SEARCH · Search NASA
Results for “READING MACHINE”
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.
Real-Time Inference For MI/RR Deblending
The Fermilab Main Injector (MI) and Recycler Ring (RR) share a common beam loss monitor (BLM) system, making loss events difficult to attribute to their source machine when beam is present in both simultaneously. The Real-time Edge AI for Distributed Systems (READS) project addresses this by deblending BLM readings in real time using machine learning (ML). The current FPGA based implementation meets the sub-3 ms latency requirement but carries a resource intensive hls4ml development cycle, motivating exploration of GPU based deployment. This paper characterizes inference latency on an NVIDIA Jetson Orin Nano and introduces a packet organization scheme for assembling synchronized event frames from seven distributed BLM DAQ streams. Using a Python based DAQ simulation with injected timing jitter in place of unavailable live beam data, the pipeline achieved an average end to end latency of 0.456 ms (σ = 0.122 ms) across 167,000 test frames, comfortably meeting the timing constraint. Early outliers were attributed to TensorRT warm-up rather than steady state limitations, suggesting GPU based inference is a viable alternative to the existing FPGA implementation.
Exploration of Real Time Inference for MI-RR Deblending on GPU/TPU Systems
The Fermilab Main Injector (MI) and Recycler Ring (RR) share a common beam loss monitor (BLM) system, making loss events difficult to attribute to their source machine when beam is present in both simultaneously. The Real-time Edge AI for Distributed Systems (READS) project addresses this by deblending BLM readings in real time using machine learning (ML). The current FPGA based implementation meets the sub-3 ms latency requirement but carries a resource intensive hls4ml development cycle, motivating exploration of GPU based deployment. This paper characterizes inference latency on an NVIDIA Jetson Orin Nano and introduces a packet organization scheme for assembling synchronized event frames from seven distributed BLM DAQ streams. Using a Python based DAQ simulation with injected timing jitter in place of unavailable live beam data, the pipeline achieved an average end to end latency of 0.456 ms (σ = 0.122 ms) across 167,000 test frames, comfortably meeting the timing constraint. Early outliers were attributed to TensorRT warm-up rather than steady state limitations, suggesting GPU based inference is a viable alternative to the existing FPGA implementation.
Genomic fingerprints of the world’s soil ecosystems
Despite the explosion of soil metagenomic data, we lack a synthesized understanding of patterns in the distribution and functions of soil microorganisms. These patterns are critical to predictions of soil microbiome responses to climate change and resulting feedbacks that regulate greenhouse gas release from soils. To address this gap, we assay 1,512 manually curated soil metagenomes using complementary annotation databases, read-based taxonomy, and machine learning to extract multidimensional genomic fingerprints of global soil microbiomes. Our objective is to uncover novel biogeographical patterns of soil microbiomes across environmental factors and ecological biomes with high molecular resolution. We reveal shifts in the potential for (i) microbial nutrient acquisition across pH gradients; (ii) stress-, transport-, and redox-based processes across changes in soil bulk density; and (iii) greenhouse gas emissions across biomes. We also use an unsupervised approach to reveal a collection of soils with distinct genomic signatures, characterized by coordinated changes in soil organic carbon, nitrogen, and cation exchange capacity and in bulk density and clay content that may ultimately reflect soil environments with high microbial activity. Genomic fingerprints for these soils highlight the importance of resource scavenging, plant-microbe interactions, fungi, and heterotrophic metabolisms. Across all analyses, we observed phylogenetic coherence in soil microbiomes—more closely related microorganisms tended to move congruently in response to soil factors. Collectively, the genomic fingerprints uncovered here present a basis for global patterns in the microbial mechanisms underlying soil biogeochemistry and help beget tractable microbial reaction networks for incorporation into process-based models of soil carbon and nutrient cycling.
First multi-institutional systematic comparison of the neutron ambient dose equivalent produced by proton therapy systems
Objective. Isochronous cyclotrons, synchrocyclotrons, and synchrotrons are used to accelerate protons for proton therapy. An accurate measurement of neutron doses generated by these accelerators and associated delivery systems and its clinical relevance requires systematic protocols and proper neutron dosimetry for a meaningful assessment. We present the first comprehensive comparison of neutron ambient dose equivalent (H*(10)) produced by clinically operational proton therapy systems. Approach. Treatment plans with 10 cm modulation-depth and ranges of 10 cm (R10M10) and 25 cm (R25M10) were created to cover a 10 × 10 × 10 cm 3 water target. The pencil beam scanning proton therapy machines studied were: two gantry-mounted synchrocyclotrons (Hyperscan, Mevion, half-gantry), two isochronous cyclotrons (ProBeam, Varian, full-gantry), one isochronous cyclotron (Proteus, IBA, full-gantry), and two synchrotrons (PROBEAT, Hitachi, full- and half-gantry). Proton beams were delivered to 30 × 30 × 40 cm 3 plastic water phantoms. WENDI-II and LUPIN-BF3-NP neutron rem-meters were positioned at three angles (0°, 45°, 90°) relative to the beam direction to measure the neutron H*(10) at distances between 50–300 cm from the isocenter. Main results. H*(10) showed dependence on beam energy, machine type, and measurement location. The highest reading was for the gantry-mounted synchrocyclotron, whereas other systems produced approximately comparable neutron doses. In all cases, the H*(10) reduced with distance from the isocenter. The H*(10) drop at 2 m distance compared to that at 0.5 m was a factor of ∼5 for the gantry-mounted synchrocyclotron whereas in other systems the decrease was a factor of 10. The WENDI-II device suffered from dead-time-associated under-estimation of the dose by a factor of ∼2–3 under the synchrocyclotron beam due to its high dose-per-pulse. However, WENDI-II and LUPIN-BF3-NP results were within reasonable agreement in isochronous cyclotron and synchrotron beams, indicating that both devices are suitable for those systems. Significance. Neutron H*(10) is dependent on various parameters including beam energy, measurement location, as well as machine design. Caution must be exercised in choosing the appropriate neutron-dose-measurement device to be used for low-duty-factor, particularly in high-instantaneous-rate proton delivery systems. By delivering the same volumetric proton dose across different machines, this work provides a benchmark for inter-system comparisons and serves as a foundation for future studies.
Post-DTL Beam Delivery
Ensuring that the beam delivered from the upgraded Front-End (FE) meets the Key Performance Parameters (KPPs) at each user facility is critical to the success of the LANSCE Accelerator Modernization Project (LAMP). For a high-intensity, multi-user facility like LANSCE, compliance with beam loss and radiation thresholds is as important as the charge delivered to each target. While early LAMPF/LANSCE operations relied on iterative tuning to minimize losses from beam halo and tail particles, the new FE may introduce different beam distributions and loss modes—making predictive modeling essential. To manage this, the F2E (Front-End to End) effort is developing detailed particle-tracking models that reflect realistic beamline conditions, including halo formation and expected diagnostic readings. These "snapshot" simulations aim to benchmark live machine performance at a given moment. This will help quantify how beam quality from the new FE will propagate downstream through the facility. Only by validating these models can we confidently assess and mitigate the potential impacts of the LAMP FE on beam delivery. Post-DTL, the beam splits to serve five major user facilities. Historically, low-energy beam transport has been modeled using TRACE, and higher-energy sections with TRANSPORT. These have now been unified into MAD-X format and validated with codes such as Elegant, pyOrbit, XSuite, Impact-Z, and HPSim. The primary focus now is on accurate modeling of full particle distributions (including beam halo) as they traverse the accelerator and beamlines to each experimental station. All models are at various stages of validation with empirical data.
Unsupervised multimodal fusion of in-process sensor data for advanced manufacturing process monitoring
Effective monitoring of manufacturing processes is crucial for maintaining product quality and operational efficiency. Modern manufacturing environments often generate vast amounts of complementary multimodal data, including visual imagery from various perspectives and resolutions, hyperspectral data, and machine health monitoring information such as actuator positions, accelerometer readings, and temperature measurements. However, fusing and interpreting this complex, high-dimensional data presents significant challenges, particularly when labeled datasets are unavailable or impractical to obtain. This paper presents a novel approach to multimodal sensor data fusion in manufacturing processes, inspired by the Contrastive Language-Image Pre-training (CLIP) model. We leverage contrastive learning techniques to correlate different data modalities without the need for labeled data, overcoming limitations of traditional supervised machine learning methods in manufacturing contexts. Our proposed method demonstrates the ability to handle and learn encoders for five distinct modalities: visual imagery, audio signals, laser position (x and y coordinates), and laser power measurements. By compressing these high-dimensional datasets into low-dimensional representational spaces, our approach facilitates downstream tasks such as process control, anomaly detection, and quality assurance. The unsupervised nature of our method makes it broadly applicable across various manufacturing domains, where large volumes of unlabeled sensor data are common. We evaluate the effectiveness of our approach through a series of experiments, demonstrating its potential to enhance process monitoring capabilities in advanced manufacturing systems. This research contributes to the field of smart manufacturing by providing a flexible, scalable framework for multimodal data fusion that can adapt to diverse manufacturing environments and sensor configurations. The proposed method paves the way for more robust, data-driven decision-making in complex manufacturing processes.
LevSeq: Rapid Generation of Sequence-Function Data for Directed Evolution and Machine Learning
Sequence-function data provides valuable information about the protein functional landscape but is rarely obtained during directed evolution campaigns. Here, we present Long-read every variant Sequencing (LevSeq), a pipeline that combines a dual barcoding strategy with nanopore sequencing to rapidly generate sequence-function data for entire protein-coding genes. LevSeq integrates into existing protein engineering workflows and comes with open-source software for data analysis and visualization. The pipeline facilitates data-driven protein engineering by consolidating sequence-function data to inform directed evolution and provide the requisite data for machine learning-guided protein engineering (MLPE). LevSeq enables quality control of mutagenesis libraries prior to screening, which reduces time and resource costs. Simulation studies demonstrate LevSeq’s ability to accurately detect variants under various experimental conditions. Lastly, we show LevSeq’s utility in engineering protoglobins for new-to-nature chemistry. Widespread adoption of LevSeq and sharing of the data will enhance our understanding of protein sequence-function landscapes and empower data-driven directed evolution.
I Can’t Read All That! Improving the Usability of Semantic Models Using Concise, Ontology-Agnostic, Building-Specific Schemas
Semantic ontologies have enabled the creation of formalized, machine-readable descriptions of heterogenous building systems by providing dictionaries of well defined concepts that can be applied to model them. Within a semantic model of a particular building, a subset of an ontology's concepts may be applied in different ways to represent a particular perspective of the building's systems. How the concepts were applied can only be understood by examining the large amount of instance data within a semantic model, which leads to usability challenges. We propose a concise, ontology-agnostic method for defining building-specific schema (b-schema) graphs that summarize the structure and content of a semantic model. This approach provides a queryable and concise representation of the model's contents, separate from the instance data within a model, that can mitigate the challenges posed by the size and complexity of semantic models in processes such as visualization, querying, validation, and the use of large language models (LLMs). We validate our approach on semantic models based on the Brick and ASHRAE S223 ontologies. Results demonstrate that b-schemas significantly reduce the complexity of visual interpretation, accelerate SPARQL queries and SHACL validation, and improve LLM-based knowledge graph question answering.
Linking Spatiotemporal Biological Data to Predict Harmful Algal Blooms
Cyanobacterial Harmful Algal Blooms (cHABs) have significant impacts on an affected region’s economy, ecology, and human health. The blooms can release toxins that kill fish and poison water for people and animals. The global adverse effects of cHABs are exacerbated by the consequences of climate change and increased pollution. Though the phenomena are well documented, scientists’ efforts to mitigate the damage are hampered by insufficient predictive models and incomplete granular knowledge of cHAB community structure. With a goal of leveraging bioinformatics and machine learning tools to better understand and predict cHABs, we are first exploring water sample data sets. Using nearly four thousand samples from the National Center for Biotechnology Information Sequence Read Archive (NCBI-SRA) across 16 years with latitude and longitude embedded in the metadata, we mapped the location of the samples onto a Lake Erie shape file. We combined information about location, date, and community taxa in the NCBI samples to discover factors that determine cHAB features. The data are separated into three distinct zones, with the majority pooled at the southwest end of the lake and occurring in 2017. The samples are rich in biological data; our next steps are to carry out whole genome sequence analysis and use the community profiles as part of our predictive machine learning model.
Real Time implementation of Artificial Intelligence compression algorithm for High-Speed Streaming Readout signals
The new generation of high-energy physics experiments plans to acquire data in streaming mode. With this approach, it is possible to access the information of the whole detector (organized in time slices) for optimal and lossless triggering of data acquisitions. With this approach, data rates, especially in large detectors, are often very high, and the network is likely to be the bottleneck for the entire Streaming Read Out system. The aim of this work is to study the implementation of a lossy compression algorithm based on Artificial Intelligence: an Autoencoder. With Machine Learning it is possible to achieve a high compression ratio and fast inference time with only a small degradation of the signals, almost negligible for the specific application. This work explores different configurations of the Autoencoder and the implementation on different hardware. Different Autoencoder configurations are explored to find the best trade-off between compression ratio and reconstruction loss, both for signals and energy spectrum. Different hardware implementations are also explored to find the best platform to achieve real-time performance for the specific application.
Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac
The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally corrected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a surrogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.
Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac
The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally cor- rected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a sur- rogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.
Intelligent Pixel Detectors: Towards a Radiation Hard ASIC with On-Chip Machine Learning in 28 nm CMOS
Detectors at future high energy colliders will face enormous technical challenges. Disentangling the unprecedented numbers of particles expected in each event will require highly granular silicon pixel detectors with billions of readout channels. With event rates as high as 40 MHz, these detectors will generate petabytes of data per second. To enable discovery within strict bandwidth and latency constraints, future trackers must be capable of fast, power efficient, and radiation hard data-reduction at the source. We are developing a radiation hard readout integrated circuit (ROIC) in 28nm CMOS with on-chip machine learning (ML) for future intelligent pixel detectors. We will show track parameter predictions using a neural network within a single layer of silicon and hardware tests on the first tape-outs produced with TSMC. Preliminary results indicate that reading out featurized clusters from particles above a modest momentum threshold could enable using pixel information at 40 MHz.
Peak2Patch: High-Fidelity Functional Group Identification through Attention-Based Fusion of Infrared and Mass Spectra
Identifying molecular structure based on spectroscopic readings is a key task in a variety of chemical and biological applications. Common spectroscopy techniques, such as Infrared (IR) Spectroscopy and Mass Spectrometry (MS), provide detailed information on the structure of molecular compounds but nonetheless require expert-level knowledge to decode. Machine learning has emerged as a potential solution for automating structure prediction from chemical spectra; however, current approaches generally focus on single sensor modalities, neglecting to leverage the complementary information contained within differing spectra. In this paper, we introduce Peak2Patch, a novel approach to fusion-enhanced prediction of functional groups from IR and mass spectra. First, we perform a detailed comparison of backbone networks for encoding both sparse mass spectra and dense IR spectra and demonstrate the superior performance of transformer neural networks over current state-of-the-art convolutional neural networks. Second, we evaluate three broad categories of fusion: early (raw feature), middle (deep feature), and late (decision) fusion, demonstrating the potential of a deep feature fusion-based approach. Lastly, we present Peak2Patch, our attention-based fusion scheme, which leverages cross-attention to mix features between encoded tokens of the two modalities. We validate our approach on a publicly available multimodal spectroscopic data set of 790k simulated molecules, demonstrating a large improvement in functional group prediction over both the previous state-of-the-art and our own strong single-modal baselines.
NovaDemux v39.07
This program is a sequence demultiplexer intended primarily for, but not limited to, Illumina sequencing machines. Typically, multiple experiments ("libraries") are pooled together and sequenced at once, with genetic molecules of these libraries tagged with a synthetic DNA "barcode". After sequencing, the data is demultiplexed into one file per library based on the barcode. However, errors in barcode reading cause misassignment and decrease yield. NovaDemux uses advanced statistical methods to maximize yield while minimizing misassignment compared to existing software.
Characterization of Soil and Rock Magnetic Properties along Multiple Hillslope Transects at Teller Road Site, Seward Peninsula, Alaska, 2018 and 2023
The magnetometer data was collected in multiple directions across the watershed hillslope at the NGEE Arctic Teller Road site at mile marker 27 (TL_MM27) on the Seward Peninsula, Alaska over multiple years in March 2018 and April 2023. The magnetic data were collected using a Geometrics Inc. G-858 gradiometer and G-857 base station in 2018 and the G-864 gradiometer and G857 base station in 2023. The data was collected (in all instances) by towing the gradiometer behind a snow machine around the watershed with the two sensors in a vertical profile with constant spacing during the continuous survey in that specific year. Magnetic total field measurements were collected by gradiometer and base station, and the data processing was performed in Geometrics MagMap2000 software. The processing steps were limited to removal of data spikes (despiking), reading dropouts, and correction/removal of bad GPS points. All offsets between sensors and GPS are stated within the data files and metadata, alongwith the processed and raw data. The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research. The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).In this data submission there are two sets of raw magnetic data (.bin and .stn for 2018 and base for 2023; raw rover mag for 2023 is in .csv) inside two .zip files that identify the year the mag data was collected. The data are proprietary format to Geometrics and can be opened and processed with MagMap2000 which can be downloaded for free at Geometrics website. There are also two processed data files *.csv for each year and two metadata files *.csv.
NANO.PTML model for read-across prediction of nanosystems in neurosciences. computational model and experimental case of study
Abstract Neurodegenerative diseases involve progressive neuronal death. Traditional treatments often struggle due to solubility, bioavailability, and crossing the Blood-Brain Barrier (BBB). Nanoparticles (NPs) in biomedical field are garnering growing attention as neurodegenerative disease drugs (NDDs) carrier to the central nervous system. Here, we introduced computational and experimental analysis. In the computational study, a specific IFPTML technique was used, which combined Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) to select the most promising Nanoparticle Neuronal Disease Drug Delivery (N2D3) systems. For the application of IFPTML model in the nanoscience, NANO.PTML is used. IF-process was carried out between 4403 NDDs assays and 260 cytotoxicity NP assays conducting a dataset of 500,000 cases. The optimal IFPTML was the Decision Tree (DT) algorithm which shown satisfactory performance with specificity values of 96.4% and 96.2%, and sensitivity values of 79.3% and 75.7% in the training (375k/75%) and validation (125k/25%) set. Moreover, the DT model obtained Area Under Receiver Operating Characteristic (AUROC) scores of 0.97 and 0.96 in the training and validation series, highlighting its effectiveness in classification tasks. In the experimental part, two samples of NPs (Fe 3 O 4 _A and Fe 3 O 4 _B) were synthesized by thermal decomposition of an iron(III) oleate (FeOl) precursor and structurally characterized by different methods. Additionally, in order to make the as-synthesized hydrophobic NPs (Fe 3 O 4 _A and Fe 3 O 4 _B) soluble in water the amphiphilic CTAB (Cetyl Trimethyl Ammonium Bromide) molecule was employed. Therefore, to conduct a study with a wider range of NP system variants, an experimental illustrative simulation experiment was performed using the IFPTML-DT model. For this, a set of 500,000 prediction dataset was created. The outcome of this experiment highlighted certain NANO.PTML systems as promising candidates for further investigation. The NANO.PTML approach holds potential to accelerate experimental investigations and offer initial insights into various NP and NDDs compounds, serving as an efficient alternative to time-consuming trial-and-error procedures.