We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Scaling laboratory results with machine learning is no silver bullet to strengthen global (micro-)plastic mitigation policy: [Dataset]
AI summary Read the abstract
This commentary examines the limitations of using machine learning to scale laboratory microplastic photosynthesis-inhibition results to global estimates, arguing that such approaches are insufficient to reliably inform international plastic mitigation policy without addressing underlying data and model uncertainties.
Supplementary Information for letter to the editor / commentary concerning the article “A global estimate of multiecosystem photosynthesis losses under microplastic pollution” (Zhu et al., 2025) https://doi.org/10.1073/pnas.2423957122
More Papers Like This
Scaling laboratory results with machine learning is no silver bullet to strengthen global (micro)plastic mitigation policy
AI summary Read the abstract
This commentary challenged a study estimating 4.11–13.52% global crop yield losses from microplastic and nanoplastic (MP/NP) pollution, arguing that the machine learning model was trained predominantly on seedlings in controlled hydroponics at high concentrations rather than field-grown mature crops. The authors identified three fundamental gaps: methodological bias in model training data, neglect of natural MP/NP concentrations in aged soil, and failure to account for complex crop yield drivers, questioning the validity of upscaling laboratory results to global hunger and sustainability policy.
Decoding the PlasticPatch: Exploring the Global MicroplasticDistribution in the Surface Layers of Marine Regions with InterpretableMachine Learning
AI summary Read the abstract
Researchers applied four interpretable machine learning algorithms to a calibrated global marine microplastic dataset to construct a predictive model of surface-layer microplastic distribution, finding that biogeochemical and anthropogenic factors are the dominant drivers of global marine microplastic pollution patterns.
Data driven methods to increase the reliability of microplastics hazard assessment
AI summary Read the abstract
Researchers applied data-driven methods to synthesize microplastic ecotoxicology studies and improve the reliability of hazard assessments for organisms. The analysis identified systematic biases in the existing literature and proposed statistical approaches to generate more robust effect size estimates.
Do microplastics affect marine ecosystem productivity?
AI summary Read the abstract
This study estimated the ecosystem-level impacts of microplastics on marine productivity by scaling up laboratory findings on individual algae and zooplankton to broader ecological models. The results suggest that microplastics may measurably reduce both primary and secondary marine productivity, with consequences for ocean carbon cycling and food webs.
What’s that microplastic? Advances in machine learning are making identifying plastics in the environment more reliable
AI summary Read the abstract
This piece reviews advances in machine learning for identifying polymer types in environmental microplastic samples, describing how models trained on spectroscopic and imaging data are improving the reliability and speed of plastic classification. Better automated identification tools are essential for building standardized datasets needed to track pollution sources, assess regulatory compliance, and understand human and ecological exposure to specific plastic types.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.