Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations

Sommer, Kélian; Kabalan, Wassim; Brunet, Romain

doi:https://doi.org/10.5194/amt-18-2083-2025

Articles | Volume 18, issue 9

https://doi.org/10.5194/amt-18-2083-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-18-2083-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 9

Research article

|

12 May 2025

Research article |

| 12 May 2025

Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations

Kélian Sommer, Wassim Kabalan, and Romain Brunet

Model code and software

Kelian98/tau2_thermalcapture: Release for Zenodo (main) Kélian Sommer https://doi.org/10.5281/zenodo.15311830

ASKabalan/infrared-cloud-detection: v0.1.0 Kélian Sommer et al. https://doi.org/10.5281/zenodo.15316607

Flax: A neural network library and ecosystem for JAX Jonathan Heek et al. http://github.com/google/flax

JAX: composable transformations of Python+NumPy programs James Bradbury et al. http://github.com/google/jax

Open Source Computer Vision Library Itseez https://github.com/itseez/opencv

pandas-dev/pandas: Pandas Pandas Development Team https://doi.org/10.5281/zenodo.3509134

Short summary

Our research introduces a novel deep-learning approach for classifying and segmenting ground-based infrared thermal images, a crucial step in cloud monitoring. Tests based on self-captured data showcase its excellent accuracy in distinguishing image types and in structure segmentation. With potential applications in astronomical observations, our work pioneers a robust solution for ground-based sky quality assessment, promising advancements in the photometric observation experiments.