We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Can AI Reliably Identify Marine Microplastics in Wildlife? Assessing Multi-Modal Foundation Models for Polymer Classification with Minimal Training
Summary
Scientists tested whether general-purpose AI tools (like the technology behind chatbots) can identify and classify tiny plastic fragments on beaches, without needing expensive lab equipment or specialized training. They found these AI models could tell plastic apart from sand fairly well, but their accuracy varied depending on the type of plastic and photo conditions, suggesting this approach could eventually offer a cheaper, faster way to track plastic pollution that ultimately makes its way into our food and water—but it isn't quite reliable enough yet for widespread use.
While existing AI-based microplastic monitoring studies predominantly rely on task-specific fine-tuned models, this study evaluates whether general-purpose multimodal foundation models with no spectroscopic instrumentation, minimal fine-tuning, and minimal computational resources can serve as accessible, low-cost tools for polymer classification under ecologically realistic field conditions with samples of plastic debris collected from coastal Sousse, Tunisia, a Mediterranean region experiencing anthropogenic pollution pressures. A curated dataset of 1080 high-resolution images was developed, representing six polymer groups (HDPE, LDPE, PA, PET, PP, PS, and mixed plastics). Fragments were imaged under standardized lighting conditions against natural sand backgrounds to preserve environmental realism. Each image was manually annotated using polygon-based boundaries to generate pixel-level segmentation masks and associated class labels, providing expert-validated ground truth for quantitative evaluation. Multimodal LLMs were evaluated using a composite scoring framework. Spatial accuracy was assessed using mean Intersection-over-Union (mIoU) against expert annotations, while polymer classification performance was measured using macro-averaged F1 scores across all categories. Model reliability was further evaluated through prompt stability testing and robustness analyses under controlled environmental perturbations designed to assess consistency across varying coastal imaging conditions. Results indicate that multimodal foundation models can distinguish plastic fragments from sand backgrounds, although performance varied across polymer classes and environmental perturbations. The weighted composite framework provides a structured approach for comparing model performance according to ecological monitoring objectives rather than computational metrics. These findings contribute to understanding the potential utility and current limitations of AI-based approaches for marine microplastic analysis and provide insights into coastal pollution patterns and ecosystem health within a One Health monitoring context.