Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Direct Use”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Efficient learning of power grid voltage control strategies via model-based deep reinforcement learning

Here this article proposes a model-based deep reinforcement learning (DRL) method to design emergency control strategies for short-term voltage stability problems in power systems. Recent advances show promising results for model-free DRL-based methods in power systems control problems. But in power systems applications, these model-free methods have certain issues related to training time (clock time) and sample efficiency; both are critical for making state-of-the-art DRL algorithms practically applicable. DRL-agent learns an optimal policy via a trial-and-error method while interacting with the real-world environment. It is also desirable to minimize the direct interaction of the DRL agent with the real-world power grid due to its safety-critical nature. Additionally, the state-of-the-art DRL-based policies are mostly trained using a physics-based grid simulator where dynamic simulation is computationally intensive, lowering the training efficiency. We propose a novel model-based DRL framework where a deep neural network (DNN)-based dynamic surrogate model (SM), instead of a real-world power grid or physics-based simulation, is utilized within the policy learning framework, making the process faster and more sample efficient. However, having stable training in model-based DRL is challenging because of the complex system dynamics of large-scale power systems. We addressed these issues by incorporating imitation learning to have a warm start in policy learning, reward-shaping, and multi-step loss in surrogate model training. Finally, we achieved 97.5% reduction in samples and 87.7% reduction in training time for an application to the IEEE 300-bus test system.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Integrating the PanDA Workload Management System with the Vera C. Rubin Observatory

The Vera C. Rubin Observatory will produce an unprecedented astronomical data set for studies of the deep and dynamic universe. Its Legacy Survey of Space and Time (LSST) will image the entire southern sky every three to four days and produce tens of petabytes of raw image data and associated calibration data over the course of the experiment’s run. More than 20 terabytes of data must be stored every night, and annual campaigns to reprocess the entire dataset since the beginning of the survey will be conducted over ten years. The Production and Distributed Analysis (PanDA) system was evaluated by the Rubin Observatory Data Management team and selected to serve the Observatory’s needs due to its demonstrated scalability and flexibility over the years, for its Directed Acyclic Graph (DAG) support, its support for multi-site processing, and its highly scalable complex workflows via the intelligent Data Delivery Service (iDDS). PanDA is also being evaluated for prompt processing where data must be processed within 60 seconds after image capture. This paper will briefly describe the Rubin Data Management system and its Data Facilities (DFs). Finally, it will describe in depth the work performed in order to integrate the PanDA system with the Rubin Observatory to be able to run the Rubin Science Pipelines using PanDA.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

AI-enabled traveling wave protection for microgrids

Grid forming inverters provide voltage and frequency regulations for microgrids; in the meantime, new challenges are introduced for microgrid protections. For instance, inverters’ control strategies can affect protection behaviors, and low short-circuit ratios and bi-directional power flows also make protection operations complex. Protection schemes based on conventional principles such as overcurrent and distance relays do not always provide reliable, sensitive, or selective operations. Here, we devise a traveling wave protection approach for microgrids using a wavelet-driven deep neural network named WaveletKernelNet (WKN). Compared with conventional methods, the presented approach provides enhanced sensitivity, higher selectivity, and better identification of various faults in microgrids. Extensive case studies validate the efficacy and excellent performance of the devised approach.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Production of CO2-Negative Building Composites Development

This project will investigate and utilize the basicity and enhanced reactivity of CO2 chemically captured in PNNL’s CO2BOLs carbon capture solvents to perform the first direct carboxylation of the aromatic rings (substituted phenols) in lignin and lignite. This project aims to develop a deep decarbonization approach that can sequester millions of tonnes of CO2 annually by reacting with two large-volume products, lignin, and lignite, to enable their use as composite fillers. The goal is to demonstrate that CO2-containing composites have comparable properties to conventional synthetic materials, meeting international building codes (IBC) while being able to sequester millions of tonnes of CO2 per year.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Statistical imprints of wave-like dark matter on multiply-imaged galaxies in strong cluster lenses from JWST

Wave-like dark matter ($ψ$DM) is an elusive dark matter (DM) candidate. The model, often also called fuzzy or ultralight DM, proposes that DM is an extremely light ($m\sim10^{-22}$ eV) boson and thereby has a kpc-scale de Broglie wavelength. Hence, interference of DM gives rise to sub-galactic density fluctuations that can be studied with strong gravitational lensing. In this paper, we use the residual power spectrum, $\mathrm{P}_δ(k)$, as a probe of $ψ$DM, which quantifies deviations from smooth lensing predictions, measured from multiply-imaged galaxies in strong cluster lenses. The key idea is that imprinted in these deviations are lensing distortions from DM substructure, which can be harnessed statistically to distinguish among DM theories. We simulate JWST-quality mock observations of strong gravitational lensing in galaxy clusters, modeling line-of-sight DM substructure within $ψ$DM and the standard cold dark matter (CDM) paradigms. Using mock deep observations ($\sim$ 20 hours), we find that $\mathrm{P}_δ(k)$ is sensitive to both $ψ$DM particle mass and fluctuation amplitude, and can distinguish $ψ$DM fluctuations from CDM subhalos. We demonstrate that $\mathrm{P}_δ(k)$ can be measured directly from data by modeling the smooth lensing with a local Curved Arc Basis formalism. With realistic modeling systematics, we find a statistically significant separation between $ψ$DM and CDM across $1 \lesssim k \lesssim 11\,\mathrm{kpc}^{-1}$ -- offering an independent probe of the wave-like nature of DM complementary to existing constraints.

Cosmology and Nongalactic Astrophysics (astro-ph.C↗
DOE OSTI2025

Gamma Ray Detection In Liquid Argon Time Projection Chambers

Gamma rays are photons in excess of 100 keV of energy and can be produced by a variety of mechanisms like radioactive decay and inelastic neutrino-argon interactions. A reconstruc- tion of Compton scattering gamma rays was developed for use in liquid argon time projection chambers. This reconstruction was tested with detectors developed to demonstrate the ca- pabilities of Deep Underground Neutrino Experiment (DUNE) Near Detector Liquid Argon target (ND LAr). In October 2024, a radioactive fluorine-18 source was placed next to the Full Scale Demonstrator. The data obtained was used to test this reconstruction algorithm. It was able to determine the direction of the photons with an error of less than 10 percent. In addition to this work, there has been significant work on designing a liquid argon based Positron Emission Tomography (PET) scanner. PET scanners detect gamma rays emitted by a tracer chemical to help screen for diseases like cancer. In addition to the applications to medical imaging, this thesis briefly explores the applications of this reconstruction to de-excitation photons produced in interactions between neutrinos and argon nuclei. These applications could improve studies focusing on neutrinos originating from accelerators and supernovae.

Murphy, Thomas [Syracuse U.]↗
DOE OSTI2021

Powering the Blue Economy: A Survey of Station-Keeping Methods for Mooringless Platforms

The term “ocean platform” is used to reference everything from stationary, typically moored, buoys to mobile water vehicles, whether they operate on the ocean’s surface or underwater. For certain applications for which relatively stationary station-keeping conditions are desired, the use of mooring systems is not always a viable alternative either for economic, environmental, regulatory, or otherwise practical reasons, or a combination thereof, (e.g., short deployments, sensitive ecosystems, very deep project sites). Maintaining a platform at a single waypoint or reference location without being moored would require additional control systems and a power source to counteract the drift forces that would naturally displace it. Mobile platforms, which are usually untethered except for remotely operated vehicles, typically require energy input to power their station-keeping capabilities so that they hold or control their location in the ocean. Currently, most of these platforms use combustion engines or batteries for this purpose, which, depending on the specific systems, may be costly, pollute the environment, or create limitations on the length of the deployment. However, powering this kind of platforms with surrounding renewable resources (waves, currents, winds, or sun) has been identified as a promising solution to expand their application. The intent of this report is to investigate station-keeping methods for various ocean platforms that are not moored or otherwise anchored to the ocean floor, or another platform or vessel, paying particular interest to technologies that use marine renewable resources to power their operation, because that is of particular interest to the U.S. Department of Energy’s Powering the Blue Economy (PBE) initiative. As a first step, 72 articles and technical reports related to mooringless station-keeping methods were collected for review. The preliminary literature review provided a broad overview of common themes across the literature from which a descriptive methodology for analyzing various platforms was developed. That is, station-keeping methods were categorized based on their predominant energy source and consumption (renewable, nonrenewable, or hybrid if the platform uses renewable and nonrenewable resources equally), and their localization strategy (drift reduction, “path-planning or “waypoint-holding”). In addition, platform types were segregated into the following groups: buoys, surface drifters, and unoccupied surface vehicles (USVs); offshore renewable energy systems; and unoccupied underwater vehicles (UUVs). The main types of station-keeping methods encountered in this report achieve their intended localization strategy by means of drift mitigation, steering, and/or propulsion. Drift mitigation is commonly accomplished via drogues and sea anchors. Stand-along steering subsystems use control surfaces (e.g., ship rudder, wing sail, etc.) that react to ocean currents, waves, or winds to provide varying-degrees of course adjustments. Combined steering and propulsion subsystems include differential thrusters, directional thrusters separate from a primary thruster that cause the platform to pitch up/down or yaw clockwise/counterclockwise, or vectored thrusters that direct the propulsion in a range of directions relative to the platform’s local coordinate system. Propulsion is often achieved by running a motor and applying active control strategies but can also involve buoyancy shifts and using sails to generate lifting forces that propel a platform in a desired direction. Future research is primarily expected to take place in the form of a technoeconomic analysis that would aim to determine the technological viability, cost, and added value of mooringless station-keeping use cases identified through this research, including docking for UUV recharging or for georeferencing drifter buoys, deep-sea floating wind farms, U.S. Navy sonar arrays, and a Pacific Ocean wave buoy network.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

High-pressure elastic properties of dolomite melt supporting carbonate-induced melting in deep upper mantle

Deeply subducted carbonates likely cause low-degree melting of the upper mantle and thus play an important role in the deep carbon cycle. However, direct seismic detection of carbonate-induced partial melts in the Earth’s interior is hindered by our poor knowledge on the elastic properties of carbonate melts. Here we report the first experimentally determined sound velocity and density data on dolomite melt up to 5.9 GPa and 2046 K by in-situ ultrasonic and sink-float techniques, respectively, as well as first-principles molecular dynamics simulations of dolomite melt up to 16 GPa and 3000 K. Using our new elasticity data, the calculated V P /V S ratio of the deep upper mantle (~180–330 km) with a small amount of carbonate-rich melt provides a natural explanation for the elevated V P /V S ratio of the upper mantle from global seismic observations, supporting the pervasive presence of a low-degree carbonate-rich partial melt (~0.05%) that is consistent with the volatile-induced or redox-regulated initial melting in the upper mantle as argued by petrologic studies. This carbonate-rich partial melt region implies a global average carbon (C) concentration of 80–140 ppm. by weight in the deep upper mantle source region, consistent with the mantle carbon content determined from geochemical studies.

58 GEOSCIENCES↗
DOE OSTI2024

Counter Data Paucity through Adversarial Invariance Encoding: A Case Study on Modeling Battery Thermal Runaway

Lithium-ion batteries, widely used for their durability and high energy storage, face the risk of internal short circuits leading to catastrophic thermal runaway events. These events, triggered by external stimuli like mechanical loads, pose safety concerns in applications such as electric vehicles. Detecting and understanding thermal runaway events is crucial, but physics-driven models struggle to explain the non-linear evolution of battery temperature during these events, considering factors like material composition and state-of-charge. Due to the rarity of these events and the cost of data collection, we propose a deep learning (DL) model to predict battery temperature responses during thermal runaway. The challenge lies in the scarcity of data, making traditional DL models prone to overfitting and learning low-quality representations of the complex process.Our approach introduces a novel few-shot architecture that incorporates an adversarially governed invariant encoding process. This architecture aims to distill "invariant" relationships by addressing distributional shifts in data across various battery properties, facilitating the detection of thermal runaway events. Specifically, our results demonstrate that deep learning models conditioned on these "invariant" representations outperform state-of-the-art baselines, achieving a remarkable 96.8% performance improvement in terms of the popular metric MAPE. This framework presents a promising direction for enhancing battery safety modeling, particularly in the context of rare and complex events like thermal runaway. Our code and code and dataset used for the paper are public1.

Tabassum, Anika [ORNL] (ORCID:0000000254600955)↗
DOE OSTI2022

Uncertainty Quantification Framework for Predicting Material Response with Large Number of Parameters: Application to Creep Prediction in Ferritic-Martensitic Steels Using Combined Crystal Plasticity and Grain Boundary Models

This paper presents an uncertainty quantification (UQ) framework for the physics-based model prediction of material response with a large number of parameters. The application problem presented in this work is that of predicting creep in Grade 91 steel at 600°C. The material response is defined with a physically based microstructural model with constitutive equations emulating several observed phenomena in Grade 91 and embodied into an explicit geometry mesoscale finite element model for prior austenite grains and grain boundaries. Creep within the grains and in grain boundaries are represented by crystal plasticity for dislocation motion and a physics-based model for cavity growth and nucleation, respectively. The creep behavior of this material is influenced by several parameters, some of which have a wide range of variation based on experimental data. UQ combined with microstructural modeling can discover the core microstructural causes of experimental variability, leading to improved materials with lower variability in critical long-term material properties. In this study, we investigate the model's uncertainty to identify material properties that may be modified during production to increase creep life and analyze different components of the crystal plasticity model for improvements. For this purpose, a quantity of interest is defined as time to minimum creep rate, which correlates well to the creep failure of the material. A deep neural network model was trained and validated to be used as a surrogate for the finite element model. Then, a variance-based sensitivity analysis is performed on the surrogate model to find the Sobol indices of the input parameters in respect to the output quantity of interest. The Sobol indices are used to reduce the dimensionality of the model. Generalized polynomial chaos expansion is used on the reduced basis models to propagate the uncertainty from the input parameters to the quantity of interest using the deep neural network surrogate model. These results are benchmarked against uncertainty propagation using Monte Carlo simulations. In conclusion, the UQ performed through the reduced basis model captures almost all the uncertainty in the model with significantly fewer simulations, making it possible to perform the UQ directly via simulations with the finite element model rather than surrogate machine-learned models.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Accelerating network layouts using graph neural networks

Graph layout algorithms used in network visualization represent the first and the most widely used tool to unveil the inner structure and the behavior of complex networks. Current network visualization software relies on the force-directed layout (FDL) algorithm, whose high computational complexity makes the visualization of large real networks computationally prohibitive and traps large graphs into high energy configurations, resulting in hard-to-interpret “hairball” layouts. Here we use Graph Neural Networks (GNN) to accelerate FDL, showing that deep learning can address both limitations of FDL: it offers a 10 to 100 fold improvement in speed while also yielding layouts which are more informative. We analytically derive the speedup offered by GNN, relating it to the number of outliers in the eigenspectrum of the adjacency matrix, predicting that GNNs are particularly effective for networks with communities and local regularities. Finally, we use GNN to generate a three-dimensional layout of the Internet, and introduce additional measures to assess the layout quality and its interpretability, exploring the algorithm’s ability to separate communities and the link-length distribution. The novel use of deep neural networks can help accelerate other network-based optimization problems as well, with applications from reaction-diffusion systems to epidemics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Reactive capture and electrochemical conversion of CO 2 with ionic liquids and deep eutectic solvents

Ionic liquids (ILs) and deep eutectic solvents (DESs) have tremendous potential for reactive capture and conversion (RCC) of CO 2 due to their wide electrochemical stability window, low volatility, and high CO 2 solubility. There is environmental and economic interest in the direct utilization of the captured CO 2 using electrified and modular processes that forgo the thermal- or pressure-swing regeneration steps to concentrate CO 2 , eliminating the need to compress, transport, or store the gas. The conventional electrochemical conversion of CO 2 with aqueous electrolytes presents limited CO 2 solubility and high energy requirement to achieve industrially relevant products. Additionally, aqueous systems have competitive hydrogen evolution. In the past decade, there has been significant progress toward the design of ILs and DESs, and their composites to separate CO 2 from dilute streams. In parallel, but not necessarily in synergy, there have been studies focused on a few select ILs and DESs for electrochemical reduction of CO 2 , often diluting them with aqueous or non-aqueous solvents. The resulting electrode–electrolyte interfaces present a complex speciation for RCC. In this review, we describe how the ILs and DESs are tuned for RCC and specifically address the CO 2 chemisorption and electroreduction mechanisms. Critical bulk and interfacial properties of ILs and DESs are discussed in the context of RCC, and the potential of these electrolytes are presented through a techno-economic evaluation.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Effects of head modeling errors on the spatial frequency representation of MEG

Abstract Objectives. We aim to investigate the effects of head model inaccuracies on signal and source reconstruction accuracies for various sensor array distances to the head. This allows for the assessment of the importance of head modeling for next-generation magnetoencephalography (MEG) sensors, optically-pumped magnetometers (OPM). Approach. A 1-shell boundary element method (BEM) spherical head model with 642 vertices of radius 9 cm and conductivity of 0.33 S m −1 was defined. The vertices were then randomly perturbed radially up to 2%, 4%, 6%, 8% and 10% of the radius. For each head perturbation case, the forward signal was calculated for dipolar sources located at 2 cm, 4 cm, 6 cm and 8 cm from the origin (center of the sphere), and for a 324 sensor array located at 10 cm to 15 cm from the origin. Equivalent current dipole (ECD) source localization was performed for each of these forward signals. The signal for each perturbed spherical head case was then analyzed in the spatial frequency domain, and the signal and ECD errors were quantified relative to the unperturbed case. Main results. In the noiseless and high signal-to-noise ratio (SNR) case of approximately ≥6 dB, inaccuracies in our spherical BEM head conductor models lead to increased signal and ECD inaccuracies when sensor arrays are placed closer to the head. This is true especially in the case of deep and superficial sources. In the noisy case however, the higher SNR for closer sensor arrays allows for an improved ECD fit and outweighs the effects of head geometry inaccuracies. Significance. OPMs may be placed directly on the head, as opposed to the more commonly used superconducting quantum interference device sensors which must be placed a few centimeters away from the head. OPMs thus allow for signals of higher spatial resolution to be captured, resulting in potentially more accurate source localizations. Our results suggest that an increased emphasis on accurate head modeling for OPMs may be necessary to fully realize its improved source localization potential.

Yeo, Wan-Jin (ORCID:0000000241417123)↗
DOE OSTI2025

Comparison of Coupled and Uncoupled Modeling of Floating Wind Farms with Shared Anchors

As design options for floating wind farms continue to be explored, shared (or multiline) anchors that secure mooring lines from multiple turbines remain a promising technology that can potentially reduce the number of anchors and overall mooring costs. This study evaluates two methods for analyzing the loads on shared anchors: one in which floating offshore wind turbines are simulated individually (using the software OpenFAST), and one in which an entire floating wind farm is simulated collectively (using the software FAST.Farm). A three-line shared anchor is evaluated for multiple loading scenarios in deep water, using the International Energy Agency 15 MW turbine on the VolturnUS-S semisubmersible platform. While the two methods produce broadly comparable results, the coupled wave loading on platforms within the farm results in wave force cancellations and amplifications that decrease multiline force directional ranges and increase multiline force extreme values (up to 7%) and standard deviations (up to 11%) for wave-driven load cases. The inclusion of wakes in FAST.Farm also reduces the net load on the shared anchor due to the velocity deficit, leading to larger differences between OpenFAST and FAST.Farm (up to 3% difference in mean loads) for load cases with operational turbines.

17 WIND ENERGY↗
DOE OSTI2021

Determining fast-S and slow-S propagation directions with SV-P data produced by buried explosives and recorded with vertical geophones

We have evaluated the concept of practicing S-wave reflection seismology with legacy 3D seismic data generated by a P-wave source and recorded with only vertical geophones. This type of S-wave imaging is based on the principle that seismic P-wave sources not only produce a downgoing illuminating P wavefield, but they also simultaneously produce a downgoing illuminating SV wavefield that, in almost all cases, is suitable for S-wave reflection imaging. The S-mode used in this study is the SV-P, or converted-P, mode. This mode involves a downgoing illuminating SV wavefield and an upgoing reflected P-mode that is recorded by vertical geophones. In flat-layered stratigraphy, the lengths of the SV and P raypaths in SV-P imaging are identical to the lengths of the SV and P raypaths in P-SV imaging with P-sources and 3C geophones. P-SV imaging of deep rocks has been practiced for more than two decades; SV-P imaging is a new concept. SV-P data should provide the same options for investigating deep rocks as do P-SV data. We have determined one of the equivalences between SV-P data extracted from vertical-geophone data and P-SV data extracted from horizontal geophones: that both modes react to azimuth-dependent variations in the S velocity in anisotropic rocks. Azimuthal variations in the SV-P traveltime can be used to define the polarization direction of the fast-S-wave mode, which is also the azimuth of the maximum horizontal stress (SHmax). Our investigation demonstrates a noninvasive method for monitoring changes in the SHmax azimuth across a CO 2 storage reservoir, or any targeted porous rock, as fluids are cycled into, and then out of, that rock’s pore space.

Geochemistry & Geophysics↗
DOE OSTI2022

Transfer learning for smart buildings: A critical review of algorithms, applications, and future perspectives

Smart buildings play a crucial role toward decarbonizing society, as globally buildings emit about one-third of greenhouse gases. In the last few years, machine learning has achieved a notable momentum that, if properly harnessed, may unleash its potential for advanced analytics and control of smart buildings, enabling the technique to scale up for supporting the decarbonization of the building sector. In this perspective, transfer learning aims to improve the performance of a target learner exploiting knowledge in related environments. The present work provides a comprehensive overview of transfer learning applications in smart buildings, classifying and analyzing 77 papers according to their applications, algorithms, and adopted metrics. The study identified four main application areas of transfer learning: (1) building load prediction, (2) occupancy detection and activity recognition, (3) building dynamics modeling, and (4) energy systems control. Furthermore, the review highlighted the role of deep learning in transfer learning applications that has been used in more than half of the analyzed studies. The paper also discusses how to integrate transfer learning in a smart building's ecosystem, identifying, for each application area, the research gaps and guidelines for future research directions.

Pinto, G↗
DOE OSTI2024

Graph Analytics for CEBAF Operations

We report on the progress achieved during a 2-year Laboratory Directed Research and Development (LDRD) project titled “Graph Analytics for CEBAF Operations”. The objective of this project is to leverage deep learning on graph representations of CEBAF’s injector beamline in order to create a tool for improving the efficiency of beam tuning tasks. Specifically, we use graphs to represent the injector beamline at any arbitrary date and time and invoke a graph neural network (GNN) to extract a low-dimensional, informative representation that can be visualized in two-dimensions. By analyzing years of operational data from the CEBAF archiver, good and bad regions of parameter space can be identified. The goal is to exercise this framework as a real-time tool to aid beam tuning, which represents the dominant source of machine downtime.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Improving North American Wildfire Prediction by Integrating a Machine-Learning Fire Model in a Land Surface Model

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

54 ENVIRONMENTAL SCIENCES↗