Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “supervised training”

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 343 records · Page 19

Selecting XFEL single-particle snapshots by geometric machine learning

A promising new route for structural biology is single-particle imaging with an X-ray Free-Electron Laser (XFEL). This method has the advantage that the samples do not require crystallization and can be examined at room temperature. However, high-resolution structures can only be obtained from a sufficiently large number of diffraction patterns of individual molecules, so-called single particles. Here, we present a method that allows for efficient identification of single particles in very large XFEL datasets, operates at low signal levels, and is tolerant to background. This method uses supervised Geometric Machine Learning (GML) to extract low-dimensional feature vectors from a training dataset, fuse test datasets into the feature space of training datasets, and separate the data into binary distributions of “single particles” and “non-single particles.” As a proof of principle, we tested simulated and experimental datasets of the Coliphage PR772 virus. We created a training dataset and classified three types of test datasets: First, a noise-free simulated test dataset, which gave near perfect separation. Second, simulated test datasets that were modified to reflect different levels of photon counts and background noise. These modified datasets were used to quantify the predictive limits of our approach. Third, an experimental dataset collected at the Stanford Linear Accelerator Center. The single-particle identification for this experimental dataset was compared with previously published results and it was found that GML covers a wide photon-count range, outperforming other single-particle identification methods. Moreover, a major advantage of GML is its ability to retrieve single particles in the presence of structural variability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Artificial Intelligence

Artificial intelligence is the study of intelligence agents as demonstrated by machines. It is an interdisciplinary field involving computer science as well as, various kinds of engineering and science, for example, robotics, bio-medical engineering, that accentuates automation of human acts and intelligence through machines. AI represents state-of-the-art use of machines to bring about algorithmic computation and understanding of tasks that include learning, problem solving, mapping, perception, and reasoning. Given the data and a description of its properties and relations between objects of interest, AI methods can perform the aforementioned tasks. Widely applied AI capabilities, e.g. learning, are now achievable at large scale through machine learning (ML), large volumes of data and specialized computational machines. ML encompasses learning without any kind of supervision (unsupervised learning) and learning with full supervision (supervised learning). Widely applied supervised learning techniques include deep learning and other machine learning methods that require less data than deep learning e.g. support vector machines, random forests. Unsupervised learning examples include dictionary learning, independent component analysis, and autoencoders. For application tasks with less labeled data, both supervised and unsupervised techniques can be adapted in a semi-supervised manner to produce accurate models and to increase the size of the labeled training data.

97 MATHEMATICS AND COMPUTING↗

Rodent Habitat on ISS: Advances in Capability for Determining Spaceflight Effects on Mammalian Physiology

Rodent research is a valuable essential tool for advancing biomedical discoveries in life sciences on Earth and in space. The National Research Counsel's Decadal survey (1) emphasized the importance of expanding NASAs life sciences research to perform long duration, rodent experiments on the International Space Station (ISS). To accomplish this objective, new flight hardware, operations, and science capabilities were developed at NASA ARC to support commercial and government-sponsored research. The flight phases of two separate spaceflight missions (Rodent Research-1 and Rodent Research-2) have been completed and new capabilities are in development. The first flight experiments carrying 20 mice were launched on Sept 21, 2014 in an unmanned Dragon Capsule, SpaceX4; Rodent Research-1 was dedicated to achieving both NASA validation and CASIS science objectives, while Rodent Reesearch-2 extended the period on orbit to 60 days. Groundbased control groups (housed in flight hardware or standard cages) were maintained in environmental chambers at Kennedy Space Center. Crewmembers previously trained in animal handling transferred mice from the Transporter into Habitats under simultaneous veterinary supervision by video streaming and were deemed healthy. Health and behavior of all mice on the ISS was monitored by video feed on a daily basis, and post-flight quantitative analyses of behavior were performed. The 10 mice from RR-1 Validation (16wk old, female C57Bl6/J) ambulated freely and actively throughout the Habitat, relying heavily on their forelimbs for locomotion. The first on-orbit dissections of mice were performed successfully, and high quality RNA (RIN values>9) and liver enzyme activities were obtained, validating the quality of sample recovery. Post-flight sample analysis revealed that body weights of FLT animals did not differ from ground controls (GC) housed in the same hardware, or vivarium controls (VIV) housed in standard cages. Organ weights analyzed post-flight showed that there were no differences between FLT and GC groups in adrenal gland and spleen weights, whereas FLT thymus and liver weights exceeded those of GC. Minimal differences between the control groups (GC and VIV) were observed. In addition, Over 3,000 aliquots collected post-flight from the four groups of mice were deposited into the Ames Life Science Data Archives for the Biospecimen Sharing Program and Genelab project. New capabilities recently developed include DEXA scanning, grip strength tests and male mice. In conclusion, new capability for long duration rodent habitation of group-housed rodents was developed and includes in-flight sample collection, thus avoiding the complication of reentry. Results obtained to date reveal the possibility of striking differences between the effects of short duration vs. long duration spaceflight. This Rodent Research system enables achievement of both basic science and translational research objectives to advance human exploration of space.

Bone Loss↗

Maiden Voyage of the Rodent Habitat on ISS: Opportunities for Investigating Molecular Mechanisms and Biomedical Consequences of Long Duration Spaceflight

Research using rodents is an essential tool for advancing biomedical research on Earth and in space. The National Research Counsel’s Decadal survey (1) emphasized the importance of expanding NASAs life sciences research to perform long duration, rodent experiments on the International Space Station (ISS). To accomplish this objective, flight hardware, operations, and science capabilities were developed at NASA ARC to support both commercial and government-sponsored research. In preparation for the maiden voyage of the Rodent Habitat hardware and operations system (Rodent Research-1), and in close consultation with a Science Working Group comprised of veterinarians and experienced spaceflight investigators, we modified existing Animal Enclosure Module hardware, developed new hardware, operations, and science activities, and performed a series of ground-based verification tests. Preflight, ground based hardware tests included a simulation of SpaceX Dragon launch conditions (vibration and hypergravity) using the Transporter, and also two long-term biocompatibility tests (32 and 92 days) using the Habitat developed for long term housing on the ISS. The launch simulation test showed that adult mice housed in Transporter hardware adapted well, even if launch simulation was followed by a period of simulated weightlessness (via hind limb unloading). The biocompatibility tests demonstrated that the Habitat successfully supported animal health and also provided a useful video imaging system that enables frequent monitoring of animal health and behavior by veterinary and scientific experts on the ground, independent of ISS crew intervention. At the conclusion of all tests, mice were deemed healthy and suitable for conducting biological research. Additional preflight analyses of tissues preserved by freezing or fixation for gene expression analyses revealed that spleen and liver tissues recovered under conditions that simulated on-orbit activities yielded high quality RNA (RIN values 8-10) and liver enzyme activities and protein content (e.g. catalase). In addition, new methods were developed to optimize future science return by dissecting tissues post-euthanasia and storage. Various tissues were harvested from either intact or partially dissected, frozen carcasses after storage for ~2-6 months; most of the tissues (brain, heart, kidney, eye, adrenal glands and skeletal muscle) were of high RNA quality for science return, whereas some tissues (small intestine, bone marrow and bones) were not. These data demonstrated the protocols developed for future flight experiments supported science return despite delayed preservation post-euthanasia or prolonged storage, and furthermore, that high-quality RNA samples from many different tissues can be recovered by dissection following prolonged storage of the tissue in situ at -80˚C. The first flight experiments carrying 20 mice were launched on Sept 21, 2014 in an unmanned Dragon Capsule, SpaceX4; Rodent Research-1 is dedicated to achieving both NASA validation and CASIS science objectives. Ground based control groups (housed in flight hardware or standard cages) were maintained in environmental chambers at Kennedy Space Center. Crewmembers previously trained in animal handling transferred mice from the Transporter into Habitats under simultaneous veterinary supervision by video streaming and were deemed healthy. Health and behavior of all mice on the ISS was monitored by video feed on a daily basis. The 10 mice for validation (16wk old, female C57Bl6/J) ambulated freely and actively throughout the Habitat, relying heavily on their forelimbs for locomotion. The first on-orbit dissections of mice were performed successfully on Oct 12 and 13, 2014, and the validation mice will reside on ISS for up to 30 days. In conclusion, new capability for long duration rodent research is under development, including in-flight sample collection (which avoids the complication of reentry); results obtained to date will be described. This new Rodent Research system enables achievement of both basic science and translational research objectives to advance human exploration of space.

maiden voyage↗

Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.

14 SOLAR ENERGY↗

Aero-Engines AI - A Machine-Learning App for Aircraft Engine Concepts Assessment

Effective deployment of machine-learning (ML) models could drive a high level of efficiency in aircraft engine conceptual design. Aero-Engines AI is a user-friendly app that has been created to deploy trained machine-learning (ML) models to assess aircraft engine concepts. It was created using tkinter, a GUI (graphical user interface) module that is built into the standard Python library. Employing tkinter greatly facilitates the sharing of ML application as an executable file which can be run on Windows machines (without the need to have Python or any library installed). The app gets user input for a turbofan design, preprocesses the input data, and deploys trained ML models to predict turbofan thrust specific fuel consumption (TSFC), engine weight, core size, and turbomachinery stage-counts. The ML predictive models were built by employing supervised deep-learning and K-nearest neighbor regression algorithms to study patterns in an existing open-source database of production and research turbofan engines. They were trained, cross-validated, and tested in Keras, an open-source neural networks API (application programming interface) written in Python, with TensorFlow (Google open-source artificial intelligence library) serving as the backend engine. The smooth deployment of these ML models using the app shows that Aero-Engines AI is an easy-touse and a time-saving tool for aircraft engine design-space exploration during the conceptual design stage. Current version of the app focuses on the performance prediction of conventional turbofans. However, the scope of the app can easily be expanded to include other engine types (such as turboshaft and hybrid-electric systems) after their ML models are developed. Overall, the use of a machine-learning app for aircraft engine concept assessment represents a promising area of development in aircraft engine conceptual design.

machine learning↗

Aero-Engines AI - A Machine-Learning App for Aircraft Engine Concepts Assessment

Effective deployment of machine-learning (ML) models could drive a high level of efficiency in aircraft engine conceptual design. Aero-Engines AI is a user-friendly app that has been created to deploy trained machine-learning (ML) models to assess aircraft engine concepts. It was created using tkinter, a GUI (graphical user interface) module that is built into the standard Python library. Employing tkinter greatly facilitates the sharing of ML application as an executable file which can be run on Windows machines (without the need to have Python or any library installed). The app gets user input for a turbofan design, preprocesses the input data, and deploys trained ML models to predict turbofan thrust specific fuel consumption (TSFC), engine weight, core size, and turbomachinery stage-counts. The ML predictive models were built by employing supervised deep-learning and K-nearest neighbor regression algorithms to study patterns in an existing open-source database of production and research turbofan engines. They were trained, cross-validated, and tested in Keras, an open-source neural networks API (application programming interface) written in Python, with TensorFlow (Google open-source artificial intelligence library) serving as the backend engine. The smooth deployment of these ML models using the app shows that Aero-Engines AI is an easy-touse and a time-saving tool for aircraft engine design-space exploration during the conceptual design stage. Current version of the app focuses on the performance prediction of conventional turbofans. However, the scope of the app can easily be easily expanded to include other engine types (such as turboshaft and hybrid-electric systems) after their ML models are developed. Overall, the use of a machine-learning app for aircraft engine concept assessment represents a promising area of development in aircraft engine conceptual design.

machine learning↗

Training courses on neutron detection systems on the ISIS research reactor: on-site and through internet training

Today, ISIS research reactor is an essential tool for Education and Training programs organized by the National Institute for Nuclear Science and Technology (INSTN) from CEA. In the field of nuclear instrumentation, the INSTN offers both, theoretical courses and training courses on the use of neutron detection systems taking advantage of the ISIS research reactor for the supply of a wide range of neutron fluxes. This paper describes the content of the training carried out on the use of neutron detectors and detection systems, on-site or remote. The ISIS reactor is a 700 kW open core pool type reactor. The facility is very flexible since neutron detectors can be inserted into the core or its vicinity, and be used at different levels of power according to the needs of the course. Neutron fluxes, typically ranging from 1 to 10{sup 12} n/cm{sup 2}.s, can be obtained for the characterisation of the neutron detectors and detection systems. For the monitoring of the neutron density at low level of power, the Instrumentation and Control (I and C) system of the reactor is equipped with two detection systems, named BN1 and BN2. Each way contains a fission chamber, type CFUL01, connected to an electronic system type SIREX.The system works in pulse mode and exhibits two outputs: the counting rate and the doubling time. For the high level of power, the I and C is equipped with two detection systems HN1 and HN2.Each way contain a boron ionization chamber (type CC52) connected to an electronics system type SIREX. The system works in current mode and has two outputs: the current and the doubling time. For each mode, the trainees can observe and measure the signal at the different stages of the electronic system, with an oscilloscope. They can understand the role of each component of the detection system: detector, cable and each electronic block. The limitation of the detection modes and their operating range can be established from the measured signal. The trainees can also modify the settings of the electronic system, such as the high voltage and the discrimination level in order to obtain all the characteristic curves of the detectors. These curves are used to define the right setting of the electronic system and to discuss the expected degradation of the detector signal resulting from the detector damage under the integrated neutron and gamma fluxes. Moreover, in addition to the study of the neutron detection systems itself, the integration of the measurements made by these detection systems in the logic of the safety system of the nuclear reactor is also addressed. Providing the trainees with an extensive overview of each part of the neutron monitoring instrumentation apply to a nuclear reactor, hands-on measurements on the ISIS reactor play a major role in ensuring a practical and comprehensive understanding of the neutron detection system and their integration in the safety system of nuclear reactors. It also gives a solid background for the follow up and the development of the neutron detection systems. In addition to on-reactor training, Internet Reactor Laboratory capability has been implemented on the ISIS reactor in 2014. For the Internet Reactor Laboratory an extensive video conference system has been implemented on ISIS reactor. The system includes 4 cameras and the transmission of the video signal given by the supervision system of the reactor which records and processes the data of the reactor. According to the pedagogic needs during the training courses, the lecturer on the ISIS reactor chooses to broadcast the relevant information at each stage of the course. For example, graph showing the histogram of the counting and current as a function of the time, or the electrical signal observed on the oscilloscope, can be broadcasted trough internet. By interacting through the video conference, the remote classroom is able to ask for changes in the reactor power or settings of the detection systems. They can also ask for the broadcast of some particular information. At the guest institution, the information is displayed in two parts or screens, as shown in the Figure 3. Concerning the interaction with - and the feedback from - the remote classroom, the camera of the video system in the remote classroom is used to ensure the contact between the trainees and the lecturer and reactor operators. Thus, the Internet Reactor Laboratory is complementary to the on reactor training courses. It allows distant learning, reducing the overall cost of the course when this is necessary. It can efficiently be used for the development of the human resources needed by the nuclear industry and the nuclear programs in countries without research reactors.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Comparison of four learning-based methods for predicting groundwater redox status

Knowing the location where groundwater denitrification occurs, or by proxy the groundwater redox status (oxic, mixed, and anoxic), is valuable information for assessing and managing potential agricultural land-use impacts on freshwater quality. We compare the efficacy of supervised (Linear Discriminant Analysis LDA; Boosted Regression Trees, BRT; and Random Forest, RF) and unsupervised (Modified Self-Organizing Map, MSOM) learning-based methods to predict groundwater redox status in the agriculturally dominated Tasman, Waikato, and Wellington regions of New Zealand. Thresholds applied to regional groundwater-quality samples provide redox status variables and learn heuristics constrained by these variables and applied to spatial factors (climate, elevation, geologic, hydrology soils, and well depth) identify optimal sets of regional predictor variables. A split-sample approach is used to train and test the learning methods ability to predict redox status using the optimal predictor variables. Overall, the supervised methods demonstrate a prediction bias toward oxic conditions and inability to perform statistically well when using independent regional data; for example, consider kappa statistics for BRT (Tasman: 0.42, Waikato: 0.38, Wellington: 0.17), RF (Tasman: 0.42, Waikato: 0.47, Wellington: 0.17 and LDA (Tasman: 0.46, Waikato: 0.32, Wellington: 0.17). By contrast, the unsupervised method performs statistically well when predicting oxic, mixed, and anoxic conditions and corresponding depths when using independent regional data; for example, consider MSOM kappa statistics for Tasman: 0.78, Waikato: 0.80, Wellington: 0.76. The unsupervised learning method provides the added benefits of being (1) able to combine predictions into 3D regional anoxic probability plots for interpreting the spatial influence of paleosols and groundwater flowpaths on redox status, and (2) readily extended to map 3D redox status across New Zealand and other countries despite data bias and sparsity.

machine learning algorithms, Random Forest, booste↗

Automated Detection of Microaneurysms Using Scale-Adapted Blob Analysis and Semi-Supervised Learning

Despite several attempts, automated detection of microaneurysm (MA) from digital fundus images still remains to be an open issue. This is due to the subtle nature of MAs against the surrounding tissues. In this paper, the microaneurysm detection problem is modeled as finding interest regions or blobs from an image and an automatic local-scale selection technique is presented. Several scale-adapted region descriptors are then introduced to characterize these blob regions. A semi-supervised based learning approach, which requires few manually annotated learning examples, is also proposed to train a classifier to detect true MAs. The developed system is built using only few manually labeled and a large number of unlabeled retinal color fundus images. The performance of the overall system is evaluated on Retinopathy Online Challenge (ROC) competition database. A competition performance measure (CPM) of 0.364 shows the competitiveness of the proposed system against state-of-the art techniques as well as the applicability of the proposed features to analyze fundus images.

59 BASIC BIOLOGICAL SCIENCES↗

Estimation of cerebral blood flow velocity during breath-hold challenge using artificial neural networks

The effect of untreated Obstructive Sleep Apnoea (OSA) on cerebral haemodynamics and CA impairment is an active field of research interest. A breath-hold challenge is usually used in clinical and research settings to simulate cardiovascular and cerebrovascular changes that mimic OSA events. This work utilises temporal arterial oxygen saturation (SpO 2 ) and photoplethysmography (PPG) signals to estimate the temporal cerebral blood flow velocity (CBFv) waveform. Measurements of CBFv, SpO 2 , and PPG, were acquired concurrently from volunteers performing two different protocols of breath-hold challenge in the supine position. Past values of the SpO 2 and PPG signals were used to estimate the current values of CBFv using different permutations and topologies of supervised learning with shallow artificial neural networks (ANNs). Measurements from one protocol were used to train the ANNs and find the optimum topologies, which in turn were tested using the other protocol. Data collected from 10 normotensive, healthy subjects (four females, age 28.5 ± 6.1 years, Body Mass Index (BMI) 24.0 ± 4.7 kg/m 2 ) were used in this study. The results show that different subjects have different optimum topologies for ANNs, thus indicating the effects of inter-subject variability on ANNs. Successfully reconstructed blind waveforms for the same subject group in the second protocol showed a reasonable accuracy of 60–80% estimation compared to the measured waveforms.

59 BASIC BIOLOGICAL SCIENCES↗

Learning Optimal Multigrid Smoothers via Neural Networks

Multigrid methods are one of the most efficient techniques for solving large sparse linear systems arising from partial differential equations (PDEs) and graph Laplacians from machine learning applications. One of the key components of multigrid is smoothing, which aims at reducing high-frequency errors on each grid level. However, finding optimal smoothing algorithms is problem-dependent and can impose challenges for many problems. In this paper, we propose an efficient adaptive framework for learning optimized smoothers from operator stencils in the form of convolutional neural networks (CNNs). Here, the CNNs are trained on small-scale problems from a given type of PDEs based on a supervised loss function derived from multigrid convergence theories and can be applied to large-scale problems of the same class of PDEs. Numerical results on anisotropic rotated Laplacian problems and variable coefficient diffusion problems demonstrate improved convergence rates and solution time compared with classical hand-crafted relaxation methods.

97 MATHEMATICS AND COMPUTING↗

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗

Confidence-Based Feature Acquisition

Confidence-based Feature Acquisition (CFA) is a novel, supervised learning method for acquiring missing feature values when there is missing data at both training (learning) and test (deployment) time. To train a machine learning classifier, data is encoded with a series of input features describing each item. In some applications, the training data may have missing values for some of the features, which can be acquired at a given cost. A relevant JPL example is that of the Mars rover exploration in which the features are obtained from a variety of different instruments, with different power consumption and integration time costs. The challenge is to decide which features will lead to increased classification performance and are therefore worth acquiring (paying the cost). To solve this problem, CFA, which is made up of two algorithms (CFA-train and CFA-predict), has been designed to greedily minimize total acquisition cost (during training and testing) while aiming for a specific accuracy level (specified as a confidence threshold). With this method, it is assumed that there is a nonempty subset of features that are free; that is, every instance in the data set includes these features initially for zero cost. It is also assumed that the feature acquisition (FA) cost associated with each feature is known in advance, and that the FA cost for a given feature is the same for all instances. Finally, CFA requires that the base-level classifiers produce not only a classification, but also a confidence (or posterior probability).

Wagstaff, Kiri L.↗

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗

Breaking the barrier of human-annotated training data for machine learning-aided plant research using aerial imagery

Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by (i) the need for a large amount of human-annotated training data for each context in which the tool is used and (ii) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study was performed to compare ML approaches that examine images collected by an uncrewed aerial vehicle to determine the presence/absence of panicles (i.e. “heading”) across thousands of field plots containing genetically diverse breeding populations of 2 Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately 9 times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by 1 to 2 orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the data set by using thousands of unlabeled images to inform the discriminative ability of a classifier so that it required minimal human-labeled training data. This method can accelerate the phenotyping of heading date as a measure of flowering time in Miscanthus across diverse contexts (e.g. in multistate trials) and opens avenues to promote the broad adoption of ML tools.

59 BASIC BIOLOGICAL SCIENCES↗

pixelvar79/ESGAN-Flowering-Detection-paper

Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by (i) the need for a large amount of human-annotated training data for each context in which the tool is used and (ii) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study was performed to compare ML approaches that examine images collected by an uncrewed aerial vehicle to determine the presence/absence of panicles (i.e. “heading”) across thousands of field plots containing genetically diverse breeding populations of 2 Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately 9 times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by 1 to 2 orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the data set by using thousands of unlabeled images to inform the discriminative ability of a classifier so that it required minimal human-labeled training data. This method can accelerate the phenotyping of heading date as a measure of flowering time in Miscanthus across diverse contexts (e.g. in multistate trials) and opens avenues to promote the broad adoption of ML tools.

Varela, Sebastian↗

Development of lean, efficient, and fast physics-framed deep-learning-based proxy models for subsurface carbon storage

In this work, we present deep-learning-based surrogate models for CCUS developed with four different algorithms and a physics-framed two-phase flow problem involving displacement of water by CO 2 . The deep-learning models were trained using 3D datasets describing the pressure plume, CO 2 saturation plume, and water extraction rate generated by numerical simulation. The hyperparameters defining the architecture of the neural networks were optimized to determine the slimmest network size and training parameters that give the most efficient performance at the least training cost. To develop a robust model that closely mimics the governing physical laws, the discretized form of the two-phase fluid transport equation was used to formulate the supervised deep-learning task. The algorithms investigated in this study predicted the data to above 95% accuracy, with the multi-layer perceptron model demonstrating the best performance by balancing training speed, prediction time, and prediction accuracy with lean network capacity. Furthermore, the surrogate models simultaneously predict reservoir pressure and CO 2 saturation in every grid block, including the surface well extraction rate and bottomhole pressure, at all simulation times for a given static model realization in just a few seconds on a standard desktop computer. A key outcome of this study is that limits can be placed on network design parameters to avoid over designing neural networks, with associated efficiencies in training and prediction times. This is very useful because large volumes of data may be generated in CCUS projects and over-design of neural network architectures imposes penalties that are antithetical to the goal of near-real time forecasting.

58 GEOSCIENCES↗