An efficient moving object tracking framework for WSNs using sequence-to-sequence learning model
Not provided.
Computer Science↗
SEARCH · Search NASA
Results for “Sequence-to-sequence model”
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.
GrainNN: A neighbor-aware long short-term memory network for predicting microstructure evolution during polycrystalline grain formation
High fidelity simulations of grain formation in alloys are an indispensable tool for process-to-mechanical-properties characterization. Such simulations, however, can be computationally expensive as they require fine spatial and temporal discretizations. Their cost becomes an obstacle to parametric studies and ensemble runs and ultimately makes downstream tasks like optimal control and uncertainty quantification challenging. To enable such downstream tasks, we introduce GrainNN, an efficient and accurate reduced-order model for epitaxial grain growth in additive manufacturing conditions. GrainNN is a sequence-to-sequence long-short-term-memory (LSTM) deep neural network that evolves the dynamics of manually crafted features. Its innovations are (1) an attention mechanism with grain-microstructure-specific transformer architecture; and (2) an overlapping combination of several clones of the network to generalize to grain configurations that are different from those used for training. This design enables GrainNN to predict grain formation for unseen physical parameters, grain number, domain size and geometry. Furthermore, GrainNN not only reconstructs the quantities of interest but also can be pointwise accurate. In our numerical experiments, we use a polycrystalline phase field method to both generate the training data and assess GrainNN. For multiparametric, ensemble simulations with many grains, GrainNN can be orders of magnitude faster than phase field simulations, while delivering 5%–15% pointwise error. Additionally, this speedup includes the cost of the phase field simulations for generating training data.
36 MATERIALS SCIENCE↗
Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings
The U.S. power grid is transforming to become smarter, cleaner, and more effi- cient. This is leading to the addition of significant distributed variable renew- able generation. Due to the variable nature of renewable generation, the short- and long-term supply-demand imbalances are less predictable, and conventional approaches to mitigating the imbalance will not be efficient or cost-effective. To address this challenge, transactive control technologies have been proposed which balance energy generation and consumption with market activity and in- frastructural limitations. Transactive control requires the ability of individual end-use loads to express flexibility as a function of a transactive signal (e.g., price). Empirical gray- and black-box models have been widely used to express flexibility, and although these approaches are generally easy to construct and simple to use, they do not capture the non-linear behavior that some end-use loads represent . Machine learning approaches have been proposed to address this limitation. Although deep learning approaches for forecasting end-use loads have been explored, certain aspects of the application of deep models to load forecasting are not well understood. These aspects include how much training data is required, and how models should be structured and trained. To that end, this work explores how to approach applying deep recurrent neural networks to short-term electrical load forecasting with a case study of four commercial office buildings. We identify data requirements for training accurate models of whole building electricity use conditioned on outdoor temperature, provide insight into model hyperparameter sensitivity, and demonstrate how readily models can be generalized to unseen buildings.
Skomski, Elliott↗
A dynamic solvent chamber propagation estimation framework using RNN for warm solvent injection in heterogeneous reservoirs
Warm solvent injection (WSI), injecting low-temperature solvent into formations to reduce the viscosity of heavy oil, is a clean technology for heavy oil production through reducing greenhouse gas emissions and water usage. The success of WSI operation depends on the uniform development and propagation of solvent chambers in reservoirs. However, reservoir heterogeneity stemming from shale barriers plays a detrimental role in the conformance of solvent chamber development and oil production rate. In this work, we developed a novel recurrent neural network (RNN)-based framework with the capability of efficiently tracking and estimating the solvent chamber positions in heterogeneous reservoirs based on only production time-series data. The developed estimation model utilizes the “sequence-to-sequence" mapping methodology to correlate observed production time-series sequence and solvent chamber edge sequence via a long short-term memory (LSTM) algorithm. The trained RNN models exhibit high accuracy, evidenced by the predicted dynamic solvent chamber locations match the corresponding true locations from numerical simulation, with a high coefficient of determination (R 2 ) and a low mean squared error. Specifically, the achieved R 2 values exceed 0.98 on both the training and testing data. The developed RNN-based workflow was tested via several cases from both regularly- and irregularly-shaped shale barriers, and the results were promising. The predicted solvent chambers showed strong agreement with those obtained from numerical simulations. The major benefits of this workflow include reducing computational time and saving overall monitoring and tracking costs for conventional techniques. In conclusion, the present work would provide a good demonstration of the capability of practical integration of machine learning methods in solving engineering problems.
58 GEOSCIENCES↗
Predicting river turbidity in Pine Island Bayou using machine learning techniques coupled with variational mode decomposition
Elevated turbidity levels pose significant public health risks by facilitating the transport of harmful pollutants, including metals, organic compounds, and pathogenic microorganisms into the surface water. These conditions create serious challenges for public recreational water use and drinking water treatment, leading to economic losses and health risks. This study utilizes water monitoring data in Pine Island Bayou, Texas, and develops a Sequence-to-Sequence (S2S) model to predict turbidity using Attention-based Gated Recurrent Units with Encoder-Decoder (AT-GRU-ED) and Long Short-Term Memory (LSTM), coupled with Variational Mode Decomposition (VMD). Compared to the model without VMD, the model demonstrates satisfactory 72-hour turbidity prediction performance, achieving MAEs of 2.60 and 3.29 NTU (reductions of 53% and 58%), RMSEs of 21.08 and 31.49 NTU (reductions of 82% and 80%), and R² values of 0.96 and 0.84 on the validation and test sets, respectively. Feature importance analysis reveals that water temperature is the dominant factor influencing seasonal turbidity patterns, while real-time hourly rainfall significantly contributes to short-term variability. Turbidity typically peaks within 48 hours after rainfall events due to lagged effects from surface runoff and upstream flow. Findings suggest suspending recreational water use and water supply pumping for three days after heavy rainfall can benefit public health and improve water treatment processes. Discharges above 100 m3/s are found to accelerate sediment dilution and transport, reducing turbidity levels more quickly after the peak. In conclusion, the proposed model demonstrates reliable 72-hour turbidity prediction, supporting decision-making for water treatment plant operations and providing early warning for public recreational water use.
Deep learning↗
Rapid wavefield forecasting for earthquake early warning via deep sequence to sequence learning
We propose a deep learning model, WaveCastNet, to forecast high-dimensional wavefields. WaveCastNet integrates a convolutional long expressive memory architecture into a sequence-to-sequence forecasting framework, enabling it to model long-term dependencies and multiscale patterns in both space and time. By sharing weights across spatial and temporal dimensions, WaveCastNet requires significantly fewer parameters than more resource-intensive models such as transformers, resulting in faster inference times. Crucially, WaveCastNet also generalizes better than transformers to rare and critical seismic scenarios, such as high-magnitude earthquakes. Here, we show the ability of the model to predict the intensity and timing of destructive ground motions in real time, using simulated data from the San Francisco Bay Area. Furthermore, we demonstrate its zero-shot capabilities by evaluating WaveCastNet on real earthquake data. Our approach does not require estimating earthquake magnitudes and epicenters, steps that are prone to error in conventional methods, nor does it rely on empirical ground-motion models, which often fail to capture strongly heterogeneous wave propagation effects.
Geophysics↗
SYMBA: symbolic computation of squared amplitudes in high energy physics with machine learning
The cross section is one of the most important physical quantities in high-energy physics and the most time consuming to compute. While machine learning has proven to be highly successful in numerical calculations in high-energy physics, analytical calculations using machine learning are still in their infancy. In this work, we use a sequence-to-sequence model, specifically, a transformer, to compute a key element of the cross section calculation, namely, the squared amplitude of an interaction. We show that a transformer model is able to predict correctly 97.6% and 99% of squared amplitudes of quantum chromodynamics and quantum electrodynamics processes, respectively, at a speed that is up to orders of magnitude faster than current symbolic computation frameworks. We discuss the performance of the current model, its limitations and possible future directions for this work.
97 MATHEMATICS AND COMPUTING↗
Spatiotemporal forecasting of the edge localized modes in tokamak plasmas using neural networks
Artificial intelligence techniques have been increasingly adopted by the plasma and fusion science to address problems like plasma reconstruction, surrogate modeling, and tokamak/stellarator optimization. A key focus in sustained fusion research is the prediction and mitigation of edge-localized-modes (ELMs), instabilities that occur in short, periodic bursts and can cause erosion to the tokamak vessel wall. Recent research has demonstrated the power of neural networks in approximating continuous functions. In this work, we build spatiotemporal forecasting models that can predict the onset of ELMs and their evolution at early stages. We leverage recent advances in generative modeling, sequence-to-sequence modeling, and Fourier neural operators to propose architectures and training strategies that can learn to forecast short to long term dynamics of the noisy signals due to ELMs. We benchmark the developed model against a state-of-the-art foundation model using the beam emission spectroscopy (BES) data that captures the plasma fluctuations due to ELMs over a 8 x 8 spatial grid. Our models demonstrate high accuracy, outperforming the baselines, in predicting the evolution of BES signals during ELM events. Furthermore, the developed models exhibit high accuracy in predicting the rapid rise and relaxation of the signals due to ELMs within 30–80 µs.
edge localized modes↗
Deep Learning Methods for Symbolic Calculations in HEP
This project develops machine learning methods to accelerate symbolic calculations in high-energy physics. Using sequence-to-sequence transformer models, we construct frameworks to predict squared amplitudes and related quantities for Standard Model processes, including quantum electrodynamics, quantum chromodynamics, and electroweak interactions. The results demonstrate that deep learning can successfully learn complex symbolic relationships and provide a scalable approach to symbolic computation with potential applications in precision calculations and collider phenomenology.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data
Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.
Ye, Zhijing↗
Recent Progress on Surface Water Quality Models Utilizing Machine Learning Techniques
Surface waterbodies are heavily exposed to pollutants caused by natural disasters and human activities. Empowering sensor technologies in water quality monitoring, sufficient measurements have become available to develop machine learning (ML) models. Numerous ML models have quickly been adopted to predict water quality indicators in various surface waterbodies. This paper reviews 78 recent articles from 2022 to October 2024, categorizing water quality models utilizing ML into three groups: Point-to-Point (P2P), which estimates the current target value based on other measurements at the same time point; Sequence-to-Point (S2P), which utilizes previous time series data to predict the target value at one time point ahead; and Sequence-to-Sequence (S2S), which uses previous time series data to forecast sequential target values in the future. The ML models used in each group are classified and compared according to water quality indicators, data availability, and model performance. Widely used strategies for improving performance, including feature engineering, hyperparameter tuning, and transfer learning, are recognized and described to enhance model effectiveness. The interpretability limitations of ML applications are discussed. This review provides a perspective on emerging ML for surface water quality models.
machine learning (ML)↗
Building a Real-Time Flood Prediction Model for Improving Early Warning Systems in Ellicott City, Maryland
As flood events in the United States grow in frequency and intensity, the use of applied remote sensing analyses is increasingly necessary for effective flood monitoring and warning systems. The NASA DEVELOP National Program partnered with the local government of Howard County, Maryland, to investigate the use of machine learning for advanced flood risk detection, and to test the feasibility of integrating this approach into the county’s flood early warning system. To strengthen the efforts of the Howard County Office of Emergency Management (OEM), the project developed a statistical model capable of hindcasting the two severe flash flood events that devastated Ellicott City and transitioned to a ‘Long Short-Term Memory’ based sequence-to-sequence deep learning model with 8-hour forecast capability. The team combined data inputs from public sources including river and precipitation gauges, NASA and NOAA Earth observations, and numerical weather model products using scripts written in the Google Colaboratory Python scripting environment. In addition to designing the deep learning architecture, the team trained and tested the model, and evaluated its performance using Nash-Sutcliffe Efficiency. The final product, the Sequentially Trained Real-time EstimAted Model (STREAM) predicts stage height for the Hudson Branch gauge in Ellicott City using data products available in near real-time, including the High-Resolution Rapid Refresh model’s accumulated precipitation forecasts supplemented by stream gauge data from the OEM and the U.S. Geological Survey. STREAM was incorporated into an online dashboard in a user-friendly interface capable of triggering the alarms that initiate emergency response protocols up to 8 hours in advance of a predicted severe flood event. The project demonstrated the potential for the integration of open data and Earth observations into a flood risk forecasting tool capable of informing near real-time decision making.
NASA DEVELOP↗
Building a Real-Time Predictive Flood Model for Improving Early Warning Systems in Ellicott City, Maryland
As flood events in the United States grow in frequency and intensity, the use of applied remote sensing analyses is increasingly necessary for effective flood monitoring and warning systems. The NASA DEVELOP National Program partnered with the Howard County government in Maryland to investigate the use of machine learning for advanced flood risk detection, and to test the feasibility of integrating this approach into the county’s flood early warning system. To strengthen the efforts of the Howard County Office of Emergency Management (OEM), the project developed a prediction model capable of hindcasting the two severe flash flood events that devastated Ellicott City, and transitioned to an Long Short-Term Memory (LSTM) based sequence-to-sequence deep learning model with 8-hour forecast capability. The team combined data inputs from public sources including river and precipitation gauges, NASA and NOAA Earth observations, and numerical weather model products using scripts written in the Google Colaboratory Python scripting environment. In addition to designing the deep learning architecture, the team trained and tested the model, and evaluated its performance using the Nash-Sutcliffe Efficiency (NSE). The final product, called the Sequentially Trained Real-time EstimAted Model (STREAM), predicts stage height for the Hudson Branch gauge in Ellicott City using data products available in near real-time, including the High-Resolution Rapid Refresh (HRRR) model’s accumulated precipitation forecasts supplemented by stream gauge data from the OEM and the U.S. Geological Survey. STREAM was incorporated into an online dashboard in a user-friendly interface capable of triggering the alarms that initiate the OEM’s emergency response protocols up to 8 hours in advance of a predicted severe flood event. The project demonstrated the potential for the integration of open data and Earth observations into a flood risk forecasting tool capable of informing near real-time decision making.
Ryan Hammock↗
A Neural Network Parametrization of Volumetric Cloud Fraction Profiles Using Satellite Observations and MERRA-2 Reanalysis Meteorological Data
Clouds play a crucial role in regulating the hydrologic cycle and Earth's radiative energy budget, yet they are often poorly represented in global climate models (GCMs). This study applies deep machine learning techniques to develop a physical parameterization of volumetric cloud fraction (VCF), the fraction of a 3-D grid volume occupied by clouds using satellite lidar-radar measurements. The neural network (NN) captures the complicated relationships between observed VCF profiles and collocated meteorological variables from MERRA-2 reanalysis data. Our results show that the NN model, particularly a sequence-to-sequence long short-term memory (LSTM) network with a sixfactor loss function, effectively learns the underlying cloud physical processes. The NN model outperforms MERRA-2 reanalysis in representing low-level clouds in tropical and subtropical regions and low- and middle-level clouds over midlatitude storm-track regions, and also improves VCF histograms. These improvements are reflected in the vertical distributions of zonally, meridionally, and globally averaged VCFs, geographic distributions of low-, middle-, and high-level clouds, and seasonal variations in monthly-mean VCF. Furthermore, the NN predictions effectively capture the El Niño-Southern Oscillation (ENSO) effects and other interannual variations. The NN parameterization is further evaluated through a sensitivity analysis, in which a single predictor is perturbed at a time. This reveals that relative humidity (RH) is the dominant factor influencing variations in globally averaged VCF at low and middle altitudes, followed by temperature. At higher altitudes, temperature becomes the primary driver of VCF through its effect on RH. Changes in wind components had minimal impact on globally averaged VCF.
Shan Zeng↗