Proceedings of The 5th International Workshop on Deep Learning in Computational Physics

Legacy of Tunka-Rex Software and Data Tunka-Rex软件和数据的遗产

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-10 DOI: 10.22323/1.410.0010

P. Bezyazeekov, N. Budnev, O. Fedorov, O. Gress, O. Grishin, A. Haungs, T. Huege, Y. Kazarina, M. Kleifges, E. Korosteleva, D. Kostunin, L. Kuzmichev, V. Lenok, N. Lubsandorzhiev, S. Malakhov, T. Marshalkina, R. Monkhoev, E. Osipova, A. Pakhorukov, L. Pankov, V. Prosin, D. Shipilov, A. Zagorodnikov, F. Schroeder

{"title":"Legacy of Tunka-Rex Software and Data","authors":"P. Bezyazeekov, N. Budnev, O. Fedorov, O. Gress, O. Grishin, A. Haungs, T. Huege, Y. Kazarina, M. Kleifges, E. Korosteleva, D. Kostunin, L. Kuzmichev, V. Lenok, N. Lubsandorzhiev, S. Malakhov, T. Marshalkina, R. Monkhoev, E. Osipova, A. Pakhorukov, L. Pankov, V. Prosin, D. Shipilov, A. Zagorodnikov, F. Schroeder","doi":"10.22323/1.410.0010","DOIUrl":"https://doi.org/10.22323/1.410.0010","url":null,"abstract":"P. Bezyazeekov,1,∗ N. Budnev,1 O. Fedorov,1 O. Gress,1 O. Grishin,1 A. Haungs,2 T. Huege,2,3 Y. Kazarina,1 M. Kleifges,4 E. Korosteleva,5 D. Kostunin,6,9 L. Kuzmichev,5 V. Lenok,2 N. Lubsandorzhiev,5 S. Malakhov,1 T. Marshalkina,1 R. Monkhoev,1 E. Osipova,5 A. Pakhorukov,1 L. Pankov,1 V. Prosin,5 F. G. Schröder,2,7 D. Shipilov8 and A. Zagorodnikov1 1Applied Physics Institute ISU, Irkutsk, 664020 Russia 2Karlsruhe Institute of Technology, Institute for Astroparticle Physics, D-76021 Karlsruhe, Germany 3Astrophysical Institute, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium 4Institut für Prozessdatenverarbeitung und Elektronik, Karlsruhe Institute of Technology (KIT), Karlsruhe, 76021 Germany 5Skobeltsyn Institute of Nuclear Physics MSU, Moscow, 119991 Russia 6DESY, Zeuthen, 15738 Germany 7Bartol Research Institute, Department of Physics and Astronomy, University of Delaware, Newark, DE, 19716, USA 8X5 Retail Group, Moscow, 119049 Russia 9JetBrains Research, 194100 St. Petersburg, Russia","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"40 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126655834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neural Network Solution of Inverse Problems of Geological Prospecting with Discrete Output 离散输出地质找矿逆问题的神经网络求解

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-10 DOI: 10.22323/1.410.0003

I. Isaev, I. Obornev, E. Obornev, E. Rodionov, M. Shimelevich, S. Dolenko

{"title":"Neural Network Solution of Inverse Problems of Geological Prospecting with Discrete Output","authors":"I. Isaev, I. Obornev, E. Obornev, E. Rodionov, M. Shimelevich, S. Dolenko","doi":"10.22323/1.410.0003","DOIUrl":"https://doi.org/10.22323/1.410.0003","url":null,"abstract":"The inverse problems of exploration geophysics are to reconstruct the spatial distribution of the properties of the medium in the Earth’s thickness from the geophysical fields measured on its surface. In particular, this paper deals with the problems of gravimetry, magnetometry, and magnetotelluric sounding, as well as their integration, i.e., the simultaneous use of several geophysical fields to restore the desired distribution. To implement the integration, a 4-layer 2D model was used, where the inverse problem was to determine the lower boundary of the layers, and each layer was characterized by variable values of the depth of the lower boundary along the section and fixed values of density, magnetization, and resistivity, both for the layer and for the entire data set. To implement the neural network solution of the inverse problem, a data set was generated by solving the direct problem, where for each pattern, the distribution of layer depth values was set randomly in a given range and with a given step, i.e. it took discrete values from a certain set. In this paper, we consider an approach involving the use of neural networks to solve the problem of multiclass classification, where class labels correspond to discrete values of the determined layer depths. The results of the solution are compared with the results of the solution of the same inverse problem in the formulation","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"128 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130008428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Use of Conditional Generative Variational Autoencoder Networks to Improve Representativity of Data in Optical Spectroscopy 利用条件生成变分自编码器网络提高光谱学中数据的代表性

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-10 DOI: 10.22323/1.410.0013

A. Efitorov, T. Dolenko, K. Laptinskiy, S. Burikov, S. Dolenko

引用次数: 0

A Convolutional Hierarchical Neural Network Classifier 卷积层次神经网络分类器

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-06 DOI: 10.22323/1.410.0014

I. Gadzhiev, S. Dolenko

{"title":"A Convolutional Hierarchical Neural Network Classifier","authors":"I. Gadzhiev, S. Dolenko","doi":"10.22323/1.410.0014","DOIUrl":"https://doi.org/10.22323/1.410.0014","url":null,"abstract":"The report presents an algorithm for constructing a convolutional hierarchical neural network classifier, which is a modification of the algorithm for constructing hierarchical neural network classifiers suggested before. The original algorithm was designed to exploit intrinsic class hierarchy to build a class tree with a neural network in each node classifying groups of initial classes (in a non-terminal node) or a subset of original classes (in a terminal node). The convolutional modification utilizes convolutional neural networks instead of regular fully connected networks in order to apply the model to image classification tasks. Use of class hierarchy for image classification should reduce the number of adjusted neural network parameters compared to deep convolutional neural networks, and therefore it should reduce training and inference time. In this context the algorithm may be compared with some pruning techniques. The convolutional hierarchical neural network classifier inherits some hyperparameters of a conventional hierarchical neural network classifier, like the activation threshold and the threshold by the share of voting patterns. The goal of this study was to explore different strategies of choosing these hyperparameters. To test these strategies, we used the CIFAR-10 dataset. Also, for demonstration purposes we apply the convolutional hierarchical neural network classifier to the CIFAR-100 dataset.","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122507729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The 5th International Workshop on Deep Learning in Computational Physics – DLCP-2021 第五届计算物理深度学习国际研讨会- dlp -2021

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-04 DOI: 10.22323/1.410.0001

A. Haungs, A. Kryukov

引用次数: 0

Modeling Images of Proton Events for the TAIGA Project Using a Generative Adversaria Network: Features of the Network Architecture and the Learning Process 使用生成对抗网络为TAIGA项目建模质子事件图像:网络架构的特征和学习过程

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-03 DOI: 10.22323/1.410.0011

J. Dubenskaya, A. Kryukov, A. Demichev

{"title":"Modeling Images of Proton Events for the TAIGA Project Using a Generative Adversaria Network: Features of the Network Architecture and the Learning Process","authors":"J. Dubenskaya, A. Kryukov, A. Demichev","doi":"10.22323/1.410.0011","DOIUrl":"https://doi.org/10.22323/1.410.0011","url":null,"abstract":"High-energy particles interacting with the Earth atmosphere give rise to extensive air showers emitting Cherenkov light. This light can be detected on the ground by imaging atmospheric Cherenkov telescopes (IACTs). One of the main problems solved during primary processing of experimental data is the separation of signal events (gamma quanta) against the hadronic background, the bulk of which is made up of proton events. To ensure correct gamma event/proton event separation under real conditions, a large amount of experimental data, including model data, is required. Thus, although proton events are considered as background, their images are also necessary for accurate registration of gamma quanta. We applied a machine learning method, namely the generative adversarial networks (GANs) to generate images of proton events for the TAIGA project. This approach allowed us to significantly increase the speed of image generation. At the same time testing the results using third-party software showed that over 95% of the generated images are correct and can be used in the experiment. In this article we provide a detailed GAN architecture suitable for generating images of proton events similar to those obtained from IACTs of the TAIGA project. The features of the training process are also discussed, including the number of learning epochs and selecting appropriate network parameters.","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124645252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Artificial Neural Networks for the Identification of Partial Differential Equations of LandSurface Schemes in Climate Models 气候模式中陆面方案偏微分方程的人工神经网络辨识

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-01 DOI: 10.22323/1.410.0005

M. Krinitskiy, V. Stepanenko, R. Chernyshev

{"title":"Artificial Neural Networks for the Identification of Partial Differential Equations of LandSurface Schemes in Climate Models","authors":"M. Krinitskiy, V. Stepanenko, R. Chernyshev","doi":"10.22323/1.410.0005","DOIUrl":"https://doi.org/10.22323/1.410.0005","url":null,"abstract":"Land surface scheme in climate models is a solver for a nonlinear PDE system, which describes thermal conductance and water diffusion in soil. Thermal conductivity 𝜆 𝑇 , water diffusivity 𝜆 𝑊 and hydraulic conductivity 𝛾 coefficients of this system are functions of the solution of the system 𝑊 and 𝑇 . For the climate models to accurately represent the Earth system’s evolution, one needs to approximate the coefficients or estimate their values empirically. Measuring the coefficients is a complicated in-lab experiment without a chance to cover the full range of environmental conditions. In this work, we propose a data-driven approach for approximating the parameters of the PDE system describing the evolution of soil characteristics. We formulate the coefficients as parametric functions, namely artificial neural networks. We propose training these neural networks with the loss function computed as a discrepancy between the PDE system solution and the measured characteristics 𝑊 and 𝑇 . We also propose a scheme inherited from the backpropagation method for calculating the gradients of the loss function w.r.t. network parameters. As a proof-of-concept step, we assessed the capabilities of our approach in three synthetic scenarios: a nonlinear thermal diffusion equation, a nonlinear liquid water 𝑊 diffusion equation, and Richards equation. We generated realistic initial conditions and simulated synthetic evolutions of 𝑊 and 𝑇 that we used as measurements in the networks‘ training procedure for these three scenarios. The results of our study show that our approach provides an opportunity for reconstructing the PDE coefficients of various forms accurately without actual knowledge of their ground truth values.","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127338483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using Modern Machine Learning Methods on KASCADE Data for Outreach and Education 在KASCADE数据上使用现代机器学习方法进行推广和教育

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-01 DOI: 10.22323/1.410.0007

V. Tokareva, D. Kostunin, I. Plokhikh, V. Sotnikov

引用次数: 0

Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels 无限通道的等变高斯过程极限卷积网络

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-01 DOI: 10.22323/1.410.0002

A. Demichev

引用次数: 0

Graph Neural Networks and Application for Cosmic-Ray Analysis 图神经网络及其在宇宙射线分析中的应用

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021) Pub Date : 2021-12-01 DOI: 10.22323/1.410.0004

P. Koundal

{"title":"Graph Neural Networks and Application for Cosmic-Ray Analysis","authors":"P. Koundal","doi":"10.22323/1.410.0004","DOIUrl":"https://doi.org/10.22323/1.410.0004","url":null,"abstract":"Deep Learning has emerged as one of the most promising areas of computational research for pattern learning, inference drawing, and decision-making, with wide-ranging applications across various scientific disciplines. This has also made it possible for faster and more precise analysis in astroparticle physics, enabling new insights from massive volumes of input data. Graph Neural Networks have materialized as a salient implementation method among the numerous deep-learning architectures over the last few years because of the unique ability to represent complex input data from a wide range of problems in its most natural form. Described using nodes and edges, graphs allow us to efficiently represent relational data and learn hidden representations of input data to obtain better model accuracy. At IceCube Neutrino Observatory, a complex multi-component detector, traditional likelihood-based analysis on a per-event basis, to reconstruct cosmic-ray air shower parameters is time-consuming and computationally costly. Using advanced and flexible models based on Graph Neural Networks naturally emerges as a possible solution, reducing the time and computing cost for performing such analysis while boosting sensitivity. This paper will outline Graph Neural Networks and discuss a possible application of using such methods at the IceCube Neutrino Observatory.","PeriodicalId":217453,"journal":{"name":"Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115166044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Proceedings of The 5th International Workshop on Deep Learning in Computational Physics — PoS(DLCP2021)最新文献