Determination of size of urban particulates from occluded scattering patterns using deep learning and data augmentation

James A Grant-Jacob,Ben Mills,Matthew Praeger,Robert W Eason,Matthew Loxham

doi:10.1088/2515-7620/abed94

Abstract

Deep learning has shown recent key breakthroughs in enabling particulate identification directly from scattering patterns. However, moving such a detector from a laboratory to a real-world environment means developing techniques for improving the neural network robustness. Here, a methodology for training data augmentation is proposed that is shown to ensure neural network accuracy, despite occlusion of the scattering pattern by simulated particulates deposited on the detector’s imaging sensor surface. The augmentation approach was shown to increase the accuracy of the network when identifying the geometric Y-dimension of the particulates by ∼62% when 1000 occlusions of size ∼5 pixels were present on the scattering pattern. This capability demonstrates the potential of data augmentation for increasing accuracy and longevity of a particulate detector operating in a real-world environment.

Highlights

One of the current global health challenges is particulate matter (PM) pollution, since it is associated with sicknesses that include respiratory disorders, cardiovascular diseases and cancer [1,2,3,4,5,6]
A dataset complied in 2016 by the World Health Organisation (WHO) for annual mean concentrations of PM2.5 and PM10 across the globe, shows that particulate levels can vary from city to city, with 100 μg m-3 of PM2.5 and 187 μg m-3 of PM10 recorded in Jaipur, India (2012 data), 29 μg m3 of PM2.5 and 64 μg m-3 of PM10 recorded in Santiago, Chile (2014 data), and 15 μg m-3 of PM2.5 and 21 μg m-3 of PM10 recorded in Southampton, UK (2013) [8]
We improve the accuracy for determining particulate sizes from occluded scattering patterns by augmenting the neural network training data via inclusion of occluded scattering pattern images, demonstrating the potential for improving the detector’s robustness when applied in a real-world environment

Summary

Introduction

One of the current global health challenges is particulate matter (PM) pollution, since it is associated with sicknesses that include respiratory disorders, cardiovascular diseases and cancer [1,2,3,4,5,6]. As cohort studies expand in size, and as methods to determine individual exposures improve, associations with further diseases affecting additional body systems are being uncovered [3] These associations are not currently established as being causal relationships, and mechanisms are not fully understood, it is becoming ever more likely that the cardiovascular and respiratory systems are not the sole sites of the deleterious effects of airborne PM [23]. Conventional methods for monitoring the size and chemical composition of particulates involve using large filter traps that collect the particulates onto a filter substrate, often with an upstream size selective inlet of impaction surface to allow size fractionation These filters need to be post-processed, usually with lab-based scientific apparatus. A simple optical detector that can determine the size of particulates, whilst being robust in the environment in which it is sensing, is highly desirable

Methods

Results

Conclusion