betbet

Support Kyushu U 日本語 ENGLISH Prospective students Current students Companies & researchers Alumni Crisis Management News Events About Office of the President University Overview Kyushu U Connect Fast Facts Public Relations Featured Academics Schools & Centers The Global University Project Alumni Resources Donation Activities and Initiatives Future Plans University Facilities Academics Faculty of Arts and Science Schools Distinctive Education Programs Double Degree Programs Student Exchange Programs Short-term Study Programs The 3 Policies: Diploma, Curriculum, and Admissions Course Registration Academic Calendar Admissions Undergraduate Admissions Graduate Admissions Tuition, Fees & Scholarships Information for International Students Campus Life Facilities and Healthcare Extracurricular / Student-Led Activities Careers & Employment Procedures Contact Information for Consultations Research Research at Kyushu University Academic Staff Educational and Research Activities Database Research Activity Support Industry-University -Government Collaboration Support Research Centers and Projects Framework to Support Collaborated Research Research Integrity 日本語 ENGLISH News Topics Features Research Close-Up Notices Important Research Results Humanities & Social Sciences Art & Design Life & Health Math & Data Physics & Chemistry Materials Technology Environment & Sustainability Events Event Calendar Categories Public Seminar Lecture, etc. Exhibition Other Place Ito Campus Hakozaki Satellite Hospital Campus Chikushi Campus Ohashi Campus Beppu Campus Off Campus About Office of the President Message from the President Kyushu University VISION 2030 Biography Honorary Doctorates History of the Presidency Kyushu U Connect University Overview Organization Charter Presidential Selection Regulations and Policies History Future Plans Mid-Term Objectives and Plans Public Relations Publications Press Releases Promotional Videos University logomark List of Social Media Accounts Virtual Backgrounds Virtual Backgrounds (Archive) Featured Academics Campus Relocation Ceremony to Commemorate Completion of Ito Campus University Facilities Alumni Resources Alumni Associations Donation Donations to Schools, Graduate Schools, and Researchers, etc. Activities and Initiatives Promoting Diversity, Equity, and Inclusion QS-APPLE 2019 Response to the 2016 Kumamoto Earthquake Schools & Centers Research Institutes Centers for Common Education and Research Organizations and Offices Hospitals Libraries Museums Others Academics Faculty of Arts and Science Schools Educational and Research Course The 3 Policies Academic Calendar Course Registration Curriculum Registration / Syllabuses Distinctive Education Programs Program for Leading Graduate Schools Admissions Undergraduate Admissions Enrolling in Undergraduate School Applicants with Disabilities Graduate Admissions Applicants with Disabilities Enrolling as a Research Student Tuition, Fees, & Scholarships Tuition and Fees Enrollment Fee Exemption/Deferment and Tuition Fee Exemption for Newly-enrolled Students Scholarships Payment of tuition Tuition Fee Exemption, Enrollment Fee Exemption/Deferment Financial Aid Double Degree Programs Student Exchange Programs Campus Life Facilities and Healthcare Student Facilities Dormitories Healthcare Personal Accident Insurance for Students/ Liability Insurance Careers & Employment New Information How to use Job and Career Support System Career Consulting Job Hunting Support for International Students Recruitment of International Students Extracurricular / Student-Led Activities Procedures Certificates National Pension System for Students Contact Information for Consultations One-Stop Consultation Service Research Research at Kyushu University Humanities and Social Sciences Art and Design Life and Health Math and Data Physics and Chemistry Materials Technology Environment and Sustainability Research Close-Up Research Centers and Projects Next-Generation Fuel Cell Research Center (NEXT-FC) Research Activity Support On-campus Consultation Research Strategy Promotion Support for Research Funding and Grants Support for Other Research Activities Industry - University - Government Collaboration Support Technological Consultation Intellectual Property Management and Use Joint Research/Sponsored Research Comprehensive Collaboration Joint Research Department Research Integrity Framework to Support Collaborative Research International ･Prospective students ･Current students ･Companies & researchers ･Alumni ･Support Kyushu U Crisis Management ･Contact Us ･Visit ･Career ･Disclaimer & Copyright ･Privacy Policy ･Sitemap 研究成果 Research Results TOP News Research Results Artificial Intelligence (AI) helps to detect precursors of tropical cyclones Artificial Intelligence (AI) helps to detect precursors of tropical cyclones 2018.12.19 Research ResultsMath & Data A research group led by Dr. Daisuke Matsuoka from the Center for Earth Information Science and Technology of the Japan Agency for Marine-Earth Science and Technology (JAMSTEC) and Professor Seiichi Uchida at Kyushu University has successfully presented a deep learning*¹ approach for identifying tropical cyclones and their precursors. In a conventional approach, prediction of tropical cyclones such as typhoons and hurricanes has usually been carried out with model-driven methods*² using climate models based on observational data and monitoring of cloud development from satellite data. In this study, the research team has applied a data-driven approach*³ to detect the precursors of a developing tropical cyclone from a vast amount of simulation data using deep learning and examined the detection accuracy. To ensure accurate identification in deep learning, a vast amount of data exceeding several thousand examples per category is required. So, the scientists first applied a tropical cyclone tracking algorithm to 20 years of climate simulation data generated by NICAM (Nonhydrostatic ICosahedral Atmospheric Model)*⁴ and created 50,000 cloud images of precursors of tropical cyclones and developing tropical cyclones. They also created 10 training data sets from the aforementioned 50,000 cloud images combined with 1 million images of clouds that did not develop into tropical cyclones, thereby making a total of 1,050,000 images. A total of 10 types of classifiers with different characteristics were formed from machine learning using a deep convolutional neural network*5. As a result of building an ensemble classifier for making final judgment by comprehensive evaluation of the results of the 10 different types of classifiers, it was found that precursors of tropical cyclones using climate simulation data from NICAM can be detected with higher accuracy. To predict actual tropical cyclones before they occur however, it is still necessary to further improve the training method and data, and ensure the same level of detection capability for cloud images from satellite observation and/or real-time simulation data with data assimilation. By adopting AI technology with deep learning in this field, it is expected to lead to a new development of big data analysis for marine and earth science with combination of data-driven and model-driven approaches. This work was supported by JST, PRESTO Grant Number JPMJPR1777, JSPS KAKENHI Grant Number 16K13885, 26700010, and 17K13010. The above results were published in Progress in Earth and Planetary Science issued by Japan Geoscience Union on December 19, 2018. Figure 1. Examples of cloud images of tropical cyclones and precursors (outgoing longwave radiation) created by applying a tropical cyclone tracking algorithm to 20 years of NICAM simulation data. Each image shows 1,000 km2 (64 × 64 grid). Figure 2. An ensemble classifier using deep convolutional neural networks (CNN). (a) In the training phase, 10 different CNN learn using different training data. (b) In the predicting phase, a single input image is classified into one of two classes by 10 different classifiers, and the weighted average is taken as the final probability of existence. In areas where the existence probability exceeds a previously assigned threshold, a tropical cyclone or its precursor is considered to be detected. Figure 3. Example of detection results using the ensemble classifier on untrained data. Areas (1,000 km2) with cloud cover of 30−95% are targeted for prediction, and are indicated by a white box. Areas targeted for prediction where the probability of existence of a tropical cyclone or precursor is predicted to be 100% (all 10 classifiers predict that a tropical cyclone or precursor exists) are indicated by a red box. The blue and red dots indicate the center points of correct answers for tropical cyclones and precursors, respectively, which are already evident from the tropical cyclone tracking algorithm. For more information on this research, see Journal Reference Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model, ,Progress in Earth and Planetary Science, 10.1186/s40645-018-0245-y Research-related inquiriesSeiichi Uchida, Professor, Faculty of Information Science and Electrical EngineeringJAMSTEC【External link】 Tweet Back to the list TOP News Research Results Artificial Intelligence (AI) helps to detect precursors of tropical cyclones Research Results Humanities & Social Sciences Art & Design Life & Health Math & Data Physics & Chemistry Materials Technology Environment & Sustainability Year 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 九州大学Kyushu University744 Motooka Nishi-ku Fukuoka 819-0395 Contact Us | Visit Career Academics Disclaimer & Copyright Admissions News Privacy Policy Research Events Sitemap Campus Life About COPYRIGHT © KYUSHU UNIVERSITY. ALL RIGHTS RESERVED.