Search

Superresolution (SR) aims to increase the resolution of images by recovering detail. Compared to standard interpolation, deep learning-based approaches learn features and their relationships to leverage prior knowledge of what low-resolution patterns look like in higher resolution. Deep neural networks can also perform image cross-calibration by learning the systematic properties of the target images. While SR for natural images aims to create perceptually convincing results, SR of scientific data requires careful quantitative evaluation. In this work, we demonstrate that deep learning can increase the resolution and calibrate solar imagers belonging to different instrumental generations. We convert solar magnetic field images taken by the Michelson Doppler Imager (resolution ∼2″ pixel−1; space based) and the Global Oscillation Network Group (resolution ∼2.″5 pixel−1; ground based) to the characteristics of the Helioseismic and Magnetic Imager (resolution ∼0.″5 pixel−1; space based). We also establish a set of performance measurements to benchmark deep-learning-based SR and calibration for scientific applications.

In the domain of space science, numerous ground-based and space-borne data of various phenomena have been accumulating rapidly, making analysis and scientific interpretation challenging. However, recent trends in the application of artificial intelligence (AI) have been shown to be promising in the extraction of information or knowledge discovery from these extensive data sets. Coincidentally, preparing these data for use as inputs to the AI algorithms, referred to as AI-readiness, is one of the outstanding challenges in leveraging AI in space science. Preparation of AI-ready data includes, among other aspects: 1) collection (accessing and downloading) of appropriate data representing the various physical parameters associated with the phenomena under study from different repositories; 2) addressing data formats such as conversion from one format to another, data gaps, quality flags and labeling; 3) standardizing metadata and keywords in accordance with NASA archive requirements or other defined standards; 4) processing of raw data such as data normalization, detrending, and data modeling; and 5) documentation of technical aspects such as processing steps, operational assumptions, uncertainties, and instrument profiles. Making all existing data AI-ready within a decade is impractical and data from future missions and investigations exacerbates this. This reveals the urgency to set the standards and start implementing them now. This article presents our perspective on the AI-readiness of space science data and mitigation strategies including definition of AI-readiness for AI applications; prioritization of data sets, storage, and accessibility; and identifying the responsible entity (agencies, private sector, or funded individuals) to undertake the task.

We present a new model for the probability that the disturbance storm time (Dst) index exceeds −100 nT, with a lead time between 1 and 3 days. Dst provides essential information about the strength of the ring current around the Earth caused by the protons and electrons from the solar wind, and it is routinely used as a proxy for geomagnetic storms. The model is developed using an ensemble of Convolutional Neural Networks that are trained using Solar and Heliospheric Observatory (SoHO) images (Michelson Doppler Imager, Extreme ultraviolet Imaging Telescope, and Large Angle and Spectrometric Coronagraph). The relationship between the SoHO images and the solar wind has been investigated by many researchers, but these studies have not explicitly considered using SoHO images to predict the Dst index. This work presents a novel methodology to train the individual models and to learn the optimal ensemble weights iteratively, by using a customized class-balanced mean square error (CB-MSE) loss function tied to a least-squares based ensemble. The proposed model can predict the probability that Dst < −100 nT 24 hr ahead with a True Skill Statistic (TSS) of 0.62 and Matthews Correlation Coefficient (MCC) of 0.37. The weighted TSS and MCC is 0.68 and 0.47, respectively. An additional validation during non-Earth-directed CME periods is also conducted which yields a good TSS and MCC score.

High-energy-density physics is the field of physics concerned with studying matter at extremely high temperatures and densities. Such conditions produce highly nonlinear plasmas, in which several phenomena that can normally be treated independently of one another become strongly coupled. The study of these plasmas is important for our understanding of astrophysics, nuclear fusion and fundamental physics—however, the nonlinearities and strong couplings present in these extreme physical systems makes them very difficult to understand theoretically or to optimize experimentally. Here we argue that machine learning models and data-driven methods are in the process of reshaping our exploration of these extreme systems that have hitherto proved far too nonlinear for human researchers. From a fundamental perspective, our understanding can be improved by the way in which machine learning models can rapidly discover complex interactions in large datasets. From a practical point of view, the newest generation of extreme physics facilities can perform experiments multiple times a second (as opposed to approximately daily), thus moving away from human-based control towards automatic control based on real-time interpretation of diagnostic data and updates of the physics model. To make the most of these emerging opportunities, we suggest proposals for the community in terms of research design, training, best practice and support for synthetic diagnostics and data analysis.

This report documents ideas for improving the field of machine learning, which arose from discussions at the ML Retrospectives workshop at NeurIPS 2019. The goal of the report is to disseminate these ideas more broadly, and in turn encourage continuing discussion about how the field could improve along these axes. We focus on topics that were most discussed at the workshop: incentives for encouraging alternate forms of scholarship, re-structuring the review process, participation from academia and industry, and how we might better train computer scientists as scientists. Videos from the workshop can be accessed at https://slideslive.com/neurips/west-114-115-retrospectives-a-venue-for-selfreflection-in-ml-research

Over the past decades of NASA’s inner solar system exploration, data obtained from the Moon alone accounts for ~76%. Most of the lunar orbital spacecraft of the past and present carried imaging cameras and spectrometers (including multispectral and hyperspectral payloads), as well as a large variety of other passive and active instruments. For example, NASA’s Lunar Reconnaissance Orbiter (LRO) has been operating for more than 10 years, providing us with ~1206 TB of lunar data which amounts to ~99.5% of the total data contributed by NASA built instruments. Given recent advances in instrument and communication capabilities, the amount of data returned from spacecraft is expected to keep rising quickly. The white paper focus on potential components of AI and ML that could help to accelerate the future exploration of the Moon and other planetary bodies. The white paper highlights on selected AI/ML-based approaches for lunar and planetary surface science and exploration, the need for open-source availability of training, validation, and testing datasets for AI-ML based approaches, and need for opportunities to further bridge the gap between industry and academia for advancing AI-ML based research in lunar and planetary science and exploration.

Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties are crucial. To address this issue we propose a Bayesian framework that decomposes uncertainties into epistemic and aleatoric uncertainties. We test the validity of our approach by super-resolving images of the Sun's magnetic field and by generating maps measuring the range of possible high resolution explanations compatible with a given low resolution magnetogram.

As modern society becomes increasingly dependent on technology, space weather events will have a farther-reaching impact than ever before. For nearly 10 years, NASA's Solar Dynamics Observatory (SDO) has continuously monitored the Sun, however, the SDO-era coincides with the weakest solar cycle of the last century: over the last 40 years, there have been nearly 500 X-class solar flares—around 10 times the number of events observed by SDO alone. It is also clear that there is no single observational survey with sufficient time coverage to enable an effective deep learning space weather forecasting application. Crucially, over the past 40 years, numerous observatories have monitored the Sun's magnetic field. However, cross calibrating magnetograms is a complex and non-trivial endeavour as the relationship between observed pixels is strongly affected by a wide range of systematics. Here we present a deep learning application that can convert magnetograms to a target survey while preserving the features and systematics of the target survey. We will first present our approach for upscaling and cross-calibrating images obtained by the Michelson Doppler Imager (MDI; on-board the Solar and Heliospheric Observatory, SOHO), to the resolution of the Helioseismic and Magnetic Imager (SDO/HMI). We will discuss the physics-based metrics, deep learning architectures, and the lessons learned along the way. This work was performed at NASA’s Frontier Development Laboratory (FDL), a public-private partnership to apply AI techniques to accelerate space science discovery and exploration.

Breakthroughs in our understanding of physical phenomena have traditionally followed improvements in instrumentation. Studies of the magnetic field of the Sun, and its influence on the solar dynamo and space weather events, have benefited from improvements in resolution and measurement frequency of new instruments. However, in order to fully understand the solar cycle, high-quality data across time-scales longer than the typical lifespan of a solar instrument are required. At the moment, discrepancies between measurement surveys prevent the combined use of all available data. In this work, we show that machine learning can help bridge the gap between measurement surveys by learning to \textbf{super-resolve} low-resolution magnetic field images and \textbf{translate} between characteristics of contemporary instruments in orbit. We also introduce the notion of physics-based metrics and losses for super-resolution to preserve underlying physics and constrain the solution space of possible super-resolution outputs.

Deep learning has proven extremely successful both in classification and regression problems, especially when it is trained on very large datasets. In the space weather context, despite the unarguably large amount of data at our disposal, it remains an open question whether historical datasets contain enough information to build a predictive deep learning system. In this work, we use multi-wavelength solar images from SOHO (Solar and Heliospheric Observatory) as inputs to a deep convolutional neural network, to predict solar wind parameters observed at L1, 3 - 5 days ahead.

Many disciplines, from human genetics and oncology to plant breeding, microbiology and virology, commonly face the challenge of analyzing rapidly increasing numbers of genomes. In case of Homo sapiens, the number of sequenced genomes will approach hundreds of thousands in the next few years. Simply scaling up established bioinformatics pipelines will not be sufficient for leveraging the full potential of such rich genomic data sets. Instead, novel, qualitatively different Computational methods and paradigms are needed.We will witness the rapid extension of Computational pan-genomics, a new sub-area of research in Computational biology. In this article, we generalize existing definitions and understand a pangenome as any collection of genomic sequences to be analyzed jointly or to be used as a reference. We examine already available approaches to construct and use pan-genomes, discuss the potential benefits of future technologies and methodologies and review open challenges from the vantage point of the above-mentioned biological disciplines. As a prominent example for a Computational paradigm shift, we particularly highlight the transition from the representation of reference genomes as strings to representations a

Contains fulltext : 190288.pdf (publisher's version ) (Open Access)

Cancer affects millions of people worldwide. With the advent of novel DNA sequencing technologies,whole genome sequencing (WGS) is becoming an integral part of cancer diagnostics that can potentially enable tailored treatments of individual patients. To alleviate these problems,a user-friendly, portable and extendable SV calling workflow, sv-callers developed, that includes four state-of-the-art tools to detect SVs in cancer genomes using on-premises HPC systems. The workflow's parallel execution environment enables to scale from a single computer to high-performance compute clusters with minimal effort. The workflow supports SV analysis in either germline or somatic mode, and requires a list of (paired) WGS samples including a reference genome as input. Users may change the workflow parameters and/or software versions using the YAML configuration files. We performed SV analyses on single and paired (tumor/normal) WGS samples, and report on the results obtained using different academic HPC systems.

Deep learning has proven extremely successful both in classification and regression problems, especially when it is trained on very large datasets. In the Space Weather context, despite the unarguably large amount of data at our disposal, it remains an open question whether historical datasets contain enough information to build a predictive deep learning system. In this work, we use multi-wavelength solar images from both SOHO (Solar and Heliospheric Observatory) and SDO (Solar Dynamics Observatory) as inputs to a convolutional neural network, to predict solar wind parameters observed at L1, 24 hours ahead. This work is part of the AIDA H2020 (http://www.aida-space.eu) project funded by the European Commission (EC).

Many disciplines, from human genetics and oncology to plant breeding, microbiology and virology, commonly face the challenge of analyzing rapidly increasing numbers of genomes. In case of Homo sapiens, the number of sequenced genomes will approach hundreds of thousands in the next few years. Simply scaling up established bioinformatics pipelines will not be sufficient for leveraging the full potential of such rich genomic data sets. Instead, novel, qualitatively different computational methods and paradigms are needed. We will witness the rapid extension of computational pan-genomics, a new sub-area of research in computational biology. In this article, we generalize existing definitions and understand a pan-genome as any collection of genomic sequences to be analyzed jointly or to be used as a reference. We examine already available approaches to construct and use pan-genomes, discuss the potential benefits of future technologies and methodologies and review open challenges from the vantage point of the above-mentioned biological disciplines. As a prominent example for a computational paradigm shift, we particularly highlight the transition from the representation of reference genomes as strings to representations as graphs. We outline how this and other challenges from different application domains translate into common computational problems, point out relevant bioinformatics techniques and identify open problems in computer science. With this review, we aim to increase awareness that a joint approach to computational pan-genomics can help address many of the problems currently faced in various domains.

Contains fulltext : 130179pub.pdf (publisher's version ) (Open Access) Contains fulltext : 130179pre.pdf (preprint version ) (Open Access)

Contains fulltext : 130186pre.pdf (preprint version ) (Open Access)