相关论文: Application and interpretation of deep learning fo…
Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study…
Solar eruptions are the most powerful drivers of space weather. To understand their cause and nature, it is crucial to know how the coronal magnetic field evolves before eruption. Here we study the formation process of a relatively…
Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual…
The solar magnetized corona is responsible for various manifestations with a space weather impact, such as flares, coronal mass ejections (CMEs) and, naturally, the solar wind. Modeling the corona's dynamics and evolution is therefore…
Convolutional neural networks (CNNs) can potentially provide powerful tools for classifying and identifying patterns in climate and environmental data. However, because of the inherent complexities of such data, which are often…
We present morphological classifications of $\sim$27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs)…
As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the…
We present several methods towards construction of precursors, which show great promise towards early predictions, of solar flare events in this paper. A data pre-processing pipeline is built to extract useful data from multiple sources,…
Recent observations demonstrated that emerging flux regions, which constitute the early stage of solar active regions, consist of emergence of numerous small-scale magnetic elements. They in turn interact, merge, and form mature sunspots.…
We report multi-wavelength ultraviolet observations taken with the IRIS satellite, concerning the emergence phase in the upper chromosphere and transition region of an emerging flux region (EFR) embedded in the pre-existing field of active…
Observing 3D magnetic fields, including orientation and strength, within the interstellar medium is vital but notoriously difficult. However, recent advances in our understanding of anisotropic magnetohydrodynamic (MHD) turbulence…
Seismic intensity prediction from early or initial seismic waves received by a few seismic stations can enhance Earthquake Early Warning (EEW) systems, particularly in ground motion-based approaches like PLUM. While many operational EEW…
This paper investigates the application of the latest machine learning technique deep neural networks for classifying road surface conditions (RSC) based on images from smartphones. Traditional machine learning techniques such as support…
We present a detailed investigation on the evolution of observed net vertical current using a time series of vector magnetograms of the active region (AR) NOAA 11158 obtained from Helioseismic Magnetic Imager. We also discuss the relation…
While deep neural networks take loose inspiration from neuroscience, it is an open question how seriously to take the analogies between artificial deep networks and biological neuronal systems. Interestingly, recent work has shown that deep…
Recent efforts have shown machine learning to be useful for the prediction of nonlinear fluid dynamics. Predictive accuracy is often a central motivation for employing neural networks, but the pattern recognition central to the network…
We establish the largest eruptive/confined flare database to date and analyze 322 flares of \emph{GOES} class M1.0 and larger that occurred during 2010$-$2019, i.e., almost spanning the entire solar cycle 24. We find that the total unsigned…
Magnetic field emerges at the surface of the Sun as sunspots and active regions. This process generates a poloidal magnetic field from a rising toroidal flux tube, it is a crucial but poorly understood aspect of the solar dynamo. The…
Magnetic flux emergence and decay in the Sun span from days to months. However, their tracking is typically limited to about half a solar rotation when relying on single-vantage-point observations. Combining observations from both the…
We report multi-wavelength ultraviolet observations taken with the IRIS satellite, concerning the emergence phase in the upper chromosphere and transition region of an emerging flux region (EFR) embedded in the unipolar plage of active…