Search NASA⌕ Search

SEARCH · Search NASA

Results for “Online 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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Purple is the new green: biopigments and spectra of Earth-like purple worlds

ABSTRACT With more than 5500 detected exoplanets, the search for life is entering a new era. Using life on Earth as our guide, we look beyond green landscapes to expand our ability to detect signs of surface life on other worlds. While oxygenic photosynthesis gives rise to modern green landscapes, bacteriochlorophyll-based anoxygenic phototrophs can also colour their habitats and could dominate a much wider range of environments on Earth-like exoplanets. Here, we characterize the reflectance spectra of a collection of purple sulfur and purple non-sulfur bacteria from a variety of anoxic and oxic environments. We present models for Earth-like planets where purple bacteria dominate the surface and show the impact of their signatures on the reflectance spectra of terrestrial exoplanets. Our research provides a new resource to guide the detection of purple bacteria and improves our chances of detecting life on exoplanets with upcoming telescopes. Our biological pigment data base for purple bacteria and the high-resolution spectra of Earth-like planets, including ocean worlds, snowball planets, frozen worlds, and Earth analogues, are available online, providing a tool for modellers and observers to train retrieval algorithms, optimize search strategies, and inform models of Earth-like planets, where purple is the new green.

Coelho, Lígia Fonseca (ORCID:0000000150081249)↗
DOE OSTI2022

A data-centric weak supervised learning for highway traffic incident detection

Using the data from loop detector sensors for near-real-time detection of traffic incidents on highways is crucial to averting major traffic congestion. While recent supervised machine learning methods offer solutions to incident detection by leveraging human-labeled incident data, the false alarm rate is often too high to be used in practice. Specifically, the inconsistency in the human labeling of the incidents significantly affects the performance of supervised learning models. To that end, we focus on a data-centric approach to improve the accuracy and reduce the false alarm rate of traffic incident detection on highways. We develop a weak supervised learning workflow to generate high-quality training labels for the incident data without the ground truth labels, and we use those generated labels in the supervised learning setup for final detection. This approach comprises three stages. First, we introduce a data preprocessing and curation pipeline that processes traffic sensor data to generate high-quality training data through leveraging labeling functions, which can be domain knowledge-related or simple heuristic rules. Second, we evaluate the training data generated by weak supervision using three supervised learning models-random forest, k-nearest neighbors, and a support vector machine ensemble-and long short-term memory classifiers. The results show that the accuracy of all of the models improves significantly after using the training data generated by weak supervision. Third, we develop an online real-time incident detection approach that leverages the model ensemble and the uncertainty quantification while detecting incidents. Finally, we show that our proposed weak supervised learning workflow achieves a high incident detection rate (0.90) and low false alarm rate (0.08).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Leveraging Calibration Transfer Techniques for Remote Monitoring of Samarium and Europium in LiCl Using Laser-Induced Florescence Spectroscopy for Radioisotope Production Applications

Radioisotope production relies on complex chemical processes that must be performed in radiological hot cells or glove boxes because of the radioactive and otherwise hazardous materials being used. In these situations, optical sensors can provide real-time monitoring to users, which is unobtainable by more traditional methods. This study explores the use of calibration transfer methods to train a model on one instrument and date and then transfer it to another instrument of the same or different configuration on a different date. By performing laser-induced fluorescence measurements of Eu(III) and Sm(III) in 10 M LiCl over the course of 6 months using two disparate spectrometers and two different training sets, a strategy for calibrating and deploying models for online monitoring was established. Three transfer techniques were compared: direct standardization (DS), piecewise direct standardization (PDS), and external parameter orthogonalization (EPO). DS and PDS outperformed EPO for day-to-day transfers, and EPO was not effective for instrument-to-instrument transfers. Transferring the initial date’s full factorial model provided better prediction performance compared with retraining models the day of measurements using a D-optimal designed calibration set. For both day-to-day and instrument-to-instrument transfers, five Kennard–Stone selected samples were sufficient. Based on this choice, the initial-date, high-resolution spectrometer model was transferred to a lower-resolution, compact spectrometer 6 months later to monitor a simulated, real-time demonstration. Here, the combined predictions of the DS and PDS transferred models were able to accurately track the anticipated concentration profiles, maintaining root-mean-square error of prediction values below 10 ppm.

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

Dynamic Role-Based Access Control Policy for Smart Grid Applications: An Offline Deep Reinforcement Learning Approach

Role-based access control (RBAC) is adopted in the information and communication technology domain for authentication purposes. However, due to a very large number of entities within organizational access control (AC) systems, static RBAC management can be inefficient, costly, and can lead to cybersecurity threats. In this paper, a novel hybrid RBAC model is proposed, based on the principles of offline deep reinforcement learning (RL) and Bayesian belief networks. The considered framework utilizes a fully offline RL agent, which models the behavioral history of users as a Bayesian belief-based trust indicator. Thus, the initial static RBAC policy is improved in a dynamic manner through off-policy learning while guaranteeing compliance of the internal users with the security rules of the system. By deploying our implementation within the smart grid domain and specifically within a Distributed Energy Resources (DER) ecosystem, we provide an end-to-end proof of concept of our model. Finally, detailed analysis and evaluation regarding the offline training phase of the RL agent are provided, while the online deployment of the hybrid RL-based RBAC model into the DER ecosystem highlights its key operation features and salient benefits over traditional RBAC models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Machine learning-based discovery of vibrationally stable materials

The identification of the ground state phases of a chemical space in the convex hull analysis is a key determinant of the synthesizability of materials. Online material databases have been instrumental in exploring one aspect of the synthesizability of many materials, namely thermodynamic stability. However, the vibrational stability, which is another aspect of synthesizability, of new materials is not known. Applying first principles approaches to calculate the vibrational spectra of materials in online material databases is computationally intractable. Here, a dataset of vibrational stability for ~3100 materials is used to train a machine learning classifier that can accurately distinguish between vibrationally stable and unstable materials. This classifier has the potential to be further developed as an essential filtering tool for online material databases that can inform the material science community of the vibrational stability or instability of the materials queried in convex hulls.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training

Distributed training increases the number of batches processed per iteration either by scaling-out (adding more nodes) or scaling-up (increasing the batch-size). However, the largest configuration does not necessarily yield the best performance. Horizontal scaling introduces additional communication overhead, while vertical scaling is constrained by computation cost and device memory limits. Thus, simply increasing the batch-size leads to diminishing returns: training time and cost decrease initially but eventually plateaus, creating a knee-point in the time/cost vs. batch-size pareto curve. The optimal batch-size therefore depends on the underlying model, data and available compute resources. Large batches also suffer from worse model quality due to the well-known “generalization gap”. In this paper, we present Tula, an online service that automatically optimizes time, cost, and convergence quality for large-batch training of convolutional models. It combines parallel-systems modeling with statistical performance prediction to identify the optimal batchsize. Tula predicts training time and cost within 7.5−14% error across multiple models, and achieves up to 20× overall speedup and improves test accuracy by ≈9% on average over standard large-batch training on various vision tasks, thus successfully mitigating the generalization gap and accelerating training at the same time.

Tyagi, Sahil [ORNL] (ORCID:0009000783144745)↗
DOE OSTI2023

Physical Education Teachers’ Representations of Their Training to Promote the Inclusion of Students with Disabilities

School inclusion is based on the need to adopt and implement a holistic view of education, training, and human development embodied in the idea of everyone, for everyone. In the context of Physical Education (PE), there are still several constraints to the realization of this universal desideratum. Among these, teacher training and qualification for the inclusion of students with Specific Health Needs (SHNs) stands out. That is, students with physical and mental health problems whose impact is significantly manifested in the learning process. Thus, the objective of this study was to identify the representations of PE teachers about their training to develop inclusive processes with students with SES. Participants in this study were 151 PE teachers from different regions and districts of Portugal (Algarve, Aveiro, Castelo Branco, Lisbon, Porto, and Viseu) who had 23.6 ± 8.1 years of teaching service. Teachers answered an online questionnaire, on the Google Forms platform, with open and closed questions about their education and training to develop inclusive processes in PE. The results indicate two significant dimensions: (1) initial training for teaching inclusive PE and (2) continuous training for inclusion. Regarding initial training, a large majority of the teachers under study, at the end of their initial training, did not have the essential skills to teach PE to students with SES. It was also identified that a large majority reported not having had any contact with students with SES throughout their training process for teaching. It was also recognized that this training was not adjusted to the development of intervention skills with students with SHN. Regarding continuous training, it was identified that attendance at this training increased their skills to teach PE to students with SHN. Workshops/actions/training courses are the main training models adopted. However, it is recognized that the training provided does not respond concretely to their training needs to intervene with students with SHN, since teachers essentially seek to improve intervention in the context of inclusive physical education. We conclude that teacher training for inclusion is not yet fully adjusted to the reality of the inclusive school paradigm. In this sense, in practical terms, the following are suggested: (1) the need for reinforcement in study plans with specific and long-term curricular units; (2) the introduction of real practice components in context; and (3) supervised pedagogical practice in diverse contexts.

Celestino, Tadeu (ORCID:0000000163087981)↗
DOE OSTI2025

Navigating the Noise: Bringing Clarity to ML Parameterization Design With O $\boldsymbol{\mathcal{O}}$(100) Ensembles

Abstract Machine‐learning (ML) parameterizations of subgrid processes (here of turbulence, convection, and radiation) may one day replace conventional parameterizations by emulating high‐resolution physics without the cost of explicit simulation. However, uncertainty about the relationship between offline and online performance (i.e., when integrated with a large‐scale general circulation model) hinders their development. Much of this uncertainty stems from limited sampling of the noisy, emergent effects of upstream ML design decisions on downstream online hybrid simulation. Our work rectifies the sampling issue via the construction of a semi‐automated, end‐to‐end pipeline for size ensembles of hybrid simulations, revealing important nuances in how systematic reductions in offline error manifest in changes to online error and online stability. For example, removing dropout and switching from a Mean Squared Error to a Mean Absolute Error loss both reduce offline error, but they have opposite effects on online error and online stability. Other design decisions, like incorporating memory, converting moisture input from specific humidity to relative humidity, using batch normalization, and training on multiple climates do not come with any such compromises. Finally, we show that ensemble sizes of may be necessary to reliably detect causally relevant differences online. By enabling rapid online experimentation at scale, we can empirically settle debates regarding subgrid ML parameterization design that would have otherwise remained unresolved in the noise.

Lin, Jerry [Department of Earth System Sciences Un↗
DOE OSTI2022

Time Delay of Wide Area Damping Control in Urban Power Grid: Model-Based Analysis and Data-Driven Compensation

Due to the rapid development of economies, large urban cities consume an increasing amount of energy and have a higher requirement for power quality. Voltage source converter based high voltage direct current (VSC-HVDC) is a promising device to transmit clean power from remote regions to urban power systems, while also providing wide area damping control (WADC) for frequency stabilization. However, the time-delay naturally existing in the VSC-HVDC system may degrade the performance of WADC and even result in instability. To address this issue, this paper develops a time-delay correction control strategy for VSC-HVDC damping control in urban power grids. First, a small signal model of WADC is built to analyze the negative impacts of time delay. Then, a data-driven approach is proposed to compensate for the inherent time delay in VSC-HVDC damping control. The extensive training data will be generated under various disturbances. After offline training, the long short-term memory network (LSTM) can be implemented online to predict the actual frequency deviation based on real-time measurements. Finally, the proposed method is validated through MATLAB-Simulink in a two-area four-machine system. The results indicate that the data-driven compensation has a strong generalization ability for random delay time constants and can improve the performance of WADC significantly.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

In recent years, advanced control strategies based on Deep Reinforcement Learning (DRL) proved to be effective in optimizing the management of integrated energy systems in buildings, reducing energy costs and improving indoor comfort conditions when compared to traditional reactive controllers. However, the scalability and implementation of DRL controllers are still limited since they require a considerable amount of time before converging to a near-optimal solution. This issue is currently addressed in literature through the offline pre-training of the DRL agent. However this solution results in two main critical issues: (1) the need to develop a building surrogate model to perform the training task, and (2) the need to perform a fine-tuning process over several training episodes to obtain a near-optimal control policy. In this context, this paper introduces an Online Transfer Learning (OTL) strategy that exploits two knowledge-sharing techniques, weight-initialization and imitation learning, to transfer a DRL control policy from a source office building to various target buildings in a simulation environment coupling EnergyPlus and Python. A DRL controller based on discrete Soft Actor–Critic (SAC) is trained on the source building to manage the operation of a cooling system consisting of a chiller and a thermal storage. Several target buildings are defined to benchmark the performance of the OTL strategy with that of a Rule-Based Controller (RBC) and two DRL-based control strategies, deployed in offline and online fashion. The strategy adopted for OTL emulates the real world implementation with a simulation process by implementing the transferred DRL agent for a single episode in the target buildings. Target buildings have the same geometrical features and are served by the same energy system as the source building, but differ in terms of weather conditions, electricity price schedules, occupancy patterns, and building envelope efficiency levels. The results show that the OTL strategy can reduce the cumulated sum of temperature violations on average by 50% and 80% respectively when compared to RBC and online DRL while enhancing the energy system operation with electricity cost savings ranging between 20% and 40%. Furthermore, the OTL agent performs slightly worse than the offline DRL controller but it does not require any modeling effort and can be implemented directly on target buildings emulating a real-world implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

DRIPS: A framework for dimension reduction and interpolation in parameter space

Reduced-order models are often used to describe the behavior of complex systems, whose simulation with a full model is too expensive, or to extract salient features from the full model’s output. We introduce a new model-reduction framework DRIPS (dimension reduction and interpolation in parameter space) that combines the offline local model reduction with the online parameter interpolation of reduced-order bases (ROBs). The offline step of this framework relies on dynamic mode decomposition (DMD) to build a low-rank linear surrogate model, equipped with a local ROB, for quantities of interest derived from the training data generated by repeatedly solving the (nonlinear) high-fidelity model for multiple parameter points. The online step consists of the construction of a parametric reduced-order model for each target/test point in the parameter space, with the interpolation of ROBs done on a Grassman manifold and the interpolation of reduced-order operators done on a matrix manifold. The DMD component enables DRIPS to model (typically low-dimensional) quantities of interest directly, without having to access the (typically high-dimensional and possibly nonlinear) operators in a high-fidelity model that governs the dynamics of the underlying high-dimensional state variables, as required in projection-based reduced-order modeling. A series of numerical experiments suggests that DRIPS yields a model reduction, which is computationally more efficient than the commonly used projection-based proper orthogonal decomposition; it does so without requiring a prior knowledge of the governing equation for quantities of interest. Furthermore, for the nonlinear systems considered, DRIPS is more accurate than Gaussian-process interpolation (Kriging).

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

A transfer learning approach to energy-efficient control of small and medium-sized commercial buildings

Model-free reinforcement learning (RL) provides a data-driven and adaptive approach to optimize building energy use while satisfying occupant comfort. This powerful tool does not need any prior knowledge about the environment and system it is optimizing and can adapt its policy based on the changes in captures. Like any other data-driven tool, it faces high training costs due to the extensive agent-environment interactions required to capture long-term building dynamics and user comfort. Transfer learning, particularly policy distillation, offers a promising way to accelerate training by leveraging pretrained RL agents in different building and system types. Here, this study investigates online student distillation, in which the student model updates its neural network weights using outputs from teacher models. The work introduces a student distillation strategy designed for efficient knowledge transfer, along with a teacher selection method that ensures high-quality guidance. The approach is validated using a highly calibrated whole building energy model for a small/medium commercial building test facility. Results show substantial reductions in training time and data requirements while surpassing the performance of ASHRAE Guideline 36, an advanced rule-based control strategy. The distilled RL model required 45% less data and achieved 20% higher cumulative rewards than a state-of-the-art RL model, with faster convergence and lower energy consumption. These outcomes demonstrate that effective transfer learning enables a scalable and data-efficient energy management solution for commercial buildings.

ASHRAE guideline 36↗
DOE OSTI2023

Primal-Dual Differentiable Programming for Distribution System Critical Load Restoration: Preprint

Swift and reliable critical load restoration (CLR) can help make a distribution system resilient towards extreme events. To optimally achieve that, alongside practical concerns such as limiting online computational burden, some studies leverage model-free reinforcement learning (RL) to train control policies. Despite the advantages provided by RL algorithms, these approaches suffer from two issues: 1) the lack of a proper mechanism for constraint enforcement, and 2) poor sample efficiency. Therefore, in this paper, a primal-dual differentiable programming (PDDP) method is developed for guiding the training leading to a constraint-satisfying policy. Additionally, the model-based nature of the proposed method aims at improving sample efficiency. The experiment on a CLR problem demonstrates that PDDP can effectively train a control policy that both achieves desirable performance and satisfies required constraints.

differentiable programming↗
DOE OSTI2024

RAP: Resource-aware Automated GPU Sharing for Multi-GPU Recommendation Model Training and Input Preprocessing

Ensuring high-quality recommendations for newly onboarded users requires the continuous retraining of Deep Learning Recommendation Models (DLRMs) with freshly generated data. To serve the online DLRM retraining, existing solutions use hundreds of CPU computing nodes designated for input preprocessing, causing significant power consumption that surpasses even the power usage of GPU trainers. To this end, we propose RAP, an end-to-end DLRM training framework that supports Resource-aware Automated GPU sharing for DLRM input Preprocessing and Training. The core idea of RAP is to accurately capture the remaining GPU computing resources during DLRM training for input preprocessing, achieving superior training efficiency without requiring additional resources. Specifically, RAP utilizes a co-running cost model to efficiently assess the costs of various input preprocessing operations, and it implements a resource-aware horizontal fusion technique that adaptively merges smaller kernels according to GPU availability, circumventing any interference with DLRM training. In addition, RAP leverages a heuristic searching algorithm that jointly optimizes both the input preprocessing graph mapping and the co-running schedule to maximize the end-to-end DLRM training throughput. The comprehensive evaluation shows that RAP achieves 78.3× speedup on average over CPU-based DLRM input preprocessing frameworks. In addition, the end-to-end training throughput of RAP is only 2.04% lower than the ideal case, which has no input preprocessing overhead.

Wang, Zheng↗
DOE OSTI2022

Strategies and Approaches for Developing Hands-On Training for Cold Climate Heat Pumps

The International Center for Appropriate and Sustainable Technology (ICAST) is in the process of implementing a program funded by the US Department of Energy (DOE) in which they are providing cold climate heat pump (CCHP) curriculum and training to HVAC workers, ranging from entry to experienced levels. They have coordinated with Santa Fe Community College (SFCC) to develop online curricula, and through their involvement with the DOE Better Buildings Workforce Accelerator, they requested technical assistance from the National Renewable Energy Laboratory (NREL) to help them develop programs that incorporate hands-on and on-the-job skills training and job placement services in coordination with local employers. This report offers a step-by step-overview of the process for developing a new workforce development and hands-on training program in a new region, outlining practices to help understand the market, and to effectively recruit, train, and connect people to HVAC jobs installing cold climate heat pumps.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Interpreting and Stabilizing Machine-Learning Parametrizations of Convection

Neural networks are a promising technique for parameterizing subgrid-scale physics (e.g., moist atmospheric convection) in coarse-resolution climate models, but their lack of interpretability and reliability prevents widespread adoption. For instance, it is not fully understood why neural network parameterizations often cause dramatic instability when coupled to atmospheric fluid dynamics. This paper introduces tools for interpreting their behavior that are customized to the parameterization task. First, we assess the nonlinear sensitivity of a neural network to lower-tropospheric stability and the midtropospheric moisture, two widely studied controls of moist convection. Second, we couple the linearized response functions of these neural networks to simplified gravity wave dynamics, and analytically diagnose the corresponding phase speeds, growth rates, wavelengths, and spatial structures. To demonstrate their versatility, these techniques are tested on two sets of neural networks, one trained with a super-parameterized version of the Community Atmosphere Model (SPCAM) and the second with a near-global cloud-resolving model (GCRM). Additionally, even though the SPCAM simulation has a warmer climate than the cloud-resolving model, both neural networks predict stronger heating/drying in moist and unstable environments, which is consistent with observations. Moreover, the spectral analysis can predict that instability occurs when GCMs are coupled to networks that support gravity waves that are unstable and have phase speeds larger than 5 m s -1 . In contrast, standing unstable modes do not cause catastrophic instability. Using these tools, differences between the SPCAM-trained versus GCRM-trained neural networks are analyzed, and strategies to incrementally improve both of their coupled online performance unveiled.

54 ENVIRONMENTAL SCIENCES↗