We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
GANsemble for Small and Imbalanced Data Sets : A Baseline for Synthetic Microplastics Data
Summary
Researchers applied a generative adversarial network ensemble approach to address the problem of small and imbalanced microplastic datasets in machine learning, producing synthetic data to improve model training for plastic particle classification.
Microplastic particle ingestion or inhalation by humans is a problem of growing concern. Unfortunately, current research methods that use machine learning to understand their potential harms are obstructed by a lack of available data. Deep learning techniques in particular are challenged by such domains where only small or imbalanced data sets are available. Overcoming this challenge often involves oversampling underrepresented classes or augmenting the existing data to improve model performance. This paper proposes GANsemble: a two-module framework connecting data augmentation with conditional generative adversarial networks (cGANs) to generate class-conditioned synthetic data. First, the data chooser module automates augmentation strategy selection by searching for the best data augmentation strategy. Next, the cGAN module uses this strategy to train a cGAN for generating enhanced synthetic data. We experiment with the GANsemble framework on a small and imbalanced microplastics data set. A Microplastic-cGAN (MPcGAN) algorithm is introduced, and baselines for synthetic microplastics (SYMP) data are established in terms of Fréchet Inception Distance (FID) and Inception Scores (IS). We also provide a synthetic microplastics filter (SYMP-Filter) algorithm to increase the quality of generated SYMP. Additionally, we show the best amount of oversampling with augmentation to fix class imbalance in small microplastics data sets. To our knowledge, this study is the first application of generative AI to synthetically create microplastics data.
Sign in to start a discussion.
More Papers Like This
GANsemble for Small and Imbalanced Data Sets: A Baseline for Synthetic Microplastics Data
Researchers developed a generative adversarial network (GAN) ensemble approach to generate synthetic training data for microplastic image classification, addressing the challenge that real microplastic image datasets are small and imbalanced by polymer type. The synthetic augmentation improved classifier accuracy and recall, particularly for underrepresented plastic categories.
Microplastic Identification Using AI-Driven Image Segmentation and GAN-Generated Ecological Context
Researchers built an AI-powered image segmentation system that can automatically identify microplastics in microscopic photos, then used a generative AI model to create synthetic training images to improve its accuracy. The system reached an F1 score of 0.91, outperforming a model trained without generated data, pointing toward faster and cheaper microplastic identification compared to current expert-driven methods.
Microplastic Identification in Seawater using Generative Adversarial Networks
Researchers trained a generative adversarial network (GAN) on microscope images of seawater samples and achieved 92.5% accuracy in automatically distinguishing microplastic particles from natural particulates. This AI-based detection approach could dramatically speed up the analysis of water samples, making routine monitoring of marine microplastic pollution faster and more scalable.
Morphological Detection and Classification of Microplastics and Nanoplastics Emerged from Consumer Products by Deep Learning
Researchers created a new open-source dataset of microscopy images for training AI models to automatically detect and classify micro- and nanoplastics. The dataset fills an important gap in available tools for microplastic research and provides a foundation for developing faster, more efficient methods to identify plastic contamination across environmental samples.
SAM-Augmented Blending for Enhanced Microplastic Detection Using YOLO11
Researchers developed a synthetic data augmentation method using SAM-generated instance masks combined with the YOLOv11 object detection architecture to improve underwater microplastic detection in images. The approach significantly improved detection performance for small, sparsely labeled microplastic objects where real training data is scarce.