skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach
Title: Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach
Abstract This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction.  more » « less
Award ID(s):
2029840
PAR ID:
10485136
Author(s) / Creator(s):
 ;  ;  ;  ;  ;  
Publisher / Repository:
DOI PREFIX: 10.1029
Date Published:
Journal Name:
Space Weather
Volume:
22
Issue:
1
ISSN:
1542-7390
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; (, Space Weather)
    Abstract This study reconstructs total electron content (TEC) maps in the vicinity of the Korean Peninsula by employing a deep convolutional generative adversarial network and Poisson blending (DCGAN‐PB). Our interest is to rebuild small‐scale ionosphere structures on the TEC map in a local region where pronounced ionospheric structures, such as the equatorial ionization anomaly, are absent. The reconstructed regional TEC maps have a domain of 120°–135.5°E longitude and 25.5°–41°N latitude with 0.5° resolution. To achieve this, we first train a DCGAN model by using the International Reference Ionosphere‐based TEC maps from 2002 to 2019 (except for 2010 and 2014) as a training data set. Next, the trained DCGAN model generates synthetic complete TEC maps from observation‐based incomplete TEC maps. Final TEC maps are produced by blending of synthetic TEC maps with observed TEC data by PB. The performance of the DCGAN‐PB model is evaluated by testing the regeneration of the masked TEC observations in 2010 (solar minimum) and 2014 (solar maximum). Our results show that a good correlation between the masked and model‐generated TEC values is maintained even with a large percentage (∼80%) of masking. The performance of the DCGAN‐PB model is not sensitive to local time, solar activity, and magnetic activity. Thus, the DCGAN‐PB model can reconstruct fine ionospheric structures in regions where observations are sparse and distinguishing ionospheric structures are absent. This model can contribute to near real‐time monitoring of the ionosphere by immediately providing complete TEC maps. 
    more » « less
  2. ; ; ; ; ; (, Space Weather)
    Abstract In this research, we present data‐driven forecasting of ionospheric total electron content (TEC) using the Long‐Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar‐terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density, and speed the three components of interplanetary magnetic field, Lyman‐alpha, the Kp, Dst, and Polar Cap (PC) indices. The TEC measurements are taken with 15‐s cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008–2017 data set, including the top five parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 h ahead, with 30‐min cadence. The results indicate that very good forecasts with low root mean square (RMS) error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar‐terrestrial environment. 
    more » « less
  3. ; ; ; (, Frontiers in Artificial Intelligence)
    Soil moisture (SM) plays a significant role in determining the probability of flooding in a given area. Currently, SM is most commonly modeled using physically-based numerical hydrologic models. Modeling the natural processes that take place in the soil is difficult and requires assumptions. Besides, hydrologic model runtime is highly impacted by the extent and resolution of the study domain. In this study, we propose a data-driven modeling approach using Deep Learning (DL) models. There are different types of DL algorithms that serve different purposes. For example, the Convolutional Neural Network (CNN) algorithm is well suited for capturing and learning spatial patterns, while the Long Short-Term Memory (LSTM) algorithm is designed to utilize time-series information and to learn from past observations. A DL algorithm that combines the capabilities of CNN and LSTM called ConvLSTM was recently developed. In this study, we investigate the applicability of the ConvLSTM algorithm in predicting SM in a study area located in south Louisiana in the United States. This study reveals that ConvLSTM significantly outperformed CNN in predicting SM. We tested the performance of ConvLSTM based models by using a combination of different sets of predictors and different LSTM sequence lengths. The study results show that ConvLSTM models can predict SM with a mean areal Root Mean Squared Error (RMSE) of 2.5% and mean areal correlation coefficients of 0.9 for our study area. ConvLSTM models can also provide predictions between discrete SM observations, making them potentially useful for applications such as filling observational gaps between satellite overpasses. 
    more » « less
  4. ; ; ; ; ; (, Engineering applications of artificial intelligence)
    This study proposes an intelligent techno-economic assessment framework for wind energy end users, using a novel dual-input convolutional bidirectional long short-term memory (Dual-ConvBiLSTM) architecture to predict dynamic levelized cost of energy (LCOE). The proposed architecture separates weight matrices for wind supervisory control and data acquisition (SCADA) data and financial data. This allows the model to integrate both data streams at every time step through a custom dual-input cell. This approach is compared with five baseline architectures: Recurrent Neural Network (RNN), LSTM, BiLSTM, ConvLSTM, and ConvBiLSTM, which process data through separate parallel branches and concatenate outputs before final prediction. The Dual-ConvBiLSTM achieves an LCOE estimate of $4.0391 cents/kWh, closest to the actual value of $4.0450 cents/kWh, with a root mean squared error reduction of 51.8% compared to RNN, 47.0% to LSTM, 40.0% to BiLSTM, 36.7% to ConvLSTM, and 34.4% to ConvBiLSTM, demonstrating superior capability in capturing complex interactions between SCADA data and financial parameters. This intelligent framework potentially enhances economic assessment and enables end users to accelerate renewable energy deployment through more reliable financial prediction. 
    more » « less
  5. ; ; ; ; ; (, Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers)
    Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email