Search

High-quality machine learning (ML)-ready datasets play a foundational role in developing new artificial intelligence (AI) models or fine-tuning existing models for scientific applications such as weather and climate analysis. Unfortunately, despite the growing development of new deep learning models for weather and climate, there is a scarcity of curated, pre-processed machine learning (ML)-ready datasets. Curating such high-quality datasets for developing new models is challenging particularly because the modality of the input data varies significantly for different downstream tasks addressing different atmospheric scales (spatial and temporal). Here we introduce WxC-Bench (Weather and Climate Bench), a multi-modal dataset designed to support the development of generalizable AI models for downstream use-cases in weather and climate research. WxC-Bench is designed as a dataset of datasets for developing ML-models for a complex weather and climate system, addressing selected downstream tasks as machine learning phenomenon. WxC-Bench encompasses several atmospheric processes from meso-$\beta$ (20 - 200 km) scale to synoptic scales (2500 km), such as aviation turbulence, hurricane intensity and track monitoring, weather analog search, gravity wave parameterization, and natural language report generation. We provide a comprehensive description of the dataset and also present a technical validation for baseline analysis. The dataset and code to prepare the ML-ready data have been made publicly available on Hugging Face -- https://huggingface.co/datasets/nasa-impact/WxC-Bench

Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which are pre-trained on a large-scale datasets, form the basis for a variety of downstream tasks. These models, especially those based on transformers in vision and language, show exceptional potential for adapting to a wide range of downstream applications. In this paper, we provide our perspective on the criteria for designing an FM for heliophysics and associated challenges and applications using the Solar Dynamics Observatory (SDO) dataset. We believe that this is the first study to design an FM in the domain of heliophysics., Comment: 31 Pages, 12 figures

Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.

Global climate models typically operate at a grid resolution of hundreds of kilometers and fail to resolve atmospheric mesoscale processes, e.g., clouds, precipitation, and gravity waves (GWs). Model representation of these processes and their sources is essential to the global circulation and planetary energy budget, but subgrid scale contributions from these processes are often only approximately represented in models using parameterizations. These parameterizations are subject to approximations and idealizations, which limit their capability and accuracy. The most drastic of these approximations is the "single-column approximation" which completely neglects the horizontal evolution of these processes, resulting in key biases in current climate models. With a focus on atmospheric GWs, we present the first-ever global simulation of atmospheric GW fluxes using machine learning (ML) models trained on the WINDSET dataset to emulate global GW emulation in the atmosphere, as an alternative to traditional single-column parameterizations. Using an Attention U-Net-based architecture trained on globally resolved GW momentum fluxes, we illustrate the importance and effectiveness of global nonlocality, when simulating GWs using data-driven schemes., Comment: International Conference on Machine Learning 2024

Swift J1357.2$-$0933 is a black-hole candidate X-ray transient, which underwent its third outburst in 2019, during which several multi-wavelength observations were carried out.~Here, we report results from the \emph{Neil Gehrels Swift} and \emph{NICER} observatories and radio data from \emph{AMI}.~For the first time,~millihertz quasi-periodic X-ray oscillations with frequencies varying between ${\sim}$~1--5~$\rm{mHz}$ were found in \emph{NICER} observations and a similar feature was also detected in one \emph{Swift}--\textsc{XRT} dataset.~Our spectral analysis indicate that the maximum value of the measured X-ray flux is much lower compared to the peak values observed during the 2011 and 2017 outbursts.~This value is ${\sim}$~100 times lower than found with \emph{MAXI} on MJD~58558 much ($\sim$~68 days) earlier in the outburst, suggesting that the \emph{Swift} and \emph{NICER} fluxes belong to the declining phase of the 2019 outburst.~An additional soft component was detected in the \textsc{XRT} observation with the highest flux level, but at a relatively low $L_{\rm X}$~$\sim$~$3{\times}10^{34}~(d/{\rm 6~kpc)}^2\rm{erg}~\rm{s}^{-1}$, and which we fitted with a disc component at a temperature of $\sim 0.17$~keV.~The optical/UV magnitudes obtained from \emph{Swift}--\textsc{UVOT} showed a correlation with X-ray observations, indicating X-ray reprocessing to be the plausible origin of the optical and UV emission.~However, the source was not significantly detected in the radio band.~There are currently a number of models that could explain this millihertz-frequency X-ray variability; not least of which involves an X-ray component to the curious dips that, so far, have only been observed in the optical., Comment: 14 pages, Accepted for publication in MNRAS

We report results from a study of XTE J1739-285, a transient neutron star low mass X-ray binary observed with AstroSat and NuSTAR during its 2019-2020 outburst. We detected accretion-powered X-ray pulsations at 386 Hz during very short intervals (0.5--1 s) of X-ray flares. These flares were observed during the 2019 observation of XTE J1739-285. During this observation, we also observed a correlation between intensity and hardness ratios, suggesting an increase in hardness with the increase in intensity. Moreover, a thermonuclear X-ray burst detected in our AstroSat observation during the 2020 outburst revealed the presence of coherent burst oscillations at 383 Hz during its decay phase. The frequency drift of 3 Hz during X-ray burst can be explained with r modes. Thus, making XTE J1739-285 belong to a subset of NS-LMXBs which exhibit both nuclear- and accretion-powered pulsations. The power density spectrum created using the AstroSat-LAXPC observations in 2020 showed the presence of a quasi-periodic oscillation at ~ 0.83 Hz. Our X-ray spectroscopy revealed significant changes in the spectra during the 2019 and 2020 outburst. We found a broad iron line emission feature in the X-ray spectrum during the 2020 observation, while this feature was relatively narrow and has a lower equivalent width in 2019,~when the source was accreting at higher rates than 2020., Comment: Accepted for publication in MNRAS, 13 pages

Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or the associated likes using different computational methods. The recent decade has seen a boom in online learning resources, and during the pandemic, there has been an exponential rise of online teaching videos without much quality control. The quality of the content could be improved if the creators could get constructive feedback on their content. Employing an army of domain expert volunteers to provide feedback on the videos might not scale. As a result, there has been a steep rise in developing computational methods to predict a user engagement score that is indicative of some form of possible user engagement, i.e., to what level a user would tend to engage with the content. A drawback in current methods is that they model various features separately, in a cascaded approach, that is prone to error propagation. Besides, most of them do not provide crucial explanations on how the creator could improve their content. In this paper, we have proposed a new unified model, CLUE for the educational domain, which learns from the features extracted from freely available public online teaching videos and provides explainable feedback on the video along with a user engagement score. Given the complexity of the task, our unified framework employs different pre-trained models working together as an ensemble of classifiers. Our model exploits various multi-modal features to model the complexity of language, context agnostic information, textual emotion of the delivered content, animation, speaker's pitch and speech emotions. Under a transfer learning setup, the overall model, in the unified space, is fine-tuned for downstream applications.