Cargando…

2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting

Recent approaches to time series forecasting, especially forecasting spatiotemporal sequences, have leveraged the approximation power of deep neural networks to model the complexity of such sequences, specifically approaches that are based on recurrent neural networks. Still, as spatiotemporal seque...

Descripción completa

Detalles Bibliográficos
Autores principales: Halim, Calvin Janitra, Kawamoto, Kazuhiko
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435848/
https://www.ncbi.nlm.nih.gov/pubmed/32731537
http://dx.doi.org/10.3390/s20154195
_version_ 1783572417790083072
author Halim, Calvin Janitra
Kawamoto, Kazuhiko
author_facet Halim, Calvin Janitra
Kawamoto, Kazuhiko
author_sort Halim, Calvin Janitra
collection PubMed
description Recent approaches to time series forecasting, especially forecasting spatiotemporal sequences, have leveraged the approximation power of deep neural networks to model the complexity of such sequences, specifically approaches that are based on recurrent neural networks. Still, as spatiotemporal sequences that arise in the real world are noisy and chaotic, modeling approaches that utilize probabilistic temporal models, such as deep Markov models (DMMs), are favorable because of their ability to model uncertainty, increasing their robustness to noise. However, approaches based on DMMs do not maintain the spatial characteristics of spatiotemporal sequences, with most of the approaches converting the observed input into 1D data halfway through the model. To solve this, we propose a model that retains the spatial aspect of the target sequence with a DMM that consists of 2D convolutional neural networks. We then show the robustness of our method to data with large variance compared with naive forecast, vanilla DMM, and convolutional long short-term memory (LSTM) using synthetic data, even outperforming the DNN models over a longer forecast period. We also point out the limitations of our model when forecasting real-world precipitation data and the possible future work that can be done to address these limitations, along with additional future research potential.
format Online
Article
Text
id pubmed-7435848
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-74358482020-08-25 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting Halim, Calvin Janitra Kawamoto, Kazuhiko Sensors (Basel) Article Recent approaches to time series forecasting, especially forecasting spatiotemporal sequences, have leveraged the approximation power of deep neural networks to model the complexity of such sequences, specifically approaches that are based on recurrent neural networks. Still, as spatiotemporal sequences that arise in the real world are noisy and chaotic, modeling approaches that utilize probabilistic temporal models, such as deep Markov models (DMMs), are favorable because of their ability to model uncertainty, increasing their robustness to noise. However, approaches based on DMMs do not maintain the spatial characteristics of spatiotemporal sequences, with most of the approaches converting the observed input into 1D data halfway through the model. To solve this, we propose a model that retains the spatial aspect of the target sequence with a DMM that consists of 2D convolutional neural networks. We then show the robustness of our method to data with large variance compared with naive forecast, vanilla DMM, and convolutional long short-term memory (LSTM) using synthetic data, even outperforming the DNN models over a longer forecast period. We also point out the limitations of our model when forecasting real-world precipitation data and the possible future work that can be done to address these limitations, along with additional future research potential. MDPI 2020-07-28 /pmc/articles/PMC7435848/ /pubmed/32731537 http://dx.doi.org/10.3390/s20154195 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Halim, Calvin Janitra
Kawamoto, Kazuhiko
2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title_full 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title_fullStr 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title_full_unstemmed 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title_short 2D Convolutional Neural Markov Models for Spatiotemporal Sequence Forecasting
title_sort 2d convolutional neural markov models for spatiotemporal sequence forecasting
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435848/
https://www.ncbi.nlm.nih.gov/pubmed/32731537
http://dx.doi.org/10.3390/s20154195
work_keys_str_mv AT halimcalvinjanitra 2dconvolutionalneuralmarkovmodelsforspatiotemporalsequenceforecasting
AT kawamotokazuhiko 2dconvolutionalneuralmarkovmodelsforspatiotemporalsequenceforecasting