Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “knowledge discovery”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 901 records · Page 50

Initial report from the ICFA Neutrino Panel

The discovery of neutrino oscillations implies that neutrinos have mass and that the flavour eigenstates mix. Non-zero neutrino masses require new physics beyond the Standard Model. Revealing the physics behind neutrino masses and mixing is among the highest priorities for particle physics in the twenty-first century. Measurements of the parameters that govern neutrino oscillations will have a profound impact on our understanding of particle physics, astrophysics and cosmology. Such a breadth of impact justifies a far-reaching experimental programme by which the properties of the neutrino that are presently unknown are determined, the three-neutrino-mixing picture is tested and the properties of the neutrino are measured with a precision sufficient to allow the physics that explains these properties to be understood. Accelerator-based neutrino-oscillation experiments are an essential component of this programme as they are the only way in which oscillations between all known flavours can be studied precisely. The accelerator-based neutrino-oscillation programme is international in both scope and engagement. The approved programme will improve our knowledge of the mixing angles and the mass-squared differences and may be able to determine the neutrino mass hierarchy. In the medium term, the Long-baseline Neutrino Experiment (LBNE) and the Tokai (J-PARC) to Hyper-Kamiokande experiment offer complementary approaches to searching for the violation of the matter-anti-matter symmetry in neutrino oscillations. For these experiments to realise their full potential coordinated programmes of hadro-production and neutrino-nucleus cross-section measurements are essential. A design study of an alternative wide-hand beam facility is underway: the Long-baseline Neutrino Observatory (LBNO) study will report by the end of 2014. New concepts such as the implementation of a neutrino beam on the European Spallation Source (ESSnuSB) and the use of muon decay-at-rest to search for the matter-anti-matter asymmetry (Daedalus) are also being studied. The Neutrino Factory, in which electron- and muon-neutrino beams are produced from the decay of muons confined within a storage ring, has been shown to offer the ultimate sensitivity and precision. The staged implementation of the facility has been studied. The attractive hrst stage, “nuSTORM”, has the potential to make detailed and precise studies of electron- and muon-neutrino-nucleus scattering and to make exquisitely sensitive searches for sterile neutrinos. A small number of measurements do not fit the elegant three-neutrino-mixing model. These measurements can be interpreted as evidence for new “sterile neutrino” states. If confirmed, these measurements will revolutionise the held. An experimental programme is underway to investigate these anomalies. It is important that these anomalies are addressed. Short-baseline contributions to this programme should have clear synergy with the long-baseline programme. This report presents the conclusions drawn by the Panel from three regional “Town Meetings” that took place between November 2013 and February 2014. The Panel recognises that to maximise the discovery potential of the accelerator-based neutrino-oscillation programme it will be essential to exploit the infrastructures that exist at CERN, FNAL and J-PARC and the expertise and resources that reside in laboratories and institutes around the world.

Cao, J.↗

Genome-Wide Transcription Factor DNA Binding Sites and Gene Regulatory Networks in Clostridium thermocellum

Clostridium thermocellum is a thermophilic bacterium recognized for its natural ability to effectively deconstruct cellulosic biomass. While there is a large body of studies on the genetic engineering of this bacterium and its physiology to-date, there is limited knowledge in the transcriptional regulation in this organism and thermophilic bacteria in general. The study herein is the first report of a large-scale application of DNA-affinity purification sequencing (DAP-seq) to transcription factors (TFs) from a bacterium. We applied DAP-seq to > 90 TFs in C. thermocellum and detected genome-wide binding sites for 11 of them. We then compiled and aligned DNA binding sequences from these TFs to deduce the primary DNA-binding sequence motifs for each TF. These binding motifs are further validated with electrophoretic mobility shift assay (EMSA) and are used to identify individual TFs’ regulatory targets in C. thermocellum . Our results led to the discovery of novel, uncharacterized TFs as well as homologues of previously studied TFs including RexA-, LexA-, and LacI-type TFs. We then used these data to reconstruct gene regulatory networks for the 11 TFs individually, which resulted in a global network encompassing the TFs with some interconnections. As gene regulation governs and constrains how bacteria behave, our findings shed light on the roles of TFs delineated by their regulons, and potentially provides a means to enable rational, advanced genetic engineering of C. thermocellum and other organisms alike toward a desired phenotype.

59 BASIC BIOLOGICAL SCIENCES↗

Genome-wide Transcription Factor DNA Binding Sites and Gene Regulatory Networks in Clostridium thermocellum

Clostridium thermocellum is a thermophilic bacterium recognized for its natural ability to effectively deconstruct cellulosic biomass. While there is a large body of studies on the genetic engineering of this bacterium and its physiology to-date, there is limited knowledge in the transcriptional regulation in this organism and thermophilic bacteria in general. The study herein is the first report of a high-throughput application of DNA-affinity purification sequencing (DAP-seq) to transcription factors (TFs) from a thermophile. We applied DAP-seq to >90 TFs in C. thermocellum and detected genome-wide binding sites for 11 of them. We then compiled and aligned DNA binding sequences from these TFs to deduce the primary DNA-binding sequence motifs for each TF. These binding motifs are further validated with electrophoretic mobility shift assay (EMSA) and are used to identify individual TFs’ regulatory targets in C. thermocellum. Our results led to the discovery of novel, uncharacterized TFs as well as homologues of previously studied TFs including RexA-, LexA- and LacI-type TFs. We then used these data to reconstruct gene regulatory networks for the 11 TFs individually, which resulted in a global network encompassing the TFs with some interconnections. As gene regulation governs and constrains how bacteria behave, our findings shed light on the roles of TFs delineated by their regulons, and potentially provides a means to enable rational, advanced genetic engineering of C. thermocellum and other organisms alike towards a desired phenotype.

09 BIOMASS FUELS↗

VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities

Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an x-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instruments and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex—a synthetic extension to the cognition of scientists—may radically transform scientific practice and discovery.

36 MATERIALS SCIENCE↗

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗

Modified Einstein's gravity as a possible missing link between sub- and super-Chandrasekhar type Ia supernovae

We explore the effect of modification to Einstein's gravity in white dwarfs for the first time in the literature, to the best of our knowledge. This leads to significantly sub- and super-Chandrasekhar limiting masses of white dwarfs, determined by a single model parameter. On the other hand, type Ia supernovae (SNeIa), a key to unravel the evolutionary history of the universe, are believed to be triggered in white dwarfs having mass close to the Chandrasekhar limit. However, observations of several peculiar, under- and over-luminous SNeIa argue for exploding masses widely different from this limit. We argue that explosions of the modified gravity induced sub- and super-Chandrasekhar limiting mass white dwarfs result in under- and over-luminous SNeIa respectively, thus unifying these two apparently disjoint sub-classes and, hence, serving as a missing link. Our discovery raises two fundamental questions. Is the Chandrasekhar limit unique? Is Einstein's gravity the ultimate theory for understanding astronomical phenomena? Both the answers appear to be no!.

79 ASTRONOMY AND ASTROPHYSICS↗

Magnetic molecular orbitals in MnSi

A large body of knowledge about magnetism is attained from models of interacting spins, which usually reside on magnetic ions. Proposals beyond the ionic picture are uncommon and seldom verified by direct observations in conjunction with microscopic theory. Here, using inelastic neutron scattering to study the itinerant near-ferromagnet MnSi, we find that the system’s fundamental magnetic units are interconnected, extended molecular orbitals consisting of three Mn atoms each rather than individual Mn atoms. This result is further corroborated by magnetic Wannier orbitals obtained by ab initio calculations. It contrasts the ionic picture with a concrete example and presents an unexplored regime of the spin waves where the wavelength is comparable to the spatial extent of the molecular orbitals. Our discovery brings important insights into not only the magnetism of MnSi but also a broad range of magnetic quantum materials where structural symmetry, electron itinerancy, and correlations act in concert.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Organizational Support for the 3rd Summer Institute on Complex Plasmas, July 30 – August 8, 2012

This grant provided partial funds for American graduate students to attend the 3rd Graduate Summer Institute on Complex Plasmas, which was held from July 30 to August 8, 2012 at Seton Hall University in South Orange, New Jersey. The Graduate Summer Institute is a topical series of instructional workshops held bi-annually on the emerging field of complex plasmas that is jointly organized through a collaboration between American and German-European Union plasmas researchers. This specialized program brings together many of the world's leading researchers in the specialized area of complex plasmas, who freely provide instructional lectures and tutorials on the most recent research and discoveries done in this branch of plasma science. The partial funds provided by this grant helped support the travel and accommodation expenses of the participating American students and tutorial instructors. Partial funds further supported the travel and accommodation of three renown American plasma researchers that provided educational tutorials to the thirty-eight participating students from the United States, Europe, and Asia. The organized program afforded a unique opportunity for the participating American graduate students to learn about and engage more deeply in an area of plasma science that is not studied in any of the graduate educational curriculums provided by universities in the United States of America. The educational experience offered by this program provided the necessary knowledge needed by future American plasma researchers to keep the national plasma research effort on the cutting-edge and keep the national plasma community as a global leader.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Automation of Vulnerability and Patch Management: Information Extraction, Association, and Optimization

Vulnerability and patch management is an integral part of a robust cybersecurity program, yet it grows increasingly complex due to the sheer amount of data that must be analyzed. Particularly in Operational Technology (OT) environments, analysis must be done manually because of the lack of automated solutions. Additionally, there are many steps in this process, from the initial discovery of the vulnerability to the implementation of its remediation, and each step in the process requires different data in order to be performed effectively. In this work, we provide approaches and strategies to assist operators in industrial or OT environments throughout the vulnerability management cycle. Security advisories provide key information about mitigation strategies, or actions that can be taken when a patch is unavailable or cannot be installed. Details of these strategies are not shared in public vulnerability databases and must be found manually. We approach this problem by designing a solution to automatically identify that information within vendor security advisories and retrieve it for operator use. We start with an approach that requires domain-specific knowledge of certain frequently-seen reference websites. Next, an approach that can work on an arbitrary website but relies on certain keywords. Finally, an approach that uses Natural Language Processing (NLP) methods and does not require specific knowledge or keywords. Each of these approaches is more general than its predecessor; we demonstrate high accuracy for all approaches Advisories also often contain details of affected products in non-standard or natural language formats. While this information can be easily understood when read by an operator, the non-standard format acts as a barrier to effective automation. We provide an approach for the first step in this process: identifying vendors in security advisories and mapping them to a standard framework for representing digital assets and software products. We evaluate five established string similarity algorithms, plus one of our own design that combines string similarity and information theory, on the task of mapping vendors to their corresponding entries in the Common Platform Enumeration (CPE) repository. Our results show that our proposed metric outperforms all others. Due to the constraints on time, finances, and personnel for organizations, Large Language Models (LLMs) may seem like attractive opportunities for security operators to speed up information gathering; however, it is still not clear whether LLMs can handle vulnerability management tasks well. To answer this question, we perform an empirical study of LLMs’ ability to provide consistent, accurate information about vulnerabilities in order to guide organizations in their adoption of LLMs. We observe poor performance for all models tested, suggesting that these models are not well-suited to the consistent retrieval of accurate vulnerability information. Finally, once vulnerabilities have been identified and any additional information has been obtained, operators must decide which remediation actions to implement based on their available resources. This already-complex problem becomes even more so when we consider that a vulnerability may have multiple avenues for remediation. We formulate this scenario as two knapsack problems and provide solutions, which we then compare against several existing strategies for vulnerability prioritization seen in real operational environments.

McClanahan, Kylie↗

Collaborative research: Dynamics of electrostatic solitary waves and their effects on current layers

The project has accomplished the following achievements including the goals outlined in the original proposal. Generation and measurements of Debye-scale electron holes in laboratory: We have generated by beam injections electron solitary waves in the LAPD experiments. The measurements were made possible by the fabrication of the state-of-the-art microprobes at UCLA to measure Debye-scale electric fields [Chiang et al., 2011]. We obtained a result that challenged the state of knowledge about electron hole generation. We found that the electron holes were not due to two-stream instability, but generated by a current-driven instability that also generated whistler-mode waves [Lefebvre et al., 2011, 2010b]. Most of the grant supported a young research scientist Bertrand Lefebvre who led the dissemination of the laboratory experimental results. In addition to two publications, our work relevant to the laboratory experiments on electron holes has resulted in 7 invited talks [Chen, 2007, 2009; Pickett et al., 2009a; Lefebvre et al., 2010a; Pickett et al., 2010; Chen et al., 2011c, b] (including those given by the co-I Jolene Pickett) and 2 contributed talks [Lefebvre et al., 2009b, a]. Discovery of elecctron phase-space-hole structure in the reconnection electron layer: Our theoretical analyses and simulations under this project led to the discovery of an inversion electric field layer whose phase-space signature is an electron hole within the electron diffusion layer in 2D anti-parallel reconnection [Chen et al., 2011a]. We carried out particle tracing studies to understand the electron orbits that result in the phase-space hole structure. Most importantly, we showed that the current density in the electron layer is limited in collisionless reconnection with negligible guide field by the cyclotron turning of meandering electrons. Comparison of electrostatic solitary waves in current layers observed by Cluster and in LAPD: We compared the ESWs observed in a supersubstorm by the Cluster spacecraft and those measured in LAPD. One of the similarities in the characteristics of ESWs observed in space and in LAPD is that the time duration tends to be approximately the inverse of the electron plasma frequency [Pickett et al., 2009b]. Discovery of suprathermal electron bursts inside a series of magnetic islands: Our effort in examining the roles of ESWs in reconnection current layers resulted in the serendipitous discovery that was published in Nature Physics. In earth’s magnetosphere, we observed through the measurements from the four Cluster spacecraft, a series of magnetic islands and suprathermal electron bursts within the islands. The islands were identified to be effectively acceleration sites for electrons [Chen et al., 2008, 2009].

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

The Importance of Earth Observations and Data Collaboration within Environmental Intelligence Supporting Arctic Research

Within the IARPC Collaboration Team activities of 2016, Arctic in-situ and remote earth observations advanced topics such as :1) exploring the role for new and innovative autonomous observing technologies in the Arctic; 2) advancing catalytic national and international community based observing efforts in support of the National Strategy for the Arctic Region; and 3) enhancing the use of discovery tools for observing system collaboration such as the U.S. National Oceanic and Atmospheric Administration (NOAA) Arctic Environmental Response Management Application (ERMA) and the U.S. National Aeronautics and Space Administration (NASA) Arctic Collaborative Environment (ACE) project geo reference visualization decision support and exploitation internet based tools. Critical to the success of these earth observations for both in-situ and remote systems is the emerging of new and innovative data collection technologies and comprehensive modeling as well as enhanced communications and cyber infrastructure capabilities which effectively assimilate and dissemination many environmental intelligence products in a timely manner. The Arctic Collaborative Environment (ACE) project is well positioned to greatly enhance user capabilities for accessing, organizing, visualizing, sharing and producing collaborative knowledge for the Arctic.

Casas, Joseph↗

Episodic hydrocarbon charge in tight Mississippian reservoirs of Central Oklahoma, USA: Insights from oil inclusion geochemistry

The unforeseen discovery of substantial hydrocarbons in ultra-tight Mississippian reservoirs in Oklahoma testifies to the complexity of the hydrocarbon charge across the flanks of the Nemaha Uplift. Based on crude oil and fluid-inclusion chemistry, the hydrocarbons at the western side of the Nemaha Uplift consist of highly-mature, thermally-cracked and less-mature uncracked hydrocarbons (0.50–1.4% calculated vitrinite reflectance, R c ). The oils are less mature on the eastern flank of the structure (0.5–0.7% R c ). Based on distributions of biomarkers and higher diamondoid (composed of three adamantane cages or more) distributions, the hydrocarbons entrapped within reservoir fluid-inclusions are sourced from the Woodford Shale and also from Mississippian carbonates. To our knowledge, this is the first work to describe oil correlations using diamondoids inside fluid inclusions. Petroleum compositions in the ultra-tight Mississippian reservoirs are highly variable, which highlights the need for a thorough assessment of mechanisms controlling charge. By integrating oil and fluid inclusion geochemistry and fluid-inclusion microthermometry with basin modeling, we show that the primary controls are: (1) proximity to the source-rock kitchen(s), (2) episodic charging from Permian through Cretaceous time, and (3) mixing.

58 GEOSCIENCES↗

OPTD: Out-of-Pile Transient Database

The DOE Advanced Reactor Technology program has supported knowledge preservation efforts to recover and preserve fuel data from the US sodium cooled fast reactor (SFR) program. Efforts have focused on establishing databases of experimental data generated during the Integral Fast Reactor program (at EBR-II, FFTF, and TREAT) as well as during related out-of-pile examinations of the fuel irradiated at EBR-II. The information in these databases is essential to support further development and licensing activities for advanced fast reactor designs. OPTD, a newly-created database of out-of-pile furnace transient tests on metallic fuel, includes records of 62 tests on irradiated fuel pins conducted in furnace apparatuses constructed in the Alpha-Gamma Hot Cell Facility at ANL. Record discovery is ongoing, and at present, the database includes hundreds of documents describing these tests and related results. Access is currently available to Department of Energy researchers and can be extended to members of industry and the public as the content is approved for distribution. This report describes the out-of-pile furnace testing program, the content available in the database, and the structure of the web-accessible interface.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Optimization techniques in self-similar compressible flow

We investigate the one-dimensional (1D) inviscid compressible flow equations for an ideal gas through the lens of optimization techniques. It is the case that, to our knowledge, optimization analysis applied to the so-called “linear velocity” solutions of the Euler compressible flow equations has not been previously conducted. Through both gradient-based and variational techniques, new variants of well-studied flow scenarios, i.e., self-similar, 1D, linear velocity solution class to idealized inviscid compressible flow equations, are determined, as encoded in both the kinematic and thermodynamic properties of this self-similar solution class. With the kinematics of the said solutions being driven by a self-similar “scale radius” and the thermodynamics being driven separately through the appearance of an arbitrary function, a myriad of new solution classes is possible. Acting as a guide to more realistic physical circumstances as well as discovery, it is the hope that the presented cases serve as the framework for future investigations into the intersection of self-similarity and optimization techniques. Fields of study that may find this work to be of interest include aerodynamic design, flow control, inertial confinement fusion, physics-informed neural networks, and other related areas of interest.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Discovery of novel plant interaction determinants from the genomes of 163 root nodule bacteria

Root nodule bacteria (RNB) or “rhizobia” are a type of plant growth promoting bacteria, typified by their ability to fix nitrogen for their plant host, fixing nearly 65% of the nitrogen currently utilized in sustainable agricultural production of legume crops and pastures. In this study, we sequenced the genomes of 110 RNB from diverse hosts and biogeographical regions, and undertook a global exploration of all available RNB genera with the aim of identifying novel genetic determinants of symbiotic association and plant growth promotion. Specifically, we performed a subtractive comparative analysis with non-RNB genomes, employed relevant transcriptomic data, and leveraged phylogenetic distribution patterns and sequence signatures based on known precepts of symbioticand host-microbe interactions. A total of 184 protein families were delineated, including known factors for nodulation and nitrogen fixation, and candidates with previously unexplored functions, for which a role in host-interaction, -regulation, biocontrol, and more, could be posited. Lastly, these analyses expand our knowledge of the RNB purview and provide novel targets for strain improvement in the ultimate quest to enhance plant productivity and agricultural sustainability.

59 BASIC BIOLOGICAL SCIENCES↗

Leveraging unlabeled SEM datasets with self-supervised learning for enhanced particle segmentation

Scanning Electron Microscopes (SEMs) are widely used in experimental science laboratories, often requiring cumbersome and repetitive user analysis. Automating SEM image analysis processes is highly desirable to address this challenge. In particle sample analysis, Machine Learning (ML) has emerged as the most effective approach for particle segmentation. However, the time-intensive process of manually annotating thousands of SEM images limits the applicability of supervised learning approaches. Self-Supervised Learning (SSL) offers a promising alternative by enabling knowledge extraction from raw, unlabeled data. This study presents a framework for evaluating SSL techniques in SEM image analysis, focusing on novel methods leveraging the ConvNeXtV2 architecture for particle detection. A dataset comprising 25,000 SEM images is curated to benchmark these proposed SSL methods. The results demonstrate that ConvNeXtV2 models, with varying parameter counts, consistently outperform other techniques in particle detection across different length scales, achieving up to a 34% reduction in relative error compared to established SSL methods. Furthermore, an ablation study explores the relationship between dataset size and SSL performance, providing actionable insights for practitioners regarding model selection and resource efficiency. This research advances the integration of SSL into autonomous analysis pipelines and supports its application in accelerating materials science discovery.

Rettenberger, Luca↗

RAG for FLAG: AI Assistance for a Physics Code

Artificial intelligence (AI) has quickly become an important tool in scientific research, where significant efforts are underway to develop tools that will expedite the research process. One area of particular impact is scientific software, which can be particularly complex, and therefore time consuming to learn and use effectively. AI assistants are increasingly helping to streamline the process by performing tasks such as interactively answering user questions or suggesting solutions. Los Alamos National Laboratory (LANL) develops several advanced scientific codes, such as FLAG, which can be used to run multiphysics simulations. With this study, our goal was to develop an AI assistant for FLAG that could help make the process of understanding the software and running physics simulations more efficient. To develop an AI assistant for FLAG, we used a method called retrieval-augmented generation (RAG), which is a technique that uses information from relevant data sources to enhance the accuracy of large language models (LLMs). We used the FLAG user manual and other FLAG documentation as the knowledge base for the RAG system. When a user provides a query, RAG retrieves relevant sections from the knowledge base in response, then uses those excerpts to generate grounded and contextually rich answers. We found that our AI assistant was able to provide context aware answers and source references to user queries. To evaluate performance, we developed a set of 40 benchmark questions and compared the accuracy of the responses to those of two standard LLMs without retrieval. Our AI assistant significantly outperformed the standard LLMs at answering FLAG-related questions, with an 82.5% accuracy rate, compared to 47.5% for both of the standard LLMs. This has the potential to make the process of learning and using FLAG much easier, especially for new users. Ultimately, it supports LANL’s broader mission by empowering scientists and engineers to focus more on discovery and analysis rather than on navigating complex software systems.

97 MATHEMATICS AND COMPUTING↗

Coevolution of Machine Learning and Process-Based Modelling to Revolutionize Earth and Environmental Sciences: A Perspective

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.

Saman Razavi↗