Unveiling microplastics with hyperspectral Raman imaging: From macroscale observations to real-world applications

Machine Learning Advancements and Strategies in Microplastic and Nanoplastic Detection

Microplastics (MPs) and nanoplastics (NPs) present formidable global environmental challenges with serious risks to human health and ecosystem sustainability. Despite their significance, the accurate assessment of environmental MP and NP pollution remains hindered by limitations in existing detection technologies, such as low resolution, substantial data volumes, and prolonged imaging times. Machine learning (ML) provides a promising pathway to overcome these challenges by enabling efficient data processing and complex pattern recognition. This systematic Review aims to address these gaps by examining the role of ML techniques combined with spectroscopy in improving the detection and characterization of NPs. We focused on the application of ML and key tools in MP and NP detection, categorizing the literature into key aspects: (1) Developing tailored strategies for constructing ML models to optimize plastic detection while expanding monitoring capabilities. Emphasis is placed on harnessing the unique molecular fingerprinting capabilities offered by spectroscopy, including both infrared (IR) and Raman spectra. (2) Providing an in-depth analysis of the challenges and issues encountered by current ML approaches for NP detection. This Review highlights the critical role of ML in advancing environmental monitoring and improving our further, deeper investigation of the widespread presence of NPs. By identifying current key challenges, this Review provides valuable insights for future direction in environmental management and public health protection.

Remote sensing research on plastics in marine and inland water: Development, opportunities and challenge

The accumulation of plastic waste from various sources into marine and inland water is considered a global problem due to its serious impacts on aquatic ecosystems and human health. In the past decade, remote sensing has played an important role in monitoring of plastic pollution in marine and inland water sources and has achieved a series of research results in this field. In this study, a comprehensive review was conducted on the development, opportunities, and challenges of datasets and methods in Marine and Inland Water Plastics Remote Sensing (MIWPRS) monitoring over the past decade, based on the Web of Science (WOS) core database. The results indicated that compared with traditional methods, remote sensing has attracted the attention of scholars due to its advantages. Since 2014, the number of related publications has been increasing year by year, especially in China and the United States, which have achieved tremendous development. The MIWPRS research focus mostly on the use of different satellite remote sensing data and related algorithms to obtain the distribution of plastics in marine and inland water. However, it faces the challenge of lacking subsequent systematic impact assessment models and key pollution prevention measures. In terms of data acquisition, there is a lack of continuous observation models due to the fluidity of marine and inland water. Therefore, MIWPRS has great development opportunities in developing specialized sensors and combining multi-source data with interdisciplinary knowledge such as artificial intelligence (AI) and GIS. It is necessary for us to improve the seasonal migration model of plastics in water and promote the development of MIWPRS towards broader and deeper fields.

Artificial intelligence in microplastic detection and pollution control

The rising prevalence of microplastics (MPs) in various ecosystems has increased the demand for advanced detection and mitigation strategies. This review examines the integration of artificial intelligence (AI) with environmental science to improve microplastic detection. Focusing on image processing, Fourier transform infrared spectroscopy (FTIR), Raman spectroscopy, and hyperspectral imaging (HSI), the review highlights how AI enhances the efficiency and accuracy of these techniques. AI-driven image processing automates the identification and quantification of MPs, significantly reducing the need for manual analysis. FTIR and Raman spectroscopy accurately distinguish MP types by analyzing their unique spectral features, while HSI captures extensive spatial and spectral data, facilitating detection in complex environmental matrices. Furthermore, AI algorithms integrate data from these methods, enabling real-time monitoring, traceability prediction, and pollution hotspot identification. The synergy between AI and spectral imaging technologies represents a transformative approach to environmental monitoring and emphasizes the need to adopt innovative tools for protecting ecosystem health.

Machine learning based workflow for (micro)plastic spectral reconstruction and classification

With the advancement of artificial intelligence, it is foreseeable that computer-assisted identification of microplastics (MPs) will become increasingly widespread. Therefore, exploring a machine learning-based workflow to facilitate the identification of MPs is both meaningful and practically significant. However, interferences present in MPs spectra often compromise identification accuracy, making the improvement of spectral quality a critical prerequisite for precise identification. This study developed a fully machine learning-based workflow that combines spectral reconstruction and identification of MPs. To enhance the quality of MPs spectra, two reconstruction models named autoencoders (AE) and V-like convolutional neural networks (VCNN) were employed. Then, four classification models including decision tree, random forest, linear support vector machines (LSVM) and 1D convolutional neural networks were developed to accurately identify MPs. In terms of reconstruction, VCNN outperformed AE with a higher R2 value of 0.965, while both models outperformed conventional widely used Savitzky-Golay algorithm. For classification, LSVM exhibited the best performance with an overall accuracy of 91.35% on the original dataset and 98.00% on the VCNN-reconstructed dataset. When applied to real environmental datasets, a slight decrease in performance was observed, but a maximum top-1 accuracy of 71.43% and top-3 accuracy of >90% was still practically significant, indicating that the combined workflow has great potential for spectral reconstruction and identification of MPs.

A Novel High-Throughput Detection Method for Plastic Debris in Organic-Rich Matrices Based on Image Fusion

Plastic pollution pervades natural environments and wildlife. Consequently, high-throughput detection methods for plastic debris are urgently needed. A novel method was developed to detect plastic debris larger than 0.5 mm, which integrated an extraction method with low organic loss and plastic damage alongside a classification method for fused images. This extraction method broadened the size range of the remaining plastic debris, while the fusion solved the low spatial resolution of hyperspectral images and the absence of spectral information in red-green-blue (RGB) images. This method was validated for plastic debris in digestate, compost, and sludge, with extraction demonstrating 100% recovery rates for all samples. After fusion, the spatial resolution of hyperspectral images was improved about five times. Classification recall for the fused hyperspectral images achieved 97 ± 8%, surpassing 83 ± 29% of the raw images. Application of this method to solid digestate detected 1030 ± 212 items/kg of plastic debris, comparable with the conventional Fourier transform infrared spectroscopic result of 1100 ± 436 items/kg. This developed method can investigate plastic debris in complex matrices, simultaneously addressing a wide range of sizes and types. This capability helps acquire reliable data to predict secondary microplastic generation and conduct a risk assessment.