Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Deep Learning for Fish Identification from Sonar Data (CRADA 481 Final Report)

In eastern regions of the United States, the American eel is a species of management and regulatory concern because of significant population declines, despite the species’ previous abundance in all tributaries of rivers flowing into the Atlantic Ocean. The American eel is also a candidate for listing under the U.S. Endangered Species Act. While hydropower construction and operation are only one of several factors contributing to this population decline, such a listing could impose additional regulatory challenges for a large number of hydropower projects. In this CRADA project, we improved technologies for identifying migrating eels with the goal of reducing the cost and time required for future American eel hydropower impact assessment and mitigation studies, while maintaining accuracy. We built on results from a previous FOA project (FOA# DE-FOA-0001662), led by the Electric Power Research Institute (EPRI), which developed a highly accurate, deep-learning method for identifying migrating eels from imaging sonar data. The current study aimed to further optimize this deep-learning model, originally designed for image classification, and to develop an object detection software capable of identifying fish from sonar videos in real time, enabling the detection of events like fish migrations and specific species, such as the American eel, at hydropower dams. The data conversion algorithms were packaged as software with a graphical user interface, and the software is evaluated by external collaborators. We focused on the American eel in this project and explored the transferability of the developed deep learning models to the sea lamprey, given the similar body shape and swimming behavior between the two species.

13 HYDRO ENERGY↗
DOE OSTI2020

Development of the Intelligent, Preventive Infrared (IR) Inspection System Housed in Hybrid Robotic Platforms

Robots and robotic systems that are designed for inspection, environmental study, and health and safety aid are becoming an increasing necessity. However, there is a number of challenges that accompany robots that are designed for these specific applications. These challenges include: navigating compact, enclosed spaces, travelling over multiple terrains and large obstacles, using the proper sensing and detection methods to assess an environment, and the use of lightweight and durable materials. The robotic platforms currently in development look at all of these challenges and attempt to overcome them. These designs specific use of hybrid robotic platforms, or platform that utilizes soft and rigid materials, allows for a more flexible platform and makes environments more navigable. To further improve the navigation of the platforms and environmental assessment, a novel infrared detection system is housed in the platforms to create a robot that can be used for the applications listed above and more. Objectives: Further develop two types of robotic platforms that utilize additive manufacturing, soft materials, and rigid materials. Continue the development of an intelligent and inhibitory infrared detection system based on an artificial intelligence (AI) algorithm. Continued study and fabrication of active soft materials designed for both sensing and actuation in hybrid robotic systems. Improve additive manufacturing fabrication to design rigid and semi-rigid components for hybrid robotic platforms. Transformable Wheel Robotic Platform: The chassis, wheels, tires and inspection system housing use different additive manufacturing techniques for fabrication. Continued work with additive manufacturing has lead to studies in metal-based printing and modular design and manufacturing. The new platform design with integrated electrical component printed. This will allow integration of the sensor housing onto the platform. Electrical components are being tested for battery life and performance. To improve this performance, such as integration of Lithium Polymer (LiPo) batteries. Snake Robotic Platform: The main focus of the development has centered around liquid-based soft actuators. That act on the principles of electrostatic and hydraulic actuation. A liquid dielectric sits between two compliant electrodes, contained by a flexible polymer shell. The electrodes and film gradually collapse toward each other from one corner of the electrode to the other. When the electrodes and film close together, a majority of the fluid is pushed into the area not covered by an electrode. A thin layer of the liquid dielectric remains between the electrode. The actuators will be stacked to cause large displacement, and move the linkages. The chassis of this platform uses purely additively manufactured linkages. Intelligent, Preventive IR Inspection System: Development of the AI for the system has lead to using a Scikit-Learn which assists in creating predictive models based on Regression, clustering, classification etc. To improve the infrared thermometry for low emissivity sources, work on the fabrication of a tandem photoconductive infrared thermometer was a main focus. Distance-Voltage-Temperature response data has been collected in the range of 7 cm - 100 cm and 200-400 deg. C. Modifications were made to the existing test bench to have a better control over the data. Automated data collection was realized using a Python code and an Arduino controlled stepper motor to increase the sample rate. A protective enclosure has been built around the setup to minimize the effect of the environment on the measurements. To better predict temperature, different AI models are being optimized. The regression model, LARS showed a high accuracy but had convergence issues and only works for the current test set-up. Results: The Transformable Wheel Robot has developed into a more flexible and modular platform. With the improvements to the current work, effort on the tire or soft gripper design been a large focus. The soft grippers will be interchange able to allow for increased performance in identified terrain types. The development of the liquid-based actuators allows the snake robotic platform to achieve the goals of being flexible and able to navigate confined spaces. However, there is room for improvement. Optimization work is currently being done in COMSOL Multiphysics. With the current IR system set-up the LARS model perfectly predicts the data; however, considering the mobility aspect of the project other models will allow for an optimized system. Testing of other model types is currently being done.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

Method to simultaneously facilitate all jet physics tasks

Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of jet physics are proceeding in parallel. We show that specially constructed machine learning models trained for a specific jet classification task can improve the accuracy, precision, or speed of all other jet physics tasks. This is demonstrated by training on a particular multiclass generation and classification task and then using the learned representation for different generation and classification tasks, for datasets with a different (full) detector simulation, for jets from a different collision system ($pp$ versus $ep$), for generative models, for likelihood ratio estimation, and for anomaly detection. We consider our omnilearn approach thus as a jet-physics foundation model. It is made publicly available for use in any area where state-of-the-art precision is required for analyses involving jets and their substructure.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

A machine-learning-driven data labeling pipeline for scientific analysis in MLExchange

This study introduces a novel labeling pipeline to accelerate the labeling process of scientific data sets by using artificial intelligence (AI)-guided tagging techniques. This pipeline includes a set of interconnected web-based graphical user interfaces (GUIs), where Data Clinic and MLCoach enable the preparation of machine learning (ML) models for data reduction and classification, respectively, while Label Maker is used for label assignment. Throughout this pipeline, data can be accessed through a direct connection to a file system or through Tiled for access through Hypertext Transfer Protocol (HTTP). Our experimental results present three use cases where this labeling pipeline has been instrumental for the study of large X-ray scattering data sets in the area of pattern recognition, the remote analysis of resonant soft X-ray scattering data and the fine-tuning process of foundation models. These use cases highlight the labeling capabilities of this pipeline, including the ability to label large data sets in a short period of time, to perform remote data analysis while minimizing data movement and to enhance the fine-tuning process of complex ML models with human involvement.

Chavez, Tanny (ORCID:0000000193172896)↗
DOE OSTI2024

Identification of integrated proteomics and transcriptomics signature of alcohol-associated liver disease using machine learning

Distinguishing between alcohol-associated hepatitis (AH) and alcohol-associated cirrhosis (AC) remains a diagnostic challenge. In this study, we used machine learning with transcriptomics and proteomics data from liver tissue and peripheral mononuclear blood cells (PBMCs) to classify patients with alcohol-associated liver disease. The conditions in the study were AH, AC, and healthy controls. We processed 98 PBMC RNAseq samples, 55 PBMC proteomic samples, 48 liver RNAseq samples, and 53 liver proteomic samples. First, we built separate classification and feature selection pipelines for transcriptomics and proteomics data. The liver tissue models were validated in independent liver tissue datasets. Next, we built integrated gene and protein expression models that allowed us to identify combined gene-protein biomarker panels. For liver tissue, we attained 90% nested-cross validation accuracy in our dataset and 82% accuracy in the independent validation dataset using transcriptomic data. We attained 100% nested-cross validation accuracy in our dataset and 61% accuracy in the independent validation dataset using proteomic data. For PBMCs, we attained 83% and 89% accuracy with transcriptomic and proteomic data, respectively. The integration of the two data types resulted in improved classification accuracy for PBMCs, but not liver tissue. We also identified the following gene-protein matches within the gene-protein biomarker panels: CLEC4M-CLC4M, GSTA1-GSTA2 for liver tissue and SELENBP1-SBP1 for PBMCs. In this study, machine learning models had high classification accuracy for both transcriptomics and proteomics data, across liver tissue and PBMCs. The integration of transcriptomics and proteomics into a multi-omics model yielded improvement in classification accuracy for the PBMC data. The set of integrated gene-protein biomarkers for PBMCs show promise toward developing a liquid biopsy for alcohol-associated liver disease.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Machine learning-enabled multiscale modeling of mechanical deformation of aluminum and Al-SiC nanocomposites

A machine learning-enabled multiscale framework is developed for modeling the mechanical response of both pure metal and nanoparticle-reinforced metal matrix nanocomposites (MMNCs). Using aluminum–silicon carbide (Al-SiC) as an example MMNC, atomistic simulations reveal three distinct deformation mechanisms (i.e., defect-free, dislocation-based, and interface separation) governed by the interfaces between the Al matrix and SiC nanoparticles. As compared with single crystal Al, the lattice undergoes a more abrupt failure once the dislocation network becomes extensive and void nucleation initiates, whereas in Al-SiC, nanoparticle interfaces enable a more gradual progression of damage. These mechanisms are captured through a combined classification-regression neural network surrogate model that bridges atomic-scale insights with continuum-scale finite element analysis. Machine learning-enabled multiscale modeling of pure Al accurately predicted strain localization and confirmed by in-situ scanning electron microscopic tensile testing on perforated Al specimens. This study underscores the promise of integrating physics-informed machine learning with hierarchical modeling to capture the interface dominated phenomena and guide the design of advanced MMNCs.

Al-SiC↗
DOE OSTI2023

Spatial controls of methane uptake in upland soils across climatic and geological regions in Greenland

Abstract In the Arctic, the spatiotemporal variation of net methane uptake in upland soils depends on unresolved interactive controls between edaphic and microbial factors not yet included in current models, underpinning the uncertainty of upscaling the Arctic methane budget. Here we show that upland soils in Greenland are consistent methane sinks (−1.83 ± 0.19 nmol methane g −1 dw d −1 ) across a N-S (64–83 °N) pedoclimatic transect. We demonstrate that methane oxidizers abundance, soil pH, and available soil copper are important controls on the spatial variation in methane oxidation. We revised a soil biogeochemical model with a high-resolution land classification and meteorological data for Greenland and tested it against our methane uptake measurements. The model simulated well the magnitudes of observed methane uptake but not the spatial variation across all sites. This work provides novel insights into the controls of methane uptake, which are critical for the accuracy of methane budgets.

Environmental Sciences & Ecology↗
DOE OSTI2025

NeuroSymbolic Approaches as a Vector for Assured Artificial Intelligence

The deployment of artificial intelligence systems in critical applications requires higher levels of assurance for safety, security, and interpretability. While neurosymbolic (NESY) approaches combining neural networks with symbolic reasoning offer potential advantages for assured AI, existing differentiable neurosymbolic frameworks face significant limitations including computational overhead and performance constraints. This report investigates the ISED (InferSampleEstimateDescend) framework as an alternative approach that enables neurosymbolic learning without requiring endtoend differentiability. We evaluate ISED’s utility for geointelligence applications by comparing neurosymbolic models against standard neural networks on aircraft classification tasks using the RarePlanes and MTARSI imagery datasets. Our results demonstrate that while ISEDbased models achieve slightly lower accuracy (89.7% vs 92.1% on RarePlanes; 91.1% vs 92.5% on MTARSI), they provide critical explainability capabilities that enable tracing incorrect predictions back to specific attribute misclassifications. We also present an automated pipeline that generates both attributeclass mappings and neurosymbolic model architectures from natural language descriptions, significantly reducing the manual effort required for NESY model deployment. These findings suggest that ISED offers a promising direction for developing assured AI systems where interpretability and reasoning transparency are prioritized alongside performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

VIC-Global Parameter Dataset Sensitivity with the Variable Infiltration Capacity Model: Evaluating the importance of dynamic land surface parameters when using the VIC-Global parameter dataset

Accurate prediction of runoff is essential to water resources management, flood risk assessment, and ecosystem protection. However, many hydrological models still have relatively substantial limitations when representing the influence of land use and land cover (LULC) on runoff generation and routing. Changes in LULC, such as deforestation, urban expansion, agricultural intensification, and wetland loss, have been shown to alter the water balance at the land surface through fundamental hydrologic processes (e.g., interception, infiltration, evapotranspiration, and soil storage). However, it remains an open question what the exact magnitude and timing of these impacts are for the spatial and temporal scales commonly used in engineering applications. In this analysis we focus on one aspect of recent LULC change for assessing human impacts, which is urbanization. Specifically we seek to determine the impacts of urbanization on the magnitude and timing of surface runoff and baseflow in HUC-12 basins in Clark County, Nevada which has experienced rapid urbanization. We use the Variable Infiltration Capacity (VIC) hydrology model with a widely used off-the-shelf dataset of land surface parameters, VIC-Global, both of which have been commonly used in the past for water and energy balance modeling for large scale hydrologic studies. We examine two scenarios where the first scenario removes all urbanized land cover and parameterizes those areas of the basins as barren or open shrubland. The second scenario tests the opposite case where all areas of the basins are classified as urban regardless of their present classification. The results from the VIC model show there is a low sensitivity for daily surface runoff between scenarios. The daily baseflow values indicate similar low sensitivity to the classification change during specific periods, but then have substantial differences during other period when large precipitation events are occurring. This is likely due to the assumed parameter values for the urban land cover classification made by the VIC-Global dataset. Using a static land cover parameterization is reasonable for large domain hydrology models that are being used for near-term planning horizons (<30 years). However, longer planning horizons where feedbacks between the atmosphere and land surface are important, especially in transient climate situations, considerations for how to update land surface parameters should be incorporated.

42 ENGINEERING↗
DOE OSTI2023

A Continental-Scale Estimate of Soil Organic Carbon Change at NEON Sites and Their Environmental and Edaphic Controls

Current carbon cycle models focus on the effects of climate and land-use change on primary productivity and microbial-mineral dependent carbon turnover in the topsoil, while less attention has been paid to vertical soil processes and soil-dependent response to land-use change along the profile. In this study, a spatial-temporal analysis was used to estimate soil organic carbon (SOC) change in topsoil/A horizon and subsoil/B horizon at National Ecological Observatory Network (NEON) sites, USA over 30 years. To separate the effects of land-use, environmental, and edaphic factors on SOC change, space-for-time substitution was used in combination with the Continuous Change Detection and Classification algorithm and Structural Equation Modeling. Results showed that (a) under natural vegetation, Spodosols and Inceptisols found in the eastern NEON sites had substantial topsoil SOC accumulation (+0.4 to +1.2 Mg C ha –1 year –1 ), while Inceptisols and Andisols in the west had a comparable magnitude of topsoil SOC loss (–0.5 to –1.8 Mg C ha –1 year –1 ); (b) Mollisols and Alfisols in the Central Plains sites were susceptible to significant SOC loss under farming and grazing; (c) Runoff/erosion and leaching potential, vertical translocation, and mineral sorption were the most important factors controlling SOC variation across the NEON sites. Our work could be used to parameterize ecosystem models simulating SOC change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling

Traditional entropy-based methods—such as cross-entropy loss in classification problems—have long been essential tools for representing the information uncertainty and physical disorder in data and for developing artificial intelligence algorithms. However, the rapid growth of data across various domains has introduced new challenges, particularly the integration of heterogeneous datasets with intrinsic disparities. To address this, we introduce a zentropy-enhanced neural network (ZENN), extending zentropy theory into the data science domain via intrinsic entropy, enabling more effective learning from heterogeneous data sources. ZENN simultaneously learns both energy and intrinsic entropy components, capturing the underlying structure of multisource data. To support this, we redesign the neural network architecture to better reflect the intrinsic properties and variability inherent in diverse datasets. We demonstrate the effectiveness of ZENN on classification tasks and energy landscape reconstructions, showing its superior generalization capabilities and robustness-particularly in predicting high-order derivatives. In image and text classification tasks, ZENN demonstrates superior generalization by introducing a learnable temperature variable that models latent multisource heterogeneity, allowing it to surpass state-of-the-art models on CIFAR-10/100, BBC News, and AG News. As a practical application in materials science, we employ ZENN to reconstruct the Helmholtz energy landscape of Fe3Pt using data generated from density functional theory and capture key material behaviors, including negative thermal expansion and the critical point in the temperature–pressure space. Overall, this work presents a zentropy-grounded framework for data-driven machine learning, positioning ZENN as a versatile and robust approach for scientific problems involving complex, heterogeneous datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Graph-based featurization methods for classifying small molecule compounds

For over a decade, drug-induced liver injury (DILI) has posed significant drawbacks in the synthesis and development of drugs and remains a consequential concern. With finite success within the existing preclinical models, DILI is one of the main causes of drug withdrawal or termination from the market. Particularly, this withdrawal occurs during the late stages of drug development (Kullak-Ublick, 2017). Since DILI is difficult to diagnose and treat, it has become an obstacle in the drug production market that in turn affects clinicians, pharmaceutical companies, and consumers. We propose a method for learning features of DILI-positive drugs based on the graphical relationships and patterns they possess within a network of biological databases. We also train various statistical and machine learning models on these learned features in order to classify the drugs as DILI-positive or negative. Our methods include Random Forest, Neural networks, and logistic regression classification. We utilize labeled DILI-positive and DILI-negative datasets, which were developed by the FDA and the National center for toxicological research, as well as additional literature datasets (Thakkar, 2020) in order to validate our results and assess our featurization and model accuracy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

DeepAstroUDA: semi-supervised universal domain adaptation for cross-survey galaxy morphology classification and anomaly detection

Abstract Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA , as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation

Background: Patient monitoring is vital in all stages of care. In particular, intensive care unit (ICU) patient monitoring has the potential to reduce complications and morbidity, and to increase the quality of care by enabling hospitals to deliver higher-quality, cost-effective patient care, and improve the quality of medical services in the ICU. Objective: We here report the development and validation of ICU length of stay and mortality prediction models. The models will be used in an intelligent ICU patient monitoring module of an Intelligent Remote Patient Monitoring (IRPM) framework that monitors the health status of patients, and generates timely alerts, maneuver guidance, or reports when adverse medical conditions are predicted. Methods: We utilized the publicly available Medical Information Mart for Intensive Care (MIMIC) database to extract ICU stay data for adult patients to build two prediction models: one for mortality prediction and another for ICU length of stay. For the mortality model, we applied six commonly used machine learning (ML) binary classification algorithms for predicting the discharge status (survived or not). For the length of stay model, we applied the same six ML algorithms for binary classification using the median patient population ICU stay of 2.64 days. For the regression-based classification, we used two ML algorithms for predicting the number of days. We built two variations of each prediction model: one using 12 baseline demographic and vital sign features, and the other based on our proposed quantiles approach, in which we use 21 extra features engineered from the baseline vital sign features, including their modified means, standard deviations, and quantile percentages. Results: We could perform predictive modeling with minimal features while maintaining reasonable performance using the quantiles approach. The best accuracy achieved in the mortality model was approximately 89% using the random forest algorithm. The highest accuracy achieved in the length of stay model, based on the population median ICU stay (2.64 days), was approximately 65% using the random forest algorithm. Conclusions: The novelty in our approach is that we built models to predict ICU length of stay and mortality with reasonable accuracy based on a combination of ML and the quantiles approach that utilizes only vital signs available from the patient’s profile without the need to use any external features. This approach is based on feature engineering of the vital signs by including their modified means, standard deviations, and quantile percentages of the original features, which provided a richer dataset to achieve better predictive power in our models.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Field validation of isotropic analytical models for simulating fabric shades

Fabric roller shades are common shading materials used in commercial and residential buildings. Accurately characterizing and modeling shades helps practitioners select the appropriate product and its control strategy based on climate and occupants' priorities, such as visual comfort and view to outdoors. Previous studies established a generalized method for modeling complex fenestration systems using data-driven tabulated bidirectional scattering distribution functions. However, deploying such a method at scale to all fabric shading products on the market is too costly and time-consuming. Analytical models that are based on a limited set of measurements (e.g., normal-normal and normal-hemispherical visible transmittance and reflectance, and directional cut-off angles) can be used to model the wide variety of shading products on the market. This study evaluates the performance of two isotropic analytical models, Roos-Wienold and Modified-Kotey, for modeling fabric roller shades, with a focus on the model's ability to predict occupant visual comfort. The performance evaluation was conducted through laboratory and field measurements and simulations. The results showed that both models are sufficient for predicting vertical illuminance at seated eye-level. Roos-Wienold model was able to predict binary visual comfort classification (glare/no-glare) under a wide range of luminance conditions, while Modified-Kotey model did not perform as well under high-contrast low-adaptation conditions. Both models are insufficient in predicting visual comfort at a four-point scale (e.g., imperceptible, perceptible, disturbing, intolerable). The two isotropic models become less accurate when the fabric exhibits high anisotropy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

An image-driven machine learning approach to kinetic modeling of a discontinuous precipitation reaction

Micrograph quantification is an essential component of several materials science studies. Machine learning methods, in particular convolutional neural networks, have previously demonstrated performance in image recognition tasks across several disciplines (e.g. materials science, medical imaging, facial recognition). Here, we apply these well-established methods to develop an approach to microstructure quantification for kinetic modeling of a discontinuous precipitation reaction in a case study on the uranium-molybdenum system. Prediction of material processing history based on image data (classification), calculation of area fraction of phases present in the micrographs (segmentation), and kinetic modeling from segmentation results were performed. Results indicate that convolutional neural networks represent microstructure image data well, and segmentation using the k-means clustering algorithm yields results that agree well with manually annotated images. Classification accuracies of original and segmented images are both 94% for a 5-class classification problem. Kinetic modeling results agree well with previously reported data using manual thresholding. The image quantification and kinetic modeling approach developed and presented here aims to reduce researcher bias introduced into the characterization process, and allows for leveraging information in limited image data sets.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Self-Supervised Cloud Classification

Abstract Low-level marine clouds play a pivotal role in Earth’s weather and climate through their interactions with radiation, heat and moisture transport, and the hydrological cycle. These interactions depend on a range of dynamical and microphysical processes that result in a broad diversity of cloud types and spatial structures, and a comprehensive understanding of cloud morphology is critical for continued improvement of our atmospheric modeling and prediction capabilities moving forward. Deep learning has recently accelerated our ability to study clouds using satellite remote sensing, and machine learning classifiers have enabled detailed studies of cloud morphology. A major limitation of deep learning approaches to this problem, however, is the large number of hand-labeled samples that are required for training. This work applies a recently developed self-supervised learning scheme to train a deep convolutional neural network (CNN) to map marine cloud imagery to vector embeddings that capture information about mesoscale cloud morphology and can be used for satellite image classification. The model is evaluated against existing cloud classification datasets and several use cases are demonstrated, including training cloud classifiers with very few labeled samples, interrogation of the CNN’s learned internal feature representations, cross-instrument application, and resilience against sensor calibration drift and changing scene brightness. The self-supervised approach learns meaningful internal representations of cloud structures and achieves comparable classification accuracy to supervised deep learning methods without the expense of creating large hand-annotated training datasets. Significance Statement Marine clouds heavily influence Earth’s weather and climate, and improved understanding of marine clouds is required to improve our atmospheric modeling capabilities and physical understanding of the atmosphere. Recently, deep learning has emerged as a powerful research tool that can be used to identify and study specific marine cloud types in the vast number of images collected by Earth-observing satellites. While powerful, these approaches require hand-labeling of training data, which is prohibitively time intensive. This study evaluates a recently developed self-supervised deep learning method that does not require human-labeled training data for processing images of clouds. We show that the trained algorithm performs competitively with algorithms trained on hand-labeled data for image classification tasks. We also discuss potential downstream uses and demonstrate some exciting features of the approach including application to multiple satellite instruments, resilience against changing image brightness, and its learned internal representations of cloud types. The self-supervised technique removes one of the major hurdles for applying deep learning to very large atmospheric datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Design, Detection, and Countermeasure of Frequency Spectrum Attack and Its Impact on Long Short-Term Memory Load Forecasting and Microgrid Energy Management

This paper introduces a frequency-domain false data injection attack called Frequency Spectrum Attack (FSA) and explores its effects on load forecasting and the energy management system (EMS) in a microgrid. The FSA analyzes time-series signals in the frequency domain to identify patterns in their frequency spectrum. It learns the distribution of dominant frequencies in a dataset of healthy signals. Subsequently, it manipulates the amplitudes of dominant frequencies within this healthy distribution, ensuring a stealthy attack against statistical analysis of the signal spectrum. We evaluated the performance of FSA on LSTM, a state-of-the-art network for load forecasting. The results show that FSA can triple the Mean Absolute Error (MAE) of predictions compared to the normal case and increase it by 70% compared to noise injection attacks. Furthermore, FSA indirectly enhances battery utilization in the EMS by 45%. We then proposed a detection method that combines statistical analysis and machine-learning-based classification techniques with features. The model effectively distinguishes FSA from healthy and noisy signals, achieving an accuracy of 98.7% and an F1-score of 98.1% on a load dataset, covering healthy, FSA, and noisy load data. Finally, a countermeasure was introduced based on the statistical analysis of the frequency spectrum of healthy signals to mitigate the impact of FSA. This countermeasure successfully reduces the MAE of the attacked model from 0.135 to 0.053, validating its effectiveness in mitigating FSA.

Nazeri, Amirhossein↗