Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “logistic regression”

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 145 records · Page 8

Effects of Reservoir Operations on Hatchery Coastal Rainbow Trout in Lake Roosevelt, Washington

Abstract It is suspected that reservoir operations limit the mitigation fishery for coastal rainbow trout Oncorhynchus mykiss irideus in Lake Roosevelt, Washington. Entrainment through Grand Coulee Dam has been suggested as the primary impact of reservoir operations. However, the causal mechanisms and effects of entrainment have been difficult to quantify. A logistic regression model was used to examine the effect of reservoir operations on the coastal rainbow trout tag return probability. Eight independent variables were studied: release location, presence–absence of a tag reward, minimum reservoir elevation (m above mean sea level (msl)) during a sample year, reservoir elevation on the fish release date, mean daily water retention time (d) 2 weeks postrelease, mean daily retention time 4 weeks postrelease, mean annual water retention time, and water year type (associated with shallow, average, or deep drawdown events). Models were selected on the basis of likelihood ratio tests, odds ratio confidence intervals (CIs), and predictive ability. Analyses indicated that the significant independent variables were release location, water year, release elevation, and mean water retention time at 4 weeks postrelease. Angler return of tagged fish was 1.86 times more likely after a shallow drawdown event than after a deep drawdown event (95% profile likelihood CI = 1.15–3.03). The effect of mean water retention time was dependent on reservoir elevation at the time of release. When release elevation was low (366–381 m above msl), increasing mean water retention time increased the probability of tag return. However, when release elevation was high (381–393 m above msl), increasing mean water retention time did not increase the probability of tag return. The logistic regression model can be used by fisheries managers to predict the impacts of hydropower operations on the coastal rainbow trout fishery in Lake Roosevelt, thereby allowing for annual adjustments to release strategies that would maximize harvest potential.

McLellan, Holly J.↗

Exploration of Factors That Influence Willingness to Consider Pooled Rideshare

Ridesharing has become an increasingly prevalent form of transportation. Although transportation network companies such as Uber and Lyft initially started as a personal rideshare service where individuals ride alone or with people they know, rideshare services have been expanded to pooled rideshare—a dynamic rideshare system where an individual rides with passengers they do not know. Despite the growth in rideshare services worldwide, the use of pooled rideshare in the U.S.A. is relatively low compared to other forms of transportation. A national U.S. survey (N = 5385) was conducted to investigate reasons why individuals are willing or unwilling to consider pooled rideshare. Exploratory and confirmatory factor analyses were performed, where the exploratory factor analysis suggests five factors, specifically,service experience,time/cost,traffic/environment,privacy, andsafety. Model fit indices of the confirmatory factor analysis verified that these five factors can represent the factors behind riders’ willingness to consider pooled rideshare. Furthermore, a binomial logistic regression was conducted to explore how the five factors influence riders’ willingness to consider pooled rideshare. The three factors that influence riders’ willingness to consider pooled rideshare wereservice experience(B = 1.05),traffic/environment(B = .38), andtime/cost(B = .26), while a lack ofprivacy(B = −1.46) can be a deterrent for pooled rideshare.Safetyis important for those who are both willing and unwilling to consider the use of pooled rideshare. Understanding these factors is important for the future of pooled rideshare services in the U.S.A.

Engineering↗

Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging

There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ~2800 galaxies with visual classification from GZ1, we reach an accuracy of ~0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ~2.5 percent galaxies are misclassified by GZ1 in our study. After correcting these galaxies’ labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).

79 ASTRONOMY AND ASTROPHYSICS↗

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗

A User-Centered Design Exploration of Factors That Influence the Rideshare Experience

The rise of real-time information communication through smartphones and wireless networks enabled the growth of ridesharing services. While personal rideshare services (individuals riding alone or with acquaintances) initially dominated the market, the popularity of pooled ridesharing (individuals sharing rides with people they do not know) has grown globally. However, pooled ridesharing remains less common in the U.S., where personal vehicle usage is still the norm. Vehicle design and rideshare services may need to be tailored to user preferences to increase pooled rideshare adoption. Based on a large, national U.S. survey (N = 5385), the results of exploratory and confirmatory factor analyses suggested that four key factors influence riders’ willingness to consider pooled ridesharing: comfort/ease of use, convenience, vehicle technology/accessibility, and passenger safety. A binomial logistic regression was conducted to determine how the four factors influence one’s willingness to consider pooled ridesharing. The two factors that positively influence riders’ willingness to consider pooled ridesharing are vehicle technology/accessibility (B = 1.10) and convenience (B = 0.94), while lack of passenger safety (B = –0.63) and comfort/ease of use (B = –0.17) are pooled ridesharing deterrents. Understanding user-centered design and service factors are critical to increase the use of pooled ridesharing services in the future.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Factors Affecting Optimal Aortic Remodeling After Thoracic Endovascular Aortic Repair of Type B (IIIb) Aortic Dissection

PurposeThe purpose of this study was to determine factors associated with entire aortic remodeling after thoracic endovascular aortic repair (TEVAR) in patients with type B dissection.Materials and MethodsThe patients with type B (IIIb) dissections who underwent TEVAR from 2006 to 2013 with minimum of 2 years of follow-up computed tomography data were retrospectively reviewed. Based on the status of false lumen remodeling of entire aorta, patients were divided into three groups: complete regression, total thrombosis, and inadequate regression with patent abdominal false lumen.ResultsA total of 90 patients (72 males, 18 females; mean age 56.6 ± 16.4 years) were included and divided into the complete regression (n = 22), total thrombosis (n = 18), and inadequate regression (n = 50) groups. Multivariate logistic regression analysis indicated that dissection extension to iliac arteries, increased preoperative number of dissection tear over abdominal aorta, and decreased preoperative abdominal aorta bifurcation true lumen ratio, as compared between the inadequate and complete regression groups, were associated with a persistent false lumen (odds ratio = 33.33, 2.304, and 0.021; all, p ≤ 0.012). Comparison of 6, 12, and 24 months postoperative data revealed no significant differences at any level, suggesting that the true lumen area ratio might not change after 6 months postoperatively.ConclusionsIncreased preoperative numbers of dissection tear around the abdominal visceral branches, dissection extension to the iliac arteries, and decreased preoperative true lumen area ratio of abdominal aorta are predictive of entire aortic remodeling after TEVAR in patients with type B dissection.Level of EvidenceIII.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Stochastic modeling of sunshine number data

In this paper, we will present a unified statistical modeling framework for estimation and forecasting sunshine number (SSN) data. Sunshine number has been proposed earlier to describe sunshine time series in qualitative terms (Theor Appl Climatol 72 (2002) 127-136) and since then, it was shown to be useful not only for theoretical purposes but also for practical considerations, e.g. those related to the development of photovoltaic energy production. Statistical modeling and prediction of SSN as a binary time series has been challenging problem, however. Our statistical model for SSN time series is based on an underlying stochastic process formulation of Markov chain type. We will show how its transition probabilities can be efficiently estimated within logistic regression framework. In fact, our logistic Markovian model can be relatively easily fitted via maximum likelihood approach. This is optimal in many respects and it also enables us to use formalized statistical inference theory to obtain not only the point estimates of transition probabilities and their functions of interest, but also related uncertainties, as well as to test of various hypotheses of practical interest, etc. It is straightforward to deal with non-homogeneous transition probabilities in this framework. Very importantly from both physical and practical points of view, logistic Markov model class allows us to test hypotheses about how SSN dependents on various external covariates (e.g. elevation angle, solar time, etc.) and about details of the dynamic model (order and functional shape of the Markov kernel, etc.). Therefore, using generalized additive model approach (GAM), we can fit and compare models of various complexity which insist on keeping physical interpretation of the statistical model and its parts. After introducing the Markovian model and general approach for identification of its parameters, we will illustrate its use and performance on high resolution SSN data from the Solar Radiation Monitoring Station of the West University of Timisoara.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems

One challenge in power-system control designs is the gap between numerical model-based analysis and complex real-world power systems. With increased data and measurements being collected from power systems, data-driven analysis (e.g., machine learning) may provide an alternative approach to reveal hidden information through learning from the real system data, and provide insights for better control scheme design during the utility planning process. Data-driven feature analysis was performed to evaluate the relationships between series compensation, power generation, and path flows in a real transmission system, as well as temporal patterns. The main data-driven analysis methods, including statistical cross-correlation, multinomial logistical regression, and classification and regression trees, were integrated for feature selection and developing predictive models of series compensation. Analysis results demonstrated the effectiveness of the proposed methodology in feature analysis and the potential to help improve power-system control scheme design.

42 ENGINEERING↗

Patterns of Care and Locoregional Treatment Outcomes in Older Esophageal Cancer Patients: The SEER-Medicare Cohort

Purpose: Optimal management of elderly patients with nonmetastatic esophageal cancer is unclear. Outcomes data after locoregional treatment are lacking for this group. Methods: We assessed outcomes associated with standard locoregional treatments in 2,626 patients (age > 65 years) from the Surveillance Epidemiology and End Results (SEER)-Medicare cohort diagnosed with nonmetastatic esophageal cancer from 1992 to 2002. In patients treated with radiotherapy alone (RT), surgery alone (S), chemoradiotherapy (CRT), or preoperative chemotherapy followed by surgery (CRT + S), overall and disease-free survival were compared using proportional hazards regression. Postoperative complications were compared using logistic regression. Results: Mean age was 76 {+-} 6 years. Seven percent underwent CRT + S, 39% CRT, 30% S, and 24% RT. One-year survival was 68% (CRT + S), 52% (CRT), 53% (S), and 16% (RT), respectively (p < 0.001). Patients who underwent CRT + S demonstrated improved overall survival compared with S alone (hazard ratio [HR] = 0.81; 95% confidence interval [CI], 0.66-0.98; p = 0.03) and RT (HR = 0.44; 95% CI, 0.35-0.55; p < 0.0001); and comparable survival to CRT (HR = 0.82; 95% CI, 0.67-1.01; p = 0.06). Patients who underwent CRT + S also had comparable postoperative mortality (HR = 0.96; 95% CI, 0.87-1.07; p = 0.45) and complications (OR = 0.89; 95% CI, 0.70-1.14; p = 0.36) compared with S alone. Conclusions: Preoperative chemoradiotherapy may be an acceptable treatment option in appropriately selected older esophageal cancer patients. This treatment modality did not appear to increase surgical complications and offered potential therapeutic benefit, particularly compared with surgery alone.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Outcomes of Sinonasal Cancer Treated With Proton Therapy

Purpose: To report disease outcomes after proton therapy (PT) for sinonasal cancer. Methods and Materials: Eighty-four adult patients without metastases received primary (13%) or adjuvant (87%) PT for sinonasal cancers (excluding melanoma, sarcoma, and lymphoma). Common histologies were olfactory neuroblastoma (23%), squamous cell carcinoma (22%), and adenoid cystic carcinoma (17%). Advanced stage (T3 in 25% and T4 in 69%) and high-grade histology (51%) were common. Surgical procedures included endoscopic resection alone (45%), endoscopic resection with craniotomy (12%), or open resection (30%). Gross residual disease was present in 26% of patients. Most patients received hyperfractionated PT (1.2 Gy [relative biological effectiveness (RBE)] twice daily, 99%) and chemotherapy (75%). The median PT dose was 73.8 Gy (RBE), with 85% of patients receiving more than 70 Gy (RBE). Prognostic factors were analyzed using Kaplan-Meier analysis and proportional hazards regression for multiple regression. Dosimetric parameters were evaluated using logistic regression. Serious, late grade 3 or higher toxicity was reported using the National Cancer Institute Common Terminology Criteria for Adverse Events, version 4. The median follow-up was 2.4 years for all patients and 2.7 years among living patients. Results: The local control (LC), neck control, freedom from distant metastasis, disease-free survival, cause-specific survival, and overall survival rates were 83%, 94%, 73%, 63%, 70%, and 68%, respectively, at 3 years. Gross total resection and PT resulted in a 90% 3-year LC rate. The 3-year LC rate was 61% for primary radiation therapy and 59% for patients with gross disease. Gross disease was the only significant factor for LC on multivariate analysis, whereas grade and continuous LC were prognostic for overall survival. Six of 12 local recurrences were marginal. Dural dissemination represented 26% of distant recurrences. Late toxicity occurred in 24% of patients (with grade 3 or higher unilateral vision loss in 2%). Conclusions: Dose-intensified, hyperfractionated PT with or without concurrent chemotherapy results in excellent LC after gross total resection, and results in patients with gross disease are encouraging. Patients with high-grade histology are at greater risk of death from distant dissemination. Continuous LC is a major determinant of survival justifying aggressive local therapy in nearly all cases.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Comparing Methods for Assessing Reliability Uncertainty Based on Pass/Fail Data Collected Over Time

In this paper, we compare statistical methods for analyzing pass/fail data collected over time; some methods are traditional and one (the RADAR or Rationale for Assessing Degradation Arriving at Random) was recently developed. These methods are used to provide uncertainty bounds on reliability. We make observations about the methods' assumptions and properties. Finally, we illustrate the differences between two traditional methods, logistic regression and Weibull failure time analysis, and the RADAR method using a numerical example.

97 MATHEMATICS AND COMPUTING↗

A Hybrid Anomaly Detection Approach for Obfuscated Malware

With the rapid evolution of malicious software, cyber threats have become increasingly sophisticated, employing advanced obfuscation techniques to evade traditional detection methods. This study presents a hybrid anomaly detection approach applied to obfuscated malware. Even though there is a large body of research in this field, existing malware detection techniques have some drawbacks, such as requiring large amounts of data, trustworthiness (imprecise results) of algorithms, and advanced obfuscation. To overcome these challenges, there is a need to employ solid and efficient techniques for malware detection. This paper proposes a hybrid approach, combining an autoencoder with traditional machine-learning methods to create an efficient malware detection framework. We used the malware memory dataset (MalMemAnalysis-2022) to evaluate this framework. The results indicate that our proposed approach can detect obfuscated malware when a deep autoencoder used for feature learning is combined with logistic regression, and it is extremely fast with an Accuracy, Detection Rate (DR), Matthew Correlation Coefficient(MCC), and Statistical Parity Difference

malware detection, Hybrid Anomly Detection, Obfusc↗

Predicting Student Success using Analytics in Course Learning Management Systems

Educational data analytics is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from the educational context. For example, predicting college student performance is crucial for both the student and educational institutions. It can support timely intervention to prevent students from failing a course, increasing efficacy of advising functions, and improving course completion rate. In this paper, we present the efforts carried out at Oak Ridge National Laboratory (ORNL) toward conducting predictive analytics to academic data collected from 2009 through 2013 and available in one of the most commonly used learning management systems, called Moodle. First, we have identified the data features useful for predicting student outcomes such as students scores in homework assignments, quizzes, exams, in addition to their activities in discussion forums and their total GPA at the same term they enrolled in the course. Then, Logistic Regression and Neural Network predictive models are used to identify students as early as possible that are in danger of failing the course they are currently enrolled in. These models compute the likelihood of any given student failing (or passing) the current course. Numerical results are presented to evaluate and compare the performance of the developed models and their predictive accuracy.

Educational data mining↗

Supervised Learning for Distribution Secondary Systems Modeling: Improving Solar Interconnection Processes

The current interconnection process and hosting capacity analysis for distributed energy resources (DERs), such as photovoltaics (PV) and battery energy storage systems, are based on analyzing grid network constraints (voltage and thermal) using only medium-voltage distribution network models. This is because most utilities do not have secondary low-voltage system models that connect service transformers and residential customers. This is important because in many cases the main impact of interconnecting DERs could occur on the low-voltage distribution systems. This paper proposes a supervised learning method to approximate local secondary models to improve the interconnection process. The proposed supervised learning method includes a decision tree model that predicts the secondary topology and a logistic regression model that predicts conductor types. The case studies demonstrate the benefits of including secondary low-voltage circuits in the interconnection process. We report the proposed modeling methodology is readily scalable and thus can reduce the cost and effort of PV interconnection for the industry and stakeholders.

14 SOLAR ENERGY↗

A spatial-statistical investigation of surface expressions associated with cyclic steaming in the Midway-Sunset Oil Field, California

In the Midway Sunset Oil Field in Central California, operators inject steam into the shallow diatomite formation to enhance heavy oil recovery through imbibition, wettability alteration, and viscosity reduction, among other mechanisms. The injected steam, however, does not always remain in the reservoir or return through the wells. In two zones in the study area, the steam comes out at the surface, creating sinkholes, seeps, and steam outlets. These phenomena, called “surface expressions,” pose safety and environmental hazards. Even though these surface expressions are a widespread problem in Central California, they are not well documented and understood. Possible causes of the surface expressions include: high injection pressure, structurally controlled flow patterns, leakage of steam through old improperly abandoned wells, high injection volumes, or flow along naturally occurring faults, among other possible factors. This work examines attributes of the zones with surface expressions in order to determine factors that may contribute to their occurrence. Spatial statistical analysis using logistic regression, random forests, and classification trees is used to explore the relationship between the surface expressions and geological and production-related attributes. The results point to a significant spatial correlation between the surface expressions and two predictors: concentration of plugged wells and geologic seal thickness. The results guide follow-up studies to further investigate the role of well abandonment and seal thickness in the occurrence of surface expressions.

02 PETROLEUM↗

Deep Learning Classification of Cheatgrass Invasion in the Western United States Using Biophysical and Remote Sensing Data

Cheatgrass (Bromus tectorum) invasion is driving an emerging cycle of increased fire frequency and irreversible loss of wildlife habitat in the western US. Yet, detailed spatial information about its occurrence is still lacking for much of its presumably invaded range. Deep learning (DL) has demonstrated success for remote sensing applications but is less tested on more challenging tasks like identifying biological invasions using sub-pixel phenomena. We compare two DL architectures and the more conventional Random Forest and Logistic Regression methods to improve upon a previous effort to map cheatgrass occurrence at >2% canopy cover. High-dimensional sets of biophysical, MODIS, and Landsat-7 ETM+ predictor variables are also compared to evaluate different multi-modal data strategies. All model configurations improved results relative to the case study and accuracy generally improved by combining data from both sensors with biophysical data. Cheatgrass occurrence is mapped at 30 m ground sample distance (GSD) with an estimated 78.1% accuracy, compared to 250-m GSD and 71% map accuracy in the case study. Furthermore, DL is shown to be competitive with well-established machine learning methods in a limited data regime, suggesting it can be an effective tool for mapping biological invasions and more broadly for multi-modal remote sensing applications.

54 ENVIRONMENTAL SCIENCES↗

The effect of modeling dose uncertainty on low-boom community noise dose-response curves

In logistic dose-response modeling, failing to account for uncertainty in estimated doses can cause an artificial flattening or attenuation of the slope of the summary curve. In Lee et al. [J. Acoust. Soc. Am. 147(4), pp. 2222-2234 (2020)], data from two NASA low-amplitude sonic boom community noise survey tests were modeled using a Bayesian multilevel logistic regression (MLR) statistical model that assumed there was no uncertainty in the noise dose estimates. However, in these community tests, the noise dose uncertainty was estimated by Page et al. [NASA/CR-2014-218180 and NASA/CR-2020-220589/Volume I] using a leave-one-out method. In the current work, a term was added to extend the Bayesian MLR model to account for the estimated noise dose uncertainty quantified in the Page et al. analyses. This uncertainty term was included in two ways, either as classical or as Berkson uncertainty, and yield similar results. When the uncertainty is accounted for in the Bayesian MLR model, the dose-response curves become 5-10% steeper, but the difference in the noise dose that elicits a 5% highly annoyed response is small (less than 1 dB). This result is encouraging for future X-59 community tests whose survey area will be sparsely populated with noise monitors.

X-59↗