Search NASA⌕ Search

SEARCH · Search NASA

Results for “Forecast Models”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption

Accurate short-term energy consumption forecasting for commercial buildings is crucial for smart grid operations. While smart meters and deep learning models enable forecasting using past data from multiple buildings, data heterogeneity from diverse buildings can reduce model performance. The impact of increasing dataset heterogeneity in time series forecasting, while keeping size and model constant, is understudied. We tackle this issue using the ComStock dataset, which provides synthetic energy consumption data for U.S. commercial buildings. Two curated subsets, identical in size and region but differing in building type diversity, are used to assess the performance of various time series forecasting models, including finetuned open-source foundation models (FMs). The results show that dataset heterogeneity and model architecture have a greater impact on post-training forecasting performance than the parameter count. Moreover, despite the higher computational cost, finetuned FMs demonstrate competitive performance compared to base models trained from scratch.

commercial buildings↗
DOE OSTI2024

Challenges of COVID-19 Case Forecasting in the US, 2020–2021

During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub ( https://covid19forecasthub.org ). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1–4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning

Forecasting rapid intensification (RI) of tropical cyclones (TC) is a mission known for large errors. One under-researched factor that affects TC intensification is salinity, which is important for density stratification in certain ocean regions and can affect the surface enthalpy flux under a strengthening hurricane. To investigate the impact and efficacy of using salinity information in state-of-the-art forecasting, we use a statistical model consisting of a variety of machine learning (ML) methods. For salinity data, we use satellite measurements of pre-storm sea surface salinity (SSS) as a proxy for the salinity stratification. We train and test the model on various ocean basins, including the Atlantic, eastern North Pacific and western North Pacific. A calibrator is trained on top of the ML models to correct and enhance probability forecasts. The calibrator significantly improves probability forecasts relative to recent works. The ML model performance is improved with the addition of SSS in the Eastern North Pacific, western North Pacific, and the Caribbean subregion of the North Atlantic, and the overall model performance is better than previous studies. SSS decreases model skill for a model trained on the full Atlantic basin. In the Indian Ocean, SSS is also notably correlated with RI occurrence, but the TC samples are not sufficient to train ML models.

hurricane↗
DOE OSTI2025

Data and scripts associated with “Sequential Precipitation Input Tagging (SPIT) to Estimate Water Transit Times and Hydrologic Tracer Dynamics within Water-Tagging Enabled Hydrologic Models” (v3)

This data package is associated with the publication “Sequential Precipitation Input Tagging (SPIT) to Estimate Water Transit Times and Hydrologic Tracer Dynamics within Water-Tagging Enabled Hydrologic Models” submitted to Journal of Advances in Modeling Earth Systems (Butler et al. 2025). This study developed the Sequential Precipitation Input Tagging (SPIT) framework to tag input precipitation and estimate water transit times and hydrologic tracers. SPIT tags all precipitation events at regular intervals over an extended period (monthly tags over seven years) in a hydrologic model from 2016-2022. SPIT is applied at six National Ecological Observatory Network (NEON) sites across the continental United States to calculate transit time distributions (TTD) and derive from these mean transit times (MTT), fractions of young water (Fyw), and hydrologic tracer concentrations in stream water (δ18O) within a water-tagging enabled version of the Weather Research and Forecast (WT-WRF-Hydro) model with national water model (NWM) configurations. We go on to validate WT-WRF-Hydro estimates against Butler et al. (2023), who analyzed the same NEON sites using stable water isotope data to estimate water transit times. This new tracking method provides a detailed picture of water movement and helps improve predictions about water availability in the future. This data package was originally published in January 2025. It was updated May 2025 (v2; new and modified files) and October 2025 (v3; new and modified files). File and folder names were not revised to indicate changes. See the change history section in the readme for more details. This data package contains the data and scripts used to develop the SPIT framework WT-WRF-Hydro (Water Tagging Weather Research and Forecasting Hydrologic) model and is associated with the following GitHub repository: https://github.com/zbutler33/SPIT-Framework. This data package contains five parent folders: (1) “Manipulated_outputs”, (2) “Metadata”, (3) “Observed”, (4) “Outputs”, and (5) “Scripts”. Each of these parent folders contains additional subfolders and files. Please see the FLMD (“v*_Butler_2024_WT_WRF_Hydro_flmd.csv”) for a list of all the files contained in this data package and descriptions for each. See the data dictionary (“v*_Butler_2024_WT_WRF_Hydro_dd.csv”) for definitions and units of all of the tabular (files ending in “.csv” and ".tsv") column headers.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Automating Rabi & Ramsey Measurements via ML

As quantum computers scale up, the manual process of qubit tune-up becomes increasingly impractical due to its time-consuming and repetitive nature. While existing research has explored some automation techniques, many models remain underutilized for this purpose. This research aims to answer the question: is qubit tune-up able to be automated using the Long Short-Term Memory (LSTM) model? For the purposes of this project, only the rabi and ramsey measurement cycle was automated. These measurements are used to fine-tune a rough qubit frequency by repeating them until the optimal qubit frequency is obtained. The LSTM model uses the qubit frequency at one time step to forecast the qubit frequency at the next time step. A rabi-ramsey simulation was made to fabricate a dataset to train and test the LSTM model. As the model was trained, the error of the model decreased. Although there wasn't enough training data to generate perfect predictions, this shows it is possible to utilize forecasting models in automating the tune-up process.

Roberts, Rachel↗
DOE OSTI2024

Automating Rabi & Ramsey Measurements via ML

As quantum computers scale up, the manual process of qubit tune-up becomes increasingly impractical due to its time-consuming and repetitive nature. While existing research has explored some automation techniques, many models remain underutilized for this purpose. This research aims to answer the question: can qubit tune-up be automated using the Long Short-Term Memory (LSTM) model? For the purposes of this project, only the rabi and ramsey measurement cycle was automated. These measurements are used to fine-tune a rough qubit frequency by repeating them until the optimal qubit frequency is obtained. The LSTM model uses the qubit frequency at one time step to forecast the qubit frequency at the next time step. A rabi-ramsey simulation was made to fabricate a dataset to train and test the LSTM model. As the model was trained, the error of the model decreased. Although there wasn t enough training data to generate perfect predictions, this shows it is possible to utilize forecasting models in automating the tune-up process.

Roberts, Rachel↗
DOE OSTI2024

Automating Rabi & Ramsey Measurements via Machine Learning

As quantum computers scale up, the manual process of qubit tune-up becomes increasingly impractical due to its time-consuming and repetitive nature. While existing research has explored some automation techniques, many models remain underutilized for this purpose. This research aims to answer the question: can qubit tune-up be automated using the Long Short-Term Memory (LSTM) model? For the purposes of this project, only the rabi and ramsey measurement cycle was automated. These measurements are used to fine-tune a rough qubit frequency by repeating them until the optimal qubit frequency is obtained. The LSTM model uses the qubit frequency at one time step to forecast the qubit frequency at the next time step. A rabi-ramsey simulation was made to fabricate a dataset to train and test the LSTM model. As the model was trained, the error of the model decreased. Although there wasn't enough training data to generate perfect predictions, this shows it is possible to utilize forecasting models in automating the tune-up process.

Roberts, Rachel↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Semi-Analytical Hierarchical Bayesian Inference of Nonlinear Model Structure in Stochastic Dynamics: Applied to Compartmental Models of Infectious Diseases

A Bayesian computational framework for parsimonious inference in stochastic nonlinear dynamical systems is presented. This framework enables the concurrent estimation of system states, time-varying parameters, time-invariant parameters, and the optimal sparsity structure of the model parameters. Because differential equation-based models are often simplified mechanistic or phenomenological representations, robust inference from noisy measurement data requires explicit treatment of model error and uncertainty. Model error and time-varying parameters can be represented as random processes, enabling inference while making minimal assumptions about the underlying sources of discrepancy and variability. Adopting stochastic differential equation representations affords the model significant flexibility, but can also render it susceptible to overfitting during statistical inversion, where the inferred model may track noise rather than the underlying signal. To alleviate the effects of overfitting and to enable the discovery of the optimal sparse representation of the time-invariant parameters, a Bayesian sparse learning algorithm is embedded within the framework. This sparse learning framework adopts an approximate hierarchical Bayesian setting defined by a series of semi-analytical expressions. The model structure inference framework is validated using a stochastic compartmental model for tracking and forecasting active cases of an infectious disease. Compartmental models describe population-level infectious disease dynamics through interactions among population fractions grouped by disease state. Mathematically, such models consist of a system of coupled ordinary differential equations. This example adopts an expressive compartmental model that includes multiple possible interactions between disease states, motivated by early uncertainty surrounding COVID-19 reinfection dynamics and their implications for long-term epidemic forecasting. The sparse learning exercise permits the inference of a priori unknown epidemiological dynamics from simulated public health data, discovering the nested compartmental model that optimizes the trade-off between average data-fit and model complexity. It is shown that inducing sparsity among the model parameters eliminates redundant interactions between compartments, equivalently revealing the optimal coupling structure between differential equations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Combining Observations and Models: A Review of the CARDAMOM Framework for Data‐Constrained Terrestrial Ecosystem Modeling

The rapid increase in the volume and variety of terrestrial biosphere observations (i.e., remote sensing data and in situ measurements) offers a unique opportunity to derive ecological insights, refine process‐based models, and improve forecasting for decision support. However, despite their potential, ecological observations have primarily been used to benchmark process‐based models, as many past and current models lack the capability to directly integrate observations and their associated uncertainties for parameterization. In contrast, data assimilation frameworks such as the CARbon DAta MOdel fraMework (CARDAMOM) and its suite of process‐based models, known as the Data Assimilation Linked Ecosystem Carbon Model (DALEC), are specifically designed for model‐data fusion. This review, motivated by a recent CARDAMOM community workshop, examines the development and applications of CARDAMOM, with an emphasis on its role in advancing ecosystem process understanding. CARDAMOM employs a Bayesian approach, using a Markov Chain Monte Carlo algorithm to enable data‐driven calibration of DALEC parameters and initial states (i.e., carbon pool sizes) through observation operators. CARDAMOM's unique ability to retrieve localized model process parameters from diverse datasets—ranging from in situ measurements to global satellite observations—makes it a highly flexible tool for analyzing spatially variable ecosystem responses to environmental change. However, assimilating these data also presents challenges, including data quality issues that propagate into model skill, as well as trade‐offs between model complexity, parameter equifinality, and predictive performance. We discuss potential solutions to these challenges, such as reducing parameter equifinality by incorporating new observations. This review also offers community recommendations for incorporating emerging datasets, integrating machine learning techniques, strengthening collaboration with remote sensing, field, and modeling communities, and expanding CARDAMOM's relevance for localized ecosystem monitoring and decision‐making. CARDAMOM enables a deep, mechanistic understanding of terrestrial ecosystem dynamics that cannot be achieved through empirical analyses of observational datasets or weakly constrained models alone.

Bayesian inference↗
DOE OSTI2024

Deep-learning-derived planetary boundary layer height from conventional meteorological measurements

Abstract. The planetary boundary layer (PBL) height (PBLH) is an important parameter for various meteorological and climate studies. This study presents a multi-structure deep neural network (DNN) model, which can estimate PBLH by integrating the morning temperature profiles and surface meteorological observations. The DNN model is developed by leveraging a rich dataset of PBLH derived from long-standing radiosonde records augmented with high-resolution micro-pulse lidar and Doppler lidar observations. We access the performance of the DNN with an ensemble of 10 members, each featuring distinct hidden-layer structures, which collectively yield a robust 27-year PBLH dataset over the southern Great Plains from 1994 to 2020. The influence of various meteorological factors on PBLH is rigorously analyzed through the importance test. Moreover, the DNN model's accuracy is evaluated against radiosonde observations and juxtaposed with conventional remote sensing methodologies, including Doppler lidar, ceilometer, Raman lidar, and micro-pulse lidar. The DNN model exhibits reliable performance across diverse conditions and demonstrates lower biases relative to remote sensing methods. In addition, the DNN model, originally trained over a plain region, demonstrates remarkable adaptability when applied to the heterogeneous terrains and climates encountered during the GoAmazon (Green Ocean Amazon; tropical rainforest) and CACTI (Cloud, Aerosol, and Complex Terrain Interactions; middle-latitude mountain) campaigns. These findings demonstrate the effectiveness of deep learning models in estimating PBLH, enhancing our understanding of boundary layer processes with implications for improving the representation of PBL in weather forecasting and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Validation of Weather Forecasting Products

Weather forecasting is a tool in which the Savannah River Site relies on to complete daily tasks. The importance and integrity of forecasting systems and models is of the utmost importance to safety at SRS. By comparing and contrasting model bias, the meteorologists and employees of the Atmospheric Technologies Group will be equipped with bias data to create more accurate forecasts. Thus, furthering the safety of individuals at SRS.

Gray, Avery↗
DOE OSTI2024

Comparison of Machine Learning-Based Predictive Models of the Nutrient Loads Delivered from the Mississippi/Atchafalaya River Basin to the Gulf of Mexico

Predicting nutrient loads is essential to understanding and managing one of the environmental issues faced by the northern Gulf of Mexico hypoxic zone, which poses a severe threat to the Gulf’s healthy ecosystem and economy. The development of hypoxia in the Gulf of Mexico is strongly associated with the eutrophication process initiated by excessive nutrient loads. Due to the complexities in the excessive nutrient loads to the Gulf of Mexico, it is challenging to understand and predict the underlying temporal variation of nutrient loads. The study was aimed at identifying an optimal predictive machine learning model to capture and predict nonlinear behavior of the nutrient loads delivered from the Mississippi/Atchafalaya River Basin (MARB) to the Gulf of Mexico. For this purpose, monthly nutrient loads (N and P) in tons were collected from US Geological Survey (USGS) monitoring station 07373420 from 1980 to 2020. Machine learning models—including autoregressive integrated moving average (ARIMA), gaussian process regression (GPR), single-layer multilayer perceptron (MLP), and a long short-term memory (LSTM) with the single hidden layer—were developed to predict the monthly nutrient loads, and model performances were evaluated by standard assessment metrics—Root Mean Square Error (RMSE) and Correlation Coefficient (R). The residuals of predictive models were examined by the Durbin–Watson statistic. The results showed that MLP and LSTM persistently achieved better accuracy in predicting monthly TN and TP loads compared to GPR and ARIMA. In addition, GPR models achieved slightly better test RMSE score than ARIMA models while their correlation coefficients are much lower than ARIMA models. Moreover, MLP performed slightly better than LSTM in predicting monthly TP loads while LSTM slightly outperformed for TN loads. Furthermore, it was found that the optimizer and number of inputs didn’t show effects on the LSTM performance while they exhibited impacts on MLP outcomes. This study explores the capability of machine learning models to accurately predict nonlinearly fluctuating nutrient loads delivered to the Gulf of Mexico. Further efforts focus on improving the accuracy of forecasting using hybrid models which combine several machine learning models with superior predictive performance for nutrient fluxes throughout the MARB.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Deep-Learning-derived Boundary Layer Height from Meteorological Data over the SGP, GOAMAZON, CACTI

The planetary boundary-layer (PBL) height (PBLH) is an important parameter for various meteorological and climate studies. This study presents a multi-structure deep neural network (DNN) model, designed to estimate PBLH by integrating morning temperature profiles with surface meteorological observations. The DNN model is developed by leveraging a rich data set of PBLH derived from long-standing radiosonde records and augmented with high-resolution micropulse lidar and Doppler lidar observations. We access the performance of the DNN with an ensemble of 10 members, each featuring distinct hidden layer structures, which collectively yield a robust 27-year PBLH data set over the Southern Great Plains from 1994 to 2020. The influence of various meteorological factors on PBLH is rigorously analyzed through the importance test. Moreover, the DNN model's accuracy is evaluated against radiosonde observations and juxtaposed with conventional remote-sensing methodologies, including Doppler lidar, ceilometer, Raman lidar, and micropulse lidar. The DNN model exhibits reliable performance across diverse conditions and demonstrates lower biases relative to remote-sensing methods. In addition, the DNN model, originally trained over a plain region, demonstrates remarkable adaptability when applied to the heterogeneous terrains and climates encountered during the GoAmazon (tropical rainforest) and CACTI (middle-latitude mountain) campaigns. These findings demonstrate the effectiveness of deep learning models in estimating PBLH, enhancing our understanding of boundary-layer dynamics with implications for enhancing the representation of PBL in weather forecasting and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Multi-Scale Integrated Monitoring System for Enhancing Methane Emission Detection, Quantification & Prediction

This report details the progress and findings of a comprehensive study on reviewing existing solutions, identifying technology gaps, and formulating an “all-in-one” integrated strategy for developing the next-generation multiscale methane monitoring and modeling platform, conducted under grant number DE-FE0032292. Co-led by Dr. David Ebert, Dr. Binbin Weng, and Dr. Chenghao Wang at the University of Oklahoma, the project’s goal was to develop an integrated approach for building this engineering platform to detect, quantify, and mitigate methane emissions across various temporal scale, spatial scales, and sectors. The planning grant study began with an extensive review of various methane sensing and monitoring technologies and systems, surveying over 100 technology providers globally. This review revealed the prevalence of optical methods over chemical methods in commercially available sensors, with Non-Dispersive Infrared (NDIR), Tunable Diode Laser Absorption Spectroscopy (TDLAS), and Optical Gas Imaging (OGI) cameras being the most prevalent options. A trend towards more advanced optical techniques was observed, driven by increased regulatory focus and technological advancements. The technical evaluation of these sensing technologies provided crucial insights into their capabilities and limitations. The study examined emerging technologies such as Differential Absorption LiDAR (DIAL), which show promise for high-precision and long-range detection. The team then investigated the features and application bandwidth of various sensing platforms, including handheld, fixed/stationary, mobile, aerials, and spaceborne monitors. Pilot field studies were conducted to assess the capabilities of solutions for different emission scenarios. Field work with sensor deployments was conducted at three distinct site types: an oil & gas industry site, a cattle ranching operation, and a waste processing facility. The team also conducted a thorough review of methane flux inverse modeling approaches, focused on physically based methods. These approaches were categorized into simple, intermediate, and advanced methods. A realtime WRF-GHG (Weather Research and Forecasting-Greenhouse Gas) modeling system was developed and applied, incorporating multiple data sources to guide field experiments and inform methane plume detection. The project identified and analyzed numerous categories of methane data sources, including satellite measurements, ground-based sensors, and inventory databases. Key platforms examined include EDGAR, EPA GHGI, NASA TROPOMI, Carbon Mapper, and Climate TRACE, among others. The team proposed an architecture for a comprehensive methane monitoring platform. This system incorporates multi-source data acquisition, advanced data processing and assimilation, interactive visualization tools, and analytical capabilities for emissions forecasting and scenario analysis. The proposed platform aims to provide a user-friendly interface catering to various stakeholders, from researchers to policymakers. The architecture includes sophisticated data ingestion methods, a centralized data warehouse, and advanced analytical tools for data fusion and interpretation. To ensure the relevance and effectiveness of the proposed system, a comprehensive survey was conducted to gather stakeholder input on system requirements. Key findings include a strong need for integrating various data types and formats, a preference for real-time data updates and advanced visualization tools, and a demand for user-friendly interfaces catering to different expertise levels.

03 NATURAL GAS↗
DOE OSTI2024

Anticipating Technical Expertise and Capability Evolution in Research Communities Using Dynamic Graph Transformers

The ability to anticipate global technical expertise and capability evolution trends is essential for national and global security, especially in safety-critical domains such as nuclear nonproliferation (NN) and rapidly emerging fields like artificial intelligence (AI). Here, in this work, we extend traditional statistical relational learning approaches (e.g., link prediction in collaboration networks) and formulate a problem of anticipating technical expertise and capability evolution using dynamic heterogeneous graph representations. We develop novel capabilities to forecast collaboration patterns, authorship behavior, and technical capability evolution at different granularities (e.g., scientist and institution levels) in two distinct research fields. We implement a dynamic graph transformer (DGT) neural architecture, which pushes the state-of-the-art graph neural network models by: 1) forecasting heterogeneous (rather than homogeneous) nodes and edges; and 2) relying on both discrete- and continuous-time inputs. We demonstrate that our DGT models predict collaboration, partnership, and expertise patterns with 0.26, 0.73, and 0.53 mean reciprocal rank values for AI and 0.48, 0.93, and 0.22 for NN domains. DGT model performance exceeds the best-performing static graph baseline models by 30%–80% across AI and NN domains. Our findings demonstrate that DGT models boost inductive task performance when previously unseen nodes appear in the test data for the domains with emerging collaboration patterns (e.g., AI). Specifically, models accurately predict which established scientists will collaborate with early career scientists and vice versa in the AI domain.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Synthetic method of analogues for emerging infectious disease forecasting

The Method of Analogues (MOA) has gained popularity in the past decade for infectious disease forecasting due to its non-parametric nature. In MOA, the local behavior observed in a time series is matched to the local behaviors of several historical time series. The known values that directly follow the historical time series that best match the observed time series are used to calculate a forecast. This non-parametric approach leverages historical trends to produce forecasts without extensive parameterization, making it highly adaptable. However, MOA is limited in scenarios where historical data is sparse. This limitation was particularly evident during the early stages of the COVID-19 pandemic, where the emerging global epidemic had little-to-no historical data. In this work, we propose a new method inspired by MOA, called the Synthetic Method of Analogues (sMOA). sMOA replaces historical disease data with a library of synthetic data that describe a broad range of possible disease trends. This model circumvents the need to estimate explicit parameter values by instead matching segments of ongoing time series data to a comprehensive library of synthetically generated segments of time series data. We demonstrate that sMOA has competitive performance with state-of-the-art infectious disease forecasting models, out-performing 78% of models from the COVID-19 Forecasting Hub in terms of averaged Mean Absolute Error and 76% of models from the COVID-19 Forecasting Hub in terms of averaged Weighted Interval Score. Additionally, we introduce a novel uncertainty quantification methodology designed for the onset of emerging epidemics. Developing versatile approaches that do not rely on historical data and can maintain high accuracy in the face of novel pandemics is critical for enhancing public health decision-making and strengthening preparedness for future outbreaks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet

Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates and the sparsity of the observations, filtering estimates can remain accurate in the long-time horizon. As a case study, we integrate FourCastNet, a weather surrogate model, within a variational data assimilation framework using partial, noisy ERA5 data. Our results show that filtering estimates remain accurate over a year-long assimilation window and provide effective initial conditions for forecasting tasks, including extreme event prediction.

Adrian, Melissa [Univ. of Chicago, IL (United Stat↗