A microfluidic approach for label-free identification of small-sized microplastics in seawater

Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors

With the massive release of microplastics (MPs) into the environment, research related to MPs is advancing rapidly. Effective research methods are necessary to identify the chemical composition, shape, distribution, and environmental impacts of MPs. In recent years, artificial intelligence (AI)-driven machine learning methods have demonstrated excellent performance in analyzing MPs in soil and water. This review provides a comprehensive overview of machine learning methods for the prediction of MPs for various tasks, and discusses in detail the data source, data preprocessing, algorithm principle, and algorithm limitation of applied machine learning. In addition, this review discusses the limitation of current machine learning methods for various task analysis in MPs along with future prospect. Finally, this review finds research potential in future work in building large generalized MPs datasets, designing high-performance but low-computational-complexity algorithms, and evaluating model interpretability.

Microfluidic sensors for the detection of emerging contaminants in water: A review

In recent years, numerous emerging contaminants have been identified in surface water, groundwater, and drinking water. Developing novel sensing methods for detecting diverse emerging pollutants in water is urgently needed, as even at low concentrations, these pollutants can pose a serious threat to human health and environmental safety. Traditional testing methods are based on laboratory equipment, which is highly sensitive but complex to operate, costly, and not suitable for on-site monitoring. Microfluidic sensors offer several benefits, including rapid evaluation, minimal sample usage, accurate liquid manipulation, compact size, automation, and in-situ detection capabilities. They provide promising and efficient analytical tools for high-performance sensing platforms in monitoring emerging contaminants in water. In this paper, recent research advances in microfluidic sensors for the detection of emerging contaminants in water are reviewed. Initially, a concise overview is provided about the various substrate materials, corresponding microfabrication techniques, different driving forces, and commonly used detection techniques for microfluidic devices. Subsequently, a comprehensive analysis is conducted on microfluidic detection methods for endocrine-disrupting chemicals, pharmaceuticals and personal care products, microplastics, and perfluorinated compounds. Finally, the prospects and future challenges of microfluidic sensors in this field are discussed.

Deep convolutional neural networks for aged microplastics identification by Fourier transform infrared spectra classification

Infrared (IR) spectroscopy is a powerful technique for detecting and identifying Microplastics (MPs) in the environment. However, the aging of MPs presents a challenge in accurately identification and classification. To address this challenge, a classification model based on deep convolutional neural networks (CNNs) was developed using infrared spectra results. Particularly, original infrared (IR) spectra were used as the sample dataset, therefore, relevant spectral details were preserved and additional noise or distortions were not introduced. The Adam (Adaptive moment estimation) algorithm was employed to accelerate gradient descent and weight update, the Dropout function was implemented to prevent overfitting and enhance the generalization performance of the network. An activation function ReLu (Rectified Linear Unit) was also utilized to simplify the co-adaptation relationship among neurons and prevent gradient disappearance. The performance of the CNN model in MPs classification was evaluated based on accuracy and robustness, and compared with other machine learning techniques. CNN model demonstrated superior capabilities in feature extraction and recognition, and greatly simplified the pre-processing procedure. The identification results of aged commercial microplastic samples showed accuracies of 40 % for Artificial Neural Network, 60 % for Random Forest, 80 % for Deep Neural Network, and 100 % for CNN, respectively. The CNN architecture developed in this work also demonstrates versatility by being suitable for both limited data cases and potential expansion to include more discrete data in the future.

Simple microfluidic devices for in situ detection of water contamination: a state-of-art review

Water security is an important global issue that is pivotal in the pursuit of sustainable resources for future generations. It is a multifaceted concept that combines water availability with the quality of the water's chemical, biological, and physical characteristics to ensure its suitability and safety. Water quality is a focal aspect of water security. Quality index data are determined and provided via laboratory testing using expensive instrumentation with high maintenance costs and expertise. Due to increased practices in this sector that can compromise water quality, innovative technologies such as microfluidics are necessary to accelerate the timeline of test procedures. Microfluidic technology demonstrates sophisticated functionality in various applications due to the chip's miniaturization system that can control the movement of fluids in tiny amounts and be used for onsite testing when integrated with smart applications. This review aims to highlight the basics of microfluidic technology starting from the component system to the properties of the chip's fabricated materials. The published research on developing microfluidic sensor devices for monitoring chemical and biological contaminants in water is summarized to understand the obstacles and challenges and explore future opportunities for advancement in water quality monitoring.