Search

Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs trained using domain-focused corpora perform better on specialized tasks. Inspired by this insight, we developed INDUS, a comprehensive suite of LLMs tailored for the closely-related domains of Earth science, biology, physics, heliophysics, planetary sciences and astrophysics, and trained using curated scientific corpora drawn from diverse data sources. The suite of models include: (1) an encoder model trained using domain-specific vocabulary and corpora to address NLP tasks, (2) a contrastive-learning based text embedding model trained using a diverse set of datasets to address information retrieval tasks and (3) smaller versions of these models created using knowledge distillation for applications which have latency or resource constraints. We also created three new scientific benchmark datasets, CLIMATE-CHANGE NER (entity-recognition), NASA-QA (extractive QA) and NASA-IR (IR) to accelerate research in these multi-disciplinary fields. We show that our models outperform both general-purpose (RoBERTa) and domain-specific (SCIBERT) encoders on these new tasks as well as existing tasks in the domains of interest. Furthermore, we demonstrate the use of these models in two industrial settings -- as a retrieval model for large-scale vector search applications and in automatic content tagging systems., Comment: EMNLP 2024 (Industry Track)

The field of Heliophysics has a branding problem. We need an answer to the question: ``What is Heliophysics\?'', the answer to which should clearly and succinctly defines our science in a compelling way that simultaneously introduces a sense of wonder and exploration into our science and our missions. Unfortunately, recent over-reliance on space weather to define our field, as opposed to simply using it as a practical and relatable example of applied Heliophysics science, narrows the scope of what solar and space physics is and diminishes its fundamental importance. Moving forward, our community needs to be bold and unabashed in our definition of Heliophysics and its big questions. We should emphasize the general and fundamental importance and excitement of our science with a new mindset that generalizes and expands the definition of Heliophysics to include new ``frontiers'' of increasing interest to the community. Heliophysics should be unbound from its current confinement to the Sun-Earth connection and expanded to studies of the fundamental nature of space plasma physics across the solar system and greater cosmos. Finally, we need to come together as a community to advance our science by envisioning, prioritizing, and supporting -- with a unified voice -- a set of bold new missions that target compelling science questions - even if they do not explore the traditional Sun- and Earth-centric aspects of Heliophysics science. Such new, large missions to expand the frontiers and scope of Heliophysics science large missions can be the key to galvanizing the public and policymakers to support the overall Heliophysics program.

This review examines complexity science in Heliophysics, describing it not as a discipline, but as a paradigm. In the context of Heliophysics, complexity science is the study of a star, interplanetary environment, magnetosphere, upper and terrestrial atmospheres, and planetary surface as interacting subsystems. Complexity science studies entities in a system (e.g., electrons in an atom, planets in a solar system, individuals in a society) and their interactions, and is the nature of what emerges from these interactions. It is a paradigm that employs systems approaches and is inherently multi- and cross-scale. Heliophysics processes span at least 15 orders of magnitude in space and another 15 in time, and its reaches go well beyond our own solar system and Earth's space environment to touch planetary, exoplanetary, and astrophysical domains. It is an uncommon domain within which to explore complexity science. This review article excavates the lived and living history of complexity science in Heliophysics. It identifies five dimensions of complexity science. It then proceeds in three epochal parts: 1) A pivotal year in the Complexity Heliophysics paradigm: 1996; 2) The transitional years that established foundations of the paradigm (1996-2010); and 3) The emergent literature largely beyond 2010. The history reveals a grand challenge that confronts most physical sciences to understand the research intersection between fundamental science (e.g., complexity science) and applied science (e.g., artificial intelligence and machine learning). A risk science framework is suggested as a way of formulating the challenges in a way that the two converge. The intention is to provide inspiration and guide future research. It will be instructive to Heliophysics researchers, but also to any reader interested in or hoping to advance the frontier of systems and complexity science., Comment: arXiv admin note: text overlap with arXiv:astro-ph/0007086 by other authors

Traditionally, data analysis and theory have been viewed as separate disciplines, each feeding into fundamentally different types of models. Modern deep learning technology is beginning to unify these two disciplines and will produce a new class of predictively powerful space weather models that combine the physical insights gained by data and theory. We call on NASA to invest in the research and infrastructure necessary for the heliophysics' community to take advantage of these advances., Comment: Heliophysics 2050 White Paper

Geomagnetically Induced Currents (GICs) arise from spatio-temporal changes to Earth's magnetic field which arise from the interaction of the solar wind with Earth's magnetosphere, and drive catastrophic destruction to our technologically dependent society. Hence, computational models to forecast GICs globally with large forecast horizon, high spatial resolution and temporal cadence are of increasing importance to perform prompt necessary mitigation. Since GIC data is proprietary, the time variability of horizontal component of the magnetic field perturbation (dB/dt) is used as a proxy for GICs. In this work, we develop a fast, global dB/dt forecasting model, which forecasts 30 minutes into the future using only solar wind measurements as input. The model summarizes 2 hours of solar wind measurement using a Gated Recurrent Unit, and generates forecasts of coefficients which are folded with a spherical harmonic basis to enable global forecasts. When deployed, our model produces results in under a second, and generates global forecasts for horizontal magnetic perturbation components at 1-minute cadence. We evaluate our model across models in literature for two specific storms of 5 August 2011 and 17 March 2015, while having a self-consistent benchmark model set. Our model outperforms, or has consistent performance with state-of-the-practice high time cadence local and low time cadence global models, while also outperforming/having comparable performance with the benchmark models. Such quick inferences at high temporal cadence and arbitrary spatial resolutions may ultimately enable accurate forewarning of dB/dt for any place on Earth, resulting in precautionary measures to be taken in an informed manner., Comment: 23 pages, 8 figures, 5 tables; accepted for publication in AGU: Spaceweather

Solar and Heliosphere physics are areas of remarkable data-driven discoveries. Recent advances in high-cadence, high-resolution multiwavelength observations, growing amounts of data from realistic modeling, and operational needs for uninterrupted science-quality data coverage generate the demand for a solar metadata standardization and overall healthy data infrastructure. This white paper is prepared as an effort of the working group "Uniform Semantics and Syntax of Solar Observations and Events" created within the "Towards Integration of Heliophysics Data, Modeling, and Analysis Tools" EarthCube Research Coordination Network (@HDMIEC RCN), with primary objectives to discuss current advances and identify future needs for the solar research cyberinfrastructure. The white paper summarizes presentations and discussions held during the special working group session at the EarthCube Annual Meeting on June 19th, 2020, as well as community contribution gathered during a series of preceding workshops and subsequent RCN working group sessions. The authors provide examples of the current standing of the solar research cyberinfrastructure, and describe the problems related to current data handling approaches. The list of the top-level recommendations agreed by the authors of the current white paper is presented at the beginning of the paper., Comment: White Paper

We develop multiple Deep Learning (DL) models that advance the state-of-the-art predictions of the global auroral particle precipitation. We use observations from low Earth orbiting spacecraft of the electron energy flux to develop a model that improves global nowcasts (predictions at the time of observation) of the accelerated particles. Multiple Machine Learning (ML) modeling approaches are compared, including a novel multi-task model, models with tail- and distribution-based loss functions, and a spatio-temporally sparse 2D-convolutional model. We detail the data preparation process as well as the model development that will be illustrative for many similar time series global regression problems in space weather and across domains. Our ML improvements are three-fold: 1) loss function engineering; 2) multi-task learning; and 3) transforming the task from time series prediction to spatio-temporal prediction. Notably, the ML models improve prediction of the extreme events, historically obstinate to accurate specification and indicate that increased expressive capacity provided by ML innovation can address grand challenges in the science of space weather., Comment: Lower resolution

Modeling and forecasting the solar wind-driven global magnetic field perturbations is an open challenge. Current approaches depend on simulations of computationally demanding models like the Magnetohydrodynamics (MHD) model or sampling spatially and temporally through sparse ground-based stations (SuperMAG). In this paper, we develop a Deep Learning model that forecasts in Spherical Harmonics space 2, replacing reliance on MHD models and providing global coverage at one minute cadence, improving over the current state-of-the-art which relies on feature engineering. We evaluate the performance in SuperMAG dataset (improved by 14.53%) and MHD simulations (improved by 24.35%). Additionally, we evaluate the extrapolation performance of the spherical harmonics reconstruction based on sparse ground-based stations (SuperMAG), showing that spherical harmonics can reliably reconstruct the global magnetic field as evaluated on MHD simulation., Comment: Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada

The electric power grid is a critical societal resource connecting multiple infrastructural domains such as agriculture, transportation, and manufacturing. The electrical grid as an infrastructure is shaped by human activity and public policy in terms of demand and supply requirements. Further, the grid is subject to changes and stresses due to solar weather, climate, hydrology, and ecology. The emerging interconnected and complex network dependencies make such interactions increasingly dynamic causing potentially large swings, thus presenting new challenges to manage the coupled human-natural system. This paper provides a survey of models and methods that seek to explore the significant interconnected impact of the electric power grid and interdependent domains. We also provide relevant critical risk indicators (CRIs) across diverse domains that may influence electric power grid risks, including climate, ecology, hydrology, finance, space weather, and agriculture. We discuss the convergence of indicators from individual domains to explore possible systemic risk, i.e., holistic risk arising from cross-domains interconnections. Our study provides an important first step towards data-driven analysis and predictive modeling of risks in the coupled interconnected systems. Further, we propose a compositional approach to risk assessment that incorporates diverse domain expertise and information, data science, and computer science to identify domain-specific CRIs and their union in systemic risk indicators.

We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable database of particle precipitation data that includes 51 satellite years of Defense Meteorological Satellite Program (DMSP) observations temporally aligned with solar wind and geomagnetic activity data. The new total electron energy flux particle precipitation nowcast model, a neural network called PrecipNet, takes advantage of increased expressive power afforded by ML approaches to appropriately utilize diverse information from the solar wind and geomagnetic activity and, importantly, their time histories. With a more capable representation of the organizing parameters and the target electron energy flux observations, PrecipNet achieves a >50% reduction in errors from a current state-of-the-art model oval variation, assessment, tracking, intensity, and online nowcasting (OVATION Prime), better captures the dynamic changes of the auroral flux, and provides evidence that it can capably reconstruct mesoscale phenomena. We create and apply a new framework for space weather model evaluation that culminates previous guidance from across the solar-terrestrial research community. The research approach and results are representative of the "new frontier" of space weather research at the intersection of traditional and data science-driven discovery and provides a foundation for future efforts., Comment: Published in Space Weather Journal

The interactions between the Sun, interplanetary space, near Earth space environment, the Earth's surface, and the power grid are, perhaps unsurprisingly, very complicated. The study of such requires the collaboration between many different organizations spanning the public and private sectors. Thus, an important component of studying space weather is the integration and analysis of heterogeneous information. As such, we have developed a modular ontology to drive the core of the data integration and serve the needs of a highly interdisciplinary community. This paper presents our preliminary modular ontology, for space weather research, as well as demonstrate a method for adaptation to a particular use-case, through the use of existential rules and explicit typing.

The authors of this white paper met on 16-17 January 2020 at the New Jersey Institute of Technology, Newark, NJ, for a 2-day workshop that brought together a group of heliophysicists, data providers, expert modelers, and computer/data scientists. Their objective was to discuss critical developments and prospects of the application of machine and/or deep learning techniques for data analysis, modeling and forecasting in Heliophysics, and to shape a strategy for further developments in the field. The workshop combined a set of plenary sessions featuring invited introductory talks interleaved with a set of open discussion sessions. The outcome of the discussion is encapsulated in this white paper that also features a top-level list of recommendations agreed by participants., Comment: Workshop Report

The space physics community continues to grow and become both more interdisciplinary and more intertwined with commercial and government operations. This has created a need for a framework to easily identify what projects can be used for specific applications and how close the tool is to routine autonomous or on-demand implementation and operation. We propose the Application Usability Level (AUL) framework and publicizing AULs to help the community quantify the progress of successful applications, metrics, and validation efforts. This framework will also aid the scientific community by supplying the type of information needed to build off of previously published work and publicizing the applications and requirements needed by the user communities. In this paper, we define the AUL framework, outline the milestones required for progression to higher AULs, and provide example projects utilizing the AUL framework. This work has been completed as part of the activities of the Assessment of Understanding and Quantifying Progress working group which is part of the International Forum for Space Weather Capabilities Assessment.

UNKNOWN

UNKNOWN