SEARCH · Search NASA
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.
This white paper primarily addresses Focal Area 2: “Predictive modeling through the use of AI techniques and AI-derived model components”. A secondary focus of the white paper is Focal Area 3: “Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods”.
Abstract Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency’s local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.
Focal Area(s): The focus area is predictive modeling through the use of AI techniques and AI-derived model components with a particular emphasis on extreme weather in Atmospheric Science and power outages and shortages in Energy Science. Science Challenge: Predicting weather extremes (e.g., heavy precipitation, strong wind, and large hailstones), and weather-related power system outages and shortages can mitigate economic losses, save lives, support renewables integration, and improve power system resiliency. However, currently, the poor reliability and large uncertainty associated with the weather extreme prediction in the current climate models make the problem intractable. The key challenges are: (1) physical factors like green-house gases (GHGs), aerosols, and land use and land cover (LULC) can significantly impact extreme storms, but the understanding of these impacts is limited, particularly globally; (2) the convective permitting resolutions needed to model severe convective storms and their impacts are computationally prohibitive with global climate models (GCMs); (3) interactions between weather extremes and power system outages are complex and subject to great uncertainty. Current outage prediction models are short lead (~ 3 days), which do not allow for long-time planning of energy production and distribution. Moreover, we have limited capacity to predict weather events leading to sustained shortages in a renewable-energy-dominated power system. These challenges drive motivation for mechanistic understanding and reliable and efficient predictive modeling of extremes and their impacts from the sub-seasonal to long term projections.
Predictive modeling of watershed to river basin scale biogeochemistry through the use of AI techniques and AI-derived model components and the use of AI to design a prediction system comprised of a hierarchy of multi-fidelity models, including AI driven model/component/parameterization selection.
It is widely hoped that artificial intelligence will boost data-driven surrogate models in science and engineering. However, fundamental spatial aspects of AI surrogate models remain under-studied. We investigate the ability of neural-network surrogate models to predict solutions to PDEs under variable boundary values. We do not wish to retrain the model when the boundary values change but to make them inputs to the model and infer the solution of the PDE under those boundary conditions. Such a capability is essential to making AI-based surrogate models practically useful. While simple feedforward networks are used for one-dimensional (1D) Poisson equation, an encoder-decoder architecture with a tensor-product layer is developed for the two-dimensional Poisson equation posed on a rectangular domain. We show that it is indeed possible to infer solutions to PDEs from variable boundary data using neural networks in this relatively simple setting, and point to future directions.
Artificial intelligence (AI) generative models, such as generative adversarial networks (GANs), variational autoencoders, and normalizing flows, have been widely used and studied as efficient alternatives for traditional scientific simulations. However, they have several drawbacks, including training instability and inability to cover the entire data distribution, especially for regions where data are rare. This is particularly challenging for whole-event, full-detector simulations in high-energy heavy-ion experiments, such as sPHENIX at the Relativistic Heavy Ion Collider and Large Hadron Collider experiments, where thousands of particles are produced per event and interact with the detector. This work investigates the effectiveness of denoising diffusion probabilistic models (DDPMs) as an AI-based generative surrogate model for the sPHENIX experiment that includes the heavy-ion event generation and response of the entire calorimeter stack. DDPM performance in sPHENIX simulation data is compared with a popular rival, GANs. Results show that both DDPMs and GANs can reproduce the data distribution where the examples are abundant (low-to-medium calorimeter energies). Nonetheless, DDPMs significantly outperform GANs, especially in high-energy regions where data are rare. Additionally, DDPMs exhibit superior stability compared to GANs. The results are consistent between both central and peripheral centrality heavy-ion collision events. Moreover, DDPMs offer a substantial speedup of approximately a factor of 100 compared to the traditional Geant4 simulation method.
We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.
With the advent of large language models (LLMs), in both the open source and proprietary domains, attention is turning to how to exploit such artificial intelligence (AI) systems in assisting complex scientific tasks, such as material synthesis, characterization, analysis and discovery. Here, we explore the utility of LLMs, particularly ChatGPT4, in combination with application program interfaces (APIs) in tasks of experimental design, programming workflows, and data analysis in scanning probe microscopy, using both in-house developed APIs and APIs given by a commercial vendor for instrument control. We find that the LLM can be especially useful in converting ideations of experimental workflows to executable code on microscope APIs. Beyond code generation, we find that the GPT4 is capable of analyzing microscopy images in a generic sense. At the same time, we find that GPT4 suffers from an inability to extend beyond basic analyses for more in-depth technical experimental design. We argue that an LLM specifically fine-tuned for individual scientific domains can potentially be a better language interface for converting scientific ideations from human experts to executable workflows. Such a synergy between human expertise and LLM efficiency in experimentation can open new doors for accelerating scientific research, enabling effective experimental protocols sharing in the scientific community.
Non-invasive seismic imaging has the potential to cost-effectively evaluate large volumes of subsurface material to inform geotechnical site investigation. However, seismic imaging using full waveform inversion (FWI) requires significant computational time and is dependent on an initial starting model. As a result, FWI has not yet been widely adopted into geotechnical practice. Previous efforts, on relatively simple two-layered models, indicate that data-driven artificial intelligence (AI) models may be as effective as FWI at predicting 2D images of shear wave velocity (V s ). Furthermore, the AI model predictions can be made almost instantaneously after data acquisition and do not require an initial starting model. We examine the generality of these findings by developing a new AI model for subsurface seismic imaging, whereby we make several notable contributions. First, we architect a multimodal AI model that combines time- and frequency-domain representations of the seismic wavefield to predict a 50 m by 20 m subsurface image of V s . Second, we developed a new diverse dataset of 100,000 images with their corresponding seismic wavefields to train the AI model. Third, we propose four physics-informed data augmentations for data-driven seismic imaging. Fourth, we develop two prediction consistency tests to evaluate the model’s performance when the true subsurface is unknown. Our final model, which has been made publicly available, is capable of predicting a subsurface V s image from a single seismic wavefield with an average, mean absolute percent error (MAPE) of 24 %. The predictive model is applied to a field dataset and shown to be consistent with local geology and shear-wave refraction measurements from the same location.
Abstract The modeling of multi-scale and multi-physics complex systems typically involves the use of scientific software that can optimally leverage extreme scale computing. Despite major developments in recent years, these simulations continue to be computationally intensive and time consuming. Here we explore the use of AI to accelerate the modeling of complex systems at a fraction of the computational cost of classical methods, and present the first application of physics informed neural operators (NOs) (PINOs) to model 2D incompressible magnetohydrodynamics (MHD) simulations. Our AI models incorporate tensor Fourier NOs as their backbone, which we implemented with the TensorLY package. Our results indicate that PINOs can accurately capture the physics of MHD simulations that describe laminar flows with Reynolds numbers Re ⩽ 250 . We also explore the applicability of our AI surrogates for turbulent flows, and discuss a variety of methodologies that may be incorporated in future work to create AI models that provide a computationally efficient and high fidelity description of MHD simulations for a broad range of Reynolds numbers. The scientific software developed in this project is released with this manuscript.
Focal Area(s): This whitepaper is responsive to focal area (1) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, unsupervised learning (including deep learning), and hardware-related efforts involving AI (e.g., edge computing). We discuss Artificial Intelligence and Machine Learning (AI/ML) enabled integration of real-time data into the extreme event modeling workflow to improve the predictive capabilities of these models, and deliver real-time feedback to remote sensors, including software and data engineering challenges.
Focal Area(s): Primary focal areas are: predictive modeling through the use of AI-derived model components; advanced methods including network design/optimization/deep learning. Science Challenge: The atmospheric, ocean and ice dynamics components of the Energy Exascale Earth System Model (E3SM) are governed by Partial Differential Equations (PDEs) and significant efforts have been made during the last decades to develop such computational models. Here we propose to fundamentally improve these PDE-based codes by enhancing them with Machine Learning (ML) sub-models for complex, poorly understood physical processes in the context of ice sheet modeling. We propose to train these models with a novel approach that allows the assimilation of the different sources of data available (direct/indirect observations and possibly simulation data), improving on existing simplified models. We also highlight computational challenges originating from the coexistence of PDE-based and ML-based models.
As large language models continue to push the bounds of AI model size, they are also being trained on unprecedented volumes of data. While individual hospitals are estimated to produce petabytes of data per year, only a small fraction is currently being used for developing AI models. Additionally, with such data resources available, healthcare is well-positioned to benefit from the current trends in AI. Moreover, the inherently multi-modal and longitudinal nature of clinical data – from omics to imaging to unstructured notes – provides a fertile ground for the development and application of cutting-edge architectures like foundation models.
Focal Areas: Advanced computational methods that integrate AI, physics, and observations to provide predictive landscape hydrological modeling over large areas (regional, continental, worldwide) while incorporating increasingly available high-resolution data from drones, lidar and satellite. Science Challenge: Landscape data is available at finer scales than can be used in physics-based hydrological (PBH) models for regional or continental terrestrial water modeling. Thus, we throw away observable detail to achieve computability. We argue that integration of AI with PBH models and observed data can be used to provide upscaling for predictive models that are computable, retain physical conservation properties, and represent the fine-scale features that affect complex flow physics through both natural and urban environments. Developing such next-generation capabilities requires outside-the-box thinking that melds the different approaches of AI modeling, PBH modeling, and observation across multiple scales from local drones to satellites.
The incorporation of Artificial Intelligence (AI) models into various optimization systems is on the rise. However, addressing complex urban and environmental management challenges often demands deep expertise in domain science and informatics. This expertise is essential for deriving data and simulation-driven insights that support informed decision-making. In this context, we investigate the potential of leveraging the pre-trained Large Language Models (LLMs) to create knowledge representations for supporting operations research. By adopting ChatGPT-4 API as the reasoning core, we outline an applied workflow that encompasses natural language processing, Methontology-based prompt tuning, and Generative Pre-trained Transformer (GPT), to automate the construction of scenario-based ontologies using existing research articles and technical manuals of urban datasets and simulations. From these ontologies, knowledge graphs can be derived using widely adopted formats and protocols, guiding various tasks towards data-informed decision support. The performance of our methodology is evaluated through a comparative analysis that contrasts our AI-generated ontology with the widely recognized pizza ontology, commonly used in tutorials for popular ontology software. We conclude with a real-world case study on optimizing the complex system of multi-modal freight transportation. Our approach advances urban decision support systems by enhancing data and metadata modeling, improving data integration and simulation coupling, and guiding the development of decision support strategies and essential software components.
We propose a novel synthesis of observational and simulated data (climatological and biological) to enhance understanding of the real-world interplay between climate (here, the water cycle) and the epidemiology of water cycle-driven infectious disease. Aligning with Focal Area 2, predictive modeling using AI techniques, we will develop systems of hierarchical models to discover latent features of the water cycle. Our approach will leverage state-of-the-art in Artificial Intelligence (AI) to measure the degree to which climate change-driven shifts in water cycle can be predicted by supplementing sparse and irregular climate data with water cycle-driven infectious disease resources.
The complexity of energy systems is well known as they are complex and intricate systems. As a result, many extant studies have used many simplifications or generalizations that do not accurately reflect the nature of this complex system. In particular, most HVAC systems are modeled as a single unit, or several large units, rather than as a hierarchical composite (e.g., as a floor rather than as a collection of disparate rooms). The net result of this is that the simulations are too generic to perform meaningful analysis, machine learning, or integrated simulation. We propose using a multi-agent multi-team strategic simulations framework called SiMAMT to better define, model, simulate, and learn the HVAC environment. SiMAMT allows us to create distinct models for each type of room, hierarchically aggregate them into units (like floors, or sections), and then into larger sets (like buildings or a campus), and then perform a simulation that interacts with each sub-element individually, the teams of sub-elements collectively, and the entire set in aggregation. Further, and most importantly, we additionally model another ‘team’ within the simulation framework - the users of the systems. Again, each individual is modeled distinctly, aggregated into sub-sets, then collected into large sets. Each user, or agent, is performing on their own but with respect to the larger team goals. This provides a simulation that has a much higher model fidelity and more applicable results that match the real-world.
Explore the source record for details and available documents.