Related papers: Beacon2Science: Enhancing STEREO/HI beacon data wi…
We analyze multi-spacecraft observations associated with the 2012 July 12 Coronal Mass Ejection (CME), covering the source region on the Sun from SDO, stereoscopic imaging observations from STEREO, magnetic field characteristics at…
In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lighting changes, and…
Methane is a potent greenhouse gas, and detecting its leaks early via hyperspectral satellite imagery can help mitigate climate change. Meanwhile, many existing missions operate in manual tasking regimes only, thus missing potential events…
Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In this paper, we propose Clear2Fog (C2F), an end-to-end,…
Tropical cyclones (TCs) pose severe threats to life, infrastructure, and economies in tropical and subtropical regions, underscoring the critical need for accurate and timely forecasts of both track and intensity. Recent advances in…
Climate science studies the structure and dynamics of Earth's climate system and seeks to understand how climate changes over time, where the data is usually stored in the format of time series, recording the climate features, geolocation,…
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local…
We investigate the source eruption, propagation and expansion characteristics, and heliospheric impacts of the 2020 November 29 coronal mass ejection (CME) and associated shock, using remote sensing and in situ observations from multiple…
The breakthrough in Deep Learning neural networks has transformed the use of AI and machine learning technologies for the analysis of very large experimental datasets. These datasets are typically generated by large-scale experimental…
This work aims at the development of signal processing algorithms that can explore the potential of a PICOSEC-MicroMegas detector and offers the ability for online, precise timing. The PICOSEC-MicroMegas detector is a novel gaseous detector…
Weather forecasting is a crucial task for meteorologic research, with direct social and economic impacts. Recently, data-driven weather forecasting models based on deep learning have shown great potential, achieving superior performance…
Accurate detection of inundated water extents during flooding events is crucial in emergency response decisions and aids in recovery efforts. Satellite Remote Sensing data provides a global framework for detecting flooding extents.…
In-situ measurements carried out by spacecraft in radial alignment are critical to advance our knowledge on the evolutionary behavior of coronal mass ejections (CMEs) and their magnetic structures during propagation through interplanetary…
Our knowledge of the properties of Coronal Mass Ejections (CMEs) in the inner heliosphere is constrained by the relative lack of plasma observations between Sun and 1 AU. In this work, we present a comprehensive catalog of 47 CMEs measured…
In this work we performed a polarimetric study of a fast and wide coronal mass ejection (CME) observed on 12 July 2012 by the COR1 and COR2 instruments onboard Solar TErrestrial RElations Observatory (STEREO) mission. The CME source region…
The radial speed of a coronal mass ejection (CME) determines the shock-driving capability of a CME as indicated by the presence of a type II radio burst. Here we report on the April 18, 2014 CME that was associated with a type II radio…
This paper presents enhancements to the SAM2 framework for video object tracking task, addressing challenges such as occlusions, background clutter, and target reappearance. We introduce a hierarchical motion estimation strategy, combining…
We present a concept study of a solar wind forecasting method for Earth, based on persistence modeling from STEREO in-situ measurements combined with multi-viewpoint EUV observational data. By comparing the fractional areas of coronal holes…
The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the \textbf{end-to-end methods}, thanks to deep learning techniques, but they face…
Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD models, manual masking, or per-object adaptation, and still…