Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 829 records · Page 46

Data for Zheng et al. (2025), "AquaMEND: Reconciling multiple impacts of salinization on soil carbon biogeochemistry"

Soil salinization, exacerbated by climate change, poses a global threat to coastal ecosystems and soil function. Salinity affects soil carbon cycling by directly impacting microbial activity and indirectly altering soil physicochemical properties, but current models inadequately represent these complexities. This dataset contains the observational and modeling data from Zheng et al. (2025), which described a process-based modeling framework that couples soil solution chemistry with microbial carbon cycling reactions to study the impacts of soil salinization. This conceptual model is implemented numerically into the open-source geochemical program PHREEQC 3.0 (Parkhurst and Appelo, 2013). This dataset consists of: - Figure2_AquaMEND_salinity_buffer: Contains model simulation outputs to assess the impact of three different cation exchange and surface complexation processes on salinity buffering (Fig. 2 from Zheng et al. 2025). - Figure3_Salinity_function: Contains salinity function fitting for literature data (Fig. 3 from Zheng et al. 2025). - Figure4_AquaMEND_microbial_mechanisms: Contains model simulation outputs for testing various microbial process-based hypotheses related to soil salinization, including microbial mortality, carbon use efficiency (CUE), extracellular enzyme activity, and other microbial mechanisms (Fig. 4 from Zheng et al. 2025). - Figure5_AquaMEND_Redox: Contains on model simulation outputs to evaluate shifts among key redox processes, such as aerobic respiration, sulfate reduction, and methanogenesis (Fig.5 from Zheng et al. 2025). - Figure6_AquaMEND_sorption: Contains on model simulation outputs for investigating the effects of salinity on dissolved organic matter (DOM) sorption and desorption processes (Fig. 6 from Zheng et al. 2025). - Figure7_AquaMEND_process_couple: Contains on model simulation outputs for exploring coupled biotic-abiotic processes and their interactions (Fig. 7 from Zheng et al. 2025). - data: Includes datasets used to develop salinity response functions and evaluate salinity buffering capacity. Datasets for MEND model calibration. - database: Contains the `.dat` file required by PHREEQC for model execution. - README.md: A Markdown plain text file describing the computational tools and directories. Files are a mixture of plain text CSV (comma-separated value) and plain text *.dat files written by the model; no special software is required to read them.

EARTH SCIENCE > AGRICULTURE > SOILS > SOIL SALINIT↗

Development of Training Materials for Pathologists to Provide Machine Learning Validation Data of Tumor-Infiltrating Lymphocytes in Breast Cancer

The High Throughput Truthing project aims to develop a dataset for validating artificial intelligence and machine learning models (AI/ML) fit for regulatory purposes. The context of this AI/ML validation dataset is the reporting of stromal tumor-infiltrating lymphocytes (sTILs) density evaluations in hematoxylin and eosin-stained invasive breast cancer biopsy specimens. After completing the pilot study, we found notable variability in the sTILs estimates as well as inconsistencies and gaps in the provided training to pathologists. Using the pilot study data and an expert panel, we created custom training materials to improve pathologist annotation quality for the pivotal study. We categorized regions of interest (ROIs) based on their mean sTILs density and selected ROIs with the highest and lowest sTILs variability. In a series of eight one-hour sessions, the expert panel reviewed each ROI and provided verbal density estimates and comments on features that confounded the sTILs evaluation. We aggregated and shaped the comments to identify pitfalls and instructions to improve our training materials. From these selected ROIs, we created a training set and proficiency test set to improve pathologist training with the goal to improve data collection for the pivotal study. We are not exploring AI/ML performance in this paper. Instead, we are creating materials that will train crowd-sourced pathologists to be the reference standard in a pivotal study to create an AI/ML model validation dataset. The issues discussed here are also important for clinicians to understand about the evaluation of sTILs in clinical practice and can provide insight to developers of AI/ML models.

60 APPLIED LIFE SCIENCES↗

RADAI: A Large-Scale Realistic Dataset for Radiation Detection Algorithm Development

Open, realistic datasets are essential for developing and benchmarking radiation detection algorithms, yet they remain scarce. The Radiological Anomaly Detection and Identification (RADAI) project was develop to create datasets that meet the training and testing needs for sophisticated radiation detection algorithms. The RADAI dataset is a large-scale synthetic resource that integrates high-fidelity Monte Carlo simulations with realistic urban scenarios to capture both background variability and source signatures. RADAI models construction-material NORM, people and vehicles, urban clutter, and dynamic environmental effects such as cosmic-ray and rain-induced transients, and they provide list-mode detector data with motion and response modeling suitable for algorithm training and evaluation. The RADAI project resulted in three publicly-released complementary datasets together with an online scoring portal for standardized performance assessment and an open software toolkit that supports data access, augmentation, model development, and evaluation. These resources enable reproducible comparisons across methods and promote rigorous studies at the scale required by contemporary machine learning. By grounding algorithm development in realistic, well-documented conditions, RADAI supports progress toward more robust detection, identification, and localization in complex urban environments.

Ghawaly, James M. [Division of Computer Science an↗

A Comprehensive Forward Model for Spaceborne Radar Instruments

We present the development and validation of a comprehensive forward model designed to enhance remote sensing capabilities of spaceborne radar instruments. To overcome limitations in existing models, we integrated a Discrete Dipole Approximation (DDA) cloud scattering database into our Radiative Transfer Model (RTM), focusing on microwave frequencies. By simulating the optical properties of non-spherical frozen hydrometeors, the DDA technique effectively reduced discrepancies between simulated and observed values, surpassing traditional Mie tables. The evaluation of DDA lookup tables involved comparisons with a collocated dataset comprising short-term forecasts and satellite microwave data, providing evidence of their superiority. Additionally, we address the challenges of assimilating active radar measurements, which offer vertically resolved insights into clouds and precipitation. We explored the assimilation of spaceborne radar measurements in Numerical Weather Prediction (NWP) models by integrating a forward radar model, along with its adjoint and tangent linear, into the data assimilation system. Evaluation using CloudSat measurements demonstrated promising agreement between simulations and observations, particularly when the input hydrometeor profiles aligned with the measured reflectivity profiles, showcasing the potential of the developed forward radar model. Moreover, we discuss other challenges in radar measurement assimilation within NWP models, including potential observation errors and biases.

Isaac Moradi↗

An Intercomparison of High Spectral Resolution Lidar and Satellite Ocean Color Backscatter Retrievals

We present an intercomparison of satellite ocean color and high spectral resolution lidar (HSRL) retrievals of upper ocean particulate backscattering (bbp) and diffuse attenuation coefficients (Kd). Ocean retrievals of bbp and Kd have been performed over a wide variety of optical and ecological domains using the NASA Langley Research Center HSRL-1 (532 nm) and the recently upgraded HSRL-2 (532 & 355 nm). These datasets provide a unique opportunity to perform a critical assessment of the HSRL technique and to explore the utility of HSRL measurements for evaluating the quality of ocean color remote sensing retrievals on regional scales. A matchup dataset of co-located and high-quality HSRL and ocean color remote sensing measurements was created using data from research flights conducted over the western North Atlantic Ocean during the NASA sponsored SABOR, NAAMES, and ACTIVATE campaigns. Overall, comparisons showed a strong agreement between HSRL and ocean color retrievals of bbp and Kd, providing confidence in our ability to retrieve upper ocean optical properties using oceanographic lidar. However, comparisons from individual flights can exhibit deviations that were not attributed to shifts in water column optical domains. In one of these cases, the simultaneous HSRL atmosphere-ocean retrievals from two consecutive days and within the same region were used to identify ocean color atmospheric correction errors resulting from the presence of absorbing aerosols. These results highlight the utility of airborne HSRL as a standalone ocean observing technology and as an independent and calibrated technique for assessing the quality of ocean color remote sensing retrievals.

Brian Collister↗

Unpaired image translation to mitigate domain shift in liquid argon time projection chamber detector responses

Deep learning algorithms often are developed and trained on a training dataset and deployed on test datasets. Any systematic difference between the training and a test dataset may severely degrade the final algorithm performance on the test dataset—what is known as the domain shift problem . This issue is prevalent in many scientific domains where algorithms are trained on simulated data but applied to real-world datasets. Typically, the domain shift problem is solved through various domain adaptation (DA) methods. However, these methods are often tailored for a specific downstream task, such as classification or semantic segmentation, and may not easily generalize to different tasks. This work explores the feasibility of using an alternative way to solve the domain shift problem that is not specific to any downstream algorithm. The proposed approach relies on modern Unpaired Image-to-Image (UI2I) translation techniques, designed to find translations between different image domains in a fully unsupervised fashion. In this study, the approach is applied to a domain shift problem commonly encountered in Liquid Argon Time Projection Chamber (LArTPC) detector research when seeking a way to translate samples between two differently distributed LArTPC detector datasets deterministically. This translation allows for mapping real-world data into the simulated data domain where the downstream algorithms can be run with much less domain-shift-related performance degradation. Conversely, using the translation from the simulated data to a real-world domain can increase the realism of the simulated dataset and reduce the magnitude of any systematic uncertainties. To evaluate the quality of the translations, we use both pixel-wise metrics and a downstream task to measure the effectiveness of UI2I methods for mitigating the domain shift problem. We adapted several popular UI2I translation algorithms to work on scientific data and demonstrated the viability of these techniques for solving the domain shift problem with LArTPC detector data. To facilitate further development of DA techniques for scientific datasets, the ‘Simple Liquid-Argon Track Samples’ dataset used in this study is also published.

97 MATHEMATICS AND COMPUTING↗

SU-F-J-140: Using Handheld Stereo Depth Cameras to Extend Medical Imaging for Radiation Therapy Planning

Purpose: A correct body contour is essential for the accuracy of dose calculation in radiation therapy. While modern medical imaging technologies provide highly accurate representations of body contours, there are times when a patient’s anatomy cannot be fully captured or there is a lack of easy access to CT/MRI scanning. Recently, handheld cameras have emerged that are capable of performing three dimensional (3D) scans of patient surface anatomy. By combining 3D camera and medical imaging data, the patient’s surface contour can be fully captured. Methods: A proof-of-concept system matches a patient surface model, created using a handheld stereo depth camera (DC), to the available areas of a body contour segmented from a CT scan. The matched surface contour is then converted to a DICOM structure and added to the CT dataset to provide additional contour information. In order to evaluate the system, a 3D model of a patient was created by segmenting the body contour with a treatment planning system (TPS) and fabricated with a 3D printer. A DC and associated software were used to create a 3D scan of the printed phantom. The surface created by the camera was then registered to a CT model that had been cropped to simulate missing scan data. The aligned surface was then imported into the TPS and compared with the originally segmented contour. Results: The RMS error for the alignment between the camera and cropped CT models was 2.26 mm. Mean distance between the aligned camera surface and ground truth model was −1.23 +/−2.47 mm. Maximum deviations were < 1 cm and occurred in areas of high concavity or where anatomy was close to the couch. Conclusion: The proof-of-concept study shows an accurate, easy and affordable method to extend medical imaging for radiation therapy planning using 3D cameras without additional radiation. Intel provided the camera hardware used in this study.

60 APPLIED LIFE SCIENCES↗

Investigation of Simple IMRT Delivery Techniques for Non-Small Cell Lung Cancer Patients with Respiratory Motion Using 4DCT

Techniques for generating simplified IMRT treatment plans for treating non-small cell lung cancer (NSCLC) patients with respiratory motion were investigated. To estimate and account for respiratory motion, 4-dimensional computed tomography (4DCT) datasets from 5 patients were used to design 5-field 6-MV ungated step-and-shoot intensity modulated radiotherapy (IMRT) plans delivering a dose of 66 Gy to the planning target volume (PTV). For each patient, 2 plans were generated using the mean intensity and the maximum intensity of 10 CT datasets from different breathing phases. The plans also utilized different margins around the clinical target volume/internal target volume (CTV/ITV) to account for tumor motion. To reduce the treatment time and ensure accurate dose delivery to moving targets, the number of intensity levels was minimized while maintaining dose coverage to PTV and minimizing dose to organs at risk (OARs). Dose-volume histograms (DVHs), dosimetric metrics, and outcome probabilities were evaluated for all plans. Plans using the averaged CT image dataset were inferior, requiring larger margins around the PTV, with a maximum of 1.5 cm, to ensure coverage of the tumor, and therefore increased the dose to OARs located in proximity of the tumor. The plans based on superimposed CT image datasets achieved full coverage of the tumor, while allowing tight margins around the PTV and minimizing the dose to OARs. A small number of intensity-levels (3 to 5), resulting in IMRT plans with a total of 13 to 30 segments, were sufficient for homogeneous PTV coverage, without affecting the sparing of OARs. In conclusion, a technique involving treatment planning with the superimposed CT scans of all respiratory phases, and the application of IMRT with only a small number of segments was feasible despite significant tumor motion; however, greater patient numbers are needed to support the statistical significance of the results presented in this work.

61 RADIATION PROTECTION AND DOSIMETRY↗

Optimizing Landsat Next Shortwave Infrared Bands for Crop Residue Characterization

This study focused on optimizing the placement of shortwave infrared (SWIR) bands for pixel-level estimation of fractional crop residue cover (f R ) for the upcoming Landsat Next mission. We applied an iterative wavelength shift approach to a database of crop residue field spectra collected in Beltsville, Maryland, USA (n = 916) and computed generalized two- and three-band spectral indices for all wavelength combinations between 2000 and 2350 nm, then used these indices to model field-measured f R . A subset of the full dataset with a Normalized Difference Vegetation Index (NDVI) < 0.3 threshold (n = 643) was generated to evaluate green vegetation impacts on f R estimation. For the two-band wavelength shift analyses applied to the NDVI < 0.3 dataset, a generalized normalized difference using 2226 nm and 2263 nm bands produced the top f R estimation performance (R 2 = 0.8222; RMSE = 0.1296). These findings were similar to the established two-band Shortwave Infrared Normalized Difference Residue Index (SINDRI) (R 2 = 0.8145; RMSE = 0.1324). Performance of the two-band generalized normalized difference and SINDRI decreased for the full-NDVI dataset (R 2 = 0.5865 and 0.4144, respectively). For the three-band wavelength shift analyses applied to the NDVI < 0.3 dataset, a generalized ratio-based index with a 2031–2085–2216 nm band combination, closely matching established Cellulose Absorption Index (CAI) bands, was top performing (R 2 = 0.8397; RMSE = 0.1231). Three-band indices with CAI-type wavelengths maintained top f R estimation performance for the full-NDVI dataset with a 2036–2111–2217 nm band combination (R 2 = 0.7581; RMSE = 0.1548). The 2036–2111–2217 nm band combination was also top performing in f R estimation (R 2 = 0.8690; RMSE = 0.0970) for an additional analysis assessing combined green vegetation cover and surface moisture effects. Our results indicate that a three-band configuration with band centers and wavelength tolerances of 2036 nm (±5 nm), 2097 nm (±14 nm), and 2214 (±11 nm) would optimize Landsat Next SWIR bands for f R estimation.

Landsat Next↗

Digital Rocks Portal (Digital Porous Media): Connecting data, simulation and community

Digital Rocks Portal (DRP, https://www.digitalrocksportal.org) organizes and preserves imaged datasets and experimental measurements of porous materials in subsurface, and beyond, with the mission to connect them to simulation and analysis, as well as educate the research community. We have over 150 projects represented in more than 200 publications, and an active community that reuses the data, most recently in multiple machine learning applications for automating image analysis as well as the prediction of transport. Such automation is crucial for performing formation evaluation tasks in near-real time. We present benchmark datasets that have played a role in recent machine learning prediction successes in the field. We further discuss the vision for further research advances, educational materials, as well as growth and sustainability plan of this digital rock physics community resource. In particular, we are in the process of expanding into a broader repository of engineered porous materials, specifically those for energy storage and the portal will transition to Digital Porous Media (DPM) in near future.

58 GEOSCIENCES↗

Template for estimating uncertainties of measured neutron-induced fission cross-sections

A template for estimating uncertainties (unc.) of measured neutron-induced fission, (n,f), cross-sections (cs) is presented. This preliminary template not only lists all expected unc. sources but also supplies ranges of unc., estimates for correlations between unc. of the same and different experiments which can be used if the information is nonexistent. If this template is applied systematically when estimating experimental covariances for an evaluation, it may help in pinpointing missing unc. for individual datasets, identifying unreasonably low unc., and estimating correlations between different experimental datasets. Thus, a detailed unc. estimate – usually, a time-intensive procedure – can be undertaken more consistently and efficiently. As an example, it is shown that unc. and correlations of 239 Pu(n,f) by Merla et al. [Proceedings of the Conference on Nuclear Data for Science and Technology 1991 Jülich (Springer-Verlag, Berlin, 1992) pp. 510–513], which are questionably low in the GMA database underlying the neutron cs standards evaluations, are distinctly larger at 14.7 MeV and more strongly correlated if this template is used for reestimating the associated covariances.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Creating Benchmark Data for Artificial Intelligence and Machine Learning Space Biology Research

To identify an appropriate AI/ML approach for a specific problem, the best practice is to measure algorithm performance through the benchmarking process. A scientific benchmark consists of an AI-ready dataset and a reference implementation on a specific scientific question. The NASA Science Mission Directorate (SMD) has started the “Benchmark Initiative for AI/ML to create scientific benchmark datasets in three applications: 1) scientific benchmarking, which finds the best algorithm for a specific problem; 2) application benchmarking, which measures algorithm performance against a set of parameters; and 3) system benchmarking, which evaluates performance of hardware and software architecture. Currently, there are no standardized datasets available to benchmark AI/ML algorithms in the domain of space biology. In this work, we constructed two AI/ML-ready biological datasets from experiments in space-flown mice: cellular imaging and RNA-seq. First, radiation-exposed immune cells harbor DNA damage foci that can be fluorescently marked to visualize the amount of damage following exposure to ionizing radiation. However, such large datasets are difficult to analyze visually, due to imaging inconsistencies and human bias, and classical image processing approaches can fail on imaging artifacts. AI/ML are therefore exciting alternative, providing the speed of machines and the accuracy of humans. We have made this dataset available at https://registry.opendata.aws/bps_microscopy/. Second, high-throughput nucleic acid sequencing (DNA-seq, RNA-seq) has become widespread in biomedical research due to the growing availability and affordability of these assays. However, most sequencing datasets suffer from high dimensionality and low sample count. In this work, we used a generative adversarial network to synthesize a standardized, AI-ready, publicly available benchmark dataset for space biology RNA-seq data with sufficient space-flown and ground control mouse liver samples from NASA GeneLab. This dataset is available at https://registry.opendata.aws/bps_rnaseq/. These datasets are now fully open the Space Biology community to test their favorite AI/ML approaches.

James Casaletto↗

An evaluation of the contouring abilities of medical dosimetry students for the anatomy of a prostate cancer patient

Prostate cancer is one of the most common diseases treated in a radiation oncology department. One of the major predictors of the treatment outcome and patient side effects is the accuracy of the anatomical contours for the treatment plan. Therefore, the purpose of this study was to determine which anatomical structures are most often contoured correctly and incorrectly by medical dosimetry students. The author also wanted to discover whether a review of the contouring rules would increase contouring accuracy. To achieve this, a male computed tomography dataset consisting of 72 transverse slices was sent to students for contouring. The students were instructed to import this dataset into their treatment planning system and contour the following structures: skin, bladder, rectum, prostate, penile bulb, seminal vesicles, left femoral head, and right femoral head. Upon completion of the contours, the contour file was evaluated against a 'gold standard' contour set using StructSure software (Standard Imaging, Inc). A review of the initial contour results was conducted and then students were instructed to contour the dataset a second time. The results of this study showed significant differences between contouring sessions. These results and the standardization of contouring rules should benefit all individuals who participate in the treatment planning of cancer patients.

61 RADIATION PROTECTION AND DOSIMETRY↗

Two-Step Hyperparameter Optimization Method: Accelerating Hyperparameter Search by Using a Fraction of a Training Dataset

Abstract Hyperparameter optimization (HPO) is an important step in machine learning (ML) model development, but common practices are archaic—primarily relying on manual or grid searches. This is partly because adopting advanced HPO algorithms introduces added complexity to the workflow, leading to longer computation times. This poses a notable challenge to ML applications, as suboptimal hyperparameter selections curtail the potential of ML model performance, ultimately obstructing the full exploitation of ML techniques. In this article, we present a two-step HPO method as a strategic solution to curbing computational demands and wait times, gleaned from practical experiences in applied ML parameterization work. The initial phase involves a preliminary evaluation of hyperparameters on a small subset of the training dataset, followed by a reevaluation of the top-performing candidate models postretraining with the entire training dataset. This two-step HPO method is universally applicable across HPO search algorithms, and we argue it has attractive efficiency gains. As a case study, we present our recent application of the two-step HPO method to the development of neural network emulators for aerosol activation. Although our primary use case is a data-rich limit with many millions of samples, we also find that using up to 0.0025% of the data—a few thousand samples—in the initial step is sufficient to find optimal hyperparameter configurations from much more extensive sampling, achieving up to 135× speedup. The benefits of this method materialize through an assessment of hyperparameters and model performance, revealing the minimal model complexity required to achieve the best performance. The assortment of top-performing models harvested from the HPO process allows us to choose a high-performing model with a low inference cost for efficient use in global climate models (GCMs).

97 MATHEMATICS AND COMPUTING↗

Mapping Mountain Front Recharge Areas in Arid Watersheds Based on a Digital Elevation Model and Land Cover Types

Here, a recent assessment that quantified potential impacts of solar energy development on water resources in the southwestern United States necessitated the development of a methodology to identify locations of mountain front recharge (MFR) in order to guide land development decisions. A spatially explicit, slope-based algorithm was created to delineate MFR zones in 17 arid, mountainous watersheds using elevation and land cover data. Slopes were calculated from elevation data and grouped into 100 classes using iterative self-organizing classification. Candidate MFR zones were identified based on slope classes that were consistent with MFR. Land cover types that were inconsistent with groundwater recharge were excluded from the candidate areas to determine the final MFR zones. No MFR reference maps exist for comparison with the study’s results, so the reliability of the resulting MFR zone maps was evaluated qualitatively using slope, surficial geology, soil, and land cover datasets. MFR zones ranged from 74 km2 to 1,547 km2 and accounted for 40% of the total watershed area studied. Slopes and surficial geologic materials that were present in the MFR zones were consistent with conditions at the mountain front, while soils and land cover that were present would generally promote groundwater recharge. Visual inspection of the MFR zone maps also confirmed the presence of well-recognized alluvial fan features in several study watersheds. While qualitative evaluation suggested that the algorithm reliably delineated MFR zones in most watersheds overall, the algorithm was better suited for application in watersheds that had characteristic Basin and Range topography and relatively flat basin floors than areas without these characteristics. Because the algorithm performed well to reliably delineate the spatial distribution of MFR, it would allow researchers to quantify aspects of the hydrologic processes associated with MFR and help local land resource managers to consider protection of critical groundwater recharge regions in their development decisions.

58 GEOSCIENCES↗

Experimental Evaluation of Acoustic Engine Liner Models Developed with COMSOL Multiphysics

Accurate modeling tools are needed to design new engine liners capable of reducing aircraft noise. The purpose of this study is to determine if a commercially-available finite element package, COMSOL Multiphysics, can be used to accurately model a range of different acoustic engine liner designs, and in the process, collect and document a benchmark dataset that can be used in both current and future code evaluation activities. To achieve these goals, a variety of liner samples, ranging from conventional perforate-over-honeycomb to extended-reaction designs, were installed in one wall of the grazing flow impedance tube at the NASA Langley Research Center. The liners were exposed to high sound pressure levels and grazing flow, and the effect of the liner on the sound field in the flow duct was measured. These measurements were then compared with predictions. While this report only includes comparisons for a subset of the configurations, the full database of all measurements and predictions is available in electronic format upon request. The results demonstrate that both conventional perforate-over-honeycomb and extended-reaction liners can be accurately modeled using COMSOL. Therefore, this modeling tool can be used with confidence to supplement the current suite of acoustic propagation codes, and ultimately develop new acoustic engine liners designed to reduce aircraft noise.

Schiller, Noah H.↗

Boron Coordination in Multicomponent Glasses: Analytical Models and Machine Learning With Uncertainty

Borosilicate glasses are extensively used in a variety of applications from kitchenware to nuclear waste immobilization due to the strong network formed by the Si-O-B bond that makes it resistant to chemical corrosion and gives it a low thermal expansion. Boron, however, exists in both trigonal BO3 and tetrahedral BO4 bonds in glass systems, which impacts the chemical durability and thermal resistance of the glass, amongst other properties. Boron coordination (N4), or the ratio of the amount of BO4 to BO3 within a glass, may aid in predicting these properties but is difficult to derive without experimental data due to the complexity of impacts from varied glass compositions and processing factors. For this reason, compositional models have been developed to predict boron coordination, but the models typically include a limited number of glass components. To help fill this gap in the models, in this work, a diverse multicomponent glass dataset of 809 glasses is compiled from a literature search, and then a number of analytical and machine learning (ML) models are trained on the dataset. Previously developed modified Bernstein and modified Du Stebbins analytical models were fitted to update parameters with the new dataset. Then, partially Bayesian neural networks, Gaussian process regressor, and heteroskedastic deterministic neural networks were evaluated. The ML models examined all have different strategies to overcome the potential for overfitting as a result of a limited training dataset, and return results that account for model uncertainty, which can be valuable for understanding model reliability. For the first time, cooling rate is introduced as an input parameter for ML models, showing consistent improvements in performance and solidifying the importance of including parameters outside of composition alone for N4 prediction. The machine learning models examined here show promise in accurate predictions of boron coordination in borosilicate glasses, all achieving R2 values of 0.91.

boron coordination↗

Time Series Foundation Models and Deep Learning Architectures for Earthquake Temporal and Spatial Nowcasting

Advancing the capabilities of earthquake nowcasting, the real-time forecasting of seismic activities, remains crucial for reducing casualties. This multifaceted challenge has recently gained attention within the deep learning domain, facilitated by the availability of extensive earthquake datasets. Despite significant advancements, the existing literature on earthquake nowcasting lacks comprehensive evaluations of pre-trained foundation models and modern deep learning architectures; each focuses on a different aspect of data, such as spatial relationships, temporal patterns, and multi-scale dependencies. This paper addresses the mentioned gap by analyzing different architectures and introducing two innovative approaches called Multi Foundation Quake and GNNCoder. We formulate earthquake nowcasting as a time series forecasting problem for the next 14 days within 0.1-degree spatial bins in Southern California. Earthquake time series are generated using the logarithm energy released by quakes, spanning 1986 to 2024. Our comprehensive evaluations demonstrate that our introduced models outperform other custom architectures by effectively capturing temporal-spatial relationships inherent in seismic data. The performance of existing foundation models varies significantly based on the pre-training datasets, emphasizing the need for careful dataset selection. However, we introduce a novel method, Multi Foundation Quake, that achieves the best overall performance by combining a bespoke pattern with Foundation model results handled as auxiliary streams.

97 MATHEMATICS AND COMPUTING↗