Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “task tuning”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Structural Anisotropy Determining the Oxygen Evolution Mechanism of Strongly Correlated Perovskite Nickelate Electrocatalyst

The regulation of reactive centers by involving the participation of lattice oxygen has been reported as an effective strategy for lowering the reaction barrier for the oxygen evolution reaction (OER). However, the control of the OER pathway by taking advantage of the intrinsic properties of catalysts remains a challenging task. Herein, we adopt perovskite nickelate (i.e., NdNiO3 (NNO)) and establish the link between structural anisotropy and the OER catalytic mechanism. The results elucidate that NNO with (100), (110), and (111) orientations display similar oxidative states and metal–oxygen covalency characteristics but distinct OER activities following the order of (100) > (110) > (111). Density function theory (DFT) results confirm that film orientation is a critical determinant of the reaction mechanism. The OER on (100)-NNO favors proceeding via a lattice-oxygen-mediated mechanism (LOM). In contrast, the reaction on (110)-NNO and (111)-NNO follows the adsorbate evolution mechanism (AEM). The anisotropic oxygen vacancy formation energy and stability are strongly correlated to the reaction mechanism and performance, which can be described in brief by the metal–oxygen bond valence. Furthermore, our results are a step toward achieving the long-sought convenient approach to tune the OER mechanism, which is applicable for a wide range of sustainable energy-related devices.

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

Autodifferentiable Ensemble Kalman Filters

Data assimilation is concerned with sequentially estimating a temporally evolving state. This task, which arises in a wide range of scientific and engineering applications, is particularly challenging when the state is high-dimensional and the state-space dynamics are unknown. This paper introduces a machine learning framework for learning dynamical systems in data assimilation. Here, our auto-differentiable ensemble Kalman filters (AD-EnKFs) blend ensemble Kalman filters for state recovery with machine learning tools for learning the dynamics. In doing so, AD-EnKFs leverage the ability of ensemble Kalman filters to scale to high-dimensional states and the power of automatic differentiation to train high-dimensional surrogate models for the dynamics. Numerical results using the Lorenz-96 model show that AD-EnKFs outperform existing methods that use expectation-maximization or particle filters to merge data assimilation and machine learning. In addition, AD-EnKFs are easy to implement and require minimal tuning.

autodifferentiation↗
NASA NTRS2024

Applying Generative-AI to NASA Documentation and Processes

This research and development project leverages generative-AI to assist in the generation of software process documentation based on NASA standards. By utilizing fine-tuned AI models, the proposed system will analyze NASA's software guidelines, helping to translate them into well-structured, compliant process documents. This assistance can reduce the manual effort required to produce such documentation, enhance consistency, and assure alignment with NASA's stringent software development and operational requirements. In addition to assisting in the generation of software process documentation, the project explores how generative-AI can help create audit checklists as well as assess the compliance of NASA provider documentation against applicable NASA standards. This approach would support the compliance auditing process, providing real-time insights and assessments. The intended result will be a streamlined process, potentially including a Python-based tool and database, that improves audit efficiency, reduces human error, lowers manpower costs and required manhours, and assures continuous compliance with NASA and industry evolving standards for safety-critical software development. Future task might be to investigate the software industry approach and standards for potential collaboration.

NASA Standards↗
NASA NTRS2012

Prediction of Traffic Complexity and Controller Workload in Mixed Equipage NextGen Environments

Controller workload is a key factor in limiting en route air traffic capacity. Past efforts to quantify and predict workload have resulted in identifying objective metrics that correlate well with subjective workload ratings during current air traffic control operations. Although these metrics provide a reasonable statistical fit to existing data, they do not provide a good mechanism for estimating controller workload for future air traffic concepts and environments that make different assumptions about automation, enabling technologies, and controller tasks. One such future environment is characterized by en route airspace with a mixture of aircraft equipped with and without Data Communications (Data Comm). In this environment, aircraft with Data Comm will impact controller workload less than aircraft requiring voice communication, altering the close correlation between aircraft count and controller workload that exists in current air traffic operations. This paper outlines a new trajectory-based complexity (TBX) calculation that was presented to controllers during a human-in-the-loop simulation. The results showed that TBX accurately estimated the workload in a mixed Data Comm equipage environment and the resulting complexity values were understood and readily interpreted by the controllers. The complexity was represented as a "modified aircraft account" that weighted different complexity factors and summed them in such a way that the controllers could effectively treat them as aircraft count. The factors were also relatively easy to tune without an extensive data set. The results showed that the TBX approach is well suited for presenting traffic complexity in future air traffic environments.

Lee, Paul U.↗
DOE OSTI2023

Iterative sampling of expensive simulations for faster deep surrogate training

Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in-the-loop; surrogates based on DNNs can effectively emulate diverse non-scalar data of the types collected in fusion and laboratory-astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. Here, in this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high-quality and wide-ranging surrogate models to be trained using 2–3 times fewer simulations compare to space-filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Natural switches in behaviour rapidly modulate hippocampal coding

Throughout their daily lives, animals and humans often switch between different behaviours. However, neuroscience research typically studies the brain while the animal is performing one behavioural task at a time, and little is known about how brain circuits represent switches between different behaviours. Here we tested this question using an ethological setting: two bats flew together in a long 135 m tunnel, and switched between navigation when flying alone (solo) and collision avoidance as they flew past each other (cross-over). Bats increased their echolocation click rate before each cross-over, indicating attention to the other bat. Hippocampal CA1 neurons represented the bat’s own position when flying alone (place coding). Notably, during cross-overs, neurons switched rapidly to jointly represent the interbat distance by self-position. This neuronal switch was very fast—as fast as 100 ms—which could be revealed owing to the very rapid natural behavioural switch. The neuronal switch correlated with the attention signal, as indexed by echolocation. Interestingly, the different place fields of the same neuron often exhibited very different tuning to interbat distance, creating a complex non-separable coding of position by distance. Theoretical analysis showed that this complex representation yields more efficient coding. Overall, our results suggest that during dynamic natural behaviour, hippocampal neurons can rapidly switch their core computation to represent the relevant behavioural variables, supporting behavioural flexibility.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2004

Lithium Polymer Electrolytes and Solid State NMR

Research is being done at the Glenn Research Center (GRC) developing new kinds of batteries that do not depend on a solution. Currently, batteries use liquid electrolytes containing lithium. Problems with the liquid electrolyte are (1) solvents used can leak out of the battery, so larger, more restrictive, packages have to be made, inhibiting the diversity of application and decreasing the power density; (2) the liquid is incompatible with the lithium metal anode, so alternative, less efficient, anodes are required. The Materials Department at GRC has been working to synthesize polymer electrolytes that can replace the liquid electrolytes. The advantages are that polymer electrolytes do not have the potential to leak so they can be used for a variety of tasks, small or large, including in the space rover or in space suits. The polymers generated by Dr. Mary Ann Meador's group are in the form of rod -coil structures. The rod aspect gives the polymer structural integrity, while the coil makes it flexible. Lithium ions are used in these polymers because of their high mobility. The coils have repeating units of oxygen which stabilize the positive lithium by donating electron density. This aids in the movement of the lithium within the polymer, which contributes to higher conductivity. In addition to conductivity testing, these polymers are characterized using DSC, TGA, FTIR, and solid state NMR. Solid state NMR is used in classifying materials that are not soluble in solvents, such as polymers. The NMR spins the sample at a magic angle (54.7') allowing the significant peaks to emerge. Although solid state NMR is a helpful technique in determining bonding, the process of preparing the sample and tuning it properly are intricate jobs that require patience; especially since each run takes about six hours. The NMR allows for the advancement of polymer synthesis by showing if the expected results were achieved. Using the NMR, in addition to looking at polymers, allows for participation on a variety of other projects, including aero-gels and carbon graphite mat en als. The goals of the polymer electrolyte research are to improve the physical properties of the polymers. This includes improving conductivity, durability, and expanding the temperature range over which it is effective. Currently, good conductivity is only present at high temperatures. My goals are to experiment with different arrangements of rods and coils to achieve these desirable properties. Some of my experiments include changing the number of repeat units in the polymer, the size of the diamines, and the types of coil. Analysis of these new polymers indicates improvement in some properties, such as lower glass transition temperature; however, they are not as flexible as desired. With further research we hope to produce polymers that encompass all of these properties to a high degree.

Berkeley, Emily R.↗
NASA NTRS2002

Test Platform for Advanced Digital Control of Brushless DC Motors (MSFC Center Director's Discretionary Fund)

A FY 2001 Center Director's Discretionary Fund task to develop a test platform for the development, implementation. and evaluation of adaptive and other advanced control techniques for brushless DC (BLDC) motor-driven mechanisms is described. Important applications for BLDC motor-driven mechanisms are the translation of specimens in microgravity experiments and electromechanical actuation of nozzle and fuel valves in propulsion systems. Motor-driven aerocontrol surfaces are also being utilized in developmental X vehicles. The experimental test platform employs a linear translation stage that is mounted vertically and driven by a BLDC motor. Control approaches are implemented on a digital signal processor-based controller for real-time, closed-loop control of the stage carriage position. The goal of the effort is to explore the application of advanced control approaches that can enhance the performance of a motor-driven actuator over the performance obtained using linear control approaches with fixed gains. Adaptive controllers utilizing an exact model knowledge controller and a self-tuning controller are implemented and the control system performance is illustrated through the presentation of experimental results.

Gwaltney, D. A.↗
NASA NTRS1992

A comparison of force control algorithms for robots in contact with flexible environments

In order to perform useful tasks, the robot end-effector must come into contact with its environment. For such tasks, force feedback is frequently used to control the interaction forces. Control of these forces is complicated by the fact that the flexibility of the environment affects the stability of the force control algorithm. Because of the wide variety of different materials present in everyday environments, it is necessary to gain an understanding of how environmental flexibility affects the stability of force control algorithms. This report presents the theory and experimental results of two force control algorithms: Position Accommodation Control and Direct Force Servoing. The implementation of each of these algorithms on a two-arm robotic test bed located in the Center for Intelligent Robotic Systems for Space Exploration (CIRSSE) is discussed in detail. The behavior of each algorithm when contacting materials of different flexibility is experimentally determined. In addition, several robustness improvements to the Direct Force Servoing algorithm are suggested and experimentally verified. Finally, a qualitative comparison of the force control algorithms is provided, along with a description of a general tuning process for each control method.

Wilfinger, Lee S.↗
DOE OSTI2021

Tunable Stochasticity in an Artificial Spin Network

Metamaterials present the possibility of artificially generating advanced functionalities through engineering of their internal structure. Artificial spin networks, in which a large number of nanoscale magnetic elements are coupled together, are promising metamaterial candidates that enable the control of collective magnetic behavior through tuning of the local interaction between elements. In this work, the motion of magnetic domain-walls in an artificial spin network leads to a tunable stochastic response of the metamaterial, which can be tailored through an external magnetic field and local lattice modifications. This type of tunable stochastic network produces a controllable random response exploiting intrinsic stochasticity within magnetic domain-wall motion at the nanoscale. An iconic demonstration used to illustrate the control of randomness is the Galton board. In this system, multiple balls fall into an array of pegs to generate a bell-shaped curve that can be modified via the array spacing or the tilt of the board. A nanoscale recreation of this experiment using an artificial spin network is employed to demonstrate tunable stochasticity. Furthermore, this type of tunable stochastic network opens new paths toward post-Von Neumann computing architectures such as Bayesian sensing or random neural networks, in which stochasticity is harnessed to efficiently perform complex computational tasks.

Artificial spin network↗
DOE OSTI2024

Trace benzene capture by decoration of structural defects in metal–organic framework materials

Abstract Capture of trace benzene is an important and challenging task. Metal–organic framework materials are promising sorbents for a variety of gases, but their limited capacity towards benzene at low concentration remains unresolved. Here we report the adsorption of trace benzene by decorating a structural defect in MIL-125-defect with single-atom metal centres to afford MIL-125-X (X = Mn, Fe, Co, Ni, Cu, Zn; MIL-125, Ti 8 O 8 (OH) 4 (BDC) 6 where H 2 BDC is 1,4-benzenedicarboxylic acid). At 298 K, MIL-125-Zn exhibits a benzene uptake of 7.63 mmol g −1 at 1.2 mbar and 5.33 mmol g −1 at 0.12 mbar, and breakthrough experiments confirm the removal of trace benzene (from 5 to <0.5 ppm) from air (up to 111,000 min g −1 of metal–organic framework), even after exposure to moisture. The binding of benzene to the defect and open Zn(II) sites at low pressure has been visualized by diffraction, scattering and spectroscopy. This work highlights the importance of fine-tuning pore chemistry for designing adsorbents for the removal of air pollutants.

Chemistry↗
DOE OSTI2026

Artificial Intelligence for Event Reconstruction and Higgs Physics at CMS and Future Colliders

This dissertation charts a trajectory in which advances in artificial intelligence (AI) play a central role in pushing the high-energy physics frontier, complementing progress driven by higher collision energies and larger colliders. The discovery potential of the LHC and future colliders relies on accurate reconstruction of increasingly complex particle collision events. In the CMS experiment, this task is performed by the particle-flow (PF) algorithm. This dissertation presents the first implementation of a machine-learning-based particle-flow (MLPF) reconstruction in the CMS detector based on transformer architectures. In simulated top quark--antiquark pair (ttbar) events under LHC Run~3 (2023--2024) conditions, MLPF improves jet energy resolution by 10--20\% compared to standard PF for jets with transverse momentum between 30--100\GeV. Runtime performance is evaluated using simulated multijet events, with a median inference time of 20\unit{ms} per event on an NVIDIA L4 GPU, compa red to approximately 110\unit{ms} for standard PF. The MLPF algorithm is also validated on Run~3 collision data, representing the first data-validated ML-based reconstruction pipeline at any LHC experiment. We then extend MLPF toward future electron--positron colliders and introduce the first full-simulation cross-detector transfer learning workflow for PF reconstruction. The model is pre-trained on simulated events from the Compact Linear Collider detector (CLICdet) and fine-tuned on the CLIC-like detector (CLD) proposed for the Future Circular Collider (FCC). This approach achieves up to a 40\% improvement in jet energy resolution over rule-based reconstruction while reducing the required training dataset size by an order of magnitude, demonstrating the potential of AI to accelerate detector development and optimization. This dissertation also demonstrates how modern AI techniques enhance the sensitivity of LHC physics analyses. A CMS search for highly Lorentz-boosted Higgs bosons decaying to \textrm{W} boson pairs is presented, focusing on the single-lepton final state. A dedicated fine-tuning strategy for \ParT yields an approximately 70\% increase in expected sensitivity relative to the baseline model. The analysis uses proton--proton collision data at a center-of-mass energy of \ensuremath{\sqrt{s}=13\TeV} collected by CMS between 2016 and 2018, corresponding to an integrated luminosity of 138\ensuremath{\ \mathrm{fb}^{-1}}. The expected significance of the search is $1.86\sigma$, with an observed signal strength of $-0.19^{+0.48}_{-0.46}$. Finally, explainable AI techniques are applied to the MLPF and \ParticleNet algorithms using layerwise relevance propagation, showing that both models base their predictions on physically meaningful features consistent with our physics intuition. Together, these results demonstrate how advanced AI methods can enhance reconstruction, analysis sensitivity, and interpretability, shaping the next era of experimental parti cle physics.

Mokhtar, Farouk [UC, San Diego]↗
DOE OSTI2025

Collaborative: in situ visual analytics technologies for extreme scale combustion simulations

This project aims to drastically enhance the usability of in situ analysis and visualization for extreme-scale scientific simulations. Current exascale computing capabilities promise to offer greater predictive ability of simulations and to further push the frontiers of science and technology. However, to validate the simulation output at extreme scale, examine the modeled phenomena, and discover previously unknowns from the output data, the output must be reduced or transformed in situ as it is being generated during the simulation such that the amount of data to examine and store is kept to a minimum. Such in situ approaches allow us to process and analyze the data and any embedded geometry to an extent that would be prohibitively expensive, if not impossible, to perform as a post hoc task. While in situ processing has been demonstrated to be a feasible and promising approach, its full potential has not yet been leveraged. In this project, we have developed comprehensive enhancements to in situ technology based on probability distributions in data. Our research focuses on jointly developing new ways of interacting with massive statistical samples while creatively utilizing new state-of-the-art computational resources to push the boundaries of in situ exploration. Moreover, we have developed new time-dependent techniques to enable previously unattainable capabilities in areas such as intelligent simulation steering and precise feature identification. We have experimentally studied our design and implementation at NERSC and OLCF, and are able to leverage existing in situ infrastructures whenever possible. While the exemplar in this project is combustion, many other fields for which turbulent transport is important, e.g., fusion, climate, astrophysics among others, encounter similar issues as simulations scale up to the exascale. This project shows its potential to generate high impact on DOE missions since the resulting technology promises to improve scientists’ ability to rapidly and correctly interpret and tune extreme-scale simulations, leading to new scientific understanding and advancements.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1999

A Survey of Collective Intelligence

This chapter presents the science of "COllective INtelligence" (COIN). A COIN is a large multi-agent systems where: i) the agents each run reinforcement learning (RL) algorithms; ii) there is little to no centralized communication or control; iii) there is a provided world utility function that, rates the possible histories of tile full system. Tile conventional approach to designing large distributed systems to optimize a world utility does not use agents running RL algorithms. Rather that approach begins with explicit modeling of the overall system's dynamics, followed by detailed hand-tuning of the interactions between the components to ensure that they "cooperate" as far as the world utility is concerned. This approach is labor-intensive, often results in highly non-robust systems, and usually results in design techniques that, have limited applicability. In contrast, with COINs we wish to solve the system design problems implicitly, via the 'adaptive' character of the RL algorithms of each of the agents. This COIN approach introduces an entirely new, profound design problem: Assuming the RL algorithms are able to achieve high rewards, what reward functions for the individual agents will, when pursued by those agents, result in high world utility? In other words, what reward functions will best ensure that we do not have phenomena like the tragedy of the commons, or Braess's paradox? Although still very young, the science of COINs has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem". It is expected that as it matures not only will COIN science expand greatly the range of tasks addressable by human engineers, but it will also provide much insight into already established scientific fields, such as economics, game theory, or population biology.

Wolpert, David H.↗
DOE OSTI2025

Feature learning and generalization in deep networks with orthogonal weights

Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such networks still exhibit fluctuations that grow linearly with the depth of the network, which may impair the training of networks with width comparable to depth. We show analytically that rectangular networks with tanh activations and weights initialized from the ensemble of orthogonal matrices have corresponding preactivation fluctuations which are independent of depth, to leading order in inverse width. Moreover, we demonstrate numerically that, at initialization, all correlators involving the neural tangent kernel (NTK) and its descendants at leading order in inverse width—which govern the evolution of observables during training—saturate at a depth of ~20, rather than growing without bound as in the case of Gaussian initializations. We speculate that this structure preserves finite-width feature learning while reducing overall noise, thus improving both generalization and training speed in deep networks with depth comparable to width. We provide some experimental justification by relating empirical measurements of the NTK to the superior performance of deep non-linear orthogonal networks trained under full-batch gradient descent on the MNIST and CIFAR-10 classification tasks.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

Simultaneous Retrieval of Aerosol and Cloud Properties During the MILAGRO Field Campaign

Estimation of Direct Climate Forcing (DCF) due to aerosols in cloudy areas has historically been a difficult task, mainly because of a lack of appropriate measurements. Recently, passive remote sensing instruments have been developed that have the potential to retrieve both cloud and aerosol properties using polarimetric, multiple view angle, and multi spectral observations, and therefore determine DCF from aerosols above clouds. One such instrument is the Research Scanning Polarimeter (RSP), an airborne prototype of a sensor on the NASA Glory satellite, which unfortunately failed to reach orbit during its launch in March of 2011. In the spring of 2006, the RSP was deployed on an aircraft based in Veracruz, Mexico, as part of the Megacity Initiative: Local and Global Research Observations (MILAGRO) field campaign. On 13 March, the RSP over flew an aerosol layer lofted above a low altitude marine stratocumulus cloud close to shore in the Gulf of Mexico. We investigate the feasibility of retrieving aerosol properties over clouds using these data. Our approach is to first determine cloud droplet size distribution using the angular location of the cloud bow and other features in the polarized reflectance. The selected cloud was then used in a multiple scattering radiative transfer model optimization to determine the aerosol optical properties and fine tune the cloud size distribution. In this scene, we were able to retrieve aerosol optical depth, the fine mode aerosol size distribution parameters and the cloud droplet size distribution parameters to a degree of accuracy required for climate modeling. This required assumptions about the aerosol vertical distribution and the optical properties of the coarse aerosol size mode. A sensitivity study was also performed to place this study in the context of future systematic scanning polarimeter observations, which found that the aerosol complex refractive index can also be observed accurately if the aerosol optical depth is larger than roughly 0.8 at a wavelength of (0.555 m).

Knobelspiesse, K.↗
DOE OSTI2026

Water-stable direct air capture of CO 2 with microcapsules of task-specific ionic liquid and their electrothermal regeneration

Microcapsules of the task specific ionic liquid (TSIL) 1-ethyl-3-methylimidazolium 2-cyanopyrrolide [EMIM][2CNpyr] with composite polydimethylsiloxane (PDMS) shells were fabricated for use in CO 2 direct air capture (DAC) conditions. The TSIL was encapsulated using an oil-in-oil emulsion as a templating procedure through two different approaches. In the first approach, a PDMS-polyurea (PU) shell was constructed by interfacial polymerization, while in the second approach, a graphene oxide (GO)-PDMS shell was constructed by cross-linking GO sheets. The composition and structure of both capsule types were fully characterized, and their CO 2 DAC performance was evaluated by gravimetric and breakthrough analysis. Both capsules exhibited competitive capacities, with the PDMS-PU capsules and the GO-PDMS capsules reaching 0.75 mol kg −1 and 0.66 mol kg −1 , respectively. We further demonstrate that both capsule systems can be regenerated with complementary electrothermal methods. Microwave (MW) regeneration was used for the PDMS-PU capsules, effectively releasing absorbed CO 2 in less than an hour. Owing to the electrical conductivity of GO, GO-PDMS capsules were regenerated via radio frequency heating (RF). This work highlights the importance and opportunity of tuning solid–liquid composite performance for advanced applications, including direct air capture of carbon dioxide.

Al-Mahbobi, Luma [Texas A&M University, College St↗
DOE OSTI2025

Improved Gas Plume Identification Using Nearest Neighbor Methods for Background Estimation

Longwave infrared (LWIR) hyperspectral imaging (HSI) can be used for many tasks in remote sensing, including detecting and identifying effluent gases by LWIR sensors on airborne platforms. Identification is used after detection to increase confidence in weakly detected plumes, reduce false positives from detection, and distinguish between similar and confounding material signatures. Background estimation is an important step used to reveal the unique spectral characteristics of the detected gas, allowing the identification model to determine what the gas is specifically. The importance of proper background estimation increases when dealing with weak signals, large libraries of gases of interest, and uncommon or heterogeneous backgrounds. In this article, we propose two methods for background estimation: a novel k-nearest segments (KNS) algorithm and the standard k-nearest neighbors (KNN) algorithm. We test our methods and three existing background estimation methods for comparison against global background estimation to determine which performs best at estimating the true background radiance under a plume and for increasing identification confidence using a neural network classification model. We compare the different methods using 640 simulated weak plumes in an urban environment. For identification, our KNS algorithm improves median neural network identification confidence by 53.2%. For background radiance estimation, the KNN algorithm provides a median of 49 times less RMSE than global background estimation. Furthermore, KNN is the easiest method to tune for different plumes, making it an excellent “out of the box” background estimator.

47 OTHER INSTRUMENTATION↗