Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “false negative”

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 217 records · Page 12

Leak Detection and H2 Sensor Development for Hydrogen Applications

The objectives of this report are: (1) Develop a low cost, low power, durable, and reliable hydrogen safety sensor for a wide range of vehicle and infrastructure applications; (2) Continually advance test prototypes guided by materials selection, sensor design, electrochemical R&D investigation, fabrication, and rigorous life testing; (3) Disseminate packaged sensor prototypes and control systems to DOE Laboratories and commercial parties interested in testing and fielding advanced prototypes for cross-validation; (4) Evaluate manufacturing approaches for commercialization; and (5) Engage an industrial partner and execute technology transfer. Recent developments in the search for sustainable and renewable energy coupled with the advancements in fuel cell powered vehicles (FCVs) have augmented the demand for hydrogen safety sensors. There are several sensor technologies that have been developed to detect hydrogen, including deployed systems to detect leaks in manned space systems and hydrogen safety sensors for laboratory and industrial usage. Among the several sensing methods electrochemical devices that utilize high temperature-based ceramic electrolytes are largely unaffected by changes in humidity and are more resilient to electrode or electrolyte poisoning. The desired sensing technique should meet a detection threshold of 1% (10,000 ppm) H 2 and response time of {approx_equal}1 min, which is a target for infrastructure and vehicular uses. Further, a review of electrochemical hydrogen sensors by Korotcenkov et.al and the report by Glass et.al suggest the need for inexpensive, low power, and compact sensors with long-term stability, minimal cross-sensitivity, and fast response. This view has been largely validated and supported by the fuel cell and hydrogen infrastructure industries by the NREL/DOE Hydrogen Sensor Workshop held on June 8, 2011. Many of the issues preventing widespread adoption of best-available hydrogen sensing technologies available today outside of cost, derive from excessive false positives and false negatives arising from signal drift and unstable sensor baseline; both of these problems necessitate the need for unacceptable frequent calibration.

08 HYDROGEN↗

From Bombs to Breast Cancer Imaging: Los Alamos National Laboratory

In the United States, one in eight women will be affected by breast cancer. According to the American Cancer Society, breast cancer is the most commonly diagnosed - as well as the second most fatal - cancer in American women. It is estimated that there will be nearly 200,000 diagnoses of breast cancer this year; more than 40,000 of these will be fatal. Although advances in medical technologies have greatly increased the odds of surviving the disease, the increase in screenings has not resulted in a significant reduction in the breast cancer mortality rate. Moreover, recent studies have even suggested that an increase in these methods might, in itself, cause cancer. A new tool for early detection and diagnosis of breast cancer, supported by an award from the Breast Cancer Research Program (BCRP) of the Congressionally Directed Medical Research Programs of Department of Defense, could give women a new advantage in the fight against breast cancer. This LANL-led project will integrate ultrasound tomography (UST) with recent discoveries in the field of cell and tissue biomechanics to improve breast cancer detection and characterization. UST uses ultrasound waves instead of X-rays to identify and characterize breast tumors. This technology reveals small mechanical-property changes within the breast. These changes are often the earliest signs of breast cancer. Additionally, UST is effective for women with dense breast tissue, who have a higher risk of developing breast cancer. Because the technology does not use radiation, UST can also be used as frequently as needed for women with a high risk of developing breast cancer. In contrast, mammography, the only routine breast-cancer screening tool currently available, is not effective for women with dense breast tissue and may come with unwanted side-effects caused by ionizing radiation. UST has great potential to become an alternative breast-cancer screening tool because of UST's advantages and benefits over mammography. Currently, there is fierce debate surrounding the age at which breast cancer screening should begin, and once begun, how often it should occur. The American Cancer Society recommends yearly mammograms starting at age 40. On the other hand, the U.S. Preventive Services Task Force recommends against routine so early. Rather, the Task Force recommends biennial mammography screening for women aged 50 to 74 years. The ten-year discrepancy in the onset of screening results from recent data suggesting that the frequent use of X-ray radiation during screenings could potentially increase the likelihood of developing cancer. This danger is increased by the low sensitivity and accuracy of mammograms, which sometimes require multiple screenings to yield results. Furthermore, mammograms are often not only inaccurate, but average appalling misdiagnoses rates: about 80% false positives and 15% false negatives. These misdiagnoses lead to unwarranted biopsies at an estimated health care cost of $2 billion per year, while at the same time, resulting in excessive cases of undetected cancer. As such, the National Cancer Institute recommends more studies on the advantages of types and frequency of screenings, as well as alternative screening options. The UST technology developed at LANL could be an alternative option to greatly improve the specificity and sensitivity of breast cancer screening without using ionizing radiation. LANL is developing high-resolution ultrasound tomography algorithms and a clinical ultrasound tomography scanner to conduct patient studies at the UNM Hospital. During UST scanning, the patient lies face-down while her breast, immersed in a tank of warm water, is scanned by phased-transducer arrays. UST uses recorded ultrasound signals to reconstruct a high-resolution three-dimensional image of the breast, showing the spatial distribution of mechanical properties within the breast. Breast cancers are detected by higher values of mechanical properties compared to surrounding tissues. Thus, high-resolution breast images obtained using LANL's novel UST algorithms have the potential to detect breast cancer at its earliest stage. The goal of this Multi-Team Award project is two-fold: (1) develop a novel, safe and cost-effective breast-imaging technique, and (2) improve the specificity and sensitivity of breast cancer imaging. The project is expected to integrate basic research with clinical studies, perform substantive cross-disciplinary training among scientists on the teams and involve participation of consumer advocates. Those involved in the project are optimistic about future developments.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Leak Detection and H2 Sensor Development for Hydrogen Applications

Recent developments in the search for sustainable and renewable energy coupled with the advancements in fuel cell powered vehicles (FCVs) have augmented the demand for hydrogen safety sensors. There are several sensor technologies that have been developed to detect hydrogen, including deployed systems to detect leaks in manned space systems and hydrogen safety sensors for laboratory and industrial usage. Among the several sensing methods electrochemical devices that utilize high temperature-based ceramic electrolytes are largely unaffected by changes in humidity and are more resilient to electrode or electrolyte poisoning. The desired sensing technique should meet a detection threshold of 1% (10,000 ppm) H 2 and response time of ≤1 min, which is a target for infrastructure and vehicular uses. Further, a review of electrochemical hydrogen sensors by Korotcenkov et.al and the report by Glass et.al suggest the need for inexpensive, low power, and compact sensors with long-term stability, minimal cross-sensitivity, and fast response. This view has been largely validated and supported by the fuel cell and hydrogen infrastructure industries by the NREL/DOE Hydrogen Sensor Workshop held on June 8, 2011. Many of the issues preventing widespread adoption of best-available hydrogen sensing technologies available today outside of cost, derive from excessive false positives and false negatives arising from signal drift and unstable sensor baseline; both of these problems necessitate the need for unacceptable frequent calibration.

08 HYDROGEN↗

CSTT Update: Fuel Quality Analyzer

Presentation summary: A Nafion® based, electrochemical hydrogen contaminant detector was tested at H2Frontier hydrogen filling station in Burbank CA during its refit and recommissioning.; A 100 sccm sample was taken from the H2F production skid and without requiring humidification; both real-time product gas and storage gas was sampled. The selfhumidifying approach using an internal reservoir worked with minimal baseline drift.; The LANL HCD easily detected CO byproduct during reformer restart (as high as 18ppm) and 11, 1ppm challenges were performed during an 850h experiment after initial installation and 10ppm testing/commissioning.; The 10ppm and 1ppm challenges produced ≈ 75% and ≈ 60% reductions in pumping current respectively. Twelve, 1ppm challenges decreased pumping current on average of 59.5% with an error of ±1.4% over 12 challenges during a 6 month time period.; Long term baseline data show a drift rate of 9x10- 7 A/h over a 600h period of testing. The addition of a 1.5V, 600s pulse approximately once a day eliminated any long term drift.; No false positives or false negatives were seen during the field tests to date.; Average water consumption rate is estimated to be ~250μl/day at 100sccm.; Project milestones successfully met.

08 HYDROGEN↗

Uranium Mass Attribute System (UMAS) Study: Evaluation of Options against the Arms Control Evaluation Criteria

In this FY19 study, a range of possible measurement systems for confirming a U-235 mass attribute were identified. The systems were reviewed for their applicability in a potential future arms control agreement, and a subset of the eight most plausible systems were selected for further evaluation against the Arms Control Evaluation Criteria (ACEC). The evaluation results were then used to identify a primary and secondary recommended measurement system for confirming a U-235 mass attribute on warheads, nuclear components of warheads, and/or materials as part of a hypothetical arms control agreement.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

Pre-Symptomatic COVID Screening

Temperature checks for fever are extensively used for preliminary COVID screenings but are ineffective during the incubation stage of infection when a person is asymptotic. Researchers at the European Centre for Disease Prevention and Control concluded that approximately 75% of passengers infected with COVID-19 and traveling from affected Chinese cities would not be detected by early screening. Core body temperature is normally kept within a narrow range and has the smallest relative standard deviation of all vital signs. Heat in the body is prioritized around internal organs at the expense of the periphery by controlling blood flow. In fact, blood flow to the skin may vary by a factor of 100 depending on thermal conditions. This adaptation causes rapid temperature fluctuations in different skin regions from changes in cardiac output, metabolism, and likely cytokine diffusion during inflammation that would not be seen in average core body temperature. Current IR and thermal scanners used for temperature checks are not necessarily reflective of core body temperatures and require cautious interpretation as they frequently result in false positive and false negative diagnosis. Hand held thermometers measure average skin temperatures and can get readings that differ from core body temperature by as much as 7°. Rather than focusing on a core body temperature threshold assessment we believe that variability of temperature patterns using a novel wearable transdermal microneedle sensor will be more sensitive to infections in the incubation stage and propose to develop a wearable transdermal temperature sensor using established Sandia microneedle technology for pre-symptomatic COVID screening that can additionally be used to monitor disease progression at later stages.

47 OTHER INSTRUMENTATION↗

Pre Symptomatic COVID Screening

Temperature checks for fever are extensively used for preliminary COVID screenings but are ineffective during the incubation stage of infection when a person is asymptotic. Researchers at the European Centre for Disease Prevention and Control concluded that approximately 75% of passengers infected with COVID-19 and traveling from affected Chinese cities would not be detected by early screening. Core body temperature is normally kept within a narrow range and has the smallest relative standard deviation of all vital signs. Heat in the body is prioritized around internal organs at the expense of the periphery by controlling blood flow. In fact, blood flow to the skin may vary by a factor of 100 depending on thermal conditions. This adaptation causes rapid temperature fluctuations in different skin regions from changes in cardiac output, metabolism, and likely cytokine diffusion during inflammation that would not be seen in average core body temperature. Current IR and thermal scanners used for temperature checks are not necessarily reflective of core body temperatures and require cautious interpretation as they frequently result in false positive and false negative diagnosis. Hand held thermometers measure average skin temperatures and can get readings that differ from core body temperature by as much as 7°. Rather than focusing on a core body temperature threshold assessment we believe that variability of temperature patterns using a novel wearable transdermal microneedle sensor will be more sensitive to infections in the incubation stage and propose to develop a wearable transdermal temperature sensor using established Sandia microneedle technology for pre symptomatic COVID screening that can additionally be used to monitor disease progression at later stages.

59 BASIC BIOLOGICAL SCIENCES↗

SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.

This report details the results of a three-fold investigation of sensitivity analysis (SA) for machine learning (ML) explainability (MLE): (1) the mathematical assessment of the fidelity of an explanation with respect to a learned ML model, (2) quantifying the trustworthiness of a prediction, and (3) the impact of MLE on the efficiency of end-users through multiple users studies. We focused on the cybersecurity domain as the data is inherently non-intuitive. As ML is being using in an increasing number of domains, including domains where being wrong can elicit high consequences, MLE has been proposed as a means of generating trust in a learned ML models by end users. However, little analysis has been performed to determine if the explanations accurately represent the target model and they themselves should be trusted beyond subjective inspection. Current state-of-the-art MLE techniques only provide a list of important features based on heuristic measures and/or make certain assumptions about the data and the model which are not representative of the real-world data and models. Further, most are designed without considering the usefulness by an end-user in a broader context. To address these issues, we present a notion of explanation fidelity based on Shapley values from cooperative game theory. We find that all of the investigated MLE explainability methods produce explanations that are incongruent with the ML model that is being explained. This is because they make critical assumptions about feature independence and linear feature interactions for computational reasons. We also find that in deployed, explanations are rarely used due to a variety of reason including that there are several other tools which are trusted more than the explanations and there is little incentive to use the explanations. In the cases when the explanations are used, we found that there is the danger that explanations persuade the end users to wrongly accept false positives and false negatives. However, ML model developers and maintainers find the explanations more useful to help ensure that the ML model does not have obvious biases. In light of these findings, we suggest a number of future directions including developing MLE methods that directly model non-linear model interactions and including design principles that take into account the usefulness of explanations to the end user. We also augment explanations with a set of trustworthiness measures that measure geometric aspects of the data to determine if the model output should be trusted.

97 MATHEMATICS AND COMPUTING↗

Agent-based Disease Surveillance and Transmission Model

The SARS-CoV-2 pandemic has driven a need for models that can predict transmission among populations and test the effectiveness of proposed interventions to control it such as testing, quarantining, vaccinations, and nonpharmaceutical interventions. Some questions of interest include:1. How rapidly will the virus spread if no action is taken? 2. How frequently should people be tested and quarantined if necessary? 3. Should unvaccinated persons be tested more frequently than the vaccinated? 4. If test results are delayed, how will that affect the spread? 5. How do test false negative rates affect the overall efficacy of testing programs? 6. How do constraints on testing resources impact the overall efficacy of testing programs? 7. How does the patient’s failure to recognize COVID symptoms and quarantine affect the spread? 8. What level of vaccination coverage is needed to suppress the epidemic? 9. What is the risk of a large outbreak (probability exceeding x infections)? 10. What is the cost effectiveness of interventions (dollars per avoided infection)? This report describes the structure of a discrete event simulation model that provides actionable information to address these questions. Parameter inputs and results of analyses have been reported in briefings provided to LLNL management and are not discussed here.

59 BASIC BIOLOGICAL SCIENCES↗

Process Anomaly Detection for Sparsely Labeled Events in Nuclear Power Plants

An essential aspect of online monitoring, subtle anomaly detection increases the detection lead time for equipment failure and enables a nuclear power plant (NPP) to mitigate unexpected partial or full outages, resulting in significant cost saving to the plant. Once an anomaly is detected by plant staff, its cause and severity are investigated. Because the vast majority of anomalies require some level of investigation, including some that require time-consuming examination, before they are passed over to the engineering organization for further analysis, plants are often equipped with tools to assist the staff in performing anomaly detection. Those tools operate as a black box and are often based on statistical methods that establish sensor correlations using preconfigured mathematical models and flag correlation deviations as anomalies. Due to the number of anomalies detected at a given NPP on a daily basis, a significant number of flagged anomalies usually await examination for days or weeks. A primary cause of this backlog is that the methods used by the tools generate many false positives. Though this is usually attributed to oversensitive model settings due to very narrow normal operation bands, it can also be associated with the model development being inadequate for the process being monitored, or with missing model inputs that could have explained misclassified positives. The performance of anomaly detection tools impacts their plant acceptance and utilization, especially when the effort to address false positives generated by the tool depletes the value or cost saved by using that tool. Thus, means to advance anomaly detection performance have been investigated by the Department of Energy’s Light Water Reactor Sustainability program. Previous and ongoing efforts have targeted unsupervised machine-learning (ML) methods, which do not require the labeling of any data fed into the ML model. By contrast, in supervised anomaly detection methods, every data point is labeled as either a normal or abnormal process condition, and the model is trained to replicate the classification process. Supervised methods usually outperform unsupervised methods, due to the added value in differentiating normal from anomalous states of the monitored process. An NPP’s corrective action program requires it to track and document, via a dedicated report, the resolution of any issues that occur within the plant. Once created, each report is reviewed by a plant screening committee, and several classifications and decisions are made. Recently, a collaborating NPP developed an artificial intelligence and ML-based classifier to categorize a condition report (CR) into classes that can serve to label the data as normal or anomalous. Applying CRs as labels represents a semi-supervised use case. Semi-supervised ML assumes that labels exist for some data points (i.e., labeled anomalies, in this case) but not for the rest. In this effort, semi-supervised ML methods were used to fuse data from CRs with anomaly detection methods in order to test the hypothesis that partially labeled anomalies would improve the accuracy of the anomaly detection methods. Specifically, two methods were used. The first is the deep Semi-supervised Anomaly Detection (deep SAD) method, which can handle labels ranging from fully unsupervised to fully supervised cases. The second is a newly designed ML method developed specifically for this effort and referred to as the high-order feature (HOF)-based method. To evaluate these two methods in controlled environments, synthetic data generators were developed and used. The first datasets used a spring-mass-damper (SMD) system simulator commonly found in mechanical engineering references. This was used to create two use cases: a one- and a three-mass system. Anomalies were introduced by changing the spring and damper coefficients while the system was actuated by random forces. The second datasets used the commercial Dymola-Modelica software to build a simplified nuclear reactor model. Anomalies were added in the form of corrupted sensor readings and/or control commands. The deep SAD method was tested using the SMD system, while the HOF method was tested using both datasets. Application of the deep SAD semi-supervised ML method demonstrated that labels can generate increased confidence in detecting true anomalies. This helped increase the number of true positives and decrease the number of false negatives—something that would aid in addressing the backlog of possible anomalies. Application of the HOF method demonstrated that labels can aid in down selecting from a candidate set of features to a more optimal subset in order to better differentiate between normal and anomalous conditions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A Numerical Comparison of Rule Ensemble Methods and Support Vector Machines

Machine or statistical learning is a growing field that encompasses many scientific problems including estimating parameters from data, identifying risk factors in health studies, image recognition, and finding clusters within datasets, to name just a few examples. Statistical learning can be described as 'learning from data' , with the goal of making a prediction of some outcome of interest. This prediction is usually made on the basis of a computer model that is built using data where the outcomes and a set of features have been previously matched. The computer model is called a learner, hence the name machine learning. In this paper, we present two such algorithms, a support vector machine method and a rule ensemble method. We compared their predictive power on three supernova type 1a data sets provided by the Nearby Supernova Factory and found that while both methods give accuracies of approximately 95%, the rule ensemble method gives much lower false negative rates.

97 MATHEMATICS AND COMPUTING↗

Multivariate analysis of progressive thermal desorption coupled gas chromatography-mass spectrometry.

Thermal decomposition of poly dimethyl siloxane compounds, Sylgard{reg_sign} 184 and 186, were examined using thermal desorption coupled gas chromatography-mass spectrometry (TD/GC-MS) and multivariate analysis. This work describes a method of producing multiway data using a stepped thermal desorption. The technique involves sequentially heating a sample of the material of interest with subsequent analysis in a commercial GC/MS system. The decomposition chromatograms were analyzed using multivariate analysis tools including principal component analysis (PCA), factor rotation employing the varimax criterion, and multivariate curve resolution. The results of the analysis show seven components related to offgassing of various fractions of siloxanes that vary as a function of temperature. Thermal desorption coupled with gas chromatography-mass spectrometry (TD/GC-MS) is a powerful analytical technique for analyzing chemical mixtures. It has great potential in numerous analytic areas including materials analysis, sports medicine, in the detection of designer drugs; and biological research for metabolomics. Data analysis is complicated, far from automated and can result in high false positive or false negative rates. We have demonstrated a step-wise TD/GC-MS technique that removes more volatile compounds from a sample before extracting the less volatile compounds. This creates an additional dimension of separation before the GC column, while simultaneously generating three-way data. Sandia's proven multivariate analysis methods, when applied to these data, have several advantages over current commercial options. It also has demonstrated potential for success in finding and enabling identification of trace compounds. Several challenges remain, however, including understanding the sources of noise in the data, outlier detection, improving the data pretreatment and analysis methods, developing a software tool for ease of use by the chemist, and demonstrating our belief that this multivariate analysis will enable superior differentiation capabilities. In addition, noise and system artifacts challenge the analysis of GC-MS data collected on lower cost equipment, ubiquitous in commercial laboratories. This research has the potential to affect many areas of analytical chemistry including materials analysis, medical testing, and environmental surveillance. It could also provide a method to measure adsorption parameters for chemical interactions on various surfaces by measuring desorption as a function of temperature for mixtures. We have presented results of a novel method for examining offgas products of a common PDMS material. Our method involves utilizing a stepped TD/GC-MS data acquisition scheme that may be almost totally automated, coupled with multivariate analysis schemes. This method of data generation and analysis can be applied to a number of materials aging and thermal degradation studies.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Nature and Consequences of Biological Reductionism for the Immunological Study of Infectious Diseases

Evolution has conserved “economic” systems that perform many functions, faster or better, with less. For example, three to five leukocyte types protect from thousands of pathogens. In order to achieve so much with so little, biological systems combine their limited elements, creating complex structures. Yet, the prevalent research paradigm is reductionist. Focusing on infectious diseases, reductionist and non-reductionist views are here described. Furthermore, the literature indicates that reductionism is associated with information loss and errors, while non-reductionist operations can extract more information from the same data. When designed to capture one-to-many/many-to-one interactions—including the use of arrows that connect pairs of consecutive observations—non-reductionist (spatial–temporal) constructs eliminate data variability from all dimensions, except along one line, while arrows describe the directionality of temporal changes that occur along the line. To validate the patterns detected by non-reductionist operations, reductionist procedures are needed. Integrated (non-reductionist and reductionist) methods can (i) distinguish data subsets that differ immunologically and statistically; (ii) differentiate false-negative from -positive errors; (iii) discriminate disease stages; (iv) capture in vivo, multilevel interactions that consider the patient, the microbe, and antibiotic-mediated responses; and (v) assess dynamics. Integrated methods provide repeatable and biologically interpretable information.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluating various composite sampling modes for detecting pathogenic SARS-CoV-2 virus in raw sewage

Inadequate sampling approaches to wastewater analyses can introduce biases, leading to inaccurate results such as false negatives and significant over- or underestimation of average daily viral concentrations, due to the sporadic nature of viral input. To address this challenge, we conducted a field trial within the University of Tennessee residence halls, employing different composite sampling modes that encompassed different time intervals (1 h, 2 h, 4 h, 6 h, and 24 h) across various time windows (morning, afternoon, evening, and late-night). Our primary objective was to identify the optimal approach for generating representative composite samples of SARS-CoV-2 from raw wastewater. Utilizing reverse transcription-quantitative polymerase chain reaction, we quantified the levels of SARS-CoV-2 RNA and pepper mild mottle virus (PMMoV) RNA in raw sewage. Our findings consistently demonstrated that PMMoV RNA, an indicator virus of human fecal contamination in water environment, exhibited higher abundance and lower variability compared to pathogenic SARS-CoV-2 RNA. Significantly, both SARS-CoV-2 and PMMoV RNA exhibited greater variability in 1 h individual composite samples throughout the entire sampling period, contrasting with the stability observed in other time-based composite samples. Through a comprehensive analysis of various composite sampling modes using the Quade Nonparametric ANCOVA test with date, PMMoV concentration and site as covariates, we concluded that employing a composite sampler during a focused 6 h morning window for pathogenic SARS-CoV-2 RNA is a pragmatic and cost-effective strategy for achieving representative composite samples within a single day in wastewater-based epidemiology applications. This method has the potential to significantly enhance the accuracy and reliability of data collected at the community level, thereby contributing to more informed public health decision-making during a pandemic.

sampling timing↗

Enhancing Docking Accuracy with PECAN2, a 3D Atomic Neural Network Trained without Co-Complex Crystal Structures

Decades of drug development research have explored a vast chemical space for highly active compounds. The exponential growth of virtual libraries enables easy access to billions of synthesizable molecules. Computational modeling, particularly molecular docking, utilizes physics-based calculations to prioritize molecules for synthesis and testing. Nevertheless, the molecular docking process often yields docking poses with favorable scores that prove to be inaccurate with experimental testing. To address these issues, several approaches using machine learning (ML) have been proposed to filter incorrect poses based on the crystal structures. However, most of the methods are limited by the availability of structure data. Here, we propose a new pose classification approach, PECAN2 (Pose Classification with 3D Atomic Network 2), without the need for crystal structures, based on a 3D atomic neural network with Point Cloud Network (PCN). The new approach uses the correlation between docking scores and experimental data to assign labels, instead of relying on the crystal structures. We validate the proposed classifier on multiple datasets including human mu, delta, and kappa opioid receptors and SARS-CoV-2 Mpro. Our results demonstrate that leveraging the correlation between docking scores and experimental data alone enhances molecular docking performance by filtering out false positives and false negatives.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗

A NEW METHOD FOR FINDING POINT SOURCES IN HIGH-ENERGY NEUTRINO DATA

The IceCube collaboration has reported the first detection of high-energy astrophysical neutrinos, including ∼50 high-energy starting events, but no individual sources have been identified. It is therefore important to develop the most sensitive and efficient possible algorithms to identify the point sources of these neutrinos. The most popular current method works by exploring a dense grid of possible directions to individual sources, and identifying the single direction with the maximum probability of having produced multiple detected neutrinos. This method has numerous strengths, but it is computationally intensive and because it focuses on the single best location for a point source, additional point sources are not included in the evidence. We propose a new maximum likelihood method that uses the angular separations between all pairs of neutrinos in the data. Unlike existing autocorrelation methods for this type of analysis, which also use angular separations between neutrino pairs, our method incorporates information about the point-spread function and can identify individual point sources. We find that if the angular resolution is a few degrees or better, then this approach reduces both false positive and false negative errors compared to the current method, and is also more computationally efficient up to, potentially, hundreds of thousands of detected neutrinos.

79 ASTRONOMY AND ASTROPHYSICS↗

PREPARING FOR ADVANCED LIGO: A STAR–GALAXY SEPARATION CATALOG FOR THE PALOMAR TRANSIENT FACTORY

The search for fast optical transients, such as the expected electromagnetic counterparts to binary neutron star mergers, is riddled with false positives (FPs) ranging from asteroids to stellar flares. While moving objects are readily rejected via image pairs separated by ∼1 hr, stellar flares represent a challenging foreground, significantly outnumbering rapidly evolving explosions. Identifying stellar sources close to and fainter than the transient detection limit can eliminate these FPs. Here, we present a method to reliably identify stars in deep co-adds of Palomar Transient Factory (PTF) imaging. Our machine-learning methodology utilizes the random forest (RF) algorithm, which is trained using >3×10{sup 6} sources with Sloan Digital Sky Survey (SDSS) spectra. When evaluated on an independent test set, the PTF RF model outperforms the SExtractor star classifier by ∼4%. For faint sources (r{sup ′}⩾21 mag), which dominate the field population, the PTF RF model produces a ∼19% improvement over SExtractor. To avoid false negatives in the PTF transient-candidate stream, we adopt a conservative stellar classification threshold, corresponding to a galaxy misclassification rate of 0.005. Ultimately, ∼1.70×10{sup 8} objects are included in our PTF point-source catalog, of which only ∼10{sup 6} are expected to be galaxies. We demonstrate that the PTF RF catalog reveals transients that otherwise would have been missed. To leverage its superior image quality, we additionally create an SDSS point-source catalog, which is also tuned to have a galaxy misclassification rate of 0.005. These catalogs have been incorporated into the PTF real-time pipelines to automatically reject stellar sources as non-extragalactic transients.

79 ASTRONOMY AND ASTROPHYSICS↗