Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “science data network”

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 1,261 records · Page 70

Predicting Local Material Thickness from Steady-State Ultrasonic Wavefield Measurements Using a Convolutional Neural Network

Acoustic steady-state excitation spatial spectroscopy (ASSESS) is a full-field, ultrasonic non-destructive evaluation (NDE) technique used to locate and characterize defects in plate-like structures. ASSESS generates a steady-state, single-tone ultrasonic excitation in a structure and a scanning laser Doppler Vibrometer (LDV) measures the resulting full-field surface velocity response. Traditional processing techniques for ASSESS data rely on wavenumber domain analysis. This paper presents the alternative use of a convolutional neural network (CNN), trained using simulated ASSESS data, to predict the local plate thickness at every pixel in the wavefield measurement directly. The defect detection accuracy of CNN-based thickness predictions are shown to improve for defects of greater size, and for defects with higher thickness reductions. The CNN demonstrates the ability to predict thickness accurately in regions where Lamb wave dispersion relations are complex or unknown, such as near the boundaries of a test specimen, so long as the CNN is trained on data that accounts for these regions. The CNN also shows generalizability to ASSESS experimental data, despite an entirely simulated training dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Data from: “Enabling FAIR data in Earth and environmental science with community-centric (meta)data reporting formats”

This dataset contains supplementary information for a manuscript describing the ESS-DIVE (Environmental Systems Science Data Infrastructure for a Virtual Ecosystem) data repository's community data and metadata reporting formats. The purpose of creating the ESS-DIVE reporting formats was to provide guidelines for formatting some of the diverse data types that can be found in the ESS-DIVE repository. The 6 teams of community partners who developed the reporting formats included scientists and engineers from across the Department of Energy National Lab network. Additionally, during the development process, 247 individuals representing 128 institutions provided input on the formats. The primary files in this dataset are 10 data and metadata crosswalk for ESS-DIVE’s reporting formats (all files ending in _crosswalk.csv). The crosswalks compare elements used in each of the reporting formats to other related standards and data resources (e.g., repositories, datasets, data systems). This dataset also contains additional files recommended by ESS-DIVE’s file-level metadata reporting format. Each data file has an associated dictionary (files ending in _dd.csv) which provide a brief description of each standard or data resource consulted in the data reporting format development process. The flmd.csv file describes each file contained within the dataset.

54 ENVIRONMENTAL SCIENCES↗

Multisensor Machine Learning to Retrieve High Spatiotemporal Resolution Land Surface Temperature

Climate change is making heat waves more frequent, long-lasting, and severe. While multiple satellite types provide data to monitor surface temperature, geostationary (GEO) sensors provide near-continuous, continental-scale observations which can better capture the diurnal variability of land surface temperature (LST) than intermittent observations from low-earth orbit (LEO) sensors. However, standard products from GEO satellites are available at coarsened spatial and temporal resolutions compared to the native sensor resolution. Using datasets from the NASA Earth Exchange, we leveraged co-located, co-temporal observations from LEO and GEO satellites to learn a data-driven mapping using a convolutional neural network. The resulting NASA Earth eXchange Artificial Intelligence LST (NEXAI-LST) achieved a mean absolute error of 1.73 K relative to the target LEO product and improves on both spatial and temporal resolution [2 km, 10 minute] compared to the GEO full disk standard product [10 km, hourly]. In validation against measurements from a ground-based sensor network, NEXAI-LST achieves similar or better fit than both LEO and GEO standard products, while depending none of the prior knowledge of land surface and atmospheric states required by physical-statistical models. Further, application of the model to unseen LEO and GEO satellites demonstrates robust generalization of the model across spatial region, time of day, and sensor. In support of NASA’s open-source science initiative, we make our NEXAI-LST product, model, and codes available to facilitate data exploration and further studies.

Kate Marie Duffy↗

CHESS 2025: Crown polygons and extracted reflectance for field sampling sites

This dataset contains (1) crown polygons for each tree, meadow, and shrub site sampled in the 2025 Colorado Headwaters Ecological Spectroscopy Study (CHESS) campaign (in geojson format, .geojson) and (2) extracted reflectance, uncertainty, and shade estimates for each crown polygon from the 2018 National Ecological Observatory Network (NEON) and 2025 CHESS campaigns. (in CSV format, .csv). Additional metadata are provided in a data dictionary describing column names and definitions (dd.csv), and in a file-level metadata file (flmd.csv). Crown polygons were manually delineated for each site in the 2025 campaign using a combination of field-collected GPS data (doi:10.15485/3022418), RGB (red, green, blue) and false color reflectance mosaics (doi:10.15485/3013535), and LiDAR-derived (Light Detection and Ranging) canopy height (CHM) and digital surface (DSM) models (DOI and citation to be added upon publication). Where there was misalignment between the spectrometer- and LiDAR-derived data products, polygons prioritized alignment with the spectrometer-derived data products. Polygons were delineated conservatively to only select pixels representative of vegetation samples collected in the field. Crown polygons for 2018 are published at (doi:10.15485/1618130) and were developed using the same protocol. For each polygon, all pixels from all flightlines were extracted where the pixel centroid was contained within the polygon. For each pixel, we extracted the surface reflectance, uncertainty, and shade estimates. Details on the extracted datasets are available at (doi:10.15485/3013527, doi:10.15485/3013535). CHESS Project Description: The Colorado Headwaters Ecological Spectroscopy Study (CHESS) comprised a multi-week airborne remote sensing and field observation campaign in the Upper Gunnison Basin, Colorado, conducted in June and July of 2025. Airborne remote sensing was conducted by the National Ecological Observatory Network Airborne Observation Platform (NEON AOP), concurrent with a field campaign run by the Rocky Mountain Biological Laboratory (RMBL), the Lawrence Berkeley National Laboratory (LBNL) and SLAC National Accelerator Laboratory Watershed Function Science Focus Area (SFA), and NASA-JPL (Jet Propulsion Laboratory) Earth Surface Mineral Dust Source Investigation (EMIT) program. Between June 10 and July 18, 2025, the NEON AOP flight team collected high-resolution aerial imaging spectroscopy and Light Detection and Ranging (LiDAR) data over three domains: the Upper East River (CRBU), Almont Triangle (ALMO), and the Upper Taylor Basin (UPTA). In coordination with the flights, a field campaign acquired ground-truth observations, including observations of vegetation composition, foliar traits, forest demography, and subsurface properties in 18 core sampling areas within the domains. Additional surface water observations were taken at over 380 point locations. All CHESS campaign datasets can be found within the CHESS ESS-DIVE data portal: https://data.ess-dive.lbl.gov/portals/chess. Funding Acknowledgment: This research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration (80NM0018D0004) and was funded by EMIT Extended Mission Phase E Science.

2018 NEON and 2025 CHESS Campaigns↗

Learning Constitutive Relations From Soil Moisture Data via Physically Constrained Neural Networks

Abstract The constitutive relations of the Richardson‐Richards equation encode the macroscopic properties of soil water retention and conductivity. These soil hydraulic functions are commonly represented by models with a handful of parameters. The limited degrees of freedom of such soil hydraulic models constrain our ability to extract soil hydraulic properties from soil moisture data via inverse modeling. We present a new free‐form approach to learning the constitutive relations using physically constrained neural networks. We implemented the inverse modeling framework in a differentiable modeling framework, JAX, to ensure scalability and extensibility. For efficient gradient computations, we implemented implicit differentiation through a nonlinear solver for the Richardson‐Richards equation. We tested the framework against synthetic noisy data and demonstrated its robustness against varying magnitudes of noise and degrees of freedom of the neural networks. We applied the framework to soil moisture data from an upward infiltration experiment and demonstrated that the neural network‐based approach was better fitted to the experimental data than a parametric model and that the framework can learn the constitutive relations.

54 ENVIRONMENTAL SCIENCES↗

Inferring microbial co-occurrence networks from amplicon data: a systematic evaluation

Microbes commonly organize into communities consisting of hundreds of species involved in complex interactions with each other. 16S ribosomal RNA (16S rRNA) amplicon profiling provides snapshots that reveal the phylogenies and abundance profiles of these microbial communities. These snapshots, when collected from multiple samples, can reveal the co-occurrence of microbes, providing a glimpse into the network of associations in these communities. However, the inference of networks from 16S data involves numerous steps, each requiring specific tools and parameter choices. Moreover, the extent to which these steps affect the final network is still unclear. In this study, we perform a meticulous analysis of each step of a pipeline that can convert 16S sequencing data into a network of microbial associations. Through this process, we map how different choices of algorithms and parameters affect the co-occurrence network and identify the steps that contribute substantially to the variance. We further determine the tools and parameters that generate robust co-occurrence networks and develop consensus network algorithms based on benchmarks with mock and synthetic data sets. The Microbial Co-occurrence Network Explorer, or MiCoNE (available at https://github.com/segrelab/MiCoNE) follows these default tools and parameters and can help explore the outcome of these combinations of choices on the inferred networks. We envisage that this pipeline could be used for integrating multiple data sets and generating comparative analyses and consensus networks that can guide our understanding of microbial community assembly in different biomes.

16S rRNA↗

Soil Moisture Active Passive Mission L4_SM Data Product Assessment (Version 2 Validated Release)

During the post-launch SMAP calibration and validation (Cal/Val) phase there are two objectives for each science data product team: 1) calibrate, verify, and improve the performance of the science algorithm, and 2) validate the accuracy of the science data product as specified in the science requirements and according to the Cal/Val schedule. This report provides an assessment of the SMAP Level 4 Surface and Root Zone Soil Moisture Passive (L4_SM) product specifically for the product's public Version 2 validated release scheduled for 29 April 2016. The assessment of the Version 2 L4_SM data product includes comparisons of SMAP L4_SM soil moisture estimates with in situ soil moisture observations from core validation sites and sparse networks. The assessment further includes a global evaluation of the internal diagnostics from the ensemble-based data assimilation system that is used to generate the L4_SM product. This evaluation focuses on the statistics of the observation-minus-forecast (O-F) residuals and the analysis increments. Together, the core validation site comparisons and the statistics of the assimilation diagnostics are considered primary validation methodologies for the L4_SM product. Comparisons against in situ measurements from regional-scale sparse networks are considered a secondary validation methodology because such in situ measurements are subject to up-scaling errors from the point-scale to the grid cell scale of the data product. Based on the limited set of core validation sites, the wide geographic range of the sparse network sites, and the global assessment of the assimilation diagnostics, the assessment presented here meets the criteria established by the Committee on Earth Observing Satellites for Stage 2 validation and supports the validated release of the data. An analysis of the time average surface and root zone soil moisture shows that the global pattern of arid and humid regions are captured by the L4_SM estimates. Results from the core validation site comparisons indicate that "Version 2" of the L4_SM data product meets the self-imposed L4_SM accuracy requirement, which is formulated in terms of the ubRMSE: the RMSE (Root Mean Square Error) after removal of the long-term mean difference. The overall ubRMSE of the 3-hourly L4_SM surface soil moisture at the 9 km scale is 0.035 cubic meters per cubic meter requirement. The corresponding ubRMSE for L4_SM root zone soil moisture is 0.024 cubic meters per cubic meter requirement. Both of these metrics are comfortably below the 0.04 cubic meters per cubic meter requirement. The L4_SM estimates are an improvement over estimates from a model-only SMAP Nature Run version 4 (NRv4), which demonstrates the beneficial impact of the SMAP brightness temperature data. L4_SM surface soil moisture estimates are consistently more skillful than NRv4 estimates, although not by a statistically significant margin. The lack of statistical significance is not surprising given the limited data record available to date. Root zone soil moisture estimates from L4_SM and NRv4 have similar skill. Results from comparisons of the L4_SM product to in situ measurements from nearly 400 sparse network sites corroborate the core validation site results. The instantaneous soil moisture and soil temperature analysis increments are within a reasonable range and result in spatially smooth soil moisture analyses. The O-F residuals exhibit only small biases on the order of 1-3 degrees Kelvin between the (re-scaled) SMAP brightness temperature observations and the L4_SM model forecast, which indicates that the assimilation system is largely unbiased. The spatially averaged time series standard deviation of the O-F residuals is 5.9 degrees Kelvin, which reduces to 4.0 degrees Kelvin for the observation-minus-analysis (O-A) residuals, reflecting the impact of the SMAP observations on the L4_SM system. Averaged globally, the time series standard deviation of the normalized O-F residuals is close to unity, which would suggest that the magnitude of the modeled errors approximately reflects that of the actual errors. The assessment report also notes several limitations of the "Version 2" L4_SM data product and science algorithm calibration that will be addressed in future releases. Regionally, the time series standard deviation of the normalized O-F residuals deviates considerably from unity, which indicates that the L4_SM assimilation algorithm either over- or under-estimates the actual errors that are present in the system. Planned improvements include revised land model parameters, revised error parameters for the land model and the assimilated SMAP observations, and revised surface meteorological forcing data for the operational period and underlying climatological data. Moreover, a refined analysis of the impact of SMAP observations will be facilitated by the construction of additional variants of the model-only reference data. Nevertheless, the “Version 2” validated release of the L4_SM product is sufficiently mature and of adequate quality for distribution to and use by the larger science and application communities.

SMAP L4_SM↗

Enhanced Multi-Modal Access to Planetary Exploration

Tomorrow's Interplanetary Network (IPN) will evolve from JPL's Deep-Space Network (DSN) and provide key capabilities to future investigators, such as simplified acquisition of higher-quality science at remote sites and enriched access to these sites. These capabilities could also be used to foster public interest, e.g., by making it possible for students to explore these environments personally, eventually perhaps interacting with a virtual world whose models could be populated by data obtained continuously from the IPN. Our paper looks at JPL's approach to making this evolution happen, starting from improved communications. Evolving space protocols (e.g., today's CCSDS proximity and file-transfer protocols) will provide the underpinning of such communications in the next decades, just as today's rich web was enabled by progress in Internet Protocols starting from the early 1970's (ARPAnet research). A key architectural thrust of this effort is to deploy persistent infrastructure incrementally, using a layered service model, where later higher-layer capabilities (such as adaptive science planning) are enabled by earlier lower-layer services (such as automated routing of object-based messages). In practice, there is also a mind shift needed from an engineering culture raised on point-to-point single-function communications (command uplink, telemetry downlink), to one in which assets are only indirectly accessed, via well-defined interfaces. We are aiming to foster a 'community of access' both among space assets and the humans who control them. This enables appropriate (perhaps eventually optimized) sharing of services and resources to the greater benefit of all participants. We envision such usage to be as automated in the future as using a cell phone is today - with all the steps in creating the real-time link being automated.

interplanetary network (IPN)↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging computer science approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth-independence and autonomy of mission operations. We present a decadal view of AI/ML architecture to support deep space mission goals, developed in concert with leaders in the field. We describe current AI/ML methods to support 1) fundamental biology, 2) in situ analytics, 3) high performance computing hardware, 4) automated science, 5) self-driving labs, 6) remote data management, 7) integrated real-time mission biomonitoring, and 8) a Precision Space Health system. Cutting-edge AI/ML approaches that can be integrated to support these domains include active learning, explainable AI, adaptive learning, causal inference, knowledge graphs, federated learning, transfer learning, and large language models. Finally, we present results from several current ML projects that are underway in the field to address key challenges of small sample n, high feature count, heterogeneity, and sparse data. These include 1) connecting omics data to phenotypic data using an ensemble model to infer causality of spaceflight rodent liver health disruption, 2) usage of explainable ML to interrogate the muscular underpinnings of spaceflight muscle atrophy, 3) ML models analyzing and determining directed acyclic graphs of human space health risk leveraging rodent bone datasets, 4) usage of large pre-trained models connecting biomedical knowledgebases with small spaceflight datasets to understand gene-to-gene interaction networks, and 5) a suite of benchmarked open science datasets (spaceflight mouse liver; radiation DNA damage) enabling programmers to identify the best ML algorithms to answer space biological science questions.

space biology↗

JANUS: Resilient and Adaptive Data Transmission for Enabling Timely and Efficient Cross-Facility Scientific Workflows

In modern science, the growing complexity of large-scale scientific projects has led to an increasing reliance on cross-facility scientific workflows, where resources and expertise from multiple institutions and geographic locations are leveraged to accelerate scientific discovery. These workflows often require transmitting huge amounts of scientific data through wide-area networks. Although high-speed networks like ESnet and transfer services such as Globus have improved data mobility, several challenges remain. The sheer volume of data can overwhelm network bandwidth, widely used transport protocols such as TCP suffer from inefficiencies due to retransmissions triggered by packet loss, and existing fault-tolerance mechanisms like erasure coding introduce substantial overhead. In this paper, we propose Janus, a resilient and adaptable data transmission approach designed for cross-facility scientific workflows. Unlike traditional TCP-based methods, Janus leverages UDP, integrates erasure coding for fault tolerance, and combines it with error-bounded lossy compression to reduce overhead. This novel design allows users to balance data transmission time and accuracy, optimizing transfer performance based on specific scientific requirements. Additionally, Janus dynamically adjusts erasure coding parameters in response to real-time network conditions, ensuring efficient data transfers even in fluctuating environments. We develop optimization models for determining ideal configurations and implement adaptive data transfer protocols to enhance reliability. Through extensive simulations and real-network experiments, we demonstrate that Janus significantly improves transfer efficiency while maintaining data fidelity.

Esaulov, Vladislav [Georgia State University, Atla↗

Challenging Implementation and Operations Traditions

The Deep Space Network (DSN) that provides for the communications link between the deep space missions and the science users currently consists of a small set of very large monolithic tracking antennas. This ground-based network includes a total of 12 antennas located in three roughly equidistant longitudes around the earth and utilizes a decentralized approach to it operations. Recently, however, studies have suggested that the number, complexity, and data throughput of the future set of space probes will be increasing dramatically. This demands more performance from the DSN than is currently available. In identifying the architecture for the future DSN required to support this mission set, one concept that proves promising is one that consists of a great many number of much smaller antennas configured in an array. This concept has been supported by the developments in antenna manufacturing technology and the consistent decrease in the cost of electronics required to receive, amplify, and combine signals from deep space probes. Furthermore, it is clear that past developments in the DSN have not benefited from the applications of economies of scale.

ANTENNA ARRAYS↗

Kamodo’s Satellite Constellation Mission Planning Tool

Kamodo provides a functional model-agnostic interface to a growing collection of Heliophysics model outputs. The CCMC, in collaboration with the Geospace Dynamics Constellation Science Team, has recently developed Kamodo’s satellite constellation mission planning tool to perform reconstructions in any pair of dimensions, including time. The ‘reconstruction’ tool enables users to fly any 4-dimensional grid of satellites through a given model data set, reconstructing what the given constellation would observe during the mission. This capability facilitates determination of what satellite configuration is best for a given science question, even allowing comparison across multiple models. This tool, written in Python, is built upon Kamodo’s flythrough tool, which in turn depends on a growing network of model-specific interfaces. Since each model interface is designed with model-agnostic syntax, the flythrough tool and the satellite constellation mission planning tool also feature model-agnostic syntax. In this work, we will describe the basic analysis choices available in the tool and provide a variety of sample workflows. The tool is freely available at https://github.com/nasa/Kamodo for the public. We invite the community to use the reconstruction tool and adapt the provided workflows for their mission planning, and to contribute their own workflows to share with others.

software↗

SM25C-2002: Kamodo’s Satellite Constellation Mission Planning Tool

Kamodo provides a functional model-agnostic interface to a growing collection of Heliophysics model outputs. The CCMC, in collaboration with the Geospace Dynamics Constellation Science Team, has recently developed Kamodo’s satellite constellation mission planning tool to perform reconstructions in any pair of dimensions, including time. The ‘reconstruction’ tool enables users to fly any 4-dimensional grid of satellites through a given model data set, reconstructing what the given constellation would observe during the mission. This capability facilitates determination of what satellite configuration is best for a given science question, even allowing comparison across multiple models. This tool, written in Python, is built upon Kamodo’s flythrough tool, which in turn depends on a growing network of model-specific interfaces. Since each model interface is designed with model-agnostic syntax, the flythrough tool and the satellite constellation mission planning tool also feature model-agnostic syntax. In this work, we will describe the basic analysis choices available in the tool and provide a variety of sample workflows. The tool is freely available at https://github.com/nasa/Kamodo for the public. We invite the community to use the reconstruction tool and adapt the provided workflows for their mission planning, and to contribute their own workflows to share with others.

python↗

CoDA 2014 special issue: Exploring data-focused research across the department of energy: Editorial

Here, this collection of papers, written by researchers at the national labs, in academia, and in industry present real problems, massive and complex datasets, and novel statistical approaches motivated by the challenges presented by experimental and computational science. You'll find explorations of the trajectories of aircraft and of the light curves of supernovae, of computer network intrusions and of nuclear forensics, of photovoltaics and overhead imagery.

97 MATHEMATICS AND COMPUTING↗

Precipitation Science at NASA MSFC

The Precipitation Research Group in NASA MSFC’s Earth Science Branch (ST-11) focuses on observations of precipitation (rain, snow, and hail) from a variety of perspectives: ground-based radars, surface gauge networks, airborne instruments, and spaceborne measurements from onboard satellites. Current work includes identifying signatures of hail and strong thunderstorms from spaceborne measurements and assessing those signatures against multiple satellite datasets and ground-based radar observations. The Precipitation Team is also involved in the development and maintenance of NASA’s global-gridded multi-satellite precipitation product (IMERG) and operating and maintaining the GPM Validation Network (VN): a software package that geometrically matches the reference ground-based weather radar observations with GPM satellite observations in 3D. The team is also responsible for the Advanced Microwave Precipitation Radiometer (AMPR) used in airborne field campaign research, which recently was used to collect data on thunderstorms that produce terrestrial gamma-ray flashes (TGFs) in the Airborne Lightning Observatory for FEGS and TGFs (ALOFT) field campaign. While the Precipitation Group largely supports NASA’s Global Precipitation Measurement (GPM) mission and Precipitation Science Team, the team also looks to the future Precipitation Measurement Mission (PMM) and Investigation of Convective Updrafts (INCUS) missions.

Sarah D Bang↗

COVID-19 dynamics across the US: A deep learning study of human mobility and social behavior

This paper presents a deep learning framework for epidemiology system identification from noisy and sparse observations with quantified uncertainty. The proposed approach employs an ensemble of deep neural networks to infer the time-dependent reproduction number of an infectious disease by formulating a tensor-based multi-step loss function that allows us to efficiently calibrate the model on multiple observed trajectories. The method is applied to a mobility and social behavior-based SEIR model of COVID-19 spread. The model is trained on Google and Unacast mobility data spanning a period of 66 days, and is able to yield accurate future forecasts of COVID-19 spread in 203 US counties within a time-window of 15 days. Interestingly, a sensitivity analysis that assesses the importance of different mobility and social behavior parameters reveals that attendance of close places, including workplaces, residential, and retail and recreational locations, has the largest impact on the effective reproduction number. Furthermore, the model enables us to rapidly probe and quantify the effects of government interventions, such as lock-down and re-opening strategies. Taken together, the proposed framework provides a robust workflow for data-driven epidemiology model discovery under uncertainty and produces probabilistic forecasts for the evolution of a pandemic that can judiciously provide information for policy and decision making. All codes and data accompanying this manuscript are available at https://github.com/PredictiveIntelligenceLab/DeepCOVID19.

60 APPLIED LIFE SCIENCES↗