Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “trigger algorithms”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Ultrafast time-resolved x-ray absorption spectroscopy of ionized urea and its dimer through ab initio nonadiabatic dynamics

Investigating the early dynamics of chemical systems following ionization is essential for our understanding of radiation damage. However, experimental as well as theoretical investigations are very challenging due to the complex nature of these processes. Time-resolved x-ray absorption spectroscopy on a femtosecond timescale, in combination with appropriate simulations, is able to provide crucial insights into the ultrafast processes that occur upon ionization due to its element-specific probing nature. In this theoretical study, we investigate the ultrafast dynamics of valence-ionized states of urea and its dimer employing Tully's fewest switches surface hopping approach using Koopmans' theorem to describe the ionized system. We demonstrate that following valence ionization through a pump pulse, the time-resolved x-ray absorption spectra at the carbon, nitrogen, and oxygen K-edges reveal rich insights into the dynamics. Excited states of the ionized system give rise to time-delayed blueshifts in the x-ray absorption spectra as a result of electronic relaxation dynamics through nonadiabatic transitions. Moreover, our statistical analysis reveals specific structural dynamics in the molecule that induce time-dependent changes in the spectra. For the urea monomer, we elucidate the possibility to trace effects of specific molecular vibrations in the time-resolved x-ray absorption spectra. For the urea dimer, where ionization triggers a proton transfer reaction, we show how the x-ray absorption spectra can reveal specific details on the progress of proton transfer.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Flame acceleration and transition to detonation in a pre-/main-chamber combustion system

Numerical simulations are performed to study the mechanism of deflagration to detonation transition (DDT) in a pre-/main-chamber combustion system with a stoichiometric ethylene–oxygen mixture. A Godunov algorithm, fifth-order in space, and third-order in time, is used to solve the fully compressible Navier–Stokes equations on a dynamically adapting mesh. A single-step, calibrated chemical diffusive model described by Arrhenius kinetics is used for energy release and conservation between the fuel and the product. The two-dimensional simulation shows that a laminar flame grows in the pre-chamber and then develops into a jet flame as it passes through the orifice. A strong shock forms immediately ahead of the flame, reflecting off the walls and interacting with the flame front. The shock–flame interactions are crucial for the development of flame instabilities, which trigger the subsequent flame development. The DDT arises due to a shock-focusing mechanism, where multiple shocks collide at the flame front. A chemical explosive mode analysis (CEMA) criterion is developed to study the DDT ignition mode. Preliminary one-dimensional computations for a laminar propagating flame, a fast flame deflagration, and a Chapman–Jouguet detonation are conducted to demonstrate the validity of CEMA on the chemical-diffusive model, as well as to determine the proper conditioning value for CEMA diagnostic. The two-dimensional analysis with CEMA indicates that the DDT initiated by the shock-focusing mechanism can form a strong thermal expansion region at the flame front that features large positive eigenvalues for the chemical explosive mode and dominance of the local autoignition mode. Thus, the CEMA criterion proposed in this study provides a robust diagnostic for identifying autoignition-supported DDT, of which the emergence of excessive local autoignition mode is found to be a precursor. The effect of grid size, initial temperature, and orifice size are then evaluated, and results show that although the close-chamber DDT is highly stochastic, the detonation initiation mechanism remains robust.

42 ENGINEERING↗
DOE OSTI2021

The Event Detection System in the NEXT-White Detector

This article describes the event detection system of the NEXT-White detector, a 5 kg high pressure xenon TPC with electroluminescent amplification, located in the Laboratorio Subterráneo de Canfranc (LSC), Spain. The detector is based on a plane of photomultipliers (PMTs) for energy measurements and a silicon photomultiplier (SiPM) tracking plane for offline topological event filtering. The event detection system, based on the SRS-ATCA data acquisition system developed in the framework of the CERN RD51 collaboration, has been designed to detect multiple events based on online PMT signal energy measurements and a coincidence-detection algorithm. Implemented on FPGA, the system has been successfully running and evolving during NEXT-White operation. The event detection system brings some relevant and new functionalities in the field. A distributed double event processor has been implemented to detect simultaneously two different types of events thus allowing simultaneous calibration and physics runs. This special feature provides constant monitoring of the detector conditions, being especially relevant to the lifetime and geometrical map computations which are needed to correct high-energy physics events. Other features, like primary scintillation event rejection, or a double buffer associated with the type of event being searched, help reduce the unnecessary data throughput thus minimizing dead time and improving trigger efficiency.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Using Cosmic Ray Muons to Assess Geological Characteristics in the Subsurface

Cosmic rays are energetic nuclei and elementary particles that originate from stars and intergalactic events. The interaction of these particles with the upper atmosphere produces a wide range of secondary particles that reach the surface of the earth, of which muons are the most prominent. With enough energy, muons can travel up to a few kilometers beneath the surface of the earth before being stopped completely. The terrestrial muon flux profile and associated zenith angle can be utilized to determine geological characteristics of a location (e.g., rock overburden and density) without having to use conventional methods such as boreholes. This work uses a low-power plastic scintillator-based muon detection system as a prototype for this non-destructive geological assay methodology. Four custom designed 102 cm x 51 cm x 5 cm plastic scintillation panels are used to realize two orthogonal detection planes. Optical photons from each scintillation panel are read using OnSemi J-Series 4x4 silicon photomultiplier (SiPM) arrays in conjunction with preamplifiers. Simultaneous triggers between detectors from two planes indicate a coincidence event which is recorded using the QuarkNet data acquisition system (DAQ) from Fermi National Accelerator Laboratory. A custom detector holder was designed to securely mount the detection system and rotate the panels along the zenith to collect data at variable angles. In order to quantify the systematic uncertainties associated with the detector, such as energy depositions and angular resolution of the detector design, a Monte Carlo (MC) simulation using Geant4 is being developed. Cosmic ray flux prediction will be included in the project by adding the CORSIKA MC code to the simulation toolchain. Simulated and experimental data will drive the development and validation of a reconstruction algorithm that, upon completion, is expected to predict average overburden and rock density. Extended detector exposure to muons can be used as a means to understand changes in the surrounding environment like rock porosity. On the experimental front, muons will initially be measured at the surface, establishing the baseline flux. This is followed by recording the muon flux at variable depths and zenith angles, where the data will be used by the reconstruction algorithm to predict the overburden. The result will be benchmarked against geological surveys. The measured flux data will also be used to benchmark independent and established models. Successful proof-of-concept demonstration of this technology can open doors for long term non-invasive geological monitoring. The detector design, experimental methodology, and the benchmarking efforts are detailed in this work.

Gadey, Harish Reddy↗
DOE OSTI2020

Simulation-driven optimization of high-order meshes in ALE hydrodynamics

Here we propose tools for high-order mesh optimization and demonstrate their benefits in the context of multi-material Arbitrary Lagrangian-Eulerian (ALE) compressible shock hydrodynamic applications. The mesh optimization process is driven by information provided by the simulation which uses the optimized mesh, such as shock positions, material regions, known error estimates, etc. These simulation features are usually represented discretely, for instance, as finite element functions on the Lagrangian mesh. The discrete nature of the input is critical for the practical applicability of the algorithms we propose and distinguishes this work from approaches that strictly require analytical information. Our methods are based on node movement through a high-order extension of the Target-Matrix Optimization Paradigm (TMOP). The proposed formulation is fully algebraic and relies only on local Jacobian matrices, so it is applicable to all types of mesh elements, in 2D and 3D, and any order of the mesh. We discuss the notions of constructing adaptive target matrices and obtaining their derivatives, reconstructing discrete data in intermediate meshes, node limiting that enables improvement of global mesh quality while preserving space-dependent local mesh features, and appropriate normalization of the objective function. The adaptivity methods are combined with automatic ALE triggers that can provide robustness of the mesh evolution and avoid excessive remap procedures. The benefits of the new high-order TMOP technology are illustrated on several simulations performed in the high-order ALE application BLAST.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Distributed Inference with Sparse and Quantized Communication

Here, we consider the problem of distributed inference where agents in a network observe a stream of private signals generated by an unknown state, and aim to uniquely identify this state from a finite set of hypotheses. We focus on scenarios where communication between agents is costly, and takes place over channels with finite bandwidth. To reduce the frequency of communication, we develop a novel event-triggered distributed learning rule that is based on the principle of diffusing low beliefs on each false hypothesis. Building on this principle, we design a trigger condition under which an agent broadcasts only those components of its belief vector that have adequate innovation, to only those neighbors that require such information. We prove that our rule guarantees convergence to the true state exponentially fast almost surely despite sparse communication, and that it has the potential to significantly reduce information flow from uninformative agents to informative agents. Next, to deal with finite-precision communication channels, we propose a distributed learning rule that leverages the idea of adaptive quantization. We show that by sequentially refining the range of the quantizers, every agent can learn the truth exponentially fast almost surely, while using just 1 bit to encode its belief on each hypothesis. For both our proposed algorithms, we rigorously characterize the trade-offs between communication-efficiency and the learning rate.

42 ENGINEERING↗
DOE OSTI2025

Bias-Variance Trade-Off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs

Physics-Informed Neural Networks (PINNs) have triggered a paradigm shift in scientific computing, leveraging mesh-free properties and robust approximation capabilities. While proving effective for low-dimensional partial differential equations (PDEs), the computational cost of PINNs remains a hurdle in high-dimensional scenarios. This is particularly pronounced when computing high-order and high-dimensional derivatives in the physics-informed loss. Randomized Smoothing PINN (RS-PINN) introduces Gaussian noise for stochastic smoothing of the original neural net model, enabling the use of Monte Carlo methods for derivative approximation, which eliminates the need for costly automatic differentiation. Despite its computational efficiency, especially in the approximation of high-dimensional derivatives, RS-PINN introduces biases in both loss and gradients, negatively impacting convergence, especially when coupled with stochastic gradient descent (SGD) algorithms. We present a comprehensive analysis of biases in RS-PINN, attributing them to the nonlinearity of the Mean Squared Error (MSE) loss as well as the intrinsic nonlinearity of the PDE itself. We propose tailored bias correction techniques, delineating their application based on the order of PDE nonlinearity. The derivation of an unbiased RS-PINN allows for a detailed examination of its advantages and disadvantages compared to the biased version. Specifically, the biased version has a lower variance and runs faster than the unbiased version, but it is less accurate due to the bias. To optimize the bias-variance trade-off, we combine the two approaches in a hybrid method that balances the rapid convergence of the biased version with the high accuracy of the unbiased version. In addition to methodological contributions, we present an enhanced implementation of RS-PINN. Extensive experiments on diverse high-dimensional PDEs, including Fokker-Planck, Hamilton-Jacobi-Bellman (HJB), viscous Burgers’, Allen-Cahn, and Sine-Gordon equations, illustrate the bias-variance trade-off and highlight the effectiveness of the hybrid RS-PINN. Empirical guidelines are provided for selecting biased, unbiased, or hybrid versions, depending on the dimensionality and nonlinearity of the specific PDE problem.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A Data Quality-Aware Framework to Reliably Forecast Photovoltaic Generation and Consumer Load for an Improved Resilience of Microgrids

Photovoltaic (PV) power and consumer load forecasting plays a critical role to ensure operational resilience of the electric grid. Most data-driven forecasting algorithms rely heavily on the continuous availability of good quality data for periodic training and validation. When deployed at the grid’s edge, prolonged disruptions to communications during extreme events degrade data quality. Factors such as missing observations, epistemic uncertainties, data drift, and concept drift are manifestations of data quality that impact the generalization of such field-deployed forecasting models. Currently, there exists no mechanism in the literature to dynamically switch between models under varying degrees of data quality as quantified by certain metrics for each factor highlighted above. This paper addresses this shortcoming by conceptually introducing a data qualityaware framework for reliable PV generation and consumer load forecasting. The framework’s design incorporates components of missing values, divergence tests, and continuous monitoring of generalization performance to detect changes in data quality caused by communications disruptions and trigger specific classes of forecasting models grouped under three use cases (UC1- UC3). As a first step towards validating this framework, real data collected from an actual field microgrid system is used to demonstrate the viability of the three use cases. Results show that the performance is the best in UC1 with an unadjusted R-square value of 0.954, followed by 0.939 for UC2 and 0.757 for UC3.

Sundararajan, Aditya↗
DOE OSTI2022

Streaming readout for next generation electron scattering experiments

Current and future experiments at the high-intensity frontier are expected to produce an enormous amount of data that needs to be collected and stored for offline analysis. Thanks to the continuous progress in computing and networking technology, it is now possible to replace the standard ‘triggered’ data acquisition systems with a new, simplified and outperforming scheme. ‘Streaming readout’ (SRO) DAQ aims to replace the hardware-based trigger with a much more powerful and flexible software-based one, that considers the whole detector information for efficient real-time data tagging and selection. Considering the crucial role of DAQ in an experiment, validation with on-field tests is required to demonstrate SRO performance. In this paper, we report results of the on-beam validation of the Jefferson Lab SRO framework. In this work, we exposed different detectors (PbWO-based electromagnetic calorimeters and a plastic scintillator hodoscope) to the Hall-D electron-positron secondary beam and to the Hall-B production electron beam, with increasingly complex experimental conditions. By comparing the data collected with the SRO system against the traditional DAQ, we demonstrate that the SRO performs as expected. Furthermore, we provide evidence of its superiority in implementing sophisticated AI-supported algorithms for real-time data analysis and reconstruction.

47 OTHER INSTRUMENTATION↗
DOE OSTI2026

Aerosol-deep convection interaction based on joint cell-thermal tracking in Large Eddy Simulations during the TRACER campaign

In cumulus clouds, aerosol concentrations control cloud droplet concentrations, modifying cloud radiative properties, precipitation processes, and cloud electrification. However, mechanisms of aerosol-deep convection interactions are not well understood due to complex cloud dynamics and microphysics. We investigate the interaction of aerosols with isolated deep convection using Large Eddy Simulations of two cases during the TRacking Aerosol Convection interactions ExpeRiment (TRACER) near Houston, Texas, using a joint cell-thermal tracking algorithm. Cumulus thermals are droplet generators, since supersaturation and droplet nucleation coincide with thermal centers, where the strongest updrafts occur. Primary ice crystal formation does not take place inside thermals, but at layers where previous thermals detrained moisture. As subsequent thermals containing supercooled droplets penetrate these layers, hail and graupel form at or near these thermals. Higher aerosol concentrations result in higher droplet concentrations that suppress drizzle, delay warm rain processes, and transport more moisture aloft. This increases snow and ice amount, as well as graupel and hail, leading to more lightning. Polluted thermals initiate at slightly higher altitudes, and are slightly larger and faster, suggesting a weak invigoration. We also find more thermals per cell, but fewer isolated cells, since convection is more aggregated and intense, especially near the end of the 24 h simulation. Non-linear mesoscale feedback likely triggered by temperature and moisture responses to aerosol-thermal interactions causes the aggregation. Time-lagged aerosol-reinitialization experiments show that the mesoscale response is the predominant forcing for the invigoration. These changes happen within one day, on a smaller scale than previously suggested.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications

Run to run variability in parallel programs caused by floating-point non-associativity has been known to significantly affect reproducibility in iterative algorithms, due to accumulating errors. Non-reproducibility can critically affect the efficiency and effectiveness of correctness testing for stochastic programs. Recently, the sensitivity of deep learning training and inference pipelines to floating-point non-associativity has been found to sometimes be extreme. It can prevent certification for commercial applications, accurate assessment of robustness and sensitivity, and bug detection. New approaches in scientific computing applications have coupled deep learning models with high-performance computing, leading to an aggravation of debugging and testing challenges. Here we perform an investigation of the statistical properties of floating-point non-associativity within modern parallel programming models, and analyze performance and productivity impacts of replacing atomic operations with deterministic alternatives on GPUs. We examine the recently-added deterministic options in PyTorch within the context of GPU deployment for deep learning, uncovering and quantifying the impacts of input parameters triggering run to run variability and reporting on the reliability and completeness of the documentation. Finally, we evaluate the strategy of exploiting automatic determinism that could be provided by deterministic hardware, using the Groq LPUTM accelerator for inference portions of the deep learning pipeline. We demonstrate the benefits that a hardware-based strategy can provide within reproducibility and correctness efforts.

Shanmugavelu, Sanjif↗
DOE OSTI2021

Online Optimization of NSLS-II Dynamic Aperture and Injection Transient (Facility Improvement Project)

The Facility Improvement Project (FIP) “Methods of online optimization of NSLS-II storage ring concurrent with user operations” proposed and approved in 2018 is now complete. The first goal is the online optimization of nonlinear beam dynamics to increase the beam lifetime and injection efficiency. We have developed a model-independent optimization technique using advanced algorithms. Using this technique, we increased the NSLS-II dynamic aperture by 20% and reduced the amplitude-dependent tune shift by a factor of two. We applied sextupole optimization to the new high-chromaticity lattice, which has been developed to improve the beam stability and to increase the single-bunch beam intensity. We were able to double the injection efficiency and exceed 90%. The second goal of this project is to provide the top-off injection with minimized perturbations of the beamline user operations. To achieve the transparent injection, we optimize the matching of four storage ring injection kickers reducing the perturbation of the stored beam orbit. The first application of the online optimization resulted in a reduction of the amplitude of residual beam oscillation by a factor of six, from 1300 μm down to 200 μm. Further improvement was limited by the timing jitter of the trigger boards. Then, we replaced all trigger boards with a new design and reduced the timing jitter by a factor of five, from 5 ns down to 1 ns. This upgrade resulted in the injection transient reduction from 200 μm to 120 μm. To optimize the full set of kicker parameters, including the trigger timing, amplitude, and pulse width, we upgraded all kicker power supplies with the capability of tunable waveform width. As a result, we have reduced the injection transient to the limit of 60 μm.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

Mitigating Cascading Outages in Severe Weather Using Simulation-Based Optimization

Severe weather events can trigger cascading power outages and lead to significant losses. In this work, we investigate cascading outage mitigation under severe weather conditions. Given day-ahead weather forecasts and component failure models, we aim to identify a set of power lines that can be hardened to minimize the expected impact of potential cascading outages. Since the expected load shedding cannot be expressed as an explicit function of line hardening decisions and system states, we developed a cascading outage simulator to estimate the expected value of load shedding under various initial weather-related disruption scenarios generated using a weather forecast. To avoid massive enumeration of all possible combinations of line hardening decisions and reduce the simulation efforts, we employed an efficient simulation-based optimization approach that quickly identifies the (near) optimal line hardening decisions in the presence of both large simulation noises due to the highly variable initial disturbances and system states, and significant randomness in the subsequent cascades. Furthermore, the algorithm is also able to utilize parallel computing to dramatically reduce computation time to support decision making in preparation for severe weather conditions. We performed a case study on the Northeast Power Coordinating Council (NPCC) 140-bus system model to demonstrate that our approach can significantly improve power grid resilience to adverse weather events.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Oak Ridge National Laboratory Pilot Demonstration of an Attestation and Anomaly Detection Framework using Distributed Ledger Technology for Power Grid Infrastructure

This report summarizes the design and pilot demonstration of a framework called Grid Guard that was created to provide increased data and device trustworthiness to electric grid devices by leveraging distributed ledger technology (DLT), specifically blockchain. Grid Guard contains a combination of core cryptographic methods such as the secure hash algorithm (SHA), and asymmetric cryptography, private permissioned blockchain, baselining configuration data, consensus algorithm (Raft) and the Hyperledger Fabric (HLF) framework. The system implements a low energy, fast, and robust enhancement to system trustworthiness within and across electric grid systems such as substations, control centers and metering infrastructures. Blockchain is a distributed database structured that provides a practically unalterable (immutable) timeline of stored transactions. By relying on hashing and the Raft consensus algorithm, if an entity tries to illegitimately alter a record at one instance of the database the other ledger nodes are not altered. They work to cross-reference each other and easily locate any incorrectly added data and remove it. The bulk raw data is stored in an off-chain storage (outside of the blockchain ledger) and a hash of this baseline data is stored in the Blockchain ledger via hashing windows of time-series and configuration data, after aggregation and filtering. The bulk off-chain data repository is then considered to be trust-anchored using the hashes stored in the blockchain. To secure the electric grid testbed devices and data, device configuration baselines were compared to those baselines that had been previously stored in the ledger. Statistical baselines for device configurations, network communication patterns, and high-speed sensor data are calculated and then stored off-chain and hashes stored in the ledger. Measurements such as three-phase voltage and current, frequency, breaker status, protection scheme settings, network configuration settings (and other device configuration artifacts) and network traffic features (packet interarrival times) are compared every minute or other selected time windows. During phase 1 of the Grid Guard DLT project different DLT technologies were studies, and an assessment was performed on DLT technology vulnerabilities, uses, and key characteristics. DLT consensus protocols were studies (e.g., RAFT, named after Reliable, Replicated, Redundant, And Fault-Tolerant). Also, cryptography, public, private and permissioned or permissionless systems were assessed. Grid Guard implements a permissioned private DLT. Consensus algorithm selection and choice of DLT implementation depended heavily on the use-case. For this use-case, parameters were selected to measure performance and existing tools for assessment. Benchmarking was performed theoretically and practically. During phase 2 hashed transactions/blocks were inserted into the ledger every second. During phase 2 of the Grid Guard DLT project, a prototype framework was developed and demonstrated for attestation of critical substation devices and data using precision timing systems that use PTP and IRIG-B protocols) on a testbed of operational devices that emulated a distribution substation, control center, and power metering infrastructure using real Operational Technology (OT). The testbed includes OT devices such as protective relays, human machine interfaces (HMI), and power meters. To determine when to collect and compare system and network baselines, an initial examination of an anomaly detection capability to identify malicious manipulation of data streams was conducted. The resulting anomaly detection was demonstrated in a set of experiments and leveraged to trigger device artifact attestation checks. Attestation checks occur against device configuration baselines when compared with the immutable blockchain-stored baselines, which provided a cryptographically supported means by which to store baselines. The electrical substation-grid testbed was created to test the Grid Guard framework. The testbed emulates the operations of a portion of a power grid and SCADA systems as closely as possible. The testbed integrates real protocols, mainly IEC 61850 standard protocols, such as the Sampled Value (SV) and the GOOSE protocols. The testbed also supports DNP3 and other layer 2 and layer 3 protocols such as Telnet, SSH, SFTP/FTP and other proprietary protocols needed to connect to industrial control system equipment. The testbed emulates real power conditions using the OpalRT hardware-in-the-loop (HIL) device which can create fault situations that cannot be easily tested on real systems. The electrical substation-grid testbed was created using real measurement, communication, and protection devices that electrical utilities commonly use.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Composited structure of non-precipitating shallow cumulus clouds

The normalized distributions of thermodynamic and dynamical variables both within and outside shallow clouds are investigated through a composite algorithm using large-eddy simulations of oceanic and continental cases. The normalized magnitude is maximum near the cloud centre and decreases outwards. While relative humidity (RH) and cloud liquid water ( q l ) decrease smoothly to match the environment, the vertical velocity, virtual potential temperature (θ v ), and potential temperature (θ) perturbations have more complicated behaviour towards the cloud boundary. Below the inversion layer, θ' v becomes negative before the vertical velocity has turned from an updraft to a subsiding shell outside the cloud, indicating the presence of a transition zone where the updraft is negatively buoyant. Due to the downdraft outside the cloud and enhanced horizontal turbulent mixing across the edge, the normalized turbulent kinetic energy (TKE) and horizontal turbulent kinetic energy (HTKE) decrease more slowly from the cloud centre outwards than the thermodynamic variables. The distributions all present asymmetric structures in response to the vertical wind shear, with more negatively buoyant air, stronger downdrafts, and larger TKE on the downshear side. We discuss several implications of the distributions for theoretical models and parameterizations. Positive buoyancy near the cloud base is mostly due to the virtual effect of water vapour, emphasizing the role of moisture in triggering. The mean vertical velocity is found to be approximately half the maximum vertical velocity within each cloud, providing a constraint to achieve possible power-law distributions for some models. Finally, the normalized distributions for different variables are used to estimate the vertical heat and moisture fluxes within clouds. The results suggest that distributions near the cloud edge and variability of maximum perturbations need careful treatment. The fluxes are underestimated in the inversion layer because cloud-top downdrafts cannot be captured well.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Deep Learning Estimation of Daily Ground–Level NO 2 Concentrations from Remote Sensing Data

The limited number of nitrogen dioxide (NO 2 ) surface measurements calls for the development of highly accurate approaches to estimating surface NO 2 concentrations. In this study, we leverage a new satellite instrument, the TROPOspheric Monitoring Instrument (TROPOMI), along with other predictor variables, to estimate daily surface NO 2 concentrations over Texas in 2019. We use the deep convolutional neural network (Deep-CNN), an advanced deep learning algorithm, to obtain estimates and achieve a correlation coefficient (R) of 0.91, an index of agreement (IOA) of 0.95, and a mean absolute bias (MAB) of 1.75 ppb in surface NO 2 estimation. Additionally, we leverage a novel approach, SHapley Additive exPlanations (SHAP), to describe how Deep-CNN understands each predictor variable. The SHAP results show that the Deep-CNN model has an advanced understanding of the dataset, revealing that TROPOMI closely captures levels of NO 2 . In addition, we show the superiority of our Deep-CNN model at estimating surface NO 2 over other well-known machine learning and regression models in the field, including the support vector machines (SVM), random forest (RF), and multiple linear regression (MLR). Although SVM and RF show strong capabilities at estimating surface NO 2 concentrations, their accuracy is inferior to that of the Deep-CNN model, ranking second and third in model accuracy in this study. The MLR, however, shows a poor ability at NO 2 estimation and ranks last among all models. Furthermore, testing the impact of sample size on model performance, we also show that, compared to other models, Deep-CNN needs more samples to trigger its strength at surface NO 2 estimation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A Heterogeneous System for Eagle Detection, Deterrent, and Wildlife Collision Detection for Wind Turbines (Final Technical Report)

This report summarizes the design, implementation, and test of an integrated system for automated detection and deterrence of eagles, with included wind turbine blade strike detection and imaging functionality. A machine learning approach was used in conjunction with a 360° camera system for automated detection and classification of golden eagles. This was developed using footage obtained from trained golden eagles and other raptors, in collaboration with wildlife biologists and professional bird handlers. Oregon State University developed a visual deterrent system, which uses inflatable anthropomorphic sculptures with random, kinetic motion to deter eagles, and conducted limited field testing on live eagles; the deterrent can be triggered by the visual detection of eagles using the vision system. Finally, a multi-sensor module was developed that is mounted at the turbine blade root. This module measures vibration and other motions to detect blade strikes, and an integrated on-blade camera captures an image of any impacting objects. Long-term, this blade strike detection system is intended to support an automatic monitoring and certification system for the eagle detection and deterent system. Independent field testing of each system component is described. Testing of the integrated system on an operational wind turbine was conducted across three separate field tests. This includes multi-day fields tests on a General Electric 1.5MW wind turbine at the National Renewable Energy Laboratory (NREL) National Wind Technology Center (NWTC) in Boulder, CO in October 2018 and July 2019; installation procedures, test procedures, and a summary of collected data are presented. A third multi-day on-turbine field test is also presented, which was performed using a General Electric 1.5MW wind turbine at the North American Wind Research and Training Center (NAWRTC) at Mesalands Community College, Tucumcari, NM in April 2019. Across these field tests, the vision system was demonstrated using unmanned aerial vehicles (UAV), and the eagle classification algorithm was not tested; the visual deterrent system was demonstrated, including automatic, remote deployment following surrogate visual detections; and, multi-sensor on-blade data was recorded across multiple wind turbine operational conditions and through more than 100 surrogate blade strikes using soft projectiles, including the successful demonstration of automatic image capture of striking objects. This data set was also used for offline development and validation of enhanced collision detection algorithms. As summarized in this report, the development and field validation of an integrated detection, deterrent, and blade collision detection system represents a critical proof of concept for future technology development of related detection and deterrent technologies, where both deterrent as well as collision detection recording devices are needed for future siting, monitoring, and operation of wind turbine installations, both onshore and offshore.

17 WIND ENERGY↗
DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗