Related papers: Self-Supervised ConvLSTM for Fermi Large Area Tele…

One of the scientific goals of the Large Synoptic Survey Telescope (LSST) is to measure the evolution of dark energy by measuring subtle distortions of galaxy shapes due to weak gravitational lensing caused by the evolving dark matter…

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…

The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon forecasting and representation learning. This architecture has…

Graph neural networks have emerged as a powerful tool for learning spatiotemporal interactions. However, conventional approaches often rely on predefined graphs, which may obscure the precise relationships being modeled. Additionally,…

We develop new efficient online algorithms for detecting transient sparse signals in TEM video sequences, by adopting the recently developed framework for sequential detection jointly with online convex optimization [1]. We cast the problem…

We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the…

Real-time traffic prediction from high-fidelity spatiotemporal traffic sensor datasets is an important problem for intelligent transportation systems and sustainability. However, it is challenging due to the complex topological dependencies…

For more than one year the Fermi Large Area Telescope has been surveying the gamma-ray sky from 20 MeV to more than 300 GeV with unprecedented statistics and angular resolution. One of the key science targets of the Fermi mission is diffuse…

In this chapter, we show how to efficiently model high-dimensional extreme peaks-over-threshold events over space in complex non-stationary settings, using extended latent Gaussian Models (LGMs), and how to exploit the fitted model in…

New remote sensing sensors now acquire high spatial and spectral Satellite Image Time Series (SITS) of the world. These series of images are a key component of classification systems that aim at obtaining up-to-date and accurate land cover…

Radio wavelengths offer a unique window into high-energy astrophysical phenomena that may be obscured or too rapidly evolving to be captured at other wavelengths. Leveraging data from the Very Large Array Sky Survey, we perform a systematic…

With large numbers of transients discovered by current and future imaging surveys, machine learning is increasingly applied to light curve and host galaxy properties to select events for follow-up. However, finding rare types of transients…

Over the next decade, we can expect time domain astronomy to flourish at optical and radio wavelengths. In parallel with these efforts, a dedicated transient "machine" operating at higher energies (X-ray band through soft gamma-rays) is…

The nature of scientific and technological data collection is evolving rapidly: data volumes and rates grow exponentially, with increasing complexity and information content, and there has been a transition from static data sets to data…

The Fermi Gamma-ray Space Telescope, a key mission in multiwavelength and multimessenger studies, has been surveying the gamma-ray sky from its low-Earth orbit since 2008. Its two scientific instruments, the Gamma-ray Burst Monitor (GBM)…

Gravitational lensing offers a powerful probe into the properties of dark matter and is crucial to infer cosmological parameters. The Legacy Survey of Space and Time (LSST) is predicted to find O(10^5) gravitational lenses over the next…

Long-term traffic prediction has always been a challenging task due to its dynamic temporal dependencies and complex spatial dependencies. In this paper, we propose a model that combines hybrid Transformer and spatio-temporal…

We derive constraints on dark matter (DM) annihilation cross section and decay lifetime from cross-correlation analyses of the data from Fermi-LAT and weak lensing surveys that cover a wide area of $\sim660$ squared degrees in total. We…

We perform two distinct spatio-spectral reconstructions of the gamma-ray sky in the range of 0.56-316 GeV based on Fermi Large Area Telescope (LAT) data. Both describe the sky brightness to be composed of a diffuse-emission and a…

We investigate a method of model-agnostic anomaly detection through studying jets, collimated sprays of particles produced in high-energy collisions. We train a transformer neural network to encode simulated QCD "event space" dijets into a…