SEARCH · Engineering Papers

Results for “learning rate”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,513 records · Page 84

All sources NASA NTRS DOE OSTI

DOE OSTI2023

A Hardware and Software Co-design Framework for Energy Efficient Neuromorphic Systems

Neuromorphic systems can be realized by a variety of algorithms and architectures. A common understanding is that spiking neuromorphic designs, which encode information into spatio-temporal spiking events, are both a biologically-accurate and efficient way of processing information. However, representing the information through timing relationships induces sophisticated circuit designs in traditional CMOS-based implementations. In recent years, high-capacity resistive memory (RRAM, aka, memristor) has demonstrated great potential in mimicking synaptic behaviors. Several RRAM-based spiking neuromorphic designs exist, most of which focus on rate coding schemes. These designs simplify circuit implementations of neuron models and explore challenges such as unsatisfactory speed, resolution, and performance. As an alternative, we will explore temporal coding spiking neuromorphic systems that encode information as the relative timing of neuron activations (spikes), which have been proven to be more adaptive and energy-efficient. Developing a neuromorphic system for spiking neural network (SNN) inference and online training, however, faces some major technical challenges: (1) It lacks circuit implementation support for temporal-coding SNN to achieve satisfying power efficiency and accuracy; (2) Although existing research works have investigated memristive synapse and neuron designs for spike-timing-dependent plasticity, the non-ideal conditions in implementation, such as device variations and signal degradation, degrade online learning accuracy of large scale systems; and (3) Non-optimized, inter-layer data traffic in SNNs, leads to unnecessary data communication costs. In this project, we plan to address these challenges by a hardware and software co-design framework that incorporates solutions at the circuit, architecture, and algorithm levels. At the circuit-level, we will elaborate on the in-situ SNN processing element designs for supporting both inference and online training modes. Variation-aware schemes will be studied to improve reliability. At the architecture level, we propose a pipelined, asynchronous architecture to retain the timing resolution of spikes. At the algorithm level, we will investigate an innovative SNN training algorithm for enabling activation sparsification and reducing unnecessary data communication costs. This neuromorphic system will provide an effective solution to real-life energy-constrained applications and significantly contribute to the exploration of next-generation high-performance computing systems under the DOE context.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Physics-Informed Machine Learning Model for Ceramic Matrix Composite Creep

A physics-informed recurrent neural network (RNN) based surrogate model is developed to emulate the nonlinear, time-dependent constitutive behavior of ceramic matrix composites (CMCs) driven by matrix damage and constituent creep at the microscale. Physics-informed constraints are introduced into the surrogate model through regularization to ground the prediction in physics and improve its predictive capabilities. Training data is generated using the high-fidelity generalized method of cells (HFGMC) approach which calls appropriate creep and damage models for each of the constituents. This coupling permits simulating the nonlinear behavior of CMCs based on constituent response at the microscale along with microstructural features such as fiber and porosity volume fraction and fiber radius. The microscale repeating unit cell is loaded under creep fatigue conditions to replicate the material loading experienced in a turbine engine. Therefore, the RNN-based surrogate model is tasked with predicting, as a function of variable input stress sequence, temperature, and microstructural features, the resulting strain history response while satisfying physical constraints related to creep rate, isochoric inelastic deformation, and strain energy density. The trained surrogate model is shown to effectively match the strain history over quantified distributions of microstructural features and relevant loading regimes and temperatures. Neural network based surrogate models can offer efficient alternatives to running computationally intensive multiscale material models to simulate the nonlinear response of large structural models. Therefore, the presented work provides evidence towards the feasibility of developing, training, and running such models for CMCs with complex microstructures, nonlinear time-dependent material response, and under non-monotonic loading conditions.

ceramic matrix composites↗

DOE OSTI2025

Transformation rate maps of dissolved organic carbon in the contiguous US

Riverine dissolved organic carbon (DOC) plays a vital role in regional and global carbon cycles. However, the processes of DOC conversion from soil organic carbon (SOC) and leaching into rivers are insufficiently understood, inconsistently represented, and poorly parameterized, particularly in land surface and Earth system models. As a first attempt to fill this gap, we propose a generic formula that directly connects SOC concentration with DOC concentration in headwater streams, where a single parameter, the transformation rate from SOC in the soil to DOC leaching flux (P r ), accounts for the overall processes governing SOC conversion to DOC and leaching from soils (along with runoff) into headwater streams. We then derive high-resolution P r maps over the contiguous US (CONUS) using SOC data from two different sources: the Harmonized World Soil Database v1.2 (HWSD) and SoilGrids 2.0. Both maps are developed following the same five major steps: (1) selecting independent catchments where observed riverine DOC data are available with reasonable quality; (2) estimating catchment-average SOC for the independent catchments; (3) estimating the P r values for these catchments based on the generic formula and catchment-average SOC; (4) developing a predictive model of P r with machine learning (ML) techniques and catchment-scale climate, hydrology, geology, and other attributes; and (5) deriving a national map of P r based on the ML model. For evaluation, we compare the DOC concentration derived using the P r map and the observed DOC concentration values at evaluation catchments. The resulting mean absolute scaled error and coefficient of determination are 0.73 and 0.47 for the HWSD-based model and 0.58 and 0.72 for the SoilGrids-based model, respectively, suggesting the effectiveness of the overall methodology. Efforts to constrain uncertainty and evaluate sensitivity of P r to different factors are discussed. To illustrate the use of such maps, we derive a riverine DOC concentration reanalysis dataset over CONUS. The two P r maps, robustly derived and empirically validated, lay a critical cornerstone for better simulating the terrestrial carbon cycle in land surface and Earth system models. Our findings not only set a foundation for improving our predictive understanding of the terrestrial carbon cycle at the regional and global scales, but also hold promises for informing policy decisions related to decarbonization and climate change mitigation. The data presented in this study are publicly available at https://doi.org/10.5281/zenodo.14563816 (Li et al., 2024).

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1998

The Recovery of TOMS-EP

On December 13th 1998, the Total Ozone Mapping Spectrometer - Earth Probe (TOMS-EP) spacecraft experienced a Single Event Upset which caused the system to reconfigure and enter a Safe Mode. This incident occurred two and a half years after the launch of the spacecraft which was designed for a two year life. A combination of factors, including changes in component behavior due to age and extended use, very unfortunate initial conditions and the safe mode processing logic prevented the spacecraft from entering its nominal long term storage mode. The spacecraft remained in a high fuel consumption mode designed for temporary use. By the time the onboard fuel was exhausted, the spacecraft was Sun pointing in a high rate flat spin. Although the uncontrolled spacecraft was initially in a power and thermal safe orientation, it would not stay in this state indefinitely due to a slow precession of its momentum vector. A recovery team was immediately assembled to determine if there was time to develop a method of despinning the vehicle and return it to normal science data collection. A three stage plan was developed that used the onboard magnetic torque rods as actuators. The first stage was designed to reduce the high spin rate to within the linear range of the gyros. The second stage transitioned the spacecraft from sun pointing to orbit reference pointing. The final stage returned the spacecraft to normal science operation. The entire recovery scenario was simulated with a wide range of initial conditions to establish the expected behavior. The recovery sequence was started on December 28th 1998 and completed by December 31st. TOMS-EP was successfully returned to science operations by the beginning of 1999. This paper describes the TOMS-EP Safe Mode design and the factors which led to the spacecraft anomaly and loss of fuel. The recovery and simulation efforts are described. Flight data are presented which show the performance of the spacecraft during its return to science. Finally, lessons learned are presented.

Robertson, Brent↗

NASA NTRS2007

Flight and Integrated Testing: Blazing the Trail for the Ares Launch Vehicles

It has been 30 years since the United States last designed and built a human-rated launch vehicle. The National Aeronautics and Space Administration (NASA) has marshaled unique resources from the government and private sectors that will carry the next generation of astronauts into space safer and more efficiently than ever and send them to the Moon to develop a permanent outpost. NASA's Flight and Integrated Test Office (FITO) located at Marshall Space Flight Center and the Ares I-X Mission Management Office have primary responsibility for developing and conducting critical ground and flight tests for the Ares I and Ares V launch vehicles. These tests will draw upon Saturn and the Space Shuttle experiences, which taught the value of using sound systems engineering practices, while also applying aerospace best practices such as "test as you fly" and other lessons learned. FITO will use a variety of methods to reduce the technical, schedule, and cost risks of flying humans safely aboard a launch vehicle.

Taylor, James L.↗

NASA NTRS2008

Investigation of Condensing Ice Heat Exchangers for MTSA Technology Development

Metabolic heat regenerated Temperature Swing Adsorption (MTSA) technology is being developed for thermal, carbon dioxide (CO2) and humidity control for a Portable Life Support Subsystem (PLSS). Metabolically-produced CO2 present in the ventilation gas of a PLSS is collected using a CO2selective adsorbent via temperature swing adsorption. The temperature swing is initiated through cooling to well below metabolic temperatures. Cooling is achieved with a sublimation heat exchanger using water or liquid carbon dioxide (LCO2) expanded below sublimation temperature when exposed to low pressure or vacuum. Subsequent super heated vapor, as well as additional coolant, is used to further cool the astronaut. The temperature swing on the adsorbent is then completed by warming the adsorbent with a separate condensing ice heat exchanger (CIHX) using metabolic heat from moist ventilation gas. The condensed humidity in the ventilation gas is recycled at the habitat. The water condensation from the ventilation gas is a significant heat transfer mechanism for the warming of the adsorbent bed because it represents as much as half of the energy potential in the moist ventilation gas. Designing a heat exchanger to efficiently transfer this energy to the adsorbent bed and allow the collection of the water is a challenge since the CIHX will operate in a temperature range from 210K to 280K. The ventilation gas moisture will first freeze and then thaw, sometimes existing in three phases simultaneously. A NASA Small Business Innovative Research (SBIR) Phase 1 contract was performed to investigate condensing and icing as applied to MTSA to enable higher fidelity modeling and assess the impact of geometry variables on CIHX performance for future CIHX design optimization. Specifically, a design tool was created using analytical relations to explore the complex, interdependent design space of a condensing ice heat exchanger. Numerous variables were identified as having nontrivial contributions to performance such as hydraulic diameter, heat exchanger effectiveness, ventilation gas mass flow rate and surface roughness. Using this tool, four test articles were designed and manufactured to map to a full MTSA subassembly (the adsorbent bed, the sublimation heat exchanger for cooling and the condensing ice heat exchanger for warming). The design mapping considered impacts due to CIHX geometry as well as subassembly impacts such as thermal mass and thermal resistance through the adsorbent bed. The test articles were tested at simulated PLSS ventilation loop temperature, moisture content and subambient pressure. Ice accumulation and melting were observed. Data and test observations were analyzed to identify drivers of the condensing ice heat exchanger performance. This paper will discuss the analytical models, the test article designs, and testing procedures. Testing issues will be discussed to better describe data and share lessons learned. Data analysis and subsequent conclusions will be presented.

Padilla, Sebastian↗

DOE OSTI2024

Stimulated Emission of Signal Photons from Dark Matter Waves

The manipulation of quantum states of light has resulted in significant advancements in both dark matter searches and gravitational wave detectors. Current dark matter searches operating in the microwave frequency range use nearly quantum-limited amplifiers. Future high frequency searches will use photon counting techniques to evade the standard quantum limit. We present a signal enhancement technique that utilizes a superconducting qubit to prepare a superconducting microwave cavity in a nonclassical Fock state and stimulate the emission of a photon from a dark matter wave. By initializing the cavity in an | n = 4 ⟩ Fock state, we demonstrate a quantum enhancement technique that increases the signal photon rate and hence also the dark matter scan rate each by a factor of 2.78. Using this technique, we conduct a dark photon search in a band around 5.965 GHz ( 24.67 μ eV ), where the kinetic mixing angle ε ≥ 4.35 × 10 − 13 is excluded at the 90% confidence level. Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

Link Scheduling in Satellite Networks via Machine Learning Over Riemannian Manifolds

Low Earth Orbit (LEO) satellites play a crucial role in enhancing global connectivity, serving a complementary solution to existing terrestrial systems. In wireless networks, scheduling is a vital process that allocates time-frequency resources to users for interference management. However, LEO satellite networks face significant challenges in scheduling their links towards ground users due to the satellites’ mobility and overlapping coverage. This paper addresses the dynamic link scheduling problem in LEO satellite networks by considering spatio-temporal correlations introduced by the satellites’ movements. The first step in the proposed solution involves modeling the network over Riemannian manifolds, thanks to their representation as symmetric positive definite matrices. We introduce two machine learning (ML)-based link scheduling techniques that model the dynamic evolution of satellite positions and link conditions over time and space. To accurately predict satellite link states, we present a recurrent neural network (RNN) over Riemannian manifolds, which captures spatio-temporal characteristics over time. Furthermore, we introduce a separate model, the convolutional neural network (CNN) over Riemannian manifolds, which captures geometric relationships between satellites and users by extracting spatial features from the network topology across all links. Simulation results demonstrate that both RNN and CNN over Riemannian manifolds deliver comparable performance to the fractional programming-based link scheduling (FPLinQ) benchmark. Remarkably, unlike other ML-based models that require extensive training data, both models only need 30 training samples to achieve over 99% of the sum rate while maintaining similar computational complexity relative to the benchmark.

42 ENGINEERING↗

DOE OSTI2023

Measurement-induced entanglement phase transitions in variational quantum circuits

Variational quantum algorithms (VQAs), which classically optimize a parametrized quantum circuit to solve a computational task, promise to advance our understanding of quantum many-body systems and improve machine learning algorithms using near-term quantum computers. Prominent challenges associated with this family of quantum-classical hybrid algorithms are the control of quantum entanglement and quantum gradients linked to their classical optimization. Known as the barren plateau phenomenon, these quantum gradients may rapidly vanish in the presence of volume-law entanglement growth, which poses a serious obstacle to the practical utility of VQAs. Inspired by recent studies of measurement-induced entanglement transition in random circuits, we investigate the entanglement transition in variational quantum circuits endowed with intermediate projective measurements. Considering the Hamiltonian Variational Ansatz (HVA) for the XXZ model and the Hardware Efficient Ansatz (HEA), we observe a measurement-induced entanglement transition from volume-law to area-law with increasing measurement rate. Moreover, we provide evidence that the transition belongs to the same universality class of random unitary circuits. Importantly, the transition coincides with a “landscape transition” from severe to mild/no barren plateaus in the classical optimization. Our work may provide an avenue for improving the trainability of quantum circuits by incorporating intermediate measurement protocols in currently available quantum hardware.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

NASA NTRS2014

Addressing Challenges to the Design & Test of Operational Lighting Environments for the International Space Station

In our day to day lives, the availability of light, with which to see our environment, is often taken for granted. The designers of land based lighting systems use sunlight and artificial light as their toolset. The availability of power, quantity of light sources, and variety of design options are often unlimited. The accessibility of most land based lighting systems makes it easy for the architect and engineer to verify and validate their design ideas. Failures with an implementation, while sometimes costly, can easily be addressed by renovation. Consider now, an architectural facility orbiting in space, 260 miles above the surface of the earth. This human rated architectural facility, the International Space Station (ISS) must maintain operations every day, including life support and appropriate human comforts without fail. The facility must also handle logistics of regular shipments of cargo, including new passengers. The ISS requires accommodations necessary for human control of machine systems. Additionally, the ISS is a research facility and supports investigations performed inside and outside its livable volume. Finally, the facility must support remote operations and observations by ground controllers. All of these architectural needs require a functional, safe, and even an aesthetic lighting environment. At Johnson Space Center, our Habitability and Human Factors team assists our diverse customers with their lighting environment challenges, via physical test and computer based analysis. Because of the complexity of ISS operational environment, our team has learned and developed processes that help ISS operate safely. Because of the dynamic exterior lighting environment, uses computational modeling to predict the lighting environment. The ISS' orbit exposes it to a sunrise every 90 minutes, causing work surfaces to quickly change from direct sunlight to earthshine to total darkness. Proper planning of vehicle approaches, robotics operations, and crewed Extra Vehicular Activities are mandatory to ensure safety to the crew and all others involved. Innovation in testing techniques is important as well. The advent of Solid State Lighting technology and the lack of stable national and international standards for its implementation pose new challenges on how to design, test and verify individual light fixtures and the environment that uses them. The ISS will soon be replacing its internal fluorescent lighting system to a solid state LED system. The Solid State Lighting Assembly will be used not only for general lighting, but also as a medical countermeasure to control the circadian rhythm of the crew. The new light source has performance criteria very specific to its spectral fingerprint, creating new challenges that were originally not as significant during the original design of the ISS. This presentation will showcase findings and toolsets our team is using to assist in the planning of tasks, and design of operational lighting environments on the International Space Station.

Clark, Toni A.↗

NASA NTRSDate not supplied

Enhancing Air Traffic Control Planning with Automatic Speech Recognition

The decisions made during the Federal Aviation Administration Air Traffic Control System Command Center's planning teleconferences hold significant sway over the National Airspace System. Held every two hours, these teleconferences convene air traffic managers and stakeholders from across the nation to discuss airspace conditions, weather, and constraints, leading to the formulation and adjustment of traffic management initiatives. Given the critical nature of these decisions, the need for accurate and efficient record-keeping is paramount. In recent years, the application of automatic speech recognition has gained popularity across diverse industries, including aviation. While traditional applications focus on transcribing air traffic control communication, this paper explores a unique application of automatic speech recognition by converting the audio from planning teleconferences into text transcriptions. This innovative approach addresses key challenges in the field, presenting potential benefits for quality assurance, real-time participation, and downstream natural language processing tasks. A notable breakthrough in the machine learning community, namely the transformer neural network architecture, forms the backbone of the proposed solution in this paper. The transformer architecture's role in this research represents a paradigm shift in the efficiency of automatic speech recognition models. By reducing the amount of in-domain training data required, this architecture allows for the fine-tuning of such models like Whisper, originally pretrained on vast English speech datasets. The adaptability of the transformer architecture proves invaluable in capturing the nuances of aviation terminology and specific language used in planning teleconferences. Leveraging the Whisper model as a baseline, our research details the fine-tuning and validation using a dataset comprising 20 hours of meticulously transcribed planning teleconferences. Notably, the baseline pretrained Whisper model exhibited a word error rate of 18.77%. Through the fine-tuning process, the model achieved a substantial improvement, demonstrating an impressive performance with a reduced word error rate of 6.82%. This substantial decrease in WER not only highlights the effectiveness of the transformer architecture but also emphasizes the practical advancements achieved through the application of automatic speech recognition in this specific domain. The utilization of automatic speech recognition in planning teleconferences in this work introduces several novelties. Firstly, the creation of text transcriptions offers a valuable tool for quality assurance and facilitates the efficient review of teleconferences. This is an important aspect of the proposed solution, given the time-sensitive and high-stakes nature of decisions made during these meetings. Furthermore, text-searchable transcriptions provide a streamlined approach for locating and validating critical information, potentially saving hours of manual effort in searching through audio recordings. Moreover, our research identifies a key use case for external facilities and stakeholders. In situations where attendance at the planning teleconference is not feasible, having access to text transcriptions in real-time or shortly after the teleconference ends, proves to be a time-saving and informative resource. This feature enhances collaboration and ensures that stakeholders can stay abreast of important discussions and decisions even in their absence. Despite the efficiency gains facilitated by the transformer architecture in automatic speech recognition technology, it is essential to acknowledge the human factors in data creation. Subject matter experts play a crucial role in accurately transcribing planning teleconferences due to the specificity and complexity of the information discussed. The research dataset, consisting of 20 hours of transcribed planning teleconferences, forms the foundation for fine-tuning and validating the Whisper model. The achieved word error rate of 6.82% demonstrates promising advancements, particularly in recognizing essential aviation terminology within the teleconferences. In conclusion, this paper presents a comprehensive exploration of the application of automatic speech recognition in Air Traffic Control System Command Center planning teleconferences, leveraging the transformer architecture for enhanced efficiency. The novel contributions lie in the improved accessibility of decision-making records, real-time participation opportunities for external stakeholders, and the potential for downstream natural language processing advancements. As the aviation industry continues to evolve, the integration of automatic speech recognition technologies holds the promise of revolutionizing decision-making processes and contributing to the overall safety and efficiency of air traffic management.

ATM↗

NASA NTRS2002

The Microwave Anisotropy Probe (MAP): Guidance, Navigation, and Control Hardware Suite

The Microwave Anisotropy Probe (MAP) was launched June 30, 2001 to create an all-sky map of the Cosmic Microwave Background. The mission's hardware suite included two Lockheed Martin AST-201 star trackers, two Kearfott Two-Axis Rate Assemblies (TARAs) mounted to provide X, Y and redundant Z-axis rates, two Adcole Digital Sun Sensor (DSS) heads sharing one set of electronics, twelve Adcole Coarse Sun Sensor (CSS) eyes, three Ithaco E-sized Reaction Wheel Assemblies (RWAs), and a Propulsion Subsystem that employed eight PRIMEX Rocket Engine Modules (REMs). This hardware has allowed MAP to meet its various Orbit and Attitude Control Requirements, including performing a complex zero-momentum scan, meeting its attitude determination requirements, and maintaining a trajectory that places MAP in a lissajous orbit around the second Sun-Earth Lagrange point (L2) via phasing loops and a lunar gravity assist. Details of MAP's attitude determination, attitude control, and trajectory design are presented separately. This paper will focus on the performance of the hardware components mentioned above, as well as the significant lessons learned through the use of these components. An emphasis will be placed on spacecraft design modifications that were needed to accommodate existing hardware designs into the MAP Observatory design.

Ward, David K.↗

NASA NTRS2005

Convergence Acceleration and Documentation of CFD Codes for Turbomachinery Applications

The development and analysis of turbomachinery components for industrial and aerospace applications has been greatly enhanced in recent years through the advent of computational fluid dynamics (CFD) codes and techniques. Although the use of this technology has greatly reduced the time required to perform analysis and design, there still remains much room for improvement in the process. In particular, there is a steep learning curve associated with most turbomachinery CFD codes, and the computation times need to be reduced in order to facilitate their integration into standard work processes. Two turbomachinery codes have recently been developed by Dr. Daniel Dorney (MSFC) and Dr. Douglas Sondak (Boston University). These codes are entitled Aardvark (for 2-D and quasi 3-D simulations) and Phantom (for 3-D simulations). The codes utilize the General Equation Set (GES), structured grid methodology, and overset O- and H-grids. The codes have been used with success by Drs. Dorney and Sondak, as well as others within the turbomachinery community, to analyze engine components and other geometries. One of the primary objectives of this study was to establish a set of parametric input values which will enhance convergence rates for steady state simulations, as well as reduce the runtime required for unsteady cases. The goal is to reduce the turnaround time for CFD simulations, thus permitting more design parametrics to be run within a given time period. In addition, other code enhancements to reduce runtimes were investigated and implemented. The other primary goal of the study was to develop enhanced users manuals for Aardvark and Phantom. These manuals are intended to answer most questions for new users, as well as provide valuable detailed information for the experienced user. The existence of detailed user s manuals will enable new users to become proficient with the codes, as well as reducing the dependency of new users on the code authors. In order to achieve the objectives listed, the following tasks were accomplished: 1) Parametric Study Of Preconditioning Parameters And Other Code Inputs; 2) Code Modifications To Reduce Runtimes; 3) Investigation Of Compiler Options To Reduce Code Runtime; and 4) Development/Enhancement of Users Manuals for Aardvark and Phantom

Marquart, Jed E.↗

NASA NTRS2015

A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

Segments↗

DOE OSTI2025

Dependence of Convective Cloud Microphysical Properties on Environmental Conditions during the TRACER and ESCAPE Field Campaigns: A Synergistic Approach of Observations, Machine Learning and Parcel Models

The sensitivity of convective clouds to aerosols and their interactions with environment, combined with limited observational constraints in parameterizations, introduces significant uncertainties in atmospheric models. Here, this study investigates the dependence of convective cloud microphysical properties on environmental conditions using a synergistic approach that combines unique observations from the TRACER and ESCAPE field campaigns, machine learning techniques, and parcel model simulations with a super-droplet microphysics scheme. A random forest algorithm identifies in-situ vertical velocity (w), temperature (T), and surface fine-mode aerosol mass concentration as the three most important environmental conditions influencing cloud properties including liquid water content (LWC), number concentration for particles with D max < 50 μm (N c ,<50), 50 μm ≤ D max ≤ 3000 μm (N c,50–3000 ), and droplet effective diameter (D e ). Results show that LWC, N c,<50 , and N c,50–3000 significantly increase with w in updrafts. Across w bins, as T decreases, LWC, D e , and N c,50–3000 increase, while N c,<50 decreases, which are closely linked to the distance above cloud bases. Warmer cloud bases yield higher LWC, greater N c,50–3000 , and smaller N c,<50 , while polluted environments produce greater N c,<50 . Parcel model simulations successfully replicate these observed dependencies. The simulation results indicate that warmer cloud bases enhance condensation generating larger droplets, and differences in droplet sizes are then amplified through collision-coalescence, resulting in a greater N c,50–3000 . Polluted conditions result in a greater N c,<50 primarily due to enhanced cloud condensation nuclei activation despite increased collision-coalescence rates compared to pristine conditions. This study provides observed quantitative patterns characterizing cloud microphysical properties as a function of key environmental parameters, offering valuable constraints for improving physics parameterizations and numerical models.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

The Deeper, Wider, Faster programme: exploring stellar flare activity with deep, fast cadenced DECam imaging via machine learning

ABSTRACT We present our 500 pc distance-limited study of stellar flares using the Dark Energy Camera as part of the Deeper, Wider, Faster programme. The data were collected via continuous 20-s cadence g-band imaging and we identify 19 914 sources with precise distances from Gaia DR2 within 12, ∼3 deg2, fields over a range of Galactic latitudes. An average of ∼74 min is spent on each field per visit. All light curves were accessed through a novel unsupervised machine learning techniques designed for anomaly detection. We identify 96 flare events occurring across 80 stars, the majority of which are M dwarfs. Integrated flare energies range from ∼1031–1037 erg, with a proportional relationship existing between increased flare energy with increased distance from the Galactic plane, representative of stellar age leading to declining yet more energetic flare events. In agreement with previous studies we observe an increase in flaring fraction from M0 to M6 spectral types. Furthermore, we find a decrease in the flaring fraction of stars as vertical distance from the galactic plane is increased, with a steep decline present around ∼100 pc. We find that $\sim 70{{\ \rm per\ cent}}$ of identified flares occur on short time-scales of <8 min. Finally, we present our associated flare rates, finding a volumetric rate of 2.9 ± 0.3 × 10−6 flares pc−3 h−1.

Webb, S.↗

DOE OSTI2024

Characterizing Mesoscale Cellular Convection in Marine Cold Air Outbreaks With a Machine Learning Approach

Abstract During marine cold‐air outbreaks (MCAOs), when cold polar air moves over warmer ocean, a well‐recognized cloud pattern develops, with open or closed mesoscale cellular convection (MCC) at larger fetch over open water. The Cold‐Air Outbreaks in the Marine Boundary Layer Experiment provided a comprehensive set of ground‐based in situ and remote sensing observations of MCAOs at a coastal location in northern Norway. MCAO periods that unambiguously exhibit open or closed MCC are determined. Individual cells observed with a profiling Ka‐band radar are identified using a watershed segmentation method. Using self‐organizing maps (SOMs), these cells are then objectively classified based on the variability in their vertical structure. The SOM nodes contain some information about the location of the cell transect relative to the center of the MCC. This adds classification noise, requiring numerous cell transects to isolate cell dynamical information. The SOM‐based classification shows that comparatively intense convection occurs only in open MCC. This convection undergoes an apparent lifecycle. Developing cells are associated with stronger updrafts, large spectrum width, larger amounts of liquid water, lower surface precipitation rates, and lower cloud tops than mature and weakening cells. The weakening of these cells is associated with the development of precipitation‐induced cold pools. The SOM classification also reveals less intense convection, with a similar lifecycle. More stratiform vertical cloud structures with weak vertical motions are common during closed MCC periods and are separated into precipitating and non‐precipitating stratiform cores. Convection is observed only occasionally in the closed MCC environment.

Meteorology & Atmospheric Sciences↗

DOE OSTI2022

Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN

Physics-informed neural network (PINN) has been successfully applied in solving a variety of nonlinear non-convex forward and inverse problems. However, the training is challenging because of the non-convex loss functions and the multiple optima in the Bayesian inverse problem. In this work, we propose a multi-variance replica exchange stochastic gradient Langevin dynamics method to tackle the challenge of the multiple local optima in the optimization and the challenge of the multiple modal posterior distribution in the inverse problem. Replica exchange methods are capable of escaping from the local traps and accelerating the convergence; two chains with different temperatures are designed where the low temperature chain aims for the local convergence, and the target of the high temperature chain is to travel globally and explore the whole loss function entropy landscape. However, it may not be efficient to solve mathematical inversion problems by using the vanilla replica method directly since the method doubles the computational cost in evaluating the forward solvers (likelihood functions) in the two chains. To address this issue, we propose to make different assumptions on the energy function estimation and this facilities one to use solvers of different fidelities in the likelihood function evaluation. More precisely, one can use a solver with low fidelity in the high temperature chain while using a solver with high fidelity in the low temperature chain. Our proposed method significantly lowers the computational cost in the high temperature chain, meanwhile preserving the accuracy and converging very fast. Here we give an unbiased estimate of the swapping rate and give an estimation of the discretization error of the scheme. To verify our idea, we design and solve four inverse problems which have multiple modes. The proposed method is also employed to train the Bayesian PINN to solve the forward and inverse problems; faster and more accurate convergence has been observed when compared to the stochastic gradient Langevin dynamics (SGLD) method and vanilla replica exchange methods.

97 MATHEMATICS AND COMPUTING↗