• Microplastics and associated contaminants in the aquatic environment: A review on their ecotoxicological effects, trophic transfer, and potential impacts to human health.

  2020cited by this paper
• Data imbalance in classification: Experimental evaluation

  2020cited by this paper
• Microplastics in aquatic environments: Occurrence, accumulation, and biological effects.

  2019cited by this paper
• A new approach for routine quantification of microplastics using Nile Red and automated software (MP-VAT).

  2019cited by this paper
• A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea.

  2019cited by this paper
• Dice Loss for Data-imbalanced NLP Tasks

  2019cited by this paper
• Identification of microplastics using Raman spectroscopy: Latest developments and future prospects.

  2018cited by this paper
• Machine learning on big data: Opportunities and challenges

  2017cited by this paper
• LinkNet: Exploiting encoder representations for efficient semantic segmentation

  2017cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• A Flexible New Technique for Camera Calibration

  2000cited by this paper
• Topological structural analysis of digitized binary images by border following

  1985cited by this paper

• Machine learning-based automatic detection and prediction of cracks and corrosion using spatiotemporal measurements from distributed fiber optic sensors

  2026cites this paper
• Advancements in microplastics detection techniques and their multidimensional impacts on aquatic ecosystems and human health

  2026cites this paper
• Advanced multi-level ensemble learning with image-based features and FTIR data for accurate identification of micro- and nanoplastics

  2026cites this paper
• “Microplastic contamination and detection in food systems: a review of machine learning, traditional methods, and other relevant factors”

  2025cites this paper
• Kernel representation-based End-to-End network-enabled decoding strategy for precise and medical diagnosis.

  2025cites this paper
• Evaluating Mangrove Sediments for Anthropogenic Marine Pollution of Heavy Metals and Microplastics in Mumbai, India

  2025cites this paper
• Advances in machine learning for the detection and characterization of microplastics in the environment

  2025cites this paper
• MPsQ-net: a novel method based on convolutional neural networks for fast and accurate quantification of stained and unstained microplastics in aqueous solutions

  2025cites this paper