Studying Deep Convolutional Neural Networks With Hexagonal Lattices for Imaging Atmospheric Cherenkov Telescope Event Reconstruction

Castaño, Daniel Nieto; Brill, Ari; Feng, Q.; Jacquemont, Mikaël; Kim, Bryan; Miener, Tjark; Vuillaume, Thomas

doi:10.22323/1.358.0753

Cited by 6 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The image preprocessing and data reading is managed by the DL1DH. Bilinear interpolation is used to map the hexagonal pixel layout of the MAGIC cameras to a Cartesian lattice to directly apply CNNs [12]. Finally, CTLearn performs training and prediction with CNN-based models, allowing for full-event reconstruction.…”

Section: Introductionmentioning

confidence: 99%

The performance of the MAGIC telescopes using deep convolutional neural networks with CTLearn

Miener,

Nieto,

López-Coto

et al. 2023

Proceedings of 7th Heidelberg International Symposium on High-Energy Gamma-Ray Astronomy — PoS(Gamma2022)

View full text Add to dashboard Cite

The Major Atmospheric Gamma Imaging Cherenkov (MAGIC) telescope system is located on the Canary Island of La Palma and inspects the very high-energy (VHE, few tens of GeV and above) gamma-ray sky. MAGIC consists of two imaging atmospheric Cherenkov telescopes (IACTs), which capture images of the air showers originating from the absorption of gamma rays and cosmic rays by the atmosphere, through the detection of Cherenkov photons emitted in the shower. The sensitivity of IACTs to gamma-ray sources is mainly determined by the ability to reconstruct the properties (type, energy, and arrival direction) of the primary particle generating the air shower. The state-of-the-art IACT pipeline for shower reconstruction is based on the parameterization of the shower images by extracting geometric and stereoscopic features and machine learning algorithms like random forest or boosted decision trees. In this contribution, we explore deep convolutional neural networks applied directly to the pixelized images of the camera as a promising method for IACT full-event reconstruction and present the performance of the method on observational data using CTLearn, a package for IACT event reconstruction that exploits deep learning.

show abstract

Section: Introductionmentioning

confidence: 99%

The performance of the MAGIC telescopes using deep convolutional neural networks with CTLearn

Miener,

Nieto,

López-Coto

et al. 2023

Proceedings of 7th Heidelberg International Symposium on High-Energy Gamma-Ray Astronomy — PoS(Gamma2022)

View full text Add to dashboard Cite

show abstract

“…Compared to other classical approaches, connected operators have the advantage of not introducing any distortions into the image (see Ref. [10] for a detailed study of image distortion in IACT event reconstruction with neural networks). This is achieved by the merging of flat zones (regions in the image with the same colour) within the image, which prevents splitting or deforming of existing features and the implementation of unwanted new edges.…”

Section: Introductionmentioning

confidence: 99%

Application of Pattern Spectra and Convolutional Neural Networks to the Analysis of Simulated Cherenkov Telescope Array Data

Aschersleben¹,

Peletier²,

Vecchi³

et al. 2021

Proceedings of 37th International Cosmic Ray Conference — PoS(ICRC2021)

View full text Add to dashboard Cite

The Cherenkov Telescope Array (CTA) will be the next generation gamma-ray observatory and will be the major global instrument for very-high-energy astronomy over the next decade, offering 5 − 10 × better flux sensitivity than current generation gamma-ray telescopes. Each telescope will provide a snapshot of gamma-ray induced particle showers by capturing the induced Cherenkov emission at ground level. The simulation of such events provides images that can be used as training data for convolutional neural networks (CNNs) to determine the energy of the initial gamma rays. Compared to other state-of-the-art algorithms, analyses based on CNNs promise to further enhance the performance to be achieved by CTA. Pattern spectra are commonly used tools for image classification and provide the distributions of the shapes and sizes of various objects comprising an image. The use of relatively shallow CNNs on pattern spectra would automatically select relevant combinations of features within an image, taking advantage of the 2D nature of pattern spectra. In this work, we generate pattern spectra from simulated gamma-ray events instead of using the raw images themselves in order to train our CNN for energy reconstruction. This is different from other relevant learning and feature selection methods that have been tried in the past. Thereby, we aim to obtain a significantly faster and less computationally intensive algorithm, with minimal loss of performance.

show abstract

“…At the moment the use of convolutional neural networks [4] as one of the methods of machine learning for TAIGA-IACT image processing has not been implemented to real data, therefore this work allowed us to study the prospects of using this method. It is known that other IACT installations [5,6] have shown promising results in image analysis of model data using convolutional neural networks. CNNs were also used for the TAIGA-IACT model data of one telescope [7,8].…”

Section: Introductionmentioning

confidence: 99%

The Preliminary Results on Analysis of TAIGA-IACT Images Using Convolutional Neural Networks

Gres¹,

Kryukov²

2021

Proceedings of the 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)

View full text Add to dashboard Cite

Studying Deep Convolutional Neural Networks With Hexagonal Lattices for Imaging Atmospheric Cherenkov Telescope Event Reconstruction

Cited by 6 publications

References 13 publications

The performance of the MAGIC telescopes using deep convolutional neural networks with CTLearn

The performance of the MAGIC telescopes using deep convolutional neural networks with CTLearn

Application of Pattern Spectra and Convolutional Neural Networks to the Analysis of Simulated Cherenkov Telescope Array Data

The Preliminary Results on Analysis of TAIGA-IACT Images Using Convolutional Neural Networks

Contact Info

Product

Resources

About