Search NASA⌕ Search

SEARCH · Search NASA

Results for “time series forecasting”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Online evolutionary neural architecture search for multivariate non-stationary time series forecasting

Time series forecasting (TSF) is one of the most important tasks in data science. TSF models are usually pre-trained with historical data and then applied on future unseen datapoints. However, real-world time series data is usually non-stationary and models trained offline usually face problems from data drift. Models trained and designed in an offline fashion can not quickly adapt to changes quickly or be deployed in real-time. To address these issues, this work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. These results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies. Additionally, results show that utilizing multiple populations of RNNs which are periodically repopulated provide significant performance improvements, allowing this online neural network architecture design and training to be successful.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Time-series forecasting using manifold learning, radial basis function interpolation, and geometric harmonics

We address a three-tier numerical framework based on nonlinear manifold learning for the forecasting of high-dimensional time series, relaxing the “curse of dimensionality” related to the training phase of surrogate/machine learning models. At the first step, we embed the high-dimensional time series into a reduced low-dimensional space using nonlinear manifold learning (local linear embedding and parsimonious diffusion maps). Then, we construct reduced-order surrogate models on the manifold (here, for our illustrations, we used multivariate autoregressive and Gaussian process regression models) to forecast the embedded dynamics. Finally, we solve the pre-image problem, thus lifting the embedded time series back to the original high-dimensional space using radial basis function interpolation and geometric harmonics. The proposed numerical data-driven scheme can also be applied as a reduced-order model procedure for the numerical solution/propagation of the (transient) dynamics of partial differential equations (PDEs). In conclusion, we assess the performance of the proposed scheme via three different families of problems: (a) the forecasting of synthetic time series generated by three simplistic linear and weakly nonlinear stochastic models resembling electroencephalography signals, (b) the prediction/propagation of the solution profiles of a linear parabolic PDE and the Brusselator model (a set of two nonlinear parabolic PDEs), and (c) the forecasting of a real-world data set containing daily time series of ten key foreign exchange rates spanning the time period 3 September 2001–29 October 2020.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Knowledge-Informed Uncertainty-Aware Machine Learning for Time Series Forecasting of Dynamical Engineered Systems

The high complexity and multiscale nature of many engineered systems—such as those in nuclear power plants—make representing and forecasting their dynamic behavior challenging. Physics-based models can be overly complex and computationally intractable, whereas machine learning (ML) tools are often data-hungry and prone to unphysical solutions. This study proposes a knowledge-informed ML-aided hybrid residual modeling approach that offers accurate and efficient time series forecasting for the operation of dynamical engineered systems. Hybrid residual modeling entails a baseline solution from domain knowledge and known physics expressions about the system dynamics integrated with an ML model to capture undiscovered information from the mismatch (i.e., residuals) between true states from measurements and baseline-predicted outputs. This study further quantifies the ML model uncertainty to provide trustworthy solutions. Real-time operational data from thermal-hydraulic flow loops of the cryogenic moderator system in Oak Ridge National Laboratory’s Spallation Neutron Source facility were used to demonstrate the potential of knowledge-informed uncertainty-aware ML in real-world applications. The state variables of the cryogenic helium loop were modeled with (1) first principles–based system identification (sysID), (2) long short-term memory (LSTM) neural network, and (3) hybrid sysID (baseline) + LSTM (residual). The superior predictive capability of the sysID+LSTM model versus stand-alone sysID and LSTM is confirmed by average performance metrics and individual data points across different prediction horizons. By creating a robust representation of the underlying physical system, the widely applicable hybrid residual modeling approach will enable the future development of digital twins for performance prediction, prognostics, and operation control.

Zhao, Xingang↗
DOE OSTI2025

Artificial intelligence time series forecasting for feed-forward laser stabilization

Laser plasma accelerators, typically operating at 1–10 Hz repetition rates, have the ability to produce high-quality electron beams in compact, all-optical-driven configurations, with the electron beams uniquely suited for a wide variety of accelerator-based applications. However, fluctuations and drifts in the laser delivery to the meter-scaled and below plasma target (the electron beam source) will translate into electron beam source variations that can limit their utility for demanding applications like light sources or linear colliders. Commercially available active feedback laser stabilization systems are intrinsically bandwidth limited due to their integration with multi-inch corrective mirror mounts which minimizes their effectiveness. In this manuscript, we present a Neural Network time series forecaster that can predict laser position fluctuations of the laser delivery to the final target well ahead of a future laser shot. The Root-Mean-Square-Error (RMSE) of the prediction accuracy was < 2 μ m for a 1 / e 2 beam radius of 34 μ m . Our feed-forward approach serves as a first-step in circumventing the bandwidth limitations imposed by the currently available stabilization systems since it allows for mirrors to be moved into position ahead of time to offset the predicted future position drift. This will help advance laser plasma accelerator research by providing greater robustness and stability needed for its applications.

Berger, Curtis↗
DOE OSTI2025

Transformers and Long Short-Term Memory Transfer Learning for GenIV Reactor Temperature Time Series Forecasting

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors.

LSTM↗
DOE OSTI2024

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2021

Discrete Graph Structure Learning for Forecasting Multiple Time Series

Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.

Shang, Chao↗
DOE OSTI2025

A Preferences Corpus and Annotation Scheme for Human-Guided Alignment of Time-Series GPTs

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings.

DPO↗
DOE OSTI2024

Automated Framework for Groundwater Monitoring Using DWT with LSTM and Transformers

Environmental monitoring is critical for safeguarding public health and ecological well-being. Traditional data structuring and workflow monitoring methods consume significant time and effort, hindering timely insights and effective decision-making. Our study addresses this challenge by presenting an AI framework that automates data cleaning, structuring, and modeling processes, specifically targeting applications in groundwater monitoring. By leveraging automation for data processing and model training, our framework establishes a novel and efficient paradigm for environmental monitoring, with its potential application to the vast network of over a hundred Department of Energy Environmental Management (DoE-EM) cleanup sites across the country. It analyzes data streams from a network of groundwater Internet-of-Things (IoT) sensors deployed at the Savannah River Site (SRS) for prediction modeling. This allows human experts to focus on analysis and decision-making, ultimately leading to better environmental outcomes.The framework employs multivariate time-series forecasting methods to study and model the behavior of varying chemical analytes. The continuous learning process is enabled by utilizing deep learning techniques. It allows the framework to become more nuanced in its analysis over time, adapting to the specific characteristics of the environmental site and the evolving nature of contaminant behavior. Deep learning models known for sequence modeling, LSTM, and Transformers are employed for time series forecasting. Data processing and structuring are essential components significantly impacting the final model's performance. This hypothesis was proven by presenting a comparative analysis of model performance with processed and unprocessed data. The feature engineering approach utilized was the Discrete Wavelet Transform, which works well with time series data.

Discrete Wavelet Transform (DWT)↗
DOE OSTI2026

FFTSF: Revisiting Sub-Seasonal Streamflow Forecasting with Simple Feedforward Network

Accurate short-to-subseasonal streamflow forecasts are vital for water management, including flood preparedness, drought mitigation, hydropower scheduling, and ecosystem protection. However, extending a forecast beyond a few days remains challenging due to complexity of hydrological processes. While recent self-attention based transformer architectures such as iTransformer have gained traction in time-series forecasting, these models suffer from several critical limitations: (1) significant computational overhead that scales quadratically with sequence length, (2) vulnerability to overfitting on limited hydrological datasets, (3) degraded performance on long-horizon forecasts due to attention decay, and (4) excessive architectural complexity that hampers interpretability and operational deployment. In this study, we propose a simple Feedforward Time Series Forecasting (FFTSF) network that directly addresses these limitations through its lightweight architecture and long-range forecasting capabilities. We evaluate FFTSF across 178 USGS stream gauges spanning diverse climate regimes by forecasting lead times of 1-, 7-, 14-, and 30-days. Our results demonstrate that FFTSF achieves competitive performance at short lead times (NSE of 0.778 for 1-day forecasts) while substantially outperforming complex baselines at longer forecast period, achieving the highest NSE (0.271) at 30-day forecasts with greater robustness and stability. For 30-day forecasts, FFTSF achieves a 71% improvement over NLinear, 57% improvement over DLinear and 12% improvement over the computationally intensive iTransformer while requiring fewer computational resources. Our findings reveal that architectural complexity is not necessary for hydrological forecasting, demonstrating that well-designed simple models can outperform attention mechanisms for subseasonal streamflow forecasting. The computational efficiency and consistent long-range performance of FFTSF make it suitable for water management applications where reliable extended forecasts are essential.

Krishnan Kutty Ambika, Anukesh [ORNL] (ORCID:00000↗
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 OSTI2022

Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps

Many-to-one maps are ubiquitous in machine learning, from the image recognition model that assigns a multitude of distinct images to the concept of ``cat'' to the time series forecasting model which assigns a range of distinct time-series to a single scalar regression value. While the primary use of such models is naturally to associate correct output to each input, in many problems it is also useful to be able to explore, understand, and sample from a model's fibers, which are the set of input values x such that f(x) = y, for fixed y in the output space. In this paper we show that popular generative architectures are ill-suited to such tasks. Motivated by this we introduce a novel generative architecture, a Bundle Network, based on the concept of a fiber bundle from (differential) topology. BundleNets exploit the idea of a local trivialization wherein a space can be locally decomposed into a product space that cleanly encodes the many-to-one nature of the map. By enforcing this decomposition in BundleNets and by utilizing state-of-the-art invertible components, investigating a network's fibers becomes natural.

Courts, Nicolas C.↗
DOE OSTI2024

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

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

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Net Load Forecasting With Disaggregated Behind-the-Meter PV Generation

As worldwide use of residential photovoltaic (PV) systems grows, system operators and utilities will need to transition from forecasting pure demand to forecasting net load with behind-the-meter (BTM) PV generation. However, PV generation can be difficult to predict and the measurements of PV generation from BTM residential systems are often invisible behind a measurement of the net load, making net load forecasting challenging. This paper proposes a novel two-stage framework for net load forecasting in areas with limited observability and high BTM PV generation. First, the profiles of observable customers are used to disaggregate the net load measurements into the pure load and PV generation. Then, separate models are used to forecast the PV generation and pure load individually, and the results are combined for a net load forecast. Further, this paper also proposes a compensator for correcting the error of the net load forecast, using historical forecast errors of the PV generation, pure load, and net load. The proposed framework is tested through two case studies for areas with high BTM PV penetration and less than 10% observable customers. The two-stage forecasting model is compared to two benchmark methods - a time series forecasting model, and a model that forecasts the net load directly using historical net load measurements. Results show that the proposed disaggregation-forecasting framework reduces the error of the net load forecast compared to both benchmark models. In addition, when the net load forecast error is periodic, the compensator can correct the error to improve the forecast accuracy.

14 SOLAR ENERGY↗