Preprints
https://doi.org/10.5194/egusphere-2025-269
https://doi.org/10.5194/egusphere-2025-269
29 Jan 2025
 | 29 Jan 2025
Status: this preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).

Aerosol type classification with machine learning techniques applied to multiwavelength lidar data from EARLINET

Ana del Águila, Pablo Ortiz-Amezcua, Siham Tabik, Juan Antonio Bravo-Aranda, Sol Fernández-Carvelo, and Lucas Alados-Arboledas

Abstract. Aerosol typing is essential for understanding atmospheric composition and its impact on the climate. Lidar-based aerosol typing has been often addressed with manual classification using optical property ranges. However, few works addressed it using automated classification with machine learning (ML) mainly due to the lack of annotated datasets. In this study, a high-vertical-resolution dataset is generated and annotated for the University of Granada (UGR) station in Southeastern Spain, which belongs to the European Aerosol Research Lidar Network (EARLINET), identifying five major aerosol types: Continental Polluted, Dust, Mixed, Smoke and Unknown. Six ML models – Decision Tree, Random Forest, Gradient Boosting, XGBoost, LightGBM and Neural Network- were applied to classify aerosol types using multiwavelength lidar data from EARLINET, for two system configurations: with and without depolarization data. LightGBM achieved the best performance, with precision, recall, and F1-Score above 90 % (with depolarization) and close to 87 % (without depolarization). The performance for each aerosol type was evaluated and dust classification improved by ~30 % with depolarization, highlighting its critical role in distinguishing aerosol types. Validation against an independent dataset from a Saharan dust event confirmed robust classification under real and extreme conditions. Compared to NATALI, a neural network-based EARLINET algorithm, the approach presented in this work shows improved aerosol classification accuracy, which emphasize the benefits of using high-resolution multiwavelength lidar data from real measurements. This highlights the potential of ML-based methods for robust and accurate aerosol typing, establishing a benchmark for future studies using multiwavelength lidar at high-resolution data from EARLINET.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share
Ana del Águila, Pablo Ortiz-Amezcua, Siham Tabik, Juan Antonio Bravo-Aranda, Sol Fernández-Carvelo, and Lucas Alados-Arboledas

Status: open (until 12 Mar 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Ana del Águila, Pablo Ortiz-Amezcua, Siham Tabik, Juan Antonio Bravo-Aranda, Sol Fernández-Carvelo, and Lucas Alados-Arboledas
Ana del Águila, Pablo Ortiz-Amezcua, Siham Tabik, Juan Antonio Bravo-Aranda, Sol Fernández-Carvelo, and Lucas Alados-Arboledas

Viewed

Total article views: 127 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
98 23 6 127 2 1
  • HTML: 98
  • PDF: 23
  • XML: 6
  • Total: 127
  • BibTeX: 2
  • EndNote: 1
Views and downloads (calculated since 29 Jan 2025)
Cumulative views and downloads (calculated since 29 Jan 2025)

Viewed (geographical distribution)

Total article views: 118 (including HTML, PDF, and XML) Thereof 118 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Feb 2025
Download
Short summary
This study applies machine learning (ML) techniques to classify aerosols using high-resolution multiwavelength lidar data from EARLINET network. We developed a reference dataset and evaluated six ML models, with LightGBM achieving over 90 % accuracy. Depolarization data proved critical for improving dust classification. Validated against a Saharan dust event, our approach improves aerosol classification and may help refine lidar-based processing strategies.
Share