Retrieval of aerosol properties from in situ, multi-angle light scattering measurements using invertible neural networks

TL;DR

This paper introduces an invertible neural network approach for rapid and accurate retrieval of aerosol properties from in situ light scattering measurements, outperforming traditional methods in speed and robustness.

Contribution

The work presents a novel invertible neural network method that simultaneously retrieves aerosol properties and simulates forward measurements, improving speed and accuracy over existing techniques.

Findings

Retrieval time is in the millisecond range.

Mean absolute percentage error is less than 1.5%.

Method is robust to measurement noise and missing data.

Abstract

Atmospheric aerosols have a major influence on the earths climate and public health. Hence, studying their properties and recovering them from light scattering measurements is of great importance. State of the art retrieval methods such as pre-computed look-up tables and iterative, physics-based algorithms can suffer from either accuracy or speed limitations. These limitations are becoming increasingly restrictive as instrumentation technology advances and measurement complexity increases. Machine learning algorithms offer new opportunities to overcome these problems, by being quick and precise. In this work we present a method, using invertible neural networks to retrieve aerosol properties from in situ light scattering measurements. In addition, the algorithm is capable of simulating the forward direction, from aerosol properties to measurement data. The applicability and performance of the algorithm are demonstrated with simulated measurement data, mimicking in situ laboratory and field measurements. With a retrieval time in the millisecond range and a weighted mean absolute percentage error of less than 1.5%, the algorithm turned out to be fast and accurate. By introducing Gaussian noise to the data, we further demonstrate that the method is robust with respect to measurement errors. In addition, realistic case studies are performed to demonstrate that the algorithm performs well even with missing measurement data.