Investigation of artificial neural network performance in the aerosol properties retrieval
Aerosols are an integral part of Earth's climate system and their effect on climate makes this field a relevant research problem. The artificial neural network (ANN) technique is an upcoming technique in different research fields. In the current work, we have evaluated the performance of an ANN...
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | article |
| Langue: | EN |
| Publié: |
IWA Publishing
2021
|
| Sujets: | |
| Accès en ligne: | https://doaj.org/article/f1833868710d4a6fbd5c6c1abbcf01ed |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| Résumé: | Aerosols are an integral part of Earth's climate system and their effect on climate makes this field a relevant research problem. The artificial neural network (ANN) technique is an upcoming technique in different research fields. In the current work, we have evaluated the performance of an ANN with its parameters in simulating the aerosol's properties. ANN evaluation is performed over three sites (Kanpur, Jaipur, and Gandhi College) in the Indian region. We evaluated the performance of ANN for model's hyperparameter (number of hidden layers) and optimizer's hyperparameters (learning rate and number of iterations). The optical properties of aerosols from AERONET (AErosol RObotic NETwork) are used as input to ANN to estimate the aerosol optical depth (AOD) and Angstrom exponent. Results emphasized the need for optimal learning rate values and the number of iterations to get accurate results with low computational cost and to avoid overfitting. We observed a 23–25% increase in computational time with an increase in iteration. Thus, a meticulous selection of these parameters should be made for accurate estimations. The result indicates that the developed ANN can be utilized to derive AOD, which is not assessed at AERONET stations. HIGHLIGHTS
In designing an ANN, we must choose the optimal number of iterations based on computational cost and quality of results.;
Our finding indicates that ANN with more hidden layers can perform reasonably well at a low number of iterations.;
The specific site may need a different set of hyperparameters for the best performance of the ANN.;
The developed ANN can be utilized to derive AOD, which is not assessed at AERONET stations; |
|---|