A Machine Learning Approach to Derive Aerosol Properties from All-Sky Camera Imagery

Abstract

We propose a methodology to derive the aerosol optical depth (AOD) and Angstrom exponent (AE) from calibrated images of an all-sky camera. It is based on a machine learning (ML) approach that establishes a relationship between AERONET measurements of AOD and AE and different signals derived from the principal plane radiance measured by an all-sky camera at three RGB channels. Gaussian process regression (GPR) has been chosen as machine learning method and applied to four models that differ in the input choice: RGB individual signals to predict spectral AOD; red signal only to predict spectral AOD and AE; blue-to-red ratio (BRR) signals to predict spectral AOD and AE; red signals to predict spectral AOD and AE at once. The novelty of our approach mostly relies on obtaining a cloud-screened and smoothed signal that enhances the aerosol features contained in the principal plane radiance and can be applied in partially cloudy conditions. In addition, a quality assurance criterion for the prediction has been also suggested, which significantly improves our results. When applied, our results are very satisfactory for all the models and almost all predictions are close to real values within ±0.02 for AOD and ±0.2 for AE, whereas the MAE is less than 0.005. They show an excellent agreement with AERONET measurements, with correlation coefficients over 0.92. Moreover, more than 87% of our predictions lie within the AERONET uncertainties (±0.01 for AOD, ±0.1 for AE) for all the output parameters of the best model. All the models offer a high degree of numerical stability with negligible sensitivities to the training data, atmospheric conditions and instrumental issues. All this supports the strength and efficiency of our models and the potential of our predictions. The optimum performance shown by our proposed methodology indicates that a well-calibrated all-sky camera can be routinely used to accurately derive aerosol properties. Together, all this makes the all-sky cameras ideal for aerosol research and this work may represent a significant contribution to the aerosol monitoring.

A Machine Learning Approach to Retrieving Aerosol Optical Depth Using Solar Radiation Measurements

“…Various alternative techniques for AOD retrieval reported in the literature fall into four primary categories: (1) backward solving radiative transfer (RT) or clear-sky models using solar radiation measurements [24][25][26][27], (2) methodologies based on sunshine duration (SD) measurements [28][29][30], (3) image processing techniques using sky radiances from all-sky imagers [31][32][33][34], and (4) machine learning (ML) and deep learning algorithms employing various independent parameters as input features [35][36][37][38][39].…”

Aerosol Optical Properties and Type Retrieval via Machine Learning and an All-Sky Imager

“…Generally, the median and standard deviation of the AOD differences were between 0.006-0.010 and 0.024-0.030, respectively. Scarlatti et al [51] recently proposed a machine learning (ML) approach for AOD and AE retrieval using the smoothing RGB signals towards the principal plane, as captured from a well-calibrated ASI installed at the University of Valencia, Spain. Different distinct ML models with varied input information were implemented.…”

“…All the aforementioned approaches revealed adequate retrieval performance against the AERONET, with R 2 exceeding 0.95. A novel point of the Scarlatti et al [51] study was the implementation of partially clouded images during ML model training.…”