Publications

Refine Results

(Filters Applied) Clear All

WSR-88D microburst detection performance evaluation

Author:
Published in:
MIT Lincoln Laboratory Report ATC-455

Summary

An empirical study of Weather Surveillance Radar 1988-Doppler (WSR-88D) microburst detection performance is conducted using Integrated Terminal Weather System (ITWS) microburst detections as reference. Data from 14 airport regions during 181 independent time periods spanning the years 2015–2022 are utilized for the evaluation. Results show that the detection and false alarm probabilities depend on event range from the WSR-88D. ITWS-level detection (~95%) and false alarm (~5%) probabilities are achieved for 0 to 20 km range, while at 20 to 30 km range, detection (~80%) and false alarm (~5%) rates meeting or exceeding Weather Systems Processor (WSP) microburst detection (≥80%) and false alarm (≤15%) probability requirements are observed. Beyond ~30 km from the radar, the WSR-88D microburst detection performance falls to operationally unacceptable levels. Timing analysis indicates that, on average, WSR-88D microburst detections lag ITWS microburst detections with a median value on the order of 30 s. The detection time difference distribution shows a normal symmetric form around zero with a thin tail extending in the positive lag direction, implying that the thin tail is responsible for the positive median lag time. The lag distribution tail is shown to be shortened, and the median lag time reduced to ~10 s, if the WSR-88D's slower base scan update modes are eliminated. The study shows that the WSR-88D (and its future replacement) could generate operationally useful microburst alerts for airports that are located close enough (less than ~20 km) to the radar. The long detection lag times for a small fraction of cases that are associated with WSR-88D scan strategies that have long base (lowest elevation angle) scan update periods is an issue that may need to be addressed if the current system is to be considered for operational air traffic control purposes. Also, the unavailability of output data from the first eight range gates (2 km) should be addressed for a future replacement radar by adding a minimum observation range requirement comparable to the Terminal Doppler Weather Radar's (TDWR; 0.5 km) to the follow-on radar program requirements.
READ LESS

Summary

An empirical study of Weather Surveillance Radar 1988-Doppler (WSR-88D) microburst detection performance is conducted using Integrated Terminal Weather System (ITWS) microburst detections as reference. Data from 14 airport regions during 181 independent time periods spanning the years 2015–2022 are utilized for the evaluation. Results show that the detection and false...

READ MORE

Radio frequency interference censoring scheme for Canadian Weather Radar

Author:
Published in:
MIT Lincoln Laboratory Report ATC-454

Summary

An automated scheme is developed for the upgraded S-band polarimetric Canadian weather radars to detect and censor radio frequency interference from wireless communication devices. The suite of algorithms employed in this scheme effectively identifies and edits out interference-contaminated reflectivity data, while preserving data dominated by weather signals. This scheme was implemented in the NextGen Weather Processor test reference system for continuous real-time testing, and is expected to be incorporated into the new Canadian Aviation Weather Systems.
READ LESS

Summary

An automated scheme is developed for the upgraded S-band polarimetric Canadian weather radars to detect and censor radio frequency interference from wireless communication devices. The suite of algorithms employed in this scheme effectively identifies and edits out interference-contaminated reflectivity data, while preserving data dominated by weather signals. This scheme was...

READ MORE

A deep learning-based velocity dealiasing algorithm derived from the WSR-88D open radar product generator

Summary

Radial velocity estimates provided by Doppler weather radar are critical measurements used by operational forecasters for the detection and monitoring of life-impacting storms. The sampling methods used to produce these measurements are inherently susceptible to aliasing, which produces ambiguous velocity values in regions with high winds and needs to be corrected using a velocity dealiasing algorithm (VDA). In the United States, the Weather Surveillance Radar-1988 Doppler (WSR-88D) Open Radar Product Generator (ORPG) is a processing environment that provides a world-class VDA; however, this algorithm is complex and can be difficult to port to other radar systems outside the WSR-88D network. In this work, a deep neural network (DNN) is used to emulate the two-dimensional WSR-88D ORPG dealiasing algorithm. It is shown that a DNN, specifically a customized U-Net, is highly effective for building VDAs that are accurate, fast, and portable to multiple radar types. To train the DNN model, a large dataset is generated containing aligned samples of folded and dealiased velocity pairs. This dataset contains samples collected from WSR-88D Level-II and Level-III archives and uses the ORPG dealiasing algorithm output as a source of truth. Using this dataset, a U-Net is trained to produce the number of folds at each point of a velocity image. Several performance metrics are presented using WSR-88D data. The algorithm is also applied to other non-WSR-88D radar systems to demonstrate portability to other hardware/software interfaces. A discussion of the broad applicability of this method is presented, including how other Level-III algorithms may benefit from this approach.
READ LESS

Summary

Radial velocity estimates provided by Doppler weather radar are critical measurements used by operational forecasters for the detection and monitoring of life-impacting storms. The sampling methods used to produce these measurements are inherently susceptible to aliasing, which produces ambiguous velocity values in regions with high winds and needs to be...

READ MORE

Visibility estimation through image analytics

Published in:
MIT Lincoln Laboratory Report ATC-453

Summary

MIT Lincoln Laboratory (MIT LL) has developed an algorithm, known as the Visibility Estimation through Image Analytics Algorithm (VEIA), that ingests camera imagery collected by the FAA Weather Cameras Program Office (WeatherCams) and estimates the meteorological visibility in statute miles. The algorithm uses the presence of edges in the imagery and the strength of those edges to provide an estimation of the meteorological visibility within the scene. The algorithm also combines the estimates from multiple camera images into one estimate for a site or location using information about the agreement between camera estimates and the position of the Sun relative to each camera's view. The final output for a site is a prevailing visibility estimate in statute miles that can be easily compared to existing automated surface observation systems (ASOS) and/or human-observed visibility. This report includes thorough discussion of the VEIA background, development methodology, and transition process to the WeatherCams office operational platform (Sections 2–4). A detailed software description with flow diagrams is also provided in Section 5. Section 6 provides a brief overview of future research and development related to the VEIA algorithm.
READ LESS

Summary

MIT Lincoln Laboratory (MIT LL) has developed an algorithm, known as the Visibility Estimation through Image Analytics Algorithm (VEIA), that ingests camera imagery collected by the FAA Weather Cameras Program Office (WeatherCams) and estimates the meteorological visibility in statute miles. The algorithm uses the presence of edges in the imagery...

READ MORE

Extended polarimetric observations of chaff using the WSR-88D weather radar network

Published in:
IEEE Transactions on Radar Systems, vol. 1, pp. 181-192, 2023.

Summary

Military chaff is a metallic, fibrous radar countermeasure that is released by aircraft and rockets for diversion and masking of targets. It is often released across the United States for training purposes, and, due to its resonant cut lengths, is often observed on the S-band Weather Surveillance Radar–1988 Doppler (WSR-88D) network. Efforts to identify and characterize chaff and other non-meteorological targets algorithmically require a statistical understanding of the targets. Previous studies of chaff characteristics have provided important information that has proven to be useful for algorithmic development. However, recent changes to the WSR-88D processing suite have allowed for a vastly extended range of differential reflectivity, a prime topic of previous studies on chaff using weather radar. Motivated by these changes, a new dataset of 2.8 million range gates of chaff from 267 cases across the United States is analyzed. With a better spatiotemporal representation of cases compared to previous studies, new analyses of height dependence, as well as changes in statistics by volume coverage pattern are examined, along with an investigation of the new "full" range of differential reflectivity. A discussion of how these findings are being used in WSR-88D algorithm development is presented, specifically with a focus on machine learning and separation of different target types.
READ LESS

Summary

Military chaff is a metallic, fibrous radar countermeasure that is released by aircraft and rockets for diversion and masking of targets. It is often released across the United States for training purposes, and, due to its resonant cut lengths, is often observed on the S-band Weather Surveillance Radar–1988 Doppler (WSR-88D)...

READ MORE

Poisoning network flow classifiers [e-print]

Summary

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to tampering only with the training data - without the ability to arbitrarily modify the training labels or any other component of the training process. We describe a trigger crafting strategy that leverages model interpretability techniques to generate trigger patterns that are effective even at very low poisoning rates. Finally, we design novel strategies to generate stealthy triggers, including an approach based on generative Bayesian network models, with the goal of minimizing the conspicuousness of the trigger, and thus making detection of an ongoing poisoning campaign more challenging. Our findings provide significant insights into the feasibility of poisoning attacks on network traffic classifiers used in multiple scenarios, including detecting malicious communication and application classification.
READ LESS

Summary

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to...

READ MORE

Improving long-text authorship verification via model selection and data tuning

Published in:
Proc. 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, LaTeCH-CLfL2023, 5 May 2023, pp. 28-37.

Summary

Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present challenges for their practical application. In this work, we investigate the effect of these challenges in the application of a Cross-Encoder Transformer-based author verification system under multiple conditions. We perform experiments with four Transformer backbones using differently tuned variants of fanfiction data and found that our BigBird pipeline outperformed Longformer, RoBERTa, and ELECTRA and performed competitively against the official top ranked system from the PAN evaluation. We also examined the effect of authors and fandoms not seen in training on model performance. Through this, we found fandom has the greatest influence on true trials, pairs of text written by the same author, and that a balanced training dataset in terms of class and fandom performed the most consistently.
READ LESS

Summary

Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present...

READ MORE

Network performance of pLEO topologies in a high-inclination Walker Delta Satellite Constellation

Published in:
IEEE Aerospace Conf. Proc., 4-11 March 2023, 188722.
Topic:
R&D group:

Summary

Low-earth-orbit satellite constellations with hundreds to thousands of satellites are emerging as practical alternatives for providing various types of data services such as global networking and large-scale sensing. The network performance of these satellite constellations is strongly dependent on the topology of the inter-satellite links (ISLs) in such systems. This paper studies the effects of six different ISL topologies, coupled with three configurations of ground relay terminals, on path failure rate, path latency, and link transmission efficiency in an example highly-inclined Walker Delta constellation with 360 satellites. These network performance parameters are calculated in the presence of satellite failures in the constellation. Trade-offs between ISL connection density and overall performance are examined and quantified. Topologies with 4 active ISLs per satellite are shown to perform significantly better than topologies requiring fewer, especially as the average number of active ISLs per satellite becomes significantly less than three. Latencies for a topology requiring 3 active ISLs per satellite are shown to be between 15 and 60% higher than for a 4-ISL reference topology. Path availabilities for the 3-ISL topology are shown to be on the order of 30% lower for a benchmark case of 10 satellite failures. The performance of near-minimal topologies (e.g., an average of 2.2 active ISLs per satellite) is much worse. Latency reductions of 10-30% and path failure rate improvements on the order of 45% are shown to be obtainable by the inclusion of 2 to 5 strategically located ground relay stations
READ LESS

Summary

Low-earth-orbit satellite constellations with hundreds to thousands of satellites are emerging as practical alternatives for providing various types of data services such as global networking and large-scale sensing. The network performance of these satellite constellations is strongly dependent on the topology of the inter-satellite links (ISLs) in such systems. This...

READ MORE

Automated exposure notification for COVID-19

Summary

Private Automated Contact Tracing (PACT) was a collaborative team and effort formed during the beginning of the Coronavirus Disease 2019 (COVID-19) pandemic. PACT's mission was to enhance contact tracing in pandemic response by designing exposure-detection functions in personal digital communication devices that have maximal public health utility while preserving privacy. This report explains and discusses the use of automated exposure notification during the COVID-19 pandemic and to provide some recommendations for those who may try to design and deploy similar technologies in future pandemics.
READ LESS

Summary

Private Automated Contact Tracing (PACT) was a collaborative team and effort formed during the beginning of the Coronavirus Disease 2019 (COVID-19) pandemic. PACT's mission was to enhance contact tracing in pandemic response by designing exposure-detection functions in personal digital communication devices that have maximal public health utility while preserving privacy...

READ MORE

A generative approach to condition-aware score calibration for speaker verification

Published in:
IEEE/ACM Trans. Audio, Speech, Language Process., Vol. 31, 2023, pp. 891-901.

Summary

In speaker verification, score calibration is employed to transform verification scores to log-likelihood ratios (LLRs) which are statistically interpretable. Conventional calibration techniques apply a global score transform. However, in condition-aware (CA) calibration, information conveying signal conditions is provided as input, allowing calibration to be adaptive. This paper explores a generative approach to condition-aware score calibration. It proposes a novel generative model for speaker verification trials, each which includes a trial score, a trial label, and the associated pair of speaker embeddings. Trials are assumed to be drawn from a discrete set of underlying signal conditions which are modeled as latent Categorical random variables, so that trial scores and speaker embeddings are drawn from condition-dependent distributions. An Expectation-Maximization (EM) Algorithm for parameter estimation of the proposed model is presented, which does not require condition labels and instead discovers relevant conditions in an unsupervised manner. The generative condition-aware (GCA) calibration transform is then derived as the log-likelihood ratio of a verification score given the observed pair of embeddings. Experimental results show the proposed approach to provide performance improvements on a variety of speaker verification tasks, outperforming static and condition-aware baseline calibration methods. GCA calibration is observed to improve the discriminative ability of the speaker verification system, as well as provide good calibration performance across a range of operating points. The benefits of the proposed method are observed for task-dependent models where signal conditions are known, for universal models which are robust across a range of conditions, and when facing unseen signal conditions.
READ LESS

Summary

In speaker verification, score calibration is employed to transform verification scores to log-likelihood ratios (LLRs) which are statistically interpretable. Conventional calibration techniques apply a global score transform. However, in condition-aware (CA) calibration, information conveying signal conditions is provided as input, allowing calibration to be adaptive. This paper explores a generative...

READ MORE