SEARCH · Search NASA
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.
This presentation applies open set recognition to classify unknown waveforms, enabling systems to not only identify known types but also reliably detect when waveforms fall outside the training distribution. This approach enhances robustness by avoiding forced misclassification of novel or anomalous signals.
We developed multiple machine learning methods for the detection and classification of new wireless communication waveforms, which is critical for targeted attacks in wireless networks and electronic warfare. Our machine learning models are capable of dynamically detecting security threats in near real time through our advanced open set recognition (OSR) approach. This model has demonstrated significant improvements in the detection of unknown waveforms, thereby enhancing the security and reliability of mission critical communications. Our approach to detecting uncertain security threats is novel; we advanced OSR techniques by incorporating domain knowledge of wireless signals. Specifically, we combined time and frequency domain model features to enhance the model’s performance. Utilizing an OSR approach eliminates the need for training data to be distributed similarly to the deployment environment and removes the requirement for the training set to contains all possible threat classes. This is crucial because it is often infeasible to determine and characterize all potential security threats in advance. Our model were trained on simulated data, generated in partnership with the University at Albany, State of New York. The data set contained a diverse array of wireless signals, including those with additive white Gaussian noise and multipath signals, with and without line of sight. This comprehensive training set allowed us to optimize our models to detect unknown waveforms under various challenging scenarios, such as low signal-to-noise ratios. By training on various waveforms, varying signal-to-noise ratio, and different sample sizes under normal conditions, our models were fine tuned to perform effectively in challenging environments.
Identifying unseen electromagnetic waveforms is critical for many applications, like interference management, electronic warfare and spectrum management. Traditionally this is done using statistical methods for anomaly detection, which has evolved to deep learning models for identifying the unseen data, formally termed as open set recognition. Some prior methods use a generative model to emulate open set data, which face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. To alleviate this issue, we propose a discriminative model that effectively combines time and frequency domain features of communication signals for accurate predictions. We further introduce a cosine similarity loss that makes the domain specific features unique to enhance the prediction rate. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10% over models without cosine loss.
Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.
In real-world applications like spectrum management and interference detection, dealing with unseen electromagnetic waveforms is critical. Although some methods attempt to simulate open set data using generator models, they face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. This results in difficulties capturing distinctive features across classes, especially in dynamic scenarios where new classes emerge. To detect unseen waveforms, we propose combining time and frequency domain features with cosine similarity loss to enhance feature distinctiveness and enabling more accurate predictions. This approach efficiently captures more comprehensive information than single-domain representations or approaches without cosine loss. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10\% over models without cosine loss.
Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.
Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.
This paper develops a conceptual model, adapted from the way research and development non-profits and universities tend to be organized, that could help amplify the reach and effectiveness of the international space architecture community. The model accommodates current activities and published positions, and increases involvement by allocating accountability for necessary professional and administrative activities. It coordinates messaging and other outreach functions to improve brand management. It increases sustainability by balancing volunteer workload. And it provides an open-ended structure that can be modified gracefully as needs, focus, and context evolve. Over the past 20 years, Space Architecture has attained some early signs of legitimacy as a discipline: an active, global community of practicing and publishing professionals; university degree programs; a draft undergraduate curriculum; and formal committee establishment within multiple professional organizations. However, the nascent field has few outlets for expression in built architecture, which exacerbates other challenges the field is experiencing in adolescence: obtaining recognition and inclusion as a unique contributor by the established aerospace profession; organizing and managing outreach by volunteers; striking a balance between setting admittance or performance credentials and attaining a critical mass of members; and knowing what to do, beyond sharing common interests, to actually increase the market demand for space architecture. This paper develops a conceptual model, adapted from the way research-anddevelopment non-profits and universities tend to be organized, that could help amplify the reach and effectiveness of the international space architecture community. The model accommodates current activities and published positions, and increases involvement by allocating accountability for necessary professional and administrative activities. It coordinates messaging and other outreach functions to improve brand management. It increases sustainability by balancing volunteer workload. And it provides an open-ended structure that can be modified gracefully as needs, focus, and context evolve. This organizational model is offered up for consideration, debate, and toughening by the space architecture community at large.
Named entity recognition (NER) has been widely used in chemical text mining for the automatic identification and extraction of chemical entities. However, existing chemical NER systems primarily focus on scenarios with abundant training data, requiring significant human effort on annotations. This poses challenges for applications in the chemical field, such as catalysis, where many advancements have traditionally relied on trial-and-error investigations and incremental adjustment of variables. This hinders catalysis science and technology progress in addressing emerging energy and environmental crises. In this work, we propose a few-shot NER model that can quickly adapt to extract new types of chemical entities by using only a limited number of annotated examples. Our model employs a metric-learning approach to transfer entity similarity knowledge from high-resource chemical domains (with abundant annotations) to enable effective entity recognition in low-resource specialized domains (limited annotation). We validate the effectiveness of our model on a few-shot chemical NER benchmark built based on six existing chemical NER data sets. Experiments show that the proposed few-shot NER model can achieve reasonable performance with only 5 examples per entity type and shows consistent improvement as the number of examples increases. Furthermore, we demonstrate how the proposed model can be trained with large language model (LLM) annotated data, opening a new pathway for rapid adaptation of NER systems. Furthermore, our approach leverages the knowledge broadness of large language models for chemistry while distilling this knowledge into a lightweight model suitable for efficient and in-house use.
As efforts of the National Aeronautics and Space Administration (NASA) and the Federal Aviation Administration (FAA) continue to digitize the air traffic management (ATM) domain, there is countless times of need for downstream natural language processing (NLP) tasks such as named entity recognition, text summarization, classification, and more. Although there are a plethora of open-sourced pre-trained transformer models in the NLP field such as BERT, RoBERTa, XLNet, and GPT-3, these models are trained on general corpora and perform poorly on domain-specific terminology and phraseology seen in ATM documents such as Notice to Airmen (NOTAMs) and Letters of Agreement (LoA). Our proposed research objective will be to first gather a large corpus of air traffic management related documents, orders, notices, books, technical papers, conference papers, articles, and other miscellaneous sources of text data from the FAA, NASA, and accredited conference and publication societies. After gathering this data, many steps will have to be taken to collate and preprocess the data into a format understandable by our test transformer models. Thirdly, we will set up training pipelines to train the RoBERTa model on its unsupervised training task masked language modelling (MLM) using resources provided by the NASA Advanced Supercomputing (NAS) facilities. Finally, these fine-tuned transformer models will be evaluated on their performance on down-stream NLP tasks as mentioned above, to show whether they will be effective when working with ATM related data or not. Once complete, this model could be made open-sourced on the HuggingFace website, where the rest of the ATM community can access and utilize this tool.
The recent reorganization and shift to managing total quality at the NASA Langley Research Center (LaRC) has placed an increasing emphasis on teams and teamwork in accomplishing day-to-day work activities and long-term projects. The purpose of this research was to review the nature of teams and teamwork at LaRC. Models of team performance and teamwork guided the gathering of information. Current and former team members served as participants; their collective experience reflected membership in over 200 teams at LaRC. The participants responded to a survey of open-ended questions which assessed various aspects of teams and teamwork. The participants also met in a workshop to clarify and elaborate on their responses. The work accomplished by the teams ranged from high-level managerial decision making (e.g., developing plans for LaRC reorganization) to creating scientific proposals (e.g., describing spaceflight projects to be designed, sold, and built). Teams typically had nine members who remained together for six months. Member turnover was around 20 percent; this turnover was attributed to heavy loads of other work assignments and little formal recognition and reward for team membership. Team members usually shared a common and valued goal, but there was not a clear standard (except delivery of a document) for knowing when the goal was achieved. However, members viewed their teams as successful. A major factor in team success was the setting of explicit a priori rules for communication. Task interdependencies between members were not complex (e.g., sharing of meeting notes and ideas about issues), except between members of scientific teams (i.e., reliance on the expertise of others). Thus, coordination of activities usually involved scheduling and attendance of team meetings. The team leader was designated by the team's sponsor. This leader usually shared power and responsibilities with other members, such that team members established their own operating procedures for decision making. Sponsors followed a hands-off policy during team operations, but they approved and reviewed team products. Most teams, particularly high-level decision-making teams, had little or no authority to carry out their decisions. Team members had few interpersonal conflicts. They monitored each other respectfully about meeting deadlines. Feedback and backup behaviors were seen as desirable aspects of teamwork, wanted by the members, and done appropriately.
While geostationary satellites, such as the GOES-R series, provide wildland fire hotspot readings at a high temporal resolution, they are prone to false negative readings and decreased confidence. One cause of decreased hotspot confidence is cloud contamination. Smoke produced from wildfire is often misinterpreted as cloud contamination, resulting in inaccurate and unsure sensor readings. To this end, we built a deep learning image segmentation model to identify smoke and cloud in true color satellite images. The model is pre-trained using self-supervised learning on over 10,000 GOES-R images to learn the underlying structure of satellite imagery. Then, the model is fine-tuned on a set of 130 labeled documents using supervised learning. The resulting model performs multi-class image segmentation with 85% accuracy and runs in under a minute on a standard personal computer. When paired alongside hotspot data, the model’s outputs can help increase confidence in wildfire location by identifying cases of cloud contamination that are due to smoke. The resulting model can be deployed in a stand-alone application or bundled in an Open Data Integration for wildland fire management (ODIN) application.
Each of 12 subjects set a binocularly viewed target to apparent eye level; the target was projected on the rear wall of an open box, the floor of which was horizontal or pitched up and down at angles of 7.5 degrees and 15 degrees. Settings of the target were systematically biased by 60% of the pitch angle when the interior of the box was illuminated, but by only 5% when the interior of the box was darkened. Within-subjects variability of the settings was less under illuminated viewing conditions than in the dark, but was independent of box pitch angle. In a second experiment, 11 subjects were tested with an illuminated pitched box, yielding biases of 53% and 49% for binocular and monocular viewing conditions, respectively. The results are discussed in terms of individual and interactive effects of optical, gravitational, and extraretinal eye-position information in determining judgements of eye level.
EXECUTIVE SUMMARY The Western States Water Council (WSWC) and the NASA Western Water Applications Office (WWAO) hosted a joint workshop on technology transfer for water management in the Western U.S. The goals of the workshop were to understand how different agencies approach the technology transfer and research to operations (R2O) process, identify best practices, and discuss existing barriers to successful technology infusion into operational water resource management systems at the state and federal level. The workshop took place August 7-9, 2019 in Irvine, CA. Key outcomes of the meeting include the following:• U.S. Rep. Grace Napolitano provided opening remarks for the workshop, where she highlighted the critical value of water data and the importance of collaboration between state and federal agencies in working to advance the use of water data in water management, planning and policy. • A total of 33 participants (including remote participants) were part of the workshop. They included principal investigators and project teams supported by NASA (Cyanobacteria Assessment Network, Evapotranspiration for Western States, Evaporative Stress Index, the Airborne Snow Observatory, Satellite-based Snow Water Equivalent in the Sierra Nevadas, and Fallowed Area Mapping) as well as representatives from federal (USGS, NOAA, USBR, EPA) and state (CA, WY, OR, NE) agency partners. • One main outcome of the meeting was the consensus that successful transitions of new applications and new technologies into operations require careful planning, effective communication within and across institutions, resources and considerable time investments. In addition, there was broad agreement that significant lead time is often required to allow for identification of financial and technical resources to sustain operational use of new data, information and tools.• The meeting included remarks from U.S. Rep. Napolitano and discussions during presentations and breakout groups about key opportunities to develop best practices and streamline the technology transfer process. • For example, one key set of best practices that emerged revolved around the the importance of building trust and establishing clear lines of communication between the research and operational institutions. The conversations led to defining two key components of trust-building. The first aspect is purely technical. It requires effectively demonstrating that the proposed application meets the end user’s needs in terms of accuracy, format, resolution, latency, metadata and documentation. The second aspect of building trust involves developing sustained, productive and mutually-beneficial relationships with the partner operational agency. The best practices presented here span both the technical as well as the relational aspects of cultivating trust. • This workshop served as a first step in developing a broader community discussion around R2O in western water management. Many of the best practices and lessons learned described in this report represent starting places for action within the WWAO, WSWC and our colleagues’ institutions. • Effective implementation of the best practices that emerged from this workshop will require sustained investments of time, resources and transition planning. In recognition of this, the WSWC and the WWAO proposed continuation of discussions begun at the workshop through a series of semi-annual or annual workshops.