Xianzhi Ao

Automatic Detection and Segmentation of Coronal Mass Ejections in LASCO C3 Images

Yunshi Zeng, Xianzhi Ao, Bingxian Luo, Jingjing Wang et autres

Abstract Coronal mass ejections (CMEs) are the key drivers of both nonrecurrent geomagnetic storms and gradual solar energetic particle events. A near real-time capability of automatic CME detection from coronagraph images is crucial for operational space weather forecasts, particularly solar proton events …

cn (code pays fourni par la source)

The New Geomagnetic Monitoring Network in China: Insights From the 2024 Mother's Day Superstorm

Jing Wang, Yan Yue, Bingxian LUO, C. M. Liu et autres

Abstract China has established a ground‐based network system, that is the Chinese Meridian Project (CMP), to continuously monitor the geomagnetic field. The superstorm in May 2024 was analyzed using the CMP data. The negative peak of the horizontal geomagnetic field ( B …

cn (code pays fourni par la source)

Multi-parameter Prediction of Solar Wind Based on Deep Learning

Zhixu GAO, Yanhong CHEN, Xianzhi Ao, Jingjing WANG et autres

太阳风中高速等离子体流与地球磁层相互作用会引发地磁暴等空间天气事件, 进而影响现代技术系统的稳定运行. 利用具有片段嵌入和交叉注意力机制的深度学习模型TimeXer来挖掘太阳风参数间的复杂依赖关系, 预测未来72 h的4个太阳风参数. 实验结果表明, TimeXer仅利用历史太阳风数据及时间信息, 即可对太阳风速度、动压、质子密度、质子温度分别实现47.65 km·s–1, 1.00 nPa, 3.13 cm–3, 4.49×104 K的预测绝对误差, 与现有的传统及深度学习方法相比, 该模型性能更优, 即使在磁暴期间, 也能较准确地捕获各太阳风参数的整体变化趋势; 基于太阳风参数依赖关系的联合建模预测优于单参数预测; 对模型交叉注意力权重的分析可反映各输入参数对不同太阳风参数预测的相对重要性.

ISNet: Decomposed Dynamic Spatio‐Temporal Neural Network for Ionospheric Scintillation Forecasts

Yanhong Chen, Xianzhi Ao, Fulu Yue, Hong Chen et autres

Abstract Accurate prediction of ionospheric scintillation is essential for ensuring the reliability of spaceborne and ground‐based radio wave technology infrastructures, including but not limited to navigation and communication systems. In this study, we propose a deep learning‐based Ionospheric Scintillation Network (ISNet), which …

cn (code pays fourni par la source)

Forecasting of the Geomagnetic Activity for the Next 3 Days Utilizing Neural Networks Based on Parameters Related to Large‐Scale Structures of the Solar Corona

Tingyu Wang, Bingxian Luo, Jingjing Wang, Xianzhi Ao et autres

Abstract With the increasing number of large constellations, it is crucial to accurately predict satellite positions and movements using upper atmosphere models driven by geomagnetic indices. Machine learning (ML) can quickly provide geomagnetic index predictions. However, previous research using ML to forecast …

cn (code pays fourni par la source)

RESEARCH ON INFLUENCING FACTORS OF FLOW RATE OF NEW TYPE PUMP

Yangyang Li, Shuaiwei LI, Xianzhi Ao, Jia Ma

By cutting a straw at a fixed point and shaping it into a triangular simple water pump, the influence of its geometry and other related parameters on the pumping speed was studied. In the research process, we analyzed the effects of half …

cn (code pays fourni par la source)

Molecular dynamics study on the evaporation of ethane, propane and their mixed fluids at the copper substrate

Jintao Wu, Liang Fu, Xianzhi Ao, Xie Wang

The organic Rankine cycle can harvest the cold energy from liquefied natural gas by using non-azeotropic working fluids. The phase transition is one of the important processes in the thermodynamics cycles. In this paper, the interfacial evaporation characteristics of ethane, propane, and …

cn (code pays fourni par la source)

Knowledge‐Informed Deep Neural Networks for Solar Flare Forecasting

Ming Li, Yanmei Cui, Bingxian Luo, Xianzhi Ao et autres

Abstract Recently, although various deep learning techniques have been applied to building space weather prediction models, a large amount of relevant prior knowledge of solar eruptions and magnetic properties is ignored during the model development. By integrating prior knowledge in flare production …

cn (code pays fourni par la source)

Impacts of CMEs on Earth Based on Logistic Regression and Recommendation Algorithm

Yurong Shi, Jingjing Wang, Yanhong Chen, Siqing Liu et autres

Coronal mass ejections (CMEs) are one of the major disturbance sources of space weather. Therefore, it is of great significance to determine whether CMEs will reach the earth. Utilizing the method of logistic regression, we first calculate and analyze the correlation coefficients …

cn (code pays fourni par la source)

Ensemble Numerical Simulations of Realistic SEP Events and the Inspiration for Space Weather Awareness

Chenxi Du, Xianzhi Ao, Bingxian Luo, Jingjing Wang et autres

Abstract The solar energetic particle (SEP) event is a kind of hazardous space weather phenomena, so its quantitative forecast is of great importance from the aspect of space environmental situation awareness. We present here a set of SEP forecast tools, which consists …

cn, us (code pays fourni par la source)

Parameters Derived from the SDO/HMI Vector Magnetic Field Data: Potential to Improve Machine-learning-based Solar Flare Prediction Models

Jingjing Wang, Siqing Liu, Xianzhi Ao, Yuhang Zhang et autres

Abstract It is well established that solar flares and coronal mass ejections (CMEs) are powered by the free magnetic energy stored in volumetric electric currents in the corona, predominantly in active regions (ARs). Much effort has been made to search for eruption-related …

cn, gb, us (code pays fourni par la source)

Deep Learning for Automatic Recognition of Magnetic Type in Sunspot Groups

Yuanhui Fang, Yanmei Cui, Xianzhi Ao

Sunspots are darker areas on the Sun’s photosphere and most of solar eruptions occur in complex sunspot groups. The Mount Wilson classification scheme describes the spatial distribution of magnetic polarities in sunspot groups, which plays an important role in forecasting solar flares. …

cn (code pays fourni par la source)