Data-Driven Closure Modeling in Sparsely Observed Dynamical Systems
Our collaborators at Texas A&M will be presenting this work.
Drennan, Daniel [Texas A&M University]↗
SEARCH · Search NASA
Results for “sparse data”
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.
3D Geologic Framework Modelling of the Los Alamos National Laboratory Site and Pajarito Plateau: Integrating a realistic 3D fault network and modelling subsurface relationships in a sparsely sampled and complex geologic region
The subsurface geology beneath the Pajarito Plateau is critical to understanding the seismic hazard of the Pajarito Fault System, yet our understanding of this geology is relatively poor. While previous 3D geologic framework models of the area have been created for the purposes of understanding hydrogeologic flow, they are inadequate for the purposes of understanding the Pajarito Fault System. The specific challenges of using oil and gas software for this purpose include: (1) the geologic complexities resulting from volcanism and tectonism; (2) a need for a high level of stratigraphic detail over a large area; (3) a near complete lack of seismic data; and (4) sparse wellbore data. Presented here is a workflow that handles these challenges of adapting commercially available software used by the oil and gas industries to this seismic hazard problem.
58 GEOSCIENCES↗
powersqueeze
powersqueeze (psqz) is a truncated power iteration library intended for high-performance computing platforms. psqz efficiently produces low-dimensional, linear measurements of graph matrix spectra by combining classical power iteration with sparse Johnson-Lindenstrauss transforms. psqz is intended to produce high-quality, fast, data-oblivious low-dimensional representations of high-dimensional sparse data such as graphs and term-document matrices. psqz is intended to replace similar workflows that depend on directly approximating a truncated eigendecomposition (e.g., the first step of spectral clustering), which is a much more expensive operation.
Priest, BenjaminW [Lawrence Livermore National Lab↗
Accelerating GNNs on GPU Sparse Tensor Cores through N:M Sparsity-Oriented Graph Reordering
Recent advancements in GPU hardware support have introduced the capability to leverage N:M sparse patterns for substantial performance gains. Graphs in Graph Neural Networks (GNNs) are typically sparse, but the sparsity is often irregular, not conforming to such sparse patterns. In this paper, we propose a novel graph reordering algorithm, the first of its kind, to reshape irregular graph data into the N:M structured sparse pattern at the tile level, allowing linear-algebra-based graph operations in GNNs to benefit from the N:M sparse hardware. The optimization is lossless, maintaining the accuracy of GNN. It can remove 98-100\% violations of the N:M sparse patterns at the vector level, and increase the proportion of conforming graphs in SuiteSparse collection from 5-9\% to 88.7-93.5\%. On A100 GPUs, the optimization accelerates Sparse Matrix Matrix (SpMM) by up to 43X (2.3X -- 7.5X on average) and speeds up the key graph operations in GNNs on real graphs by as much as 8.6X (3.5X on average).
artificial intelligence, graph neural networks↗
Prong Segmentation using Point Set Transformers in Multiple View Neutrino Detectors
NOvA is a long-baseline neutrino experiment studying neutrino oscillations by detecting neutrinos from the NuMI beam at Fermilab. Its physics analysis relies on accurate prong segmentation, which involves matching each hit to its source particle and identifying the particle type. This task has commonly been addressed using a combination of traditional clustering algorithms and convolutional neural networks (CNNs). However, NOvA’s detector design presents data as two sparse and decoupled 2D images (XZ and YZ views) rather than a native 3D representation, posing a significant challenge for traditional CNN-based models. In this talk, we propose a novel neural network based on the Point Set Transformer. By treating detector hits as sparse point clouds and implementing a cross-view attention mechanism, our model enables efficient information mixing between both views. Evaluated on NOvA simulated data, our model achieves superior accuracy while requiring significantly fewer computational resources compared to other models. Furthermore, the model demonstrates great performance when applied to Liquid Argon Time Projection Chamber (LArTPC) data, which shows its potential as a universal prong segmentation algorithm for multiple view neutrino detectors.
Liu, Jiaxi [UC, Irvine]↗
Machine Learning Based Metamodel for Faster Life Cycle Assessment of Large Portfolio of Buildings
Managing a large portfolio of buildings involves decisions on reuse, retrofit, renovation, rehabilitation, and new construction, influenced by trade-offs between performance metrics such as cost, time, and operational flexibility over the building's life cycle. Traditional life cycle assessment tools for evaluating these metrics can be labor- and compute-intensive, requiring extensive data and modeling for each building. Metamodels (or surrogate models) using machine learning have been explored as faster alternatives, but training these models has been hindered by the limited availability of comprehensive data on key life cycle metrics. Recent advancements in machine learning, particularly deep learning techniques like zero-shot and few-shot learning, allow models to learn from sparse or limited data. We propose a machine learning-based metamodel that leverages these techniques for rapid estimation of key building life cycle metrics. This presentation will cover the model architecture, data collection, training, and validation processes, along with an ongoing case study applied to a large portfolio of buildings. We will discuss the model's performance in terms of accuracy, compute time, limitations, and its potential for expanding to additional life cycle metrics. This data-driven approach offers a promising direction for the rapid evaluation of large building portfolios.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
BCSR on GPU: A Way Forward Extreme-scale Graph Processing on Accelerator-enabled Frontier Supercomputer
Handling large graphs in a distributed environment requires effective partitioning across processors and efficient management of local partitions. In 2D partitioning, local graphs often become too sparse, making memory-efficient data structures crucial. Using the Compressed Sparse Row (CSR) format wastes space, especially for > 83% of vertices with empty edges for the sparse graphs. This study explores bit-CSR (BCSR), a modified CSR representation, on GPUs to reduce memory usage in graph computations. We achieved 16.67% memory savings on a sparse rmat dataset with 268 million vertices and 357 million edges, without performance degradation, supported by both theoretical and experimental storage savings of 33%. However, we observed a 1.7× slowdown in degree lookup times due to bitwise operations on AMD CPUs. This analysis highlights the potential of BCSR on GPUs for improving Graph500 benchmark performance on GPU-accelerated systems, such as the Frontier supercomputer.
Sattar, Naw Safrin↗
AEPF: Attention-Enabled Point Fusion for 3D Object Detection
Current state-of-the-art (SOTA) LiDAR-only detectors perform well for 3D object detection tasks, but point cloud data are typically sparse and lacks semantic information. Detailed semantic information obtained from camera images can be added with existing LiDAR-based detectors to create a robust 3D detection pipeline. With two different data types, a major challenge in developing multi-modal sensor fusion networks is to achieve effective data fusion while managing computational resources. With separate 2D and 3D feature extraction backbones, feature fusion can become more challenging as these modes generate different gradients, leading to gradient conflicts and suboptimal convergence during network optimization. To this end, we propose a 3D object detection method, Attention-Enabled Point Fusion (AEPF). AEPF uses images and voxelized point cloud data as inputs and estimates the 3D bounding boxes of object locations as outputs. An attention mechanism is introduced to an existing feature fusion strategy to improve 3D detection accuracy and two variants are proposed. These two variants, AEPF-Small and AEPF-Large, address different needs. AEPF-Small, with a lightweight attention module and fewer parameters, offers fast inference. AEPF-Large, with a more complex attention module and increased parameters, provides higher accuracy than baseline models. Experimental results on the KITTI validation set show that AEPF-Small maintains SOTA 3D detection accuracy while inferencing at higher speeds. AEPF-Large achieves mean average precision scores of 91.13, 79.06, and 76.15 for the car class’s easy, medium, and hard targets, respectively, in the KITTI validation set. Results from ablation experiments are also presented to support the choice of model architecture.
Chemistry↗
Predicting Drug Effects from High-dimensional Asymmetric Drug Data Sets using Graph Neural Networks: A Comprehensive Analysis of Multi-target Drug Effect Prediction
Graph neural networks (GNNs) have emerged as one of the most effective Machine learning (ML) techniques for drug effect prediction from drug molecular graphs. Despite having immense potential, GNN models lack performance when using data sets that contain high dimensional asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects is beyond practicality. Such an implication provides a testbed to address this challenge as multi-target prediction problems, aiming to predict all drug effects at a time. We develop standard and hybrid graph neural networks (GNNs)to perform two separate tasks that are multi-regression for continuous values and multi-label classification for categorical values contained in our data sets. Since this step makes the target data even more sparse and introduces asymmetric label co-occurrence, the learning of multi-label classification models becomes difficult and heavily impacts the GNN's performance. To address these challenges, we propose a new data oversampling technique to improve multi-label classification performances on all the given imbalanced molecular graph data sets. Using the technique, we improve the data imbalance ratio of the drug effects better than before while protecting the data set's integrity. Finally, we evaluate multi-label classification performance using the best-performant hybrid GNN model on all the oversampled data sets obtained from the proposed oversampling technique. These results outperform those of other ML models including GNN models when they are trained on the original data sets or oversampled data sets using MLSMOTE (a well-known oversampling technique) in all evaluation metrics precision, recall, and F1 score by a significant margin.
Bose, Avishek [ORNL]↗
Subspace-Driven Learning for Anomaly Detection in Process Transients
Nuclear power plant (NPP) monitoring and diagnostic centers are actively investigating and implementing automated anomaly detection algorithms to help plants catch anomalies sooner, thereby preventing or reducing the duration of unexpected shutdowns. Current machine learning-based anomaly detection methods are expected to be highly effective during stable, full-power operations because NPPs typically operate as baseload power generators, meaning there are extensive operating data available from plant equipment. However, it is expected that anomaly detection methods will face significant challenges during transient conditions (i.e., when power output falls below full power) because plants only occasionally operate at these lower power levels, generating sparse transient operational data, and resulting in false alarms or missed detections. Here, to address this issue, transfer learning is used, which for this problem leverages knowledge (in the form of learned features) from stable, full-power operations to improve detection accuracy during transient conditions, even with limited data. In this effort, a novel subspace approach is developed to transfer a subset of the data features from full power operation to transients. This approach is validated through experiments using synthetic data and was found to outperform two baseline transfer learning approaches in anomaly detection performance across a range of amounts of transient data used in the training process.
46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
Informing forest carbon inventories under the Paris Agreement using ground-based forest monitoring data
Human interactions with forests have shaped Earth's climate for millennia and will continue to do so as we target net-zero emission goals. Accurately characterizing these climate impacts requires making reliable forest carbon data available for forest monitoring and planning. Here, we develop a semi-automated process for submitting forest carbon measurements from the largest relevant scientific database to the International Panel on Climate Change's Emission Factor Database, which currently has sparse forest carbon data. Building this bridge from scientific research to international policy is an important step towards managing forests in a net-zero motivated future. Humans have been influencing Earth's climate via transformative impacts on forests for millennia, and forests are now recognized as critical to climate change mitigation under the Paris Agreement. The efficacy of climate change mitigation planning and reporting depends on quality data on forest carbon (C) stocks and changes. The Emission Factor Database (EFDB) of the International Panel on Climate Change (IPCC) is intended to be a definitive source for such data, but needs comprehensive and well-documented data to be so. To facilitate submission of forest C estimates from scientific studies to EFDB, we develop and document a process for semi-automated data submission from the Global Forest C database (ForC v4.0), which is the largest compilation of ground-based forest C estimates. We then assess the data currently available through ForC and provide recommendations for improving forest data collection, analysis, and reporting. As of September 2024, ForC contained ~19,286 records potentially relevant to EFDB, 1068 of which had been submitted and posted to EFDB. These represented 19% of the total EFDB records for forest land. Records were unevenly distributed across variables and geographic regions. ForC records (37%) reviewed could not be submitted because the original publication lacked required information. In the future, ground-based forest C estimates should target gaps in the record, and studies should ensure that they report all information necessary for inclusion in EFDB. Given that climate change is rapidly impacting the world's forests, timely reporting of recent estimates will be critical to accurate forest C inventories.
54 ENVIRONMENTAL SCIENCES↗
Predicting Open Quantum Dynamics with Data-Informed Quantum-Classical Dynamics
We introduce a data-informed quantum-classical dynamics (DIQCD) approach for predicting the evolution of an open quantum system. The equation of motion in DIQCD is a Lindblad equation with a flexible, time-dependent Hamiltonian that can be optimized to fit sparse and noisy data from local observations of an extensive open quantum system. We demonstrate the accuracy and efficiency of DIQCD for both experimental and simulated quantum devices. We show that DIQCD can predict entanglement dynamics of ultracold molecules (calcium fluoride) in optical tweezer arrays. DIQCD also successfully predicts carrier mobility in organic semiconductors (rubrene) with accuracy comparable to nearly exact numerical methods.
Lindblad equation↗
Exploring the Whole Set of Accurate Sparse Interpretable Models
In data science applications, there are often many models that fit the data well. This phenomenon was called the Rashomon Effect by Leo Breiman. The set of good models is called the Rashomon Set, and the goal of this project is to locate, store, and study the Rashomon sets for classes of interpretable models, including decision trees and generalized additive models.
97 MATHEMATICS AND COMPUTING↗
Uncertainty-Guided Prediction Horizon of Phase-Resolved Ocean Wave Forecasting Under Data Sparsity: Experimental and Numerical Evaluation
Accurate short-term wave forecasting is critical for the safe and efficient operation of marine structures that rely on real-time, phase-resolved ocean wave information for control and monitoring purposes (e.g., digital twins). These systems often depend on environmental sensors (e.g., waverider buoys, wave-sensing LIDAR). Challenges arise when upstream sensor data are missing, sparse, or phase-shifted due to drift. This study investigates the performance of two machine learning models, time-series dense encoder (TiDE) and long short-term memory (LSTM), for forecasting phase-resolved ocean surface elevations under varying degrees of data degradation. We introduce the τ-trimming algorithm, which adapts the prediction horizon based on uncertainty thresholds derived from historical forecasts. Numerical wave tank (NWT) and wave basin experiments are used to benchmark model performance under short- and long-term data masking, spatially coarse sensor grids, and upstream phase shifts. Results show under a 50% probability of upstream data loss, the τ-trimmed TiDE model achieves a 46% reduction in error at the most upstream target, compared to 22% for LSTM. Furthermore, phase misalignment in upstream data introduces a near-linear increase in forecast error. Under moderate model settings, a ±3 s misalignment increases the mean absolute error by approximately 0.5 m, while the same error is accumulated at ±4 s using the more conservative approach. These findings inform the design of resilient, uncertainty-aware wave forecasting systems suited for realistic offshore sensing environments.
42 ENGINEERING↗
Grid Topology Discovery Algorithm Evaluation of Suitability for Utility Deployment (CRADA 606 Final Report)
This work presents the results of a field-informed demonstration aimed at evaluating the practical suitability of a topology discovery algorithm for utility environments. We demonstrated an algorithm that uses a graph-theory-informed state estimation approach for model selection. In collaboration with Survalent and Peninsula Light Co., the algorithm was applied to real feeder models and field measurements from supervisory control and data acquisition (SCADA) and advanced metering infrastructure (AMI) systems to identify the operational topology of a power distribution system. The demonstration assessed the algorithm’s performance under realistic data conditions, including sparse and noisy measurements, and examined its ability to identify the most likely network configurations. The results confirmed that the approach can effectively narrow down feasible topologies, providing operators with improved situational awareness of network status. Key lessons learned emphasize the need for systematic data validation and strategic sensor placement to enhance observability. These insights inform future deployment strategies and guide refinements for broader adoption in utility operations.
24 POWER TRANSMISSION AND DISTRIBUTION↗
A ModEx Framework for Watershed Subsurface Investigation With Limited Geophysical Data Using Machine Learning and Hydrologic Modeling
Abstract Subsurface heterogeneity influences watershed hydrology strongly but remains difficult to characterize at catchment scales with sparse and costly field data. Geophysical surveys such as electromagnetic induction (EMI) provide local spatial subsurface images yet scaling them to watershed scales and converting EMI‐derived resistivity into hydraulic properties remains a challenge. We present a Model–Experiment (ModEx) framework that integrates limited EMI data with machine learning (ML) and hydrologic modeling to improve process representation and guide field investigations. Sparse EMI surveys were scaled to the catchment scale using a Random Forest model, and the resulting resistivity fields were combined with nearby borehole constraints to parameterize a hydrologic model. The EMI‐informed hydrological simulations improved predictions of streamflow sustained by subsurface flow and shallow saturation patterns. By combining EMI data and ML with hydrologic modeling, the ModEx framework guides future subsurface surveys, providing a transferable and efficient strategy for data–model integration across diverse watersheds. Plain Language Summary Mapping the underground network of soil and rock that controls water is essential for predicting floods and droughts, but seeing underground is difficult and expensive. We cannot drill everywhere, so scientists use geophysical tools to scan broad areas. There are two key challenges: these geophysical scans are often sparse across the whole watershed, and the geophysical data is hard to translate into water‐related properties. We used artificial intelligence to solve these problems. We taught a computer to find patterns linking the limited geophysical data to the land surface properties. This allowed it to fill in the gaps and create a complete, useful subsurface map for the entire watershed. This new map improves hydrologic simulations, leading to more accurate predictions of water movement in the watershed. It also helps scientists build better models with less data and generates a priority map showing where to measure next, making future investigations more efficient. Key Points Limited EMI scaled with ML improves catchment‐scale subsurface parameterization for hydrologic models The framework integrates hydrologic modeling with limited geophysical data to support subsurface investigation design ModEx framework offers a transferable data–model integration strategy that quantifies and reduces uncertainty guiding watershed studies
Chen, Hang↗
Machine Learning Eliminates Reanalysis Warm Bias and Reveals Weaker Winter Surface Cooling Over Arctic Sea Ice
The surface energy budget governs Arctic sea-ice growth/melt, yet observations are sparse, and reanalysis data sets suffer from systematic biases. Here, we train a neural network with observational data to bias-correct hourly ERA5 fluxes over Arctic ice-covered regions (≥70°N; sea-ice concentration >80%) for 1994–2024. Training data cover two full seasonal cycles and different sea-ice regimes. The neural network reduces RMSE for net shortwave radiation by ∼40%, downward longwave radiation by ∼16% and the total surface energy budget by ∼55%, eliminating the wintertime warm bias of ∼4 K in ERA5. Wintertime surface cooling is reduced by ∼50%, yielding thermodynamic ice-growth estimates of ∼80–120 cm, consistent with SMOS–CryoSat satellite thickness increases and in contrast to the 150–200 cm growth implied by ERA5. Our bias-corrected data capture the observed clear/cloudy states of the winter boundary layer and can be used to study Arctic climatology, evaluate climate models and drive sea-ice-ocean models.
Hossain, Akil [Alfred Wegener Institute for Polar ↗
Bayesian Gaussian process inference for neutron spin echo measurement
Neutron spin echo (NSE) spectroscopy provides unique access to microscopic dynamics, but its application is often constrained by low neutron flux, long acquisition times, and significant noise. Here, we present a Bayesian inference approach based on Gaussian process regression (GPR) to reconstruct high-quality spin echo signals from sparse and noisy data by exploiting correlations in reciprocal space. Benchmarks on synthetic datasets and validation with experimental NSE measurements of dendrimers show that GPR suppresses noise, interpolates missing intensity values, and accommodates irregular observations. The method improves accuracy, shortens acquisition times, and enables high-throughput and real-time studies. Beyond NSE, the framework is broadly applicable to other low signal-to-noise ratio scattering techniques, thereby extending the scope of neutron spectroscopy.
Tung, Chi-Huan [Oak Ridge National Laboratory (ORN↗