Learning closure models for Turbulence: Calibration of BHR using Machine Learning techniques
Explore the source record for details and available documents.
Djibrilla Boureima, Ismael↗
SEARCH · Engineering Papers
Results for “Learning”
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.
Advanced Machine Learning and Computational Methods: SMART (Science-informed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications) Phase 2
For presentation at the 2023 FECM/Carbon Management Review Meeting, Pittsburgh, PA, August 28-September 1, 2023.
Schuetter, Jared↗
Does geography matter? A study of technological learning and innovation in the U.S. Solar photovoltaic balance-of-systems (PV BOS) industry
Different learning channels (i.e., learning from upstream actors, local network, global codified knowledge, etc.) coexist in firms’ technological innovation processes. Although firms are exposed to globalization and convenient communication and transportation tools, researchers still argue about the role of geography in technology innovation. Geographic proximity can facilitate knowledge spillover and network-building. Localized learning and the significance of geography indicate the importance of local knowledge in innovative activities. Local knowledge tends to be more closely aligned with local firms’ technological demand and easier to understand and absorb, because they are created and applied in the same context. However, following Schumpeter, innovation researchers believe that diverse knowledge, especially knowledge from external industries and geographically distant places, is a valuable source for innovation, especially disruptive innovation. Therefore, firms must balance different learning channels, especially between localized learning and global learning. However, it is still unclear about the extent to which localized learning is important for technology innovations and which factors influence the degree of localized learning. Meanwhile, most studies in the area of localized learning usually take no account of the international dimension and the interdependent of knowledge at different geographic scales. Different learning channels (i.e., learning from upstream actors, local network, global codified knowledge, etc.) coexist in firms’ technological innovation processes. Although firms are exposed to globalization and convenient communication and transportation tools, researchers still argue about the role of geography in technology innovation. Geographic proximity can facilitate knowledge spillover and network-building. Localized learning and the significance of geography indicate the importance of local knowledge in innovative activities. Local knowledge tends to be more closely aligned with local firms’ technological demand and easier to understand and absorb, because they are created and applied in the same context. However, following Schumpeter, innovation researchers believe that diverse knowledge, especially knowledge from external industries and geographically distant places, is a valuable source for innovation, especially disruptive innovation. Therefore, firms must balance different learning channels, especially between localized learning and global learning. However, it is still unclear about the extent to which localized learning is important for technology innovations and which factors influence the degree of localized learning. Meanwhile, most studies in the area of localized learning usually take no account of the international dimension and the interdependent of knowledge at different geographic scales. To address this research gap, this paper empirically investigated firms’ learning and innovation processes in relation to the geography. The aim is to answer the following three questions: 1) how does geographic distance influence knowledge spillover; 2) how technological characteristics influence knowledge acquisition choices as regards local vs. non-local knowledge? and 3) how do local and non-local knowledge affect the quality of innovation? The subject of our empirical inquiry is photovoltaic balance-of-systems (PV BOS) components. This choice is primarily motivated by two factors: (1) large-scale deployment of distributed solar PV technologies is widely considered to be an important piece in addressing the environmental impacts of the electricity sector, making PV an important technology to study; furthermore, there is a general consensus that the biggest barrier for a wider deployment of PV is the high price of non-module components, and (2) technological aspects of non-module components of PV systems make local conditions (climate, regulation, learning networks, etc.) salient, thus affording a rich empirical setting to explore the geography-innovation-economy interactions at the local level. We find that the localization effect of technological learning in the solar PV BOS industry is at state level, the number of citations-based linkages decreases with distance, and we also find that international knowledge significantly contributes to the quality of patents, which suggests that state border might be a barrier of current knowledge spillover, and only focusing on local innovation networks is not sufficient for promoting PV BOS innovation.
29 ENERGY PLANNING, POLICY, AND ECONOMY↗
Conceptualizing impact assessment as a learning process
This paper explores how project developers and their consultants, government regulators and stakeholders can learn from the impact assessment (IA) process, thus potentially improving its effectiveness and enhancing project sustainability. Despite the benefits that learning can bring to an organization, failure to learn appears commonplace both within the IA process and, once approved, subsequent industrial development. To nurture organizational learning through IA, enabling structures that foster information sharing and interpretation and enhance organizational memory are needed. In this paper learning outcomes are grouped into three categories: acquisition of knowledge and skills, developing new behaviors and developing sustainability-oriented norms and values. Means to achieve such outcomes include education and training, experiential learning, learning through public participation (social learning) and a ‘learning organization approach’. Societal expectations increasingly demand not only projects that ‘pass’ the review criteria of regulators, financiers and the community, but IA processes capable of delivering sustainable outcomes that include learning and sharing of knowledge. It is proposed that learning be treated as a purposeful – not as an accidental – outcome of IA, and facilitated by adopting a ‘learning organization approach’ coupled with best practice such as early stakeholder engagement. - Highlights: • Proponents are challenged to develop projects that deliver sustainable outcomes. • Passing the test of government approval may be insufficient to obtain a social license. • Learning by all stakeholders is vital to meet these challenges. • Learning outcomes have to go beyond instrumental learning to reach new behaviors, norms and values. • A “learning organization approach” can promote mutual learning and improve project design.
54 ENVIRONMENTAL SCIENCES↗
Deep active learning for classifying cancer pathology reports
Abstract Background Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. Results We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. Conclusions Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.
59 BASIC BIOLOGICAL SCIENCES↗
Development of the Mathematics of Learning Curve Models for Evaluating Small Modular Reactor Economics
The cost of nuclear power is a straightforward yet complicated topic. It is straightforward in that the cost of nuclear power is a function of the cost to build the nuclear power plant, the cost to operate and maintain it, and the cost to provide fuel for it. It is complicated in that some of those costs are not necessarily known, introducing uncertainty into the analysis. For large light water reactor (LWR)-based nuclear power plants, the uncertainty is mainly contained within the cost of construction. The typical costs of operations and maintenance (O&M), as well as fuel, are well known based on the current fleet of LWRs. However, the last currently operating reactor to come online was Watts Bar 1 in May 1996; thus, the expected construction costs for gigawatt (GW)-class reactors in the United States are based on information nearly two decades old. Extrapolating construction, O&M, and fuel costs from GW-class LWRs to LWR-based small modular reactors (SMRs) introduces even more complication. The per-installed-kilowatt construction costs for SMRs are likely to be higher than those for the GW-class reactors based on the property of the economy of scale. Generally speaking, the economy of scale is the tendency for overall costs to increase slower than the overall production capacity. For power plants, this means that doubling the power production capacity would be expected to cost less than twice as much. Applying this property in the opposite direction, halving the power production capacity would be expected to cost more than half as much. This can potentially make the SMRs less competitive in the electricity market against the GW-class reactors, as well as against other power sources such as natural gas and subsidized renewables. One factor that can potentially aid the SMRs in achieving economic competitiveness is an economy of numbers, as opposed to the economy of scale, associated with learning curves. The basic concept of the learning curve is that the more a new process is repeated, the more efficient the process can be made. Assuming that efficiency directly relates to cost means that the more a new process is repeated successfully and efficiently, the less costly the process can be made. This factor ties directly into the factory fabrication and modularization aspect of the SMR paradigm—manufacturing serial, standardized, identical components for use in nuclear power plants can allow the SMR industry to use the learning curves to predict and optimize deployment costs. Thus, SMR deployment cost estimates can be modeled using learning curve theory to provide some insight into how and when SMRs would be competitive with both the GW-class reactors and other mutual competitors. However, assuming static learning curve behavior for all aspects of SMR construction is likely an invalid approach—not all components and systems in SMRs will be subject to learning, and those that are subject to learning may not learn at the same rate. A learning curvebased model must be capable of tracking these unique behaviors. At the same time, the behavior of the aggregated and integrated SMR deployment is a more useful metric for discussion and comparison—ultimately, the most useful learning curve information is that which describes power plant deployment as a whole. Therefore, the goal of SMR component and systems learning modeling includes a method to produce an overall power plant learning model. This report describes the mathematics of learning curves that can be used for estimating unit cost in future production for individual components and aggregated systems. All necessary assumptions are provided to support the derivations presented. Future work will demonstrate the implementation of this methodology and provide example calculations of SMR cost
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
TU-CD-BRD-00: Incident Learning / RO-ILS
It has long been standard practice in radiation oncology to report internally when a patient’s treatment has not gone as planned and to report events to regulatory agencies when legally required. Most potential errors are caught early and never affect the patient. Quality assurance steps routinely prevent errors from reaching the patient, and these “near misses” are much more frequent than treatment errors. A growing number of radiation oncology facilities have implemented incident learning systems to report and analyze both errors and near misses. Using the term “incident learning” instead of “event reporting” emphasizes the need to use these experiences to change the practice and make future errors less likely and promote an educational, non-punitive environment. There are challenges in making such a system practical and effective. Speakers from institutions of different sizes and practice environments will share their experiences on how to make such a system work and what benefits their clinics have accrued. Questions that will be addressed include: How to create a system that is easy for front line staff to access How to motivate staff to report How to promote the system as positive and educational and not punitive or demeaning How to organize the team for reviewing and responding to reports How to prioritize which reports to discuss in depth How not to dismiss the rest How to identify underlying causes How to design corrective actions and implement change How to develop useful statistics and analysis tools How to coordinate a departmental system with a larger risk management system How to do this without a dedicated quality manager Some speakers’ experience is with in-house systems and some will share experience with the AAPM/ASTRO national Radiation Oncology Incident Learning System (RO-ILS). Reports intended to be of value nationally need to be comprehensible to outsiders; examples of useful reports will be shown. There will be ample time set aside for audience members to contribute to the discussion. Learning Objectives: Learn how to promote the use of an incident learning system in a clinic. Learn how to convert “event reporting” into “incident learning”. See examples of practice changes that have come out of learning systems. Learn how the RO-ILS system can be used as a primary internal learning system. Learn how to create succinct, meaningful reports useful to outside readers. Gary Ezzell chairs the AAPM committee overseeing RO-ILS and has received an honorarium from ASTRO for working on the committee reviewing RO-ILS reports. Derek Brown is a director of http://TreatSafely.org . Brett Miller has previously received travel expenses and an honorarium from Varian. Phillip Beron has nothing to report.
60 APPLIED LIFE SCIENCES↗
TU-CD-BRD-01: Making Incident Learning Practical and Useful: Challenges and Previous Experiences
It has long been standard practice in radiation oncology to report internally when a patient’s treatment has not gone as planned and to report events to regulatory agencies when legally required. Most potential errors are caught early and never affect the patient. Quality assurance steps routinely prevent errors from reaching the patient, and these “near misses” are much more frequent than treatment errors. A growing number of radiation oncology facilities have implemented incident learning systems to report and analyze both errors and near misses. Using the term “incident learning” instead of “event reporting” emphasizes the need to use these experiences to change the practice and make future errors less likely and promote an educational, non-punitive environment. There are challenges in making such a system practical and effective. Speakers from institutions of different sizes and practice environments will share their experiences on how to make such a system work and what benefits their clinics have accrued. Questions that will be addressed include: How to create a system that is easy for front line staff to access How to motivate staff to report How to promote the system as positive and educational and not punitive or demeaning How to organize the team for reviewing and responding to reports How to prioritize which reports to discuss in depth How not to dismiss the rest How to identify underlying causes How to design corrective actions and implement change How to develop useful statistics and analysis tools How to coordinate a departmental system with a larger risk management system How to do this without a dedicated quality manager Some speakers’ experience is with in-house systems and some will share experience with the AAPM/ASTRO national Radiation Oncology Incident Learning System (RO-ILS). Reports intended to be of value nationally need to be comprehensible to outsiders; examples of useful reports will be shown. There will be ample time set aside for audience members to contribute to the discussion. Learning Objectives: Learn how to promote the use of an incident learning system in a clinic. Learn how to convert “event reporting” into “incident learning”. See examples of practice changes that have come out of learning systems. Learn how the RO-ILS system can be used as a primary internal learning system. Learn how to create succinct, meaningful reports useful to outside readers. Gary Ezzell chairs the AAPM committee overseeing RO-ILS and has received an honorarium from ASTRO for working on the committee reviewing RO-ILS reports. Derek Brown is a director of http://TreatSafely.org . Brett Miller has previously received travel expenses and an honorarium from Varian. Phillip Beron has nothing to report.
60 APPLIED LIFE SCIENCES↗
What Machine Learning Can and Cannot Do for Inertial Confinement Fusion
Machine learning methodologies have played remarkable roles in solving complex systems with large data, well-defined input–output pairs, and clearly definable goals and metrics. The methodologies are effective in image analysis, classification, and systems without long chains of logic. Recently, machine-learning methodologies have been widely applied to inertial confinement fusion (ICF) capsules and the design optimization of OMEGA (Omega Laser Facility) capsule implosion and NIF (National Ignition Facility) ignition capsules, leading to significant progress. As machine learning is being increasingly applied, concerns arise regarding its capabilities and limitations in the context of ICF. ICF is a complicated physical system that relies on physics knowledge and human judgment to guide machine learning. Additionally, the experimental database for ICF ignition is not large enough to provide credible training data. Most researchers in the field of ICF use simulations, or a mix of simulations and experimental results, instead of real data to train machine learning models and related tools. They then use the trained learning model to predict future events. This methodology can be successful, subject to a careful choice of data and simulations. However, because of the extreme sensitivity of the neutron yield to the input implosion parameters, physics-guided machine learning for ICF is extremely important and necessary, especially when the database is small, the uncertain-domain knowledge is large, and the physical capabilities of the learning models are still being developed. In this work, we identify problems in ICF that are suitable for machine learning and circumstances where machine learning is less likely to be successful. This study investigates the applications of machine learning and highlights fundamental research challenges and directions associated with machine learning in ICF.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Materials representation and transfer learning for multi-property prediction
The adoption of machine learning in materials science has rapidly transformed materials property prediction. Hurdles limiting full capitalization of recent advancements in machine learning include the limited development of methods to learn the underlying interactions of multiple elements as well as the relationships among multiple properties to facilitate property prediction in new composition spaces. To address these issues, we introduce the Hierarchical Correlation Learning for Multi-property Prediction (H-CLMP) framework that seamlessly integrates: (i) prediction using only a material's composition, (ii) learning and exploitation of correlations among target properties in multi-target regression, and (iii) leveraging training data from tangential domains via generative transfer learning. The model is demonstrated for prediction of spectral optical absorption of complex metal oxides spanning 69 three-cation metal oxide composition spaces. H-CLMP accurately predicts non-linear composition-property relationships in composition spaces for which no training data are available, which broadens the purview of machine learning to the discovery of materials with exceptional properties. This achievement results from the principled integration of latent embedding learning, property correlation learning, generative transfer learning, and attention models. The best performance is obtained using H-CLMP with transfer learning [H-CLMP(T)] wherein a generative adversarial network is trained on computational density of states data and deployed in the target domain to augment prediction of optical absorption from composition. H-CLMP(T) aggregates multiple knowledge sources with a framework that is well suited for multi-target regression across the physical sciences.
36 MATERIALS SCIENCE↗
Active meta-learning for predicting and selecting perovskite crystallization experiments
Autonomous experimentation systems use algorithms and data from prior experiments to select and perform new experiments in order to meet a specified objective. In most experimental chemistry situations, there is a limited set of prior historical data available, and acquiring new data may be expensive and time consuming, which places constraints on machine learning methods. Active learning methods prioritize new experiment selection by using machine learning model uncertainty and predicted outcomes. Meta-learning methods attempt to construct models that can learn quickly with a limited set of data for a new task. Here in this paper, we applied the model-agnostic meta-learning (MAML) model and the Probabilistic LATent model for Incorporating Priors and Uncertainty in few-Shot learning (PLATIPUS) approach, which extends MAML to active learning, to the problem of halide perovskite growth by inverse temperature crystallization. Using a dataset of 1870 reactions conducted using 19 different organoammonium lead iodide systems, we determined the optimal strategies for incorporating historical data into active and meta-learning models to predict reaction compositions that result in crystals. We then evaluated the best three algorithms (PLATIPUS and active-learning k-nearest neighbor and decision tree algorithms) with four new chemical systems in experimental laboratory tests. With a fixed budget of 20 experiments, PLATIPUS makes superior predictions of reaction outcomes compared to other active-learning algorithms and a random baseline.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms
Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.
97 MATHEMATICS AND COMPUTING↗
Applications of Federated Learning in Semiconductor Manufacturing [Poster]
As semiconductor manufacturers explore advanced data analytics and modeling techniques and data hungry machine learning models increase in popularity due to their accuracy in solving generalized problems and ability to learn complex relationships, federated learning emerges as a privacy preserving machine learning technique for preserving data privacy and ensuring intellectual property protection. Federated Learning is a machine learning technique focused on training models using distributed data that never needs to be centrally stored, allowing the use of advanced machine learning techniques without compromising data privacy, and in the semiconductor manufacturing industry advanced machine learning techniques can reduce cost and time, but maintaining data privacy is essential to maintaining a competitive advantage. This paper systematically reviews existing literature on applications of federated learning in the semiconductor manufacturing industry with a focus on identifying common themes, algorithms, and gaps within the literature to drive future research directions. The findings reveal five key themes, including improvements in quality assurance, virtual models, privacy preservation, reliable data practices, and emerging trends and developments. By identifying key themes in literature on federated learning and semiconductor manufacturing and analyzing gaps and discussed methodologies, this study highlights several potential future research directions to expand the application of federated learning techniques in the semiconductor manufacturing domain.
42 ENGINEERING↗
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications
Abstract Robust quantification of predictive uncertainty is a critical addition needed for machine learning applied to weather and climate problems to improve the understanding of what is driving prediction sensitivity. Ensembles of machine learning models provide predictive uncertainty estimates in a conceptually simple way but require multiple models for training and prediction, increasing computational cost and latency. Parametric deep learning can estimate uncertainty with one model by predicting the parameters of a probability distribution but does not account for epistemic uncertainty. Evidential deep learning, a technique that extends parametric deep learning to higher-order distributions, can account for both aleatoric and epistemic uncertainties with one model. This study compares the uncertainty derived from evidential neural networks to that obtained from ensembles. Through applications of the classification of winter precipitation type and regression of surface-layer fluxes, we show evidential deep learning models attaining predictive accuracy rivaling standard methods while robustly quantifying both sources of uncertainty. We evaluate the uncertainty in terms of how well the predictions are calibrated and how well the uncertainty correlates with prediction error. Analyses of uncertainty in the context of the inputs reveal sensitivities to underlying meteorological processes, facilitating interpretation of the models. The conceptual simplicity, interpretability, and computational efficiency of evidential neural networks make them highly extensible, offering a promising approach for reliable and practical uncertainty quantification in Earth system science modeling. To encourage broader adoption of evidential deep learning, we have developed a new Python package, Machine Integration and Learning for Earth Systems (MILES) group Generalized Uncertainty for Earth System Science (GUESS) (MILES-GUESS) ( https://github.com/ai2es/miles-guess ), that enables users to train and evaluate both evidential and ensemble deep learning. Significance Statement This study demonstrates a new technique, evidential deep learning, for robust and computationally efficient uncertainty quantification in modeling the Earth system. The method integrates probabilistic principles into deep neural networks, enabling the estimation of both aleatoric uncertainty from noisy data and epistemic uncertainty from model limitations using a single model. Our analyses reveal how decomposing these uncertainties provides valuable insights into reliability, accuracy, and model shortcomings. We show that the approach can rival standard methods in classification and regression tasks within atmospheric science while offering practical advantages such as computational efficiency. With further advances, evidential networks have the potential to enhance risk assessment and decision-making across meteorology by improving uncertainty quantification, a longstanding challenge. This work establishes a strong foundation and motivation for the broader adoption of evidential learning, where properly quantifying uncertainties is critical yet lacking.
Schreck, John S.↗
Using learning curves on energy-efficient technologies to estimate future energy savings and emission reduction potentials in the U.S. iron and steel industry
Increasing concerns on non-sustainable energy use and climate change spur a growing research interest in energy efficiency potentials in various critical areas such as industrial production. This paper focuses on learning curve aspects of energy efficiency measures in the U.S iron and steel sector. A number of early-stage efficient technologies (i.e., emerging or demonstration technologies) are technically feasible and have the potential to make a significant contribution to energy saving and CO 2 emissions reduction, but fall short economically to be included. However, they may also have the cost effective potential for significant cost reduction and/or performance improvement in the future under learning effects such as ‘learning-by-doing’. The investigation is carried out using ISEEM, a technology oriented, linear optimization model. We investigated how steel demand is balanced with/without the availability learning curve, compared to a Reference scenario. The retrofit (or investment in some cases) costs of energy efficient technologies decline in the scenario where learning curve is applied. The analysis also addresses market penetration of energy efficient technologies, energy saving, and CO 2 emissions in the U.S. iron and steel sector with/without learning impact. Accordingly, the study helps those who use energy models better manage the price barriers preventing unrealistic diffusion of energy-efficiency technologies, better understand the market and learning system involved, predict future achievable learning rates more accurately, and project future savings via energy-efficiency technologies with presence of learning. We conclude from our analysis that, most of the existing energy efficiency technologies that are currently used in the U.S. iron and steel sector are cost effective. Penetration levels increases through the years, even though there is no price reduction. However, demonstration technologies are not economically feasible in the U.S. iron and steel sector with the current cost structure. In contrast, some of the demonstration technologies are adapted in the mid-term and their penetration levels increase as the prices go down with learning curve. We also observe large penetration of 225kg pulverized coal injection with the presence of learning.
29 ENERGY PLANNING, POLICY, AND ECONOMY↗
Reinforcement Learning Approach to Cybersecurity in Space (RELACSS)
Securing satellite groundstations against cyber-attacks is vital to national security missions. However, these cyber threats are constantly evolving. As vulnerabilities are discovered and patched, new vulnerabilities are discovered and exploited. In order to automate the process of discovering existing vulnerabilities and the means to exploit them, a reinforcement learning framework is presented in this report. We demonstrate that this framework can learn to successfully navigate an unknown network and detect nodes of interest despite the presence of a moving target defense. The agent then exfiltrates a file of interest from the node as quickly as possible. This framework also incorporates a defensive software agent that learns to impede the attacking agents progress. This setup allows for the agents to work against each other and improve their abilities. We anticipate that this capability will help uncover unforeseen vulnerabilities and the means to mitigate them. The modular nature of the framework enables users to swap out learning algorithms and modify the reward functions in order to adapt the learning tasks to various use cases and environments. Several algorithms, viz., tabular Q learning, deep Q networks, proximal policy optimization, advantage actor-critic, generative adversarial imitation learning, are explored for the agents and the results highlighted. The agent learns to solve the tasks in a light-weight abstract environment. Once the agent learns to perform sufficiently well, it can be deployed in a minimega virtual machine environment (or a real network) with wrappers that map abstract actions to software commands. The agent also uses a local representation of the actions called a ‘slot-mechanism’. This allows the agent to learn in a certain network and generalize it to different networks. The defensive agent learns to predict the actions taken by an offensive agent and uses that information to anticipate the threat. This information can then either be used to raise an alarm or to take actions to thwart the attack. We believe that with the appropriate reward design, a representative environment, and action set, this framework can be generalized to tackle other cybersecurity tasks. By sufficiently training these agents, we can anticipate vulnerabilities leading to robust future designs. We can also deploy automated defensive agents that can help secure satellite groundstation and their vital national security missions.
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
CRCNS22 Learning Rules in the Hippocampus and their Mapping to Neuromorphic Systems (Final Technical Report)
Large scale biologically-realistic computational models are key to investigating the interplay between structure and function in nervous systems, thus paving the way to new clinical methods and neuro-inspired computing solutions. This project focuses on the hippocampus, in particular the CA3-CA1 regions, due to their role in associative learning and memory, pattern separation and completion, and spatial navigation. Investigations into the neuronal organization and learning rule(s) of this circuit can shed light into how declarative memories are formed, stored, recalled and forgotten and inform computational, experimental and clinical neuroscience work. Our project aims at developing a novel data-driven methodology supported by a broad heterogeneous base of neuroscience experimental knowledge and inspired from advances in computer science and engineering. Specifically, this work will benchmark existing and new learning rules within a full-scale spiking neural network simulation of the CA3-CA1 region. The model will be based on an open-source repository, called the Hippocampome, which contains neuronal morphologies, firing patterns, synapse probabilities, and most other required parameters for all known neuron types in the rodent hippocampal formation. The model will be first trained in a supervised fashion for associative memory tasks using backpropagation through time traditionally used in computer science, enhanced with a new technique called the surrogate gradient method. This optimization method will be used to obtain a global loss minimization, but it is not biologically inspired as it assumes the use of data not locally available to the synapses. However, we propose its use as a benchmarking tool, to compare the training performance of local biologically plausible and hardware-mappable learning rules at scale. New rules or combinations will be proposed and tested as needed, based on the obtained results. Progress in this area will also drive the development of novel hardware-mappable algorithms for continual lifelong learning and categorization of new events from few presented examples. This project goes beyond the existing state-of-the-art by looking at large scale realistic neuronal circuits as networks trainable via global optimization methods such as surrogate gradient descent. The objective function of the brain that supports learning is largely unknown, but it is likely that it operates through local learning rules. Studying network trajectories around local minima as proposed in this work represents a useful strategy for understanding whether a network is training by using a specific (set of) learning rule(s). Starting from a completely untrained network is a challenging test since it is difficult to determine how the learning rule affects the trajectory of the network. This interdisciplinary project will help understand what rule governs learning in these regions or if multiple learning rules are involved. The work will develop a robust methodology to measure if the network is converging to the target solution, oscillating around it, or diverging away.
59 BASIC BIOLOGICAL SCIENCES↗
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]↗