Micro-kinetic modeling of temporal analysis of products data using kinetics-informed neural networks
Kinetics-informed neural networks improve fit quality for multi-pulse and noisy temporal analysis of products datasets.
Nai, Dingqi↗
SEARCH · Search NASA
Results for “Temporal modeling”
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.
Modeling the temporal network dynamics of neuronal cultures
Not Available
59 BASIC BIOLOGICAL SCIENCES↗
Algae under attack: Mathematical modeling of temporal population dynamics between biofuel-relevant microalgae and predatory bacteria
Explore the source record for details and available documents.
Energy - Biomass, Energy↗
A Neural PDE Solver with Temporal Stencil Modeling
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
Joint Resource Modeling and Assessment for Hybrid Distributed Solar and Wind Systems
The inherent variability and uncertainty in distributed energy resources can presents myriad challenges to the planning and operations of power systems. These risks are poised to become larger as the penetration of renewable energy sources rises in the power generation mix. Hybrid solar-wind energy systems are able to mitigate some of these risks by their complementary resource availability. Surface solar and wind fields are coupled and correlated in both space and time. Appropriately estimating the hybrid solar wind energy system requires simulating the spatio-temporal structure of these fields that can be produced for each time horizon. We introduce a novel joint spatio-temporal stochastic differential equation (SPDE) approach that captures the spatio-temporal dynamics of solar and wind fields and their joint dependency over a domain for each time step. In the case study on Colorado, we consider nonstationary three-level hierarchical spatio temporal models for both hourly solar irradiance data and wind speed data in Colorado. Dependence between the solar irradiance data and wind speed data is captured by a shared spatio-temporal random effect. Our approach performs well in terms of the prediction score criterion.
joint modeling↗
Modeling atmospheric data and identifying dynamics Temporal data-driven modeling of air pollutants
Atmospheric modelling has recently experienced a surge with the advent of deep learning. Most of these models, however, predict concentrations of pollutants following a data-driven approach in which the physical laws that govern their behaviors and relationships remain hidden. Furthermore, with the aid of real-world air quality data collected hourly in different stations throughout Madrid, we present a case study using a series of data-driven techniques with the following goals: (1) Find systems of ordinary differential equations that model the concentration of pollutants and their changes over time; (2) assess the performance and limitations of our model using stability analysis; (3) reconstruct the time series of chemical pollutants not measured in certain stations using delay coordinate embedding results.
54 ENVIRONMENTAL SCIENCES↗
Simulations of aerosol pH in China using WRF-Chem (v4.0): sensitivities of aerosol pH and its temporal variations during haze episodes
Aerosol pH is a fundamental property of aerosols in terms of atmospheric chemistry and its impact on air quality, climate, and health. Precise estimation of aerosol pH in chemical transport models (CTMs) is critical for aerosol modeling and thus influences policy development that partially relies on results from model simulations. We report the Weather Research and Forecasting Model coupled with Chemistry (WRF-Chem) simulated PM 2.5 pH over China during a period with heavy haze episodes in Beijing, and explore the sensitivity of the modeled aerosol pH to factors including emissions of nonvolatile cations (NVCs) and NH 3 , aerosol phase state assumption, and heterogeneous production of sulfate. We find that default WRF-Chem could predict spatial patterns of PM 2.5 pH over China similar to other CTMs, but with generally lower pH values, largely due to the underestimation of alkaline species (NVCs and NH 3 ) and the difference in thermodynamic treatments between different models. Increasing NH 3 emissions in the model would improve the modeled pH in comparison with offline thermodynamic model calculations of pH constrained by observations. In addition, we find that the aerosol phase state assumption and heterogeneous sulfate production are important in aerosol pH predictions for regions with low relative humidity (RH) and high anthropogenic SO 2 emissions, respectively. These factors should be better constrained in model simulations of aerosol pH in the future. Analysis of the modeled temporal trend of PM 2.5 pH in Beijing over a haze episode reveals a clear decrease in pH from 5.2 ± 0.9 in a clean period to 3.6 ± 0.5 in a heavily polluted period. The increased acidity under more polluted conditions is largely due to the formation and accumulation of secondary species including sulfuric acid and nitric acid, even though being modified by alkaline species (NVCs, NH 3 ). Our result suggests that NO 2 oxidation is unlikely to be important for heterogeneous sulfate production during the Beijing haze as the effective pH for NO 2 oxidation of S(IV) is at a higher pH of ~6.
54 ENVIRONMENTAL SCIENCES↗
Geomancy: Automated Performance Enhancement through Data Layout Optimization
Large distributed storage systems such as high- performance computing (HPC) systems used by national or international laboratories require sufficient performance and scale for demanding scientific workloads and must handle shifting workloads with ease. Ideally, data is placed in locations to optimize performance, but the size and complexity of large storage systems inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address these issues, we have developed Geomancy, a tool that models the placement of data within a distributed storage system and reacts to drops in performance. Using a combination of machine learning techniques suitable for temporal modeling, Geomancy determines when and where a bottleneck may happen due to changing workloads and suggests changes in the layout that mitigate or prevent them. Our approach to optimizing throughput offers benefits for storage systems such as avoiding potential bottlenecks and increasing overall I/O throughput from 11% to 30%.
Bel, Oceane M.↗
Wastewater reuse benefits for municipal complete retention lagoons: Life cycle assessment and dynamic modeling
Complete retention lagoons with wastewater reuse for agricultural purposes may offer sustainability advantages over alternative systems for small communities in semiarid regions. This study quantifies the environmental life cycle impact of adopting agriculture water reuse systems using case study data to estimate operating and building infrastructure impacts and spatial–temporal modeling to quantify resource trade-offs. Water reuse system benefits are highly dependent on supply–storage–demand dynamics. The relative size of irrigated agricultural land to the lagoon size was the most significant factor influencing site water application rates. The benefits are sensitive to changes in air emissions occurring from the agricultural land and further emphasize the importance of proper fertilizer management when adopting water reuse systems. Wastewater reuse from complete retention lagoons reduce life cycle GHG emissions, primarily through excavation reductions, offset fertilizer use, and especially from increased crop yields from wastewater reuse at previously rainfed sites.
54 ENVIRONMENTAL SCIENCES↗
A Comparative Study of Physics‐Informed and Data‐Driven Neural Networks for Compound Flood Simulation at River‐Ocean Interfaces: A Case Study of Hurricane Irene
Simulating compound flooding (CF) at the river-ocean interface within large-scale Earth System Models (ESMs) presents significant challenges due to complex interactions between river discharge, storm surge, and tides. This study assesses the comparative advantages of physics-informed and data-driven machine learning (ML) approaches for enhancing local ESM performance. We systematically compare data-driven neural network models (i.e., CNNs, U-Net, Long Short-Term Memory (LSTM), Gated Recurrent Unit), and physics-informed neural network (PINN) models, including vanilla PINN and a finite-difference-based PINN (FD-PINN). Specifically, FD-PINN is introduced to enhance computational efficiency, accelerating vanilla PINNs by ∼6.5 times while improving accuracy. To enhance data-driven model training, a new data-generation approach is developed to sample historical fluvial and coastal flood events, which ensures a robust data set for extreme event prediction. The models are evaluated using a realistic one-dimensional river domain extracted from an ESM's river mesh and the Hurricane Irene event as an independent test case. Results show that FD-PINN achieves accurate predictions with significantly reduced computational costs relative to vanilla PINNs. Among data-driven models, the best overall performance is achieved by a CNN-LSTM hybrid, which balances accuracy and efficiency. While a fully connected CNN (CNN-FC) provides the best accuracy, it incurs high computational cost. Architectures lacking strong temporal modeling tend to underperform on unseen events. These findings highlight the importance of sequence-aware designs for robust generalization. This study reveals the trade-offs between physics-informed and data-driven models and proposes an adaptive hybrid framework for integrating ML into ESMs to enhance local flood simulations.
Earth Systems Modeling↗
Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics With Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis
Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and interconnected nature of complex patterns, which hinder the understanding of their underlying physical processes. Existing AI methods often face limitations in interpretability, computational efficiency, and scalability, reducing their applicability in real-world scenarios. This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs), to reduce complex patterns into lower-dimensional latent spaces and visualize them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN. These visualizations, presented through coordinated and interactive views and tailored glyphs, enable intuitive exploration of complex multivariate temporal patterns, identifying patterns’ similarities and uncover their potential correlations for a better interpretability of the AI outputs. The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes. Additionally, novel metrics and visualizations are introduced to validate the models and assess the performance, efficiency, and consistency of latent maps generated by VAE, which have been utilized in prior studies for latent space cartography and used as a benchmark in this study, and the emerging TFT architecture under various configurations. These analyses provide actionable insights for model parameter tuning and reliability improvements. Comparative results highlight that TFT achieves shorter run times and superior scalability to diverse time-series data shapes compared to VAE. This work advances fault diagnosis in multivariate time series, fostering explainable AI to support critical system operations.
Explainable AI↗
Modeling Spatial Distribution of Snow Water Equivalent by Combining Meteorological and Satellite Data with Lidar Maps
Abstract An accurate characterization of the water content of snowpack, or snow water equivalent (SWE), is necessary to quantify water availability and constrain hydrologic and land surface models. Recently, airborne observations (e.g., lidar) have emerged as a promising method to accurately quantify SWE at high resolutions (scales of ∼100 m and finer). However, the frequency of these observations is very low, typically once or twice per season in the Rocky Mountains of Colorado. Here, we present a machine learning framework that is based on random forests to model temporally sparse lidar-derived SWE, enabling estimation of SWE at unmapped time points. We approximated the physical processes governing snow accumulation and melt as well as snow characteristics by obtaining 15 different variables from gridded estimates of precipitation, temperature, surface reflectance, elevation, and canopy. Results showed that, in the Rocky Mountains of Colorado, our framework is capable of modeling SWE with a higher accuracy when compared with estimates generated by the Snow Data Assimilation System (SNODAS). The mean value of the coefficient of determination R 2 using our approach was 0.57, and the root-mean-square error (RMSE) was 13 cm, which was a significant improvement over SNODAS (mean R 2 = 0.13; RMSE = 20 cm). We explored the relative importance of the input variables and observed that, at the spatial resolution of 800 m, meteorological variables are more important drivers of predictive accuracy than surface variables that characterize the properties of snow on the ground. This research provides a framework to expand the applicability of lidar-derived SWE to unmapped time points. Significance Statement Snowpack is the main source of freshwater for close to 2 billion people globally and needs to be estimated accurately. Mountainous snowpack is highly variable and is challenging to quantify. Recently, lidar technology has been employed to observe snow in great detail, but it is costly and can only be used sparingly. To counter that, we use machine learning to estimate snowpack when lidar data are not available. We approximate the processes that govern snowpack by incorporating meteorological and satellite data. We found that variables associated with precipitation and temperature have more predictive power than variables that characterize snowpack properties. Our work helps to improve snowpack estimation, which is critical for sustainable management of water resources.
54 ENVIRONMENTAL SCIENCES↗
Using Temporal Deep Learning Models to Estimate Daily Snow Water Equivalent Over the Rocky Mountains
Abstract In this study we construct and compare three different deep learning (DL) models for estimating daily snow water equivalent (SWE) from high‐resolution gridded meteorological fields over the Rocky Mountain region. To train the DL models, Snow Telemetry (SNOTEL) station‐based SWE observations are used as the prediction target. All DL models produce higher median Nash‐Sutcliffe Efficiency (NSE) values than a conceptual SWE model and interpolated gridded data sets, although mean squared errors also tend to be higher. Sensitivity of the SWE prediction to the model's input variables is analyzed using an explainable artificial intelligence (XAI) method, yielding insight into the physical relationships learned by the models. This method reveals the dominant role precipitation and temperature play in snowpack dynamics. In applying our models to estimate SWE throughout the Rocky Mountains, an extrapolation problem arises since the statistical properties of SWE (e.g., annual maximum) and geographical properties of individual grid points (e.g., elevation) differ from the training data. This problem is solved by normalizing the SWE with its historical maximum value to alleviate extrapolation for all tested DL models. Our work shows that the DL models are promising tools for estimating SWE, and sufficiently capture relevant physical relationships to make them useful for spatial and temporal extrapolation of SWE values.
54 ENVIRONMENTAL SCIENCES↗
A semiparametric latent factor model for large scale temporal data with heteroscedasticity
Large scale temporal data have flourished in a vast array of applications, and their sophisticated structures, especially the heteroscedasticity among subjects with inter- and intra-temporal dependence, have fueled a great demand for new statistical models. In this paper, with covariate information, we consider a flexible model for large scale temporal data with subject-specific heteroscedasticity. Formally, the model employs latent semiparametric factors to simultaneously account for the subject-specific heteroscedasticity and the contemporaneous and/or serial correlations. The subject-specific heteroscedasticity is modeled as the product of the unobserved factor process and subject’s covariate effect, which is further characterized via additive models. For estimation, we propose a two-step procedure. First, the latent factor process and nonparametric loading are recovered through projection-based methods, and following, we estimate the regression components by approaches motivated from the generalized least squares. By scrupulously examining the non-asymptotic rates for recovering the factor process and its loading, we show the consistency and efficiency of estimated regression coefficients in the absence of prior knowledge of latent factor process and subject’s covariate effect. Here, the statistical guarantees remain valid even for finite time points that makes our method particularly appealing when the subjects significantly outnumber the observation time points. Using comprehensive simulations, we demonstrate the finite sample performance of our method, which corroborates the theoretical findings. Finally, we apply our method to a data set of air quality and energy consumption collected at 129 monitoring sites in the United States in 2015.
97 MATHEMATICS AND COMPUTING↗
Foundation Models of Scientific Knowledge for Chemistry: Opportunities, Challenges and Lessons Learned
Foundation models pre-trained on large corpora demonstrate significant gains across many natural language processing tasks and domains e.g., law, healthcare, education, etc. However, only limited efforts have investigated the opportunities and limitations of applying these powerful models to science and security applications. In this work we develop foundation models of scientific knowledge for chemistry to augment scientists with the advanced ability to perceive and reason at scale previously unimagined. Specifically, we build large-scale (1.47B parameter) general-purpose models for chemistry that can be effectively used to perform a wide range of in-domain and out-of-domain tasks. Evaluating these models in a zero-shot setting, we analyze the effect of model and data scaling, knowledge depth, and temporality on model performance in context of model training efficiency. Our novel findings demonstrate that (1) model size significantly contributes to the task performance when evaluated in a zero-shot setting; (2) data quality (aka diversity) affects model performance more than data quantity; (3) similarly, unlike previous work (Luu et al., 2021) temporal order of the documents in the corpus boosts model performance only for specific tasks, e.g., SciQ; and (4) models pre-trained from scratch perform better on in-domain tasks than those tuned from general-purpose models like Open AI’s GPT-2.
Foundation Models, Chemistry↗
Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models
We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively.
ARIMA↗
Robust Importance Sampling for Bayesian Model Calibration with Spatio-Temporal Data
This paper addresses two challenges in Bayesian calibration: 1) computational speed of existing sampling algorithms, and 2) calibration with spatio-temporal responses. The commonly used Markov Chain Monte Carlo (MCMC) approaches require many sequential model evaluations making the computational expense prohibitive. This paper proposes an efficient sampling algorithm: iterative importance sampling with genetic algorithm (IISGA). While iterative importance sampling enables computational efficiency, the genetic algorithm enables robustness by preventing sample degeneration and avoids getting stuck in multimodal search spaces. An inflated likelihood further enables robustness in high-dimensional parameter spaces by enlarging the target distribution. Spatio-temporal data complicate both surrogate modeling, which is necessary for expensive computational models, and the likelihood estimation. In this work, singular value decomposition is investigated for reducing the high-dimensional field data to a lower-dimensional space prior to Bayesian calibration. Then the likelihood is formulated and Bayesian inference is performed in the lower-dimension, latent space. An illustrative example is provided to demonstrate IISGA relative to existing sampling methods, and then IISGA is employed to calibrate a thermal battery model with 26 uncertain calibration parameters and spatio-temporal response data.
97 MATHEMATICS AND COMPUTING↗
Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales
As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.
Houben, Nikolaus↗