Microplastic pollution monitoring with holographic classification and deep learning

Abstract

The observation and detection of the microplastic pollutants generated by industrial manufacturing require the use of precise optical systems. Digital holography is well suited for this task because of its non-contact and non-invasive detection features and the ability to generate information-rich holograms. However, traditional digital holography usually requires post-processing steps, which is time-consuming and may not achieve the final object detection performance. In this work, we develop a deep learning-based holographic classification method, which computes directly on the raw holographic data to extract quantitative information of the microplastic pollutants so as to classify them according to the extent of the pollution. We further show that our method can generalize to the classification task of other micro-objects through cross-dataset validation. Without bulky optical devices, our system can be further developed into a portable microplastics detection system, with wide applicability in the monitoring of microplastic particle pollution in the ecological environment.

Holographic and polarization features analysis for microplastics characterization and water monitoring

“…This method can further help in the study of toxicity testing on micro-organisms and the environmental MPs pollution monitoring. 14…”

Snapshot Polarization-Sensitive Holography for Detecting Microplastics in Turbid Water

“…Therefore, it should be of great significance to evaluate and understand such degradation phenomena when detecting MP particles through various scattering media. Unfortunately, most previous studies attempting to detect MPs in the aqueous phase − have ignored this critical issue. They either placed the pretreated MP samples in clean media for observation or paid less attention to the variation of the employed water media.…”

Toward an All-Optical Fingerprint of Synthetic and Natural Microplastic Fibers by Polarization-Sensitive Holographic Microscopy

“…Furthermore, numerical focus extension has been demonstrated to be particularly useful for samples with complex and\or elongated structures. , For all these reasons, DH can be seen as an effective alternative investigation modality on MP and micron-sized fiber fragments (MFFs), especially to overcome the issue related to dry measurements and filtration steps. The DH adverse aspect is the lack of specificity so that, in recent years, many efforts have been made to overcome this gap, for example, combining DH with artificial intelligence (AI) to monitor, identify, and count MPs in heterogeneous water samples; ,, particularly, as some authors have described, a non-contact and non-invasive method that combines 3D phase-contrast imaging with machine learning (ML) based on a proper analysis of holographic phase-contrast patterns relying on fractal geometry. The method is viable to discern between MPs and the microplankton within a wide scale range.…”