Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Domain adaptation”

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 1,009 records · Page 56
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Tackling Climate Change with Machine Learning

Climate change is one of the greatest challenges facing humanity, and we, as machine learning (ML) experts, may wonder how we can help. Here we describe how ML can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by ML, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the ML community to join the global effort against climate change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Bayesian Optimized Deep Ensemble for Uncertainty Quantification of Deep Neural Networks: a System Safety Case Study on Sodium Fast Reactor Thermal Stratification Modeling

Deep neural networks (DNNs) are increasingly important to scientific computing and engineering system simulations. Accurate uncertainty quantification (UQ) for DNNs is critical in safety-sensitive engineering domains. Traditional Deep Ensemble (DE) methods, while easy to implement, frequently suffer from poorly calibrated uncertainty estimates and limited predictive accuracy due to reliance on fixed architectures with varied weight initializations. To address these issues, we introduce a workflow that combines Bayesian Optimization (BO) and DE. The workflow is modular, scalable, and integrates parallel BO initialized with Sobol sequences to individually optimize the hyperparameters of each ensemble member. This method enhances ensemble diversity, improves predictive accuracy, and provides reliable uncertainty estimates. We evaluate the proposed BODE approach in a sodium fast reactor thermal stratification modeling case study, where we used a densely connected convolutional neural network to predict turbulent viscosity during the reactor transient with consideration of data noise. We benchmark its performance against several optimization approaches, including baseline deep ensemble, evolutionary algorithm-optimized ensemble, ensemble formed via random search combined with greedy selection, and a BO ensemble using random initialization. Here, our results demonstrate superior performance of the developed BODE approach. In noise-free scenarios, BODE notably reduces incorrect aleatoric uncertainty and significantly enhances predictive accuracy. Under conditions of 5% and 10% Gaussian noise, BODE adaptively quantifies uncertainty proportional to data noise, achieving up to an 80% reduction in root mean square error compared to baseline methods and producing well-calibrated prediction intervals.

Bayesian optimization↗
DOE OSTI2024

Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects

This is the conference paper accompanying an oral presentation “Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects” at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24 , 2024. Carbon capture and storage (CCS) technology is critical for mitigating climate change but requires effective subsurface reservoir management to ensure safe containment of injected CO2. Accurate predictions of reservoir pressure and saturation are essential for assessing long-term CCS performance. Traditional numerical simulations, while effective, are computationally intensive, time-consuming, and constrained by data discretization. Previous work has shown the effectiveness of MeshGraphNets (MGN), a graph-based machine learning framework, as an innovative alternative for predicting reservoir behavior. MGN leverages graph neural networks (GNNs) and mesh representations to model complex geological formations, offering superior adaptability across different discretizations and reservoir configurations. Classic MGN implementations utilize an autoregressive technique to predict future behavior based on current predictions, but this technique is hampered by error accumulation over time. To enhance the model accuracy in time-series predictions, this study implemented a multi-step rollout strategy that integrates autoregressive predictions during training to stabilize prediction of saturation over time. Using the Illinois Basin – Decatur Project (IBDP) dataset, comprising 100 simulations of CO2 injection, pressure, and saturation changes, the framework demonstrated its ability to learn spatial dependencies and temporal dynamics. With inputs including permeabilities, porosities, and injection rates, MGN accurately predicted CO2 plume evolution over time, even with limited training data. Moreover, the addition of a multi-step rollout procedure during training improved the ability of MGN to predict stably over time by ~15%. This research positions MGN, enhanced with multi-step rollout capabilities, as a robust and efficient tool for CCS applications. It advances the field by enabling precise, computationally efficient predictions of reservoir behavior, providing a foundation for the broader adoption of machine learning frameworks in CCS and other geoscience domains.

Holcomb, Paul↗
NASA NTRS2024

Federal USS Synthesis Effort: 2023 Flight Test Report. A NASA and Department of Defense Joint Evaluation of Multi-Domain Airspace Integration

In recent years, advancements in technology have greatly improved the utility and applicability of Uncrewed Aircraft Systems (UAS) and have highlighted the need for and importance of UAS Traffic Management (UTM). Onboard sense and avoid systems, ground-based sensors, and long- range command and control (C2) systems have significantly expanded the possibilities for UAS beyond visual line of sight (BVLOS) operations. Initially, research on UTM flights focused on their interactions with other UTM operations, but that has since been expanded to include interactions with the flight profiles of Advanced Air Mobility (AAM) and upper Class E Traffic Management (ETM) operations. Recognizing the potential of these systems and the increase in UAS autonomy, the Department of Defense (DoD) is working towards integrating these missions and systems into a unified DoD Federal ecosystem. The Federal USS Synthesis Effort (FUSE) aims to develop a live system that can efficiently combine this wide range of UTM, AAM, and ETM systems, thus enabling expanded operations within a single common operating environment. The goal of the Federal USS Synthesis Effort (FUSE) is for NASA and the DoD to develop a live system that can efficiently combine UTM, AAM, and ETM systems. The most recent endeavor in this effort was a live flight test conducted near Grand Forks Air Force Base in June, 2023, where the FUSE ecosystem successfully demonstrated integrating UTM, AAM, and ETM operations while providing a single, shared COP to users. Additional investigations were made during the test, including assessing the usefulness of the system and its capability to support UAS weighing over 55 lbs.; testing user messaging capabilities and a DoD adaptation of a Federal USS; and assessing user workload, automated vs manual control, and the usability of NASA’s XTMClient.

Federal USS↗
NASA NTRS1996

Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics

We postulated that aging is associated with disruption in the fractallike long-range correlations that characterize healthy sinus rhythm cardiac interval dynamics. Ten young (21-34 yr) and 10 elderly (68-81 yr) rigorously screened healthy subjects underwent 120 min of continuous supine resting electrocardiographic recording. We analyzed the interbeat interval time series using standard time and frequency domain statistics and using a fractal measure, detrended fluctuation analysis, to quantify long-range correlation properties. In healthy young subjects, interbeat intervals demonstrated fractal scaling, with scaling exponents (alpha) from the fluctuation analysis close to a value of 1.0. In the group of healthy elderly subjects, the interbeat interval time series had two scaling regions. Over the short range, interbeat interval fluctuations resembled a random walk process (Brownian noise, alpha = 1.5), whereas over the longer range they resembled white noise (alpha = 0.5). Short (alpha s)- and long-range (alpha 1) scaling exponents were significantly different in the elderly subjects compared with young (alpha s = 1.12 +/- 0.19 vs. 0.90 +/- 0.14, respectively, P = 0.009; alpha 1 = 0.75 +/- 0.17 vs. 0.99 +/- 0.10, respectively, P = 0.002). The crossover behavior from one scaling region to another could be modeled as a first-order autoregressive process, which closely fit the data from four elderly subjects. This implies that a single characteristic time scale may be dominating heartbeat control in these subjects. The age-related loss of fractal organization in heartbeat dynamics may reflect the degradation of integrated physiological regulatory systems and may impair an individual's ability to adapt to stress.

NASA Discipline Cardiopulmonary↗
DOE OSTI2021

mosartwmpy: A Python implementation of the MOSART-WM coupled hydrologic routing and water management model

mosartwmpy is a Python implementation of the Model for Scale Adaptive River Transport with Water Management (MOSART-WM). This new version retains the functionality of the legacy model (written in FORTRAN) while providing new features to enhance user experience and extensibility. MOSART is a large-scale river-routing model used to study riverine dynamics of water, energy, and biogeochemistry cycles across local, regional, and global scales (Li et al., 2013). The WM component introduced by Voisin et al. (2013) represents river regulation through reservoir storage and release operations, diversions from reservoir releases, and allocation to sectoral water demands. Each reservoir release is independently calibrated using long-term mean monthly inflow into the reservoir, long-term mean monthly demand associated with this reservoir, and reservoir goals (flood control, irrigation, recreation, etc.). Generic monthly pre-release rules and storage targets are set up for individual reservoirs; however, those releases are updated annually for inter-annual variability (dry or wet year) and daily for environmental constraints such as flow minimum release and minimum/maximum storage levels. The WM model allows an evaluation of the impact of water management over multiple river basins at once (global, continental scales) and with consistent representation of human operations over the full domain.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Paired Simulations and Experimental Investigations into the Calcium-Dependent Conformation of Albumin

Serum albumin is the most abundant protein in blood plasma, and it is involved in multiple biological processes. Serum albumin has recently been adapted for improving biomaterial integration with bone tissue, and studies have shown the importance of this protein in bone repair and regeneration. However, the mechanism of action is not yet clear. In stark contrast, other studies have demonstrated that albumin blocks cell adhesion to surfaces, which is seen as a limitation to its bone healing role. These apparent contradictions suggest that the conformation of albumin facilitates its bioactivity, leading to enhanced bone repair. Serum albumin is known to play a major role in maintaining the calcium ion concentration in blood plasma. Due to the prevalence of calcium at bone repair and regeneration sites, it has been hypothesized that calcium binding to serum albumin triggers a conformational change, leading to bioactivity. In the current study, molecular modeling approaches including molecular docking, atomic molecular dynamics (MD) simulation, and coarse-grained MD simulation were used to test this hypothesis by investigating the conformational changes induced in bovine serum albumin by interaction with calcium ions. The computational results were qualitatively validated with experimental Fourier-transform infrared spectroscopy analysis. We find that free calcium ions in solution transiently bind with the three major loops in albumin, triggering a conformational change where N-terminal and C-terminal domains separate from each other in a partial unfolding process. The separation distance between these domains was found to correlate with the calcium ion concentration. The experimental data support the simulation results showing that albumin has enhanced conformational heterogeneity upon exposure to intermediate levels of calcium, without any significant secondary structure changes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2015

Human Systems Integration (HSI) Practitioner's Guide

The NASA/SP-2015-3709, Human Systems Integration (HSI) Practitioner's Guide, also known as the "HSIPG," provides a tool for implementing HSI activities within the NASA systems engineering framework. The HSIPG is written to aid the HSI practitioner engaged in a program or project (P/P), and serves as a knowledge base to allow the practitioner to step into an HSI lead or team member role for NASA missions. Additionally, this HSIPG is written to address the role of HSI in the P/P management and systems engineering communities and aid their understanding of the value added by incorporating good HSI practices into their programs and projects. Through helping to build a community of knowledgeable HSI practitioners, this document also hopes to build advocacy across the Agency for establishing strong, consistent HSI policies and practices. Human Systems Integration (HSI) has been successfully adopted (and adapted) by several federal agencies-most notably the U.S. Department of Defense (DoD) and the Nuclear Regulatory Commission (NRC)-as a methodology for reducing system life cycle costs (LCCs). These cost savings manifest themselves due to reductions in required numbers of personnel, the practice of human-centered design, decreased reliance on specialized skills for operations, shortened training time, efficient logistics and maintenance, and fewer safety-related risks and mishaps due to unintended human/system interactions. The HSI process for NASA establishes how cost savings and mission success can be realized through systems engineering. Every program or project has unique attributes. This HSIPG is not intended to provide one-size-fits-all recommendations for HSI implementation. Rather, HSI processes should be tailored to the size, scope, and goals of individual situations. The instructions and processes identified here are best used as a starting point for implementing human-centered system concepts and designs across programs and projects of varying types, including manned and unmanned, human spaceflight, aviation, robotics, and environmental science missions. The practitioner using this guide should have expertise in Systems Engineering or other disciplines involved in producing systems with anticipated human interactions. (See section 1.6 of this guide for further discussion on HSI discipline domains.) The HSIPG provides an "HSI layer" to the NASA Systems Engineering Engine (SEE), detailed in NASA Procedural Requirement (NPR) 7123.1B, NASA Systems Engineering Processes and Requirements, and further explained in NASA/SP-2007-6105, Systems Engineering Handbook (see HSIPG Table 2.2-1, NASA Documents with HSI Content, for specific references and document versions).

Zumbado, Jennifer Rochlis↗
NASA NTRSDate not supplied

Creating A Consistent Historical NASA POWER Solar Radiation Dataset to Support Renewable Energy, Building Energy Efficiency and Agro-Climatology Decisions

Prediction of Worldwide Energy Resources (POWER) project provides irradiance dataset to support renewable energy, building energy efficiency and agricultural needs. These datasets are derived from Global Energy and Water Cycle Experiment Surface Radiation Budget (GEWEX SRB) and Clouds and the Earth’s Radiant Energy System (CERES SYN1Deg). A systematic bias has been reported between these two datasets for the years with overlapping observations. For obtaining a consistent climate data record spanning the entire time record of observations, it is crucial to understand and remove the bias in the irradiance dataset. Inconsistency in solar radiation data can lead to inaccurate conclusions about solar energy potential and obscure real trends in solar radiation patterns that would impact energy availability assessments. In this study, we adapt quantile mapping approach to remove the systematic bias and to improve reliability of shortwave and longwave irradiance data. We present a validation of the bias corrected data against ground truth. For each 1° latitude and 1° longitude grid box across the globe, we match the CDFs of the reference dataset (CERES SYN1Deg) to that of the SRB dataset, thereby, adjusting the irradiance values to match the empirical distribution of two different measurements. The performance of quantile mapping is evaluated by using the metrics such as Mean Absolute Deviation (MAD). The results indicate that the quantile mapping significantly improves the accuracy and reliability of solar irradiance dataset especially for the weather conditions associated with high cloud cover and extreme irradiance values. The initial range of MAD for the studied sites for daily data was 4 to 19 Wm-2. After correction these reduced to 3 to 7 Wm-2. The findings from this study have important implications for solar energy system design, agricultural planning, and climate modeling community. Reducing the inconsistency and biases in solar irradiance dataset can enable better planning and operation of solar energy systems, leading to increased efficiency and cost-effectiveness. Additionally, this work also contributes to the statistical post-processing techniques in the renewable energy domain and highlights the potential of historical and near-real-time NASA POWER dataset as a valuable resource for solar energy research and applications.

POWER↗
NASA NTRS2011

Fast Image Texture Classification Using Decision Trees

Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

Thompson, David R.↗
NASA NTRS1993

A comparison of low-gravity measurements on-board Columbia during STS-40

The first NASA Spacelab Life Sciences mission (SLS-1) flew 5 June to 14 June 1991 on the orbiter Columbia (STS-40). The purpose of the mission was to investigate the human body's adaptation to the low-gravity conditions of space flight and the body's readjustment after the mission to the 1g environment of earth. In addition to the life sciences experiments manifested for the Spacelab module, a variety of experiments in other scientific disciplines flew in the Spacelab and in Get Away Special (GAS) Canisters on the GAS Bridge Assembly. Several principal investigators designed and flew specialized accelerometer systems to better assess the results of their experiments by means of a low-gravity environment characterization. This was also the first flight of the NASA Microgravity Science and Applications Division (MSAD) sponsored Space Acceleration Measurement System (SAMS) and the first flight of the NASA Orbiter Experiments Office (OEX) sponsored Orbital Acceleration Research Experiment accelerometer (OARE). We present a brief introduction to seven STS-40 accelerometer systems and discuss and compare the resulting data. During crew sleep periods, acceleration magnitudes in the 10(exp -6) to 10(exp -5)g range were recorded in the Spacelab module and on the GAS Bridge Assembly. Magnitudes increased to the 10(exp -4) level during periods of nominal crew activity. Vernier thruster firings caused acceleration shifts on the order of 10(exp -4)g and primary thruster firings caused accelerations as great as 10(exp -2) g. Frequency domain analysis revealed typical excitation of Orbiter and Spacelab structural modes at 3.5, 4.7, 5.2, 6.2, 7, and 17 Hz.

Rogers, M. J. B.↗
NASA NTRS2004

Adaptive, Distributed Control of Constrained Multi-Agent Systems

Product Distribution (PO) theory was recently developed as a broad framework for analyzing and optimizing distributed systems. Here we demonstrate its use for adaptive distributed control of Multi-Agent Systems (MASS), i.e., for distributed stochastic optimization using MAS s. First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (Probability dist&&on on the joint state of the agents. When the game in question is a team game with constraints, that equilibrium optimizes the expected value of the team game utility, subject to those constraints. One common way to find that equilibrium is to have each agent run a Reinforcement Learning (E) algorithm. PD theory reveals this to be a particular type of search algorithm for minimizing the Lagrangian. Typically that algorithm i s quite inefficient. A more principled alternative is to use a variant of Newton's method to minimize the Lagrangian. Here we compare this alternative to RL-based search in three sets of computer experiments. These are the N Queen s problem and bin-packing problem from the optimization literature, and the Bar problem from the distributed RL literature. Our results confirm that the PD-theory-based approach outperforms the RL-based scheme in all three domains.

Bieniawski, Stefan↗
DOE OSTI2022

MPAS-Seaice (v1.0.0): sea-ice dynamics on unstructured Voronoi meshes

Abstract. We present MPAS-Seaice, a sea-ice model which uses the Model for Prediction Across Scales (MPAS) framework and spherical centroidal Voronoi tessellation (SCVT) unstructured meshes. As well as SCVT meshes, MPAS-Seaice can run on the traditional quadrilateral grids used by sea-ice models such as CICE. The MPAS-Seaice velocity solver uses the elastic–viscous–plastic (EVP) rheology and the variational discretization of the internal stress divergence operator used by CICE, but adapted for the polygonal cells of MPAS meshes, or alternatively an integral (“finite-volume”) formulation of the stress divergence operator. An incremental remapping advection scheme is used for mass and tracer transport. We validate these formulations with idealized test cases, both planar and on the sphere. The variational scheme displays lower errors than the finite-volume formulation for the strain rate operator but higher errors for the stress divergence operator. The variational stress divergence operator displays increased errors around the pentagonal cells of a quasi-uniform mesh, which is ameliorated with an alternate formulation for the operator. MPAS-Seaice shares the sophisticated column physics and biogeochemistry of CICE and when used with quadrilateral meshes can reproduce the results of CICE. We have used global simulations with realistic forcing to validate MPAS-Seaice against similar simulations with CICE and against observations. We find very similar results compared to CICE, with differences explained by minor differences in implementation such as with interpolation between the primary and dual meshes at coastlines. We have assessed the computational performance of the model, which, because it is unstructured, runs with 70 % of the throughput of CICE for a comparison quadrilateral simulation. The SCVT meshes used by MPAS-Seaice allow removal of equatorial model cells and flexibility in domain decomposition, improving model performance. MPAS-Seaice is the current sea-ice component of the Energy Exascale Earth System Model (E3SM).

58 GEOSCIENCES↗
NASA NTRS1993

A comparison of low-gravity measurements on-board Columbia during STS-40

The first NASA Spacelab Life Sciences mission (SLS-1) flew 5 Jun. to 14 Jun. 1991 on the orbiter Columbia (STS-40). The purpose of the mission was to investigate the human body's adaptation to the low-gravity conditions of space flight and the body's readjustment after the mission to the 1 g environment of earth. In addition to the life sciences experiments manifested for the Spacelab module, a variety of experiments in other scientific disciplines flew in the Spacelab and in Get Away Special (GAS) Canisters on the GAS Bridge Assembly. Several principal investigators designed and flew specialized accelerometer systems to better assess the results of their experiments by means of a low-gravity environment characterization. This was also the first flight of the NASA Microgravity Science and Applications Division (MSAD) sponsored Space Acceleration Measurement System (SAMS) and the first flight of the NASA Orbiter Experiments Office (OEX) sponsored Orbital Acceleration Research Experiment accelerometer (OARE). A brief introduction to seven STS-40 accelerometer systems are presented and the resulting data are discussed and compared. During crew sleep periods, acceleration magnitudes in the 10(exp -6) to 10(exp -5) g range were recorded in the Spacelab module and on the GAS Bridge Assembly. Magnitudes increased to the 10(exp -4) g level during periods of nominal crew activity. Vernier thruster firings caused acceleration shifts on the order of 10(exp -4) g and primary thruster firings caused accelerations as great as 10(exp -2) g. Frequency domain analysis revealed typical excitation of Orbiter and Spacelab structural modes at 3.5, 4.7, 5.2, 6.2, 7, and 17 Hz.

Rogers, Melissa J. B.↗
NASA NTRS2004

Adjoint Algorithm for CAD-Based Shape Optimization Using a Cartesian Method

Adjoint solutions of the governing flow equations are becoming increasingly important for the development of efficient analysis and optimization algorithms. A well-known use of the adjoint method is gradient-based shape optimization. Given an objective function that defines some measure of performance, such as the lift and drag functionals, its gradient is computed at a cost that is essentially independent of the number of design variables (geometric parameters that control the shape). More recently, emerging adjoint applications focus on the analysis problem, where the adjoint solution is used to drive mesh adaptation, as well as to provide estimates of functional error bounds and corrections. The attractive feature of this approach is that the mesh-adaptation procedure targets a specific functional, thereby localizing the mesh refinement and reducing computational cost. Our focus is on the development of adjoint-based optimization techniques for a Cartesian method with embedded boundaries.12 In contrast t o implementations on structured and unstructured grids, Cartesian methods decouple the surface discretization from the volume mesh. This feature makes Cartesian methods well suited for the automated analysis of complex geometry problems, and consequently a promising approach to aerodynamic optimization. Melvin et developed an adjoint formulation for the TRANAIR code, which is based on the full-potential equation with viscous corrections. More recently, Dadone and Grossman presented an adjoint formulation for the Euler equations. In both approaches, a boundary condition is introduced to approximate the effects of the evolving surface shape that results in accurate gradient computation. Central to automated shape optimization algorithms is the issue of geometry modeling and control. The need to optimize complex, "real-life" geometry provides a strong incentive for the use of parametric-CAD systems within the optimization procedure. In previous work, we presented an effective optimization framework that incorporates a direct-CAD interface. In this work, we enhance the capabilities of this framework with efficient gradient computations using the discrete adjoint method. We present details of the adjoint numerical implementation, which reuses the domain decomposition, multigrid, and time-marching schemes of the flow solver. Furthermore, we explain and demonstrate the use of CAD in conjunction with the Cartesian adjoint approach. The final paper will contain a number of complex geometry, industrially relevant examples with many design variables to demonstrate the effectiveness of the adjoint method on Cartesian meshes.

Nemec, Marian↗
DOE OSTI2025

Multi-head physics-informed neural networks for learning functional priors and uncertainty quantification

In numerous applications, the integration of prior knowledge and historical information is essential, particularly for tasks requiring the solution of ordinary or partial differential equations (ODEs/PDEs) in data-sparse or noisy environments. For instance, achieving accurate solutions to time-dependent PDEs with limited initial condition measurements necessitates an effective strategy for embedding prior knowledge. Hard-parameter sharing architectures in neural networks (NNs) have demonstrated success in both traditional and scientific machine learning domains, facilitating the learning of informative representations. Here, in this study, we introduce a novel, yet efficient, method to enhance physics-informed neural networks (PINNs) by incorporating a multi-head structure that enables the learning of functional priors from both empirical data and governing physical laws. This prior information can then be used to address data sparsity and high-level noise in solving ODE/PDE problems with uncertainty quantification (UQ). The approach, termed Multi-Head PINN (MH-PINN), consists of a shared body NN and multiple head NNs, each corresponding to an individual PINN instance. Our framework for functional prior learning is carried out in two stages: (1) training the MH-PINNs to develop a shared body NN alongside multiple head NNs, and (2) employing these trained head NNs to estimate a prior distribution through a normalizing flow-based density estimator. The learned functional prior can then be applied as a regularization mechanism in deterministic contexts or as an informative prior within a Bayesian inference framework, aiding in the resolution of subsequent ODE/PDE tasks. We evaluate the efficacy of MH-PINNs across five benchmark problems, including a high-dimensional parametric PDE, all characterized by data sparsity or substantial noise levels. Our findings reveal that MH-PINNs deliver accurate solutions and robust UQ, demonstrating adaptability across a range of complex and challenging scenarios.

Bayesian inference↗
NASA NTRSDate not supplied

NASA Earth Systems Digital Twins (ESDT)

"Similarly to artificial intelligence, which is now revolutionizing many aspects of our daily lives, Earth system digital twin technologies have the potential to revolutionize the way Earth Science research will be conducted in the future, and how results and knowledge from this research will provide information to support decision making and yield impactful societal benefits. An Earth System Digital Twin or ESDT is a dynamic and interactive information system that first provides a digital replica of the past and current states of the Earth or Earth system as accurately and timely as possible; second, allows for computing forecasts of future states under nominal assumptions and based on the current replica; and third, offers the capability to investigate many hypothetical scenarios under varying impact assumptions. In other words, an ESDT provides the integrated What-Now, What-Next, and What-If pictures of the Earth or Earth system, by continuously ingesting newly observed data and by leveraging multiple interconnected models, machine learning as well advanced computing and visualization capabilities. Digital twins have been developed in engineering since 2002, but the interest in digital twins for the Earth domain is more recent and stems from the convergence of several developments: - The huge amount of diverse data that has now been collected continuously for more than 50 years, and that is becoming more and more difficult to access, understand, and utilize. - At the same time, because of climate change and its impacts the information produced by all of this data is becoming of interest to many new non-traditional users for analyzing and predicting various phenomena. - Because of advances in computational and visualization capabilities and the parallel unprecedented development of machine learning (ML), extracting relevant information from these large amounts of data and running complex models faster has become possible. As a result, it is becoming necessary and possible to build intuitive and interactive frameworks that will enable users with various skill levels and/or organizational hierarchy levels to easily access large amounts of targeted information along with the relevant tools and models (Earth system and human activity models), to support them in analyzing and visualizing this information, to help them understand interactions among models, to visualize the potential outcomes of various impacts, and to support decision or policy making. The full power of digital twins is that, through an integrated representation and standardized tools and software technologies, the same digital replica can address the needs of multiple users at various resolutions (spatial and temporal) and for various applications (science, economic, policy, etc.) – “from farmer to scientist”. With all these interests at stake, the challenges of building optimal digital twins are many and complex. The first challenge is to determine if a Digital Twin should be global or local, and multi-domain or thematic. For example, some domains such as Climate or Weather will require a global Digital Twin or Digital Twin capabilities while science areas such as Biodiversity might be more local. We can also envision that multiple thematic ESDTs, e.g., Air Quality, Wildfires, Hydrology could be federated or provide input to other ESDTs, either on a regional level or to a more global ESDT. Overall, we can imagine a future “web” of Digital Twins co-existing in a hierarchy or in a network, and capable of being connected or federated depending on the needs. This last point brings up the very important challenge of interoperability, including standards and protocols that will need to be built into these systems from the beginning. Each individual digital twin would have full flexibility in internal construction but would need standards-based interfaces (input and output) or hooks to make it compatible with others. Another challenge when building digital twins will be to decide how to organize each digital replica. Based on the applications targeted by the DT under implementation, various amounts and types of raw data, Analysis Ready Data (ARD) and information will need to be incorporated. Depending on the required latencies and needs of the users, various solutions can be considered, including Data Cubes, Data Lakes, pointers, or computing information on demand. We envision that each ESDT will choose a solution adapted to its specific objectives. Another important challenge is the type(s) of visualization that will be used, as well as the level of interactivity and refresh rate that will be required. Again, this will depend on the objectives of the ESDT, but also on the various users’ needs. In most cases, several types of visualizations and human interfaces will need to be offered depending on the projected users of that system. In parallel to the challenges highlighted above, there are also many tools and technologies that will need to be developed or improved for all types of digital twins. Among those are improved machine learning technologies, for example providing explainability, but also ML techniques for causality and providing a better integration of physics models. Additionally, reliable uncertainty quantification methods will be needed for all ESDT components, from validating data fusion and assimilation to assessing the accuracy of ML models and weighing the values of decisions supported by those systems. This presentation introduces the ESDT concept, presents several ESDT use cases, and a proposed ESDT architecture framework, as well as various technologies being developed by the Advanced Information Systems Technology (AIST) Program."

Earth Science Remote Sensing; Information Systems↗
DOE OSTI2021

Developing and testing capabilities for simulating cases with heterogeneous land/water surfaces in a novel atmospheric large eddy simulation code

Large eddy simulations (LES) are the primary computational tool used to simulate high Reynolds number three-dimensional turbulent flows. In the context of earth system sciences, particularly atmospheric science, LES are uniquely able to resolve the scales of atmospheric motion that are key for building process-level understanding of boundary layer turbulence, atmosphere-surface interaction, clouds, and cloud-aerosol-chemistry interaction, and are a core limited-area modeling capability. Increasing demands are being placed on LES code bases as growing high performance computing resources allow LES to address a wider range of scientific problems. In addition, LES are emerging as a source of high-quality machine learning training data. These demands necessitate an agile and extensible code base that allows the model to quickly adapt to emergent needs. However, LES have largely relied on legacy Fortran code bases that lack flexibility. A new, Python-based LES capability called Predicting INteractions of Aerosol and Clouds in Large Eddy Simulation (PINACLES) has been developed as part of the Department of Energy’s Earth System Model Development (ESMD) program area’s Enabling Aerosol-cloud interactions at Global convection-permitting scalES (EAGLES) project. PINACLES was developed from the ground up with a philosophy of maximizing scientific throughput, by attempting to optimize for both model throughput and software extensibility. The initial development of PINACLES delivered a state-of-the-art idealized LES capability solving the non-hydrostatic anelastic equations of motion with doubly periodic boundary conditions and idealized homogenous surface boundary conditions. Here we provide a final report on the outcomes of a fiscal year 2021 Seed Laboratory Directed Research Project that extended PINACLES in two key ways. First, PINACLES was coupled to a state-of-the-art land surface model enabling it to simulate spatially inhomogeneous land-atmosphere interactions that are known to control key atmospheric processes. Second, the dynamical core of PINACLES was modified to permit non-periodic boundary conditions. This model enhancement enables simulation of realistic cases with boundary conditions prescribed from atmospheric reanalysis and enables nested simulations conducted on a hierarchy of computational domains with increasing resolution. Together, these extensions to PINACLES make it a formidable modeling capability and expand its potential application to diverse components of DOE’s atmospheric science portfolio.

42 ENGINEERING↗