18 Jan 2024
 | 18 Jan 2024
Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).

IceDetectNet: A rotated object detection algorithm for classifying components of aggregated ice crystals with a multi-label classification scheme

Huiying Zhang, Xia Li, Fabiola Ramelli, Robert O. David, Julie Pasquier, and Jan Henneberger

Abstract. The shape of ice crystals affects their radiative properties, growth rate, fall speed, and collision efficiency and thus, plays a significant role in cloud optical properties and precipitation formation. Ambient conditions like temperature and humidity determine the basic habit of ice crystals, while microphysical processes such as riming and aggregation further shape them, resulting in a diverse set of ice crystal shapes and densities. Current classification algorithms face two major challenges: (1) ice crystals are often classified as a whole (on the image scale), necessitating identification of the dominant component of aggregated ice crystals, and (2) single-label classifications lead to information loss because of the compromise between basic habit and microphysical process information. To address these limitations, here we present a two-pronged solution: a rotated object detection algorithm (IceDetectNet) that classifies each component of an aggregated ice crystal individually, and a multi-label classification scheme that considers both basic habits and physical processes simultaneously. IceDetectNet was trained and tested on two independent datasets obtained by a holographic imager during the NASCENT campaign in Ny-Ålesund, Svalbard, in November 2019 and April 2020. The algorithm correctly classifies 92 % of the ice crystals as either aggregate or non-aggregate and achieved an overall accuracy of 86 % for basic habits and 82 % for microphysical processes classification. On the component scale, IceDetectNet demonstrated high detection and classification accuracy across all sizes, indicating its ability to effectively classify individual components of aggregated ice crystals. Furthermore, the algorithm demonstrated good generalization ability by classifying ice crystals from an independent test dataset with overall accuracies above 70 %. IceDetectNet can provide a deeper understanding of ice crystal shapes, leading to better estimates of ice crystal mass, fall velocity, and radiative properties and thus, has the potential to improve precipitation forecasts and climate projections.

Huiying Zhang, Xia Li, Fabiola Ramelli, Robert O. David, Julie Pasquier, and Jan Henneberger

Status: open (until 21 Mar 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Huiying Zhang, Xia Li, Fabiola Ramelli, Robert O. David, Julie Pasquier, and Jan Henneberger
Huiying Zhang, Xia Li, Fabiola Ramelli, Robert O. David, Julie Pasquier, and Jan Henneberger


Total article views: 180 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
145 31 4 180 2 2
  • HTML: 145
  • PDF: 31
  • XML: 4
  • Total: 180
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 18 Jan 2024)
Cumulative views and downloads (calculated since 18 Jan 2024)

Viewed (geographical distribution)

Total article views: 176 (including HTML, PDF, and XML) Thereof 176 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 21 Feb 2024
Short summary
Our innovative IceDetectNet algorithm classifies each part of aggregated ice crystals, taking into account both their basic shape and physical processes. Trained on ice crystal images from the Arctic taken by a holographic camera, it correctly classifies over 92 % of the ice crystals. The more detailed insights into the components of aggregated ice crystals have the potential to improve our estimates of microphysical properties such as riming rate and ice water content.