Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting

Afan Galih Salman, Yaya Heryadi, Edi Abdurahman, Wayan Suparta

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

Weather forecasting has gained attention many researchers from various research communities due to its effect to the global human life. The emerging deep learning techniques in the last decade coupled and the wide availability of massive weather observation data have motivated many researches to explore hidden hierarchical pattern in the large volume of weather dataset for weather forecasting. The purposes of this research are to build a robust and adaptive statistical model for forecasting univariate weather variable in Indonesian airport area and to explore the effect of intermediate weather variable related to accuracy prediction using single layer Long Short Memory Model (LSTM) model and multi layers LSTM model. The proposed forecasting model is an extension of LSTM model by adding intermediate variable signal into LSTM memory block. The premise is that two highly related patterns in input dataset will rectify the input patterns so make it easier for the model to learn and recognize the pattern from the training dataset. In an effort to achieve a robust model for learning and recognizing weather pattern, this research will also explore various architectures such as single layer LSTM and Multiple Layer LSTM (4 layers LSTM). The dataset is weather variable data collected by Weather Underground at Hang Nadim Indonesia airport. This research used visibility as predicted data and temperature, pressure, humidity, dew point as intermediates data. The best model of LSTM in this experiment is multiple layers LSTM and the best intermediate data is pressure variable. Using the pressure variable this model has gained the validation accuracy 0.8060 and RMSE 0.0775.

Original languageEnglish
Pages (from-to)89-98
Number of pages10
JournalProcedia Computer Science
Volume135
DOIs
Publication statusPublished - 1 Jan 2018
Externally publishedYes
Event3rd International Conference on Computer Science and Computational Intelligence, ICCSCI 2018 - Tangerang, Indonesia
Duration: 7 Sep 20188 Sep 2018

Fingerprint

Weather forecasting
Airports
Long short-term memory
Data storage equipment
Visibility
Atmospheric humidity
Availability

Keywords

  • intermediate
  • LSTM
  • RMSE
  • validation accuracy
  • weather forecasting

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting. / Salman, Afan Galih; Heryadi, Yaya; Abdurahman, Edi; Suparta, Wayan.

In: Procedia Computer Science, Vol. 135, 01.01.2018, p. 89-98.

Research output: Contribution to journalConference article

@article{cd3cc9e9782f4490a00a0c84bf315627,
title = "Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting",
abstract = "Weather forecasting has gained attention many researchers from various research communities due to its effect to the global human life. The emerging deep learning techniques in the last decade coupled and the wide availability of massive weather observation data have motivated many researches to explore hidden hierarchical pattern in the large volume of weather dataset for weather forecasting. The purposes of this research are to build a robust and adaptive statistical model for forecasting univariate weather variable in Indonesian airport area and to explore the effect of intermediate weather variable related to accuracy prediction using single layer Long Short Memory Model (LSTM) model and multi layers LSTM model. The proposed forecasting model is an extension of LSTM model by adding intermediate variable signal into LSTM memory block. The premise is that two highly related patterns in input dataset will rectify the input patterns so make it easier for the model to learn and recognize the pattern from the training dataset. In an effort to achieve a robust model for learning and recognizing weather pattern, this research will also explore various architectures such as single layer LSTM and Multiple Layer LSTM (4 layers LSTM). The dataset is weather variable data collected by Weather Underground at Hang Nadim Indonesia airport. This research used visibility as predicted data and temperature, pressure, humidity, dew point as intermediates data. The best model of LSTM in this experiment is multiple layers LSTM and the best intermediate data is pressure variable. Using the pressure variable this model has gained the validation accuracy 0.8060 and RMSE 0.0775.",
keywords = "intermediate, LSTM, RMSE, validation accuracy, weather forecasting",
author = "Salman, {Afan Galih} and Yaya Heryadi and Edi Abdurahman and Wayan Suparta",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.procs.2018.08.153",
language = "English",
volume = "135",
pages = "89--98",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Single Layer & Multi-layer Long Short-Term Memory (LSTM) Model with Intermediate Variables for Weather Forecasting

AU - Salman, Afan Galih

AU - Heryadi, Yaya

AU - Abdurahman, Edi

AU - Suparta, Wayan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Weather forecasting has gained attention many researchers from various research communities due to its effect to the global human life. The emerging deep learning techniques in the last decade coupled and the wide availability of massive weather observation data have motivated many researches to explore hidden hierarchical pattern in the large volume of weather dataset for weather forecasting. The purposes of this research are to build a robust and adaptive statistical model for forecasting univariate weather variable in Indonesian airport area and to explore the effect of intermediate weather variable related to accuracy prediction using single layer Long Short Memory Model (LSTM) model and multi layers LSTM model. The proposed forecasting model is an extension of LSTM model by adding intermediate variable signal into LSTM memory block. The premise is that two highly related patterns in input dataset will rectify the input patterns so make it easier for the model to learn and recognize the pattern from the training dataset. In an effort to achieve a robust model for learning and recognizing weather pattern, this research will also explore various architectures such as single layer LSTM and Multiple Layer LSTM (4 layers LSTM). The dataset is weather variable data collected by Weather Underground at Hang Nadim Indonesia airport. This research used visibility as predicted data and temperature, pressure, humidity, dew point as intermediates data. The best model of LSTM in this experiment is multiple layers LSTM and the best intermediate data is pressure variable. Using the pressure variable this model has gained the validation accuracy 0.8060 and RMSE 0.0775.

AB - Weather forecasting has gained attention many researchers from various research communities due to its effect to the global human life. The emerging deep learning techniques in the last decade coupled and the wide availability of massive weather observation data have motivated many researches to explore hidden hierarchical pattern in the large volume of weather dataset for weather forecasting. The purposes of this research are to build a robust and adaptive statistical model for forecasting univariate weather variable in Indonesian airport area and to explore the effect of intermediate weather variable related to accuracy prediction using single layer Long Short Memory Model (LSTM) model and multi layers LSTM model. The proposed forecasting model is an extension of LSTM model by adding intermediate variable signal into LSTM memory block. The premise is that two highly related patterns in input dataset will rectify the input patterns so make it easier for the model to learn and recognize the pattern from the training dataset. In an effort to achieve a robust model for learning and recognizing weather pattern, this research will also explore various architectures such as single layer LSTM and Multiple Layer LSTM (4 layers LSTM). The dataset is weather variable data collected by Weather Underground at Hang Nadim Indonesia airport. This research used visibility as predicted data and temperature, pressure, humidity, dew point as intermediates data. The best model of LSTM in this experiment is multiple layers LSTM and the best intermediate data is pressure variable. Using the pressure variable this model has gained the validation accuracy 0.8060 and RMSE 0.0775.

KW - intermediate

KW - LSTM

KW - RMSE

KW - validation accuracy

KW - weather forecasting

UR - http://www.scopus.com/inward/record.url?scp=85053152677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053152677&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2018.08.153

DO - 10.1016/j.procs.2018.08.153

M3 - Conference article

AN - SCOPUS:85053152677

VL - 135

SP - 89

EP - 98

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -