0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Detection Methods Sign in to save

naviiidz/hfus-mp-characterization: v1.0.0

Zenodo (CERN European Organization for Nuclear Research) 2026
Navid

Summary

This is a software repository release accompanying a research paper on using high-frequency ultrasound to identify and size microplastic particles. The code supports machine-learning classification and size estimation workflows for ultrasound-based microplastic detection.

Body Systems

This software release contains the code used for ultrasound-based characterization of microplastic particles, including material identification and particle size estimation using high-frequency ultrasound signals. The repository includes data processing pipelines, peak-based signal extraction routines, feature computation, and implementations of classical machine-learning methods as well as a one-dimensional convolutional neural network (1D-CNN) for material classification. Particle size estimation is implemented using material-specific machine-learning models trained on extracted acoustic features. The code is designed to operate with the accompanying Zenodo dataset and supports reproducible evaluation of ultrasound-based microplastic detection, classification, and size estimation workflows. This release corresponds to version v1.0.0 and is linked to the associated npj Emerging Contaminants publication.

Share this paper