THEORY2

User Tools

Site Tools

Trace: • zoom • sidebar • new-user • sidebar • start • welcome • program • next
dlcp2025:program

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
dlcp2025:program [24/06/2025 19:21] – [Машинное обучение для статистической детализации характеристик пространственного распределения осадков в Московском регионе] admindlcp2025:program [31/08/2025 07:29] (current) – [42. Возможность применения метода нормализующих потоков для извлечения редких гамма событий в эксперименте TAIGA] admin
Line 1: Line 1:
 {{ :dlcp2025:dlcp25-logo.png?200|}} {{ :dlcp2025:dlcp25-logo.png?200|}}
  
-====== Program (DFAFT) ======+====== Program ======
 //17.06.2025// //17.06.2025//
  
 **The list of accepted reports.** **The list of accepted reports.**
  
-<color /orange>Please note that the first author should be the presenter.</color>+<color /orange>The first author is the presenter.</color>
  
 //If someone did not find themselves in the list, please inform us by email [[dlcp@sinp.msu.ru]]// //If someone did not find themselves in the list, please inform us by email [[dlcp@sinp.msu.ru]]//
Line 97: Line 97:
 ==== 81. Проблема аугментация данных атмосферных черенковских телескопов в стерео режиме на примере установки TAIGA-IACT ==== ==== 81. Проблема аугментация данных атмосферных черенковских телескопов в стерео режиме на примере установки TAIGA-IACT ====
  
-//**Д.Журов**(1,3), А.Крюков(1), Ю.Дубенская(1), E. Gres(1,3); С.Поляков(3), ЕюПостников(1), А.Разумов(1), П.Волчугов(1), А.Демичев(1) \\ +//**Д.Журов**(1,3), А.Крюков(1), Ю.Дубенская(1), E. Gres(1,3), С.Поляков(3), Е.Постников(1), А.Разумов(1), П.Волчугов(1), А.Демичев(1) \\ 
 (1) SINP MSU, (2) IIAP NAS RA, (3) IPA IGU // (1) SINP MSU, (2) IIAP NAS RA, (3) IPA IGU //
  
Line 109: Line 109:
 ==== 42. Возможность применения метода нормализующих потоков для извлечения редких гамма событий в эксперименте TAIGA ==== ==== 42. Возможность применения метода нормализующих потоков для извлечения редких гамма событий в эксперименте TAIGA ====
  
-//**А.Крюков**(1), А.Разумов(1), Д.Журов(1,3), Ю.Дубенская(1), E. Gres(1,3); С.Поляков(3), Е.Постников(1), П.Волчугов(1), А.Демичев(1) \\ +//**А.Крюков**(1), А.Разумов(1), Д.Журов(1,3), Ю.Дубенская(1), E. Gres(1,3), С.Поляков(3), Е.Постников(1), П.Волчугов(1), А.Демичев(1) \\ 
 (1) SINP MSU, (2) IIAP NAS RA, (3) IPA IGU // (1) SINP MSU, (2) IIAP NAS RA, (3) IPA IGU //
  
Line 210: Line 210:
 ==== 92. Intercomparison of machine learning approaches for identifying hail from basic weather parameters ==== ==== 92. Intercomparison of machine learning approaches for identifying hail from basic weather parameters ====
  
-//**Blinov P.D.** (1), Chernokulsky A.V. (2), Krinitsky M.A. (3, 4), Bugrimov S.A. (5) \\ (1) National Research University - Higher School of Economics, Moscow, Russia, (2) A.M. Obukhov Institute of Atmospheric Physics RAS, Moscow, Russia, (3) P.P. Shirshov Institute of Oceanology RAS, Moscow, Russia (4) Moscow Institute of Physics and Technology, Russia (5) Lomonosov Moscow State University, Moscow, Russia//+//**Blinov P.D.** (1), Chernokulsky A.V. (2), Krinitsky M.A. (3, 4), Bugrimov A.V. (5) \\ (1) National Research University - Higher School of Economics, Moscow, Russia, (2) A.M. Obukhov Institute of Atmospheric Physics RAS, Moscow, Russia, (3) P.P. Shirshov Institute of Oceanology RAS, Moscow, Russia (4) Moscow Institute of Physics and Technology, Russia (5) Lomonosov Moscow State University, Moscow, Russia//
  
 This work presents an integrated approach to hail diagnosis using ERA5 reanalysis data and Russian ground observations. We investigate the efficacy of three distinct methodologies: a Convolutional Neural Network (CNN), a Gradient Boosting on Trees (CatBoost) model, and a traditional threshold approach based on the composite WMAXSHEAR index. Interpretability analysis was conducted using SHAP (SHapley Additive Explanations) and reparameterization techniques. A comparative study of the models' performance was carried out. The practical applicability of the proposed methods is further illustrated through a real-case example.  This work presents an integrated approach to hail diagnosis using ERA5 reanalysis data and Russian ground observations. We investigate the efficacy of three distinct methodologies: a Convolutional Neural Network (CNN), a Gradient Boosting on Trees (CatBoost) model, and a traditional threshold approach based on the composite WMAXSHEAR index. Interpretability analysis was conducted using SHAP (SHapley Additive Explanations) and reparameterization techniques. A comparative study of the models' performance was carried out. The practical applicability of the proposed methods is further illustrated through a real-case example. 
Line 225: Line 225:
 [4] National Oceanic and Atmospheric Administration, ACE Real Time Solar Wind, [[https://www.swpc.noaa.gov/products/ace-real-time-solar-wind ]] [4] National Oceanic and Atmospheric Administration, ACE Real Time Solar Wind, [[https://www.swpc.noaa.gov/products/ace-real-time-solar-wind ]]
  
-==== Машинное обучение для статистической детализации характеристик пространственного распределения осадков в Московском регионе ====+==== 96. Машинное обучение для статистической детализации характеристик пространственного распределения осадков в Московском регионе ====
  
 //**Ярынич Юлия Ивановна**(1,2), Варенцов Михаил Иванович(1,2,3), Криницкий Михаил Алексеевич(4,5,1), Степаненко Виктор Михайлович(1,2) \\  //**Ярынич Юлия Ивановна**(1,2), Варенцов Михаил Иванович(1,2,3), Криницкий Михаил Алексеевич(4,5,1), Степаненко Виктор Михайлович(1,2) \\ 
dlcp2025/program.1750792908.txt.gz · Last modified: by admin