On July 18, 2024, CCF TF ushered in its 140th event with the theme of "AI for Science". The event was planned and presented by CCF TF algorithm and AI SIG, and invited Chen Kai, senior R&D engineer from Baidu, Guo Zhendong, assistant professor of Xi'an Jiaotong University, Meng Xuhui of Huazhong University of Science and Technology, and Sun Zhenxu, associate researcher of the Institute of Mechanics of the Chinese Academy of Sciences. The content shared was wonderful, the discussion was lively, and the feedback from the audience was positive. The event was broadcast live online through the Tencent Meeting platform and CCF video account "China Computer Federation", attracting the participation of many professionals. This article will review the highlights and insights from the event.
CCF TF
The expert reports related to CCF TF activities are included in the CCF Digital Library [TF Album], welcome to press and hold to identify and watch the wonderful sharing. This event report will also be included in the near future, welcome to review!
As an emerging branch in the field of artificial intelligence, AI for Science is gradually showing its strong potential and wide application prospects. With the continuous progress and accumulation of high-performance computing, deep learning algorithms, and scientific big data, AI for Science has achieved remarkable results in many disciplines such as physics, chemistry, biology, and materials science.
In recent years, domestic and foreign research institutions, universities and technology companies have increased their investment in this field, and are committed to developing more advanced AI models and algorithms to promote in-depth innovation in scientific research. The application of AI for Science not only accelerates the process of scientific experiments, but also improves the accuracy and efficiency of data analysis, providing scientists with new research perspectives and methods.
Baidu Paddle - Artificial Intelligence Technology Innovation and Scientific Computing Exploration
Chen Kai, a senior R&D engineer from Baidu, gave a report entitled "Baidu Paddle - Artificial Intelligence Technology Innovation and Scientific Computing Exploration". The report provides a comprehensive introduction to Baidu's PaddlePaddle deep learning platform and its wide range of applications in the field of AI scientific computing. Baidu has promoted the application of AI in scientific computing through the multi-dimensional layout of the paddle platform in the chip layer, framework layer, model layer and application layer, especially in the fields of fluid computing, weather forecasting and biological computing. At the same time, Baidu PaddlePaddle continues to promote the progress and development of AI scientific computing by optimizing technology, supporting open-source tools, and scientific research collaboration.
Research on Intelligent Flow Field Prediction Method Based on Physical Information Augmentation
Guo Zhendong, an assistant professor from Xi'an Jiaotong University, gave a presentation entitled "Research on Intelligent Flow Field Prediction Method Enhanced by Physical Information". The report focuses on the intelligent design optimization of turbomachinery, and focuses on the intelligent flow field prediction method enhanced by physical information. By embedding physical knowledge, fusing multi-source data, and using reduced-order models, the generalization ability and prediction accuracy of the model are improved. The research covers modeling from 2D to 3D, demonstrating the great potential of AI for complex engineering problems.
《Deep learning for multi-fidelity data fusion and uncertainty quantification》
Professor Meng Xuhui from Huazhong University of Science and Technology gave a presentation entitled "Deep learning for multi-fidelity data fusion and uncertainty quantification". The report focuses on multi-fidelity data fusion and uncertainty quantification, and focuses on the methods to improve model accuracy by fusing data with different precision when high-quality data is scarce. He demonstrated the ability of neural networks to approximate arbitrary continuous functions, discussed the influence of data noise and incompleteness on prediction uncertainty, and proposed an optimization strategy based on uncertainty quantification, which effectively improved the prediction accuracy.
Assimilation of Wind Field Data Based on Physical Information Neural Network
Sun Zhenxu, an associate researcher from the Institute of Mechanics of the Chinese Academy of Sciences, gave a report entitled "Assimilation of Wind Field Data Based on Physics-based Neural Networks". The report focuses on physics-based neural network wind field data assimilation techniques, focusing on how to improve the accuracy of wind field predictions by fusing multiple measurements and physical equations. In this study, a multivariate data assimilation framework fused with PIN was constructed to successfully realize the reconstruction of high-resolution wind farms, and the influence of different data types and locations on the assimilation accuracy was discussed, which provided a new technical path for wind power plant environment perception.
AI for Science is changing with each passing day, and I hope this event can bring inspiration and thinking to everyone and promote the development of technology.
Upcoming Events
| Instalments | date | SIG | topic | form |
| TF148 | September 12 | Algorithms and AI | Research and application of large models of education | online |
About CCF TF
Founded in June 2017, CCF TF Tech Frontier aims to provide a top-level communication platform for engineers, better serve computer professionals in the business world, help professional and technical professionals in the business community develop their careers, achieve normalized cooperation and development by building a platform, and promote technical exchanges between enterprises, academia and enterprises. At present, 12 SIGs (Special Interest Groups) have been established, including knowledge graph, data science, intelligent manufacturing, architecture, security, intelligent equipment and interaction, digital transformation and enterprise architecture, algorithm and AI, intelligent front-end, engineer culture, R&D efficiency, and quality engineering, to provide rich technical front-line content sharing.
Join the CCF
Join CCF members to enjoy more value-added activities and make a good investment in your own technology growth.
Click on the link to learn more about membership benefits:
CCF Individual Membership Benefits CCF Corporate Membership Benefits
Identify or scan the QR code to join
Welcome to pay attention to the official account of CCFTF and CCF Business Headquarters, and the excitement will be opened one after another!
Follow the CCFTF for TF activity information
Pay attention to the CCF business headquarters to book a meeting venue at a discount
CCF Recommended
【Articles】
- The 2024 TF event is officially launched! Unlock the annual plan with one click