Neural network and regression methods for optimizations between two meteorological factors

Ki Hong Shin, Woonhak Baek, Kyungsik Kim, Cheol Hwan You, Ki Ho Chang, Dong In Lee, Seong Soo Yum

Research output: Contribution to journalArticle

Abstract

This paper is concerned with the temporal variation characteristics of two meteorological factors (temperature and humidity) in four metropolitan cities (Seoul, Busan, Daegu, Daejeon) in South Korea. Data are extracted from seven years (2008 to 2014) of hourly time series data in meteorological offices of the Korea Meteorological Administration. Using the detrended cross-correlation analysis (DCCA) method, the DCCA coefficient of temperature is compared to that of humidity from daily time series data during four seasons in the four metropolitan cities. In particular, as window size s increases, the DCCA cross-correlation coefficient approaches 0.034 at a time lag of 14 days in the case of spring in Seoul. We find the weak cross-correlation between temperature and humidity at different time lags of 14, 21 and 28 days in spring in Seoul, and the errors E T in the ANN are relatively larger values than that of any other season in both the ANN and the MRM. Particularly, in the ANN model, there exist relatively a large error value of temperature as the characteristics of the non-stationary, deterministically chaotic and noisy meteorological data extracted for the short-term prediction rather than the long-term prediction.

Original languageEnglish
Pages (from-to)778-796
Number of pages19
JournalPhysica A: Statistical Mechanics and its Applications
Volume523
DOIs
Publication statusPublished - 2019 Jun 1

Fingerprint

Cross-correlation
cross correlation
regression analysis
Regression
Neural Networks
Correlation Analysis
Humidity
optimization
Optimization
humidity
Time Lag
Time Series Data
time lag
South Korea
temperature
Prediction
Korea
Noisy Data
predictions
correlation coefficients

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Condensed Matter Physics

Cite this

Shin, Ki Hong ; Baek, Woonhak ; Kim, Kyungsik ; You, Cheol Hwan ; Chang, Ki Ho ; Lee, Dong In ; Yum, Seong Soo. / Neural network and regression methods for optimizations between two meteorological factors. In: Physica A: Statistical Mechanics and its Applications. 2019 ; Vol. 523. pp. 778-796.
@article{7c9c1c17fb6c431a94c1a39fcc966a01,
title = "Neural network and regression methods for optimizations between two meteorological factors",
abstract = "This paper is concerned with the temporal variation characteristics of two meteorological factors (temperature and humidity) in four metropolitan cities (Seoul, Busan, Daegu, Daejeon) in South Korea. Data are extracted from seven years (2008 to 2014) of hourly time series data in meteorological offices of the Korea Meteorological Administration. Using the detrended cross-correlation analysis (DCCA) method, the DCCA coefficient of temperature is compared to that of humidity from daily time series data during four seasons in the four metropolitan cities. In particular, as window size s increases, the DCCA cross-correlation coefficient approaches 0.034 at a time lag of 14 days in the case of spring in Seoul. We find the weak cross-correlation between temperature and humidity at different time lags of 14, 21 and 28 days in spring in Seoul, and the errors E T in the ANN are relatively larger values than that of any other season in both the ANN and the MRM. Particularly, in the ANN model, there exist relatively a large error value of temperature as the characteristics of the non-stationary, deterministically chaotic and noisy meteorological data extracted for the short-term prediction rather than the long-term prediction.",
author = "Shin, {Ki Hong} and Woonhak Baek and Kyungsik Kim and You, {Cheol Hwan} and Chang, {Ki Ho} and Lee, {Dong In} and Yum, {Seong Soo}",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/j.physa.2019.01.113",
language = "English",
volume = "523",
pages = "778--796",
journal = "Physica A: Statistical Mechanics and its Applications",
issn = "0378-4371",
publisher = "Elsevier",

}

Neural network and regression methods for optimizations between two meteorological factors. / Shin, Ki Hong; Baek, Woonhak; Kim, Kyungsik; You, Cheol Hwan; Chang, Ki Ho; Lee, Dong In; Yum, Seong Soo.

In: Physica A: Statistical Mechanics and its Applications, Vol. 523, 01.06.2019, p. 778-796.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network and regression methods for optimizations between two meteorological factors

AU - Shin, Ki Hong

AU - Baek, Woonhak

AU - Kim, Kyungsik

AU - You, Cheol Hwan

AU - Chang, Ki Ho

AU - Lee, Dong In

AU - Yum, Seong Soo

PY - 2019/6/1

Y1 - 2019/6/1

N2 - This paper is concerned with the temporal variation characteristics of two meteorological factors (temperature and humidity) in four metropolitan cities (Seoul, Busan, Daegu, Daejeon) in South Korea. Data are extracted from seven years (2008 to 2014) of hourly time series data in meteorological offices of the Korea Meteorological Administration. Using the detrended cross-correlation analysis (DCCA) method, the DCCA coefficient of temperature is compared to that of humidity from daily time series data during four seasons in the four metropolitan cities. In particular, as window size s increases, the DCCA cross-correlation coefficient approaches 0.034 at a time lag of 14 days in the case of spring in Seoul. We find the weak cross-correlation between temperature and humidity at different time lags of 14, 21 and 28 days in spring in Seoul, and the errors E T in the ANN are relatively larger values than that of any other season in both the ANN and the MRM. Particularly, in the ANN model, there exist relatively a large error value of temperature as the characteristics of the non-stationary, deterministically chaotic and noisy meteorological data extracted for the short-term prediction rather than the long-term prediction.

AB - This paper is concerned with the temporal variation characteristics of two meteorological factors (temperature and humidity) in four metropolitan cities (Seoul, Busan, Daegu, Daejeon) in South Korea. Data are extracted from seven years (2008 to 2014) of hourly time series data in meteorological offices of the Korea Meteorological Administration. Using the detrended cross-correlation analysis (DCCA) method, the DCCA coefficient of temperature is compared to that of humidity from daily time series data during four seasons in the four metropolitan cities. In particular, as window size s increases, the DCCA cross-correlation coefficient approaches 0.034 at a time lag of 14 days in the case of spring in Seoul. We find the weak cross-correlation between temperature and humidity at different time lags of 14, 21 and 28 days in spring in Seoul, and the errors E T in the ANN are relatively larger values than that of any other season in both the ANN and the MRM. Particularly, in the ANN model, there exist relatively a large error value of temperature as the characteristics of the non-stationary, deterministically chaotic and noisy meteorological data extracted for the short-term prediction rather than the long-term prediction.

UR - http://www.scopus.com/inward/record.url?scp=85063318217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063318217&partnerID=8YFLogxK

U2 - 10.1016/j.physa.2019.01.113

DO - 10.1016/j.physa.2019.01.113

M3 - Article

AN - SCOPUS:85063318217

VL - 523

SP - 778

EP - 796

JO - Physica A: Statistical Mechanics and its Applications

JF - Physica A: Statistical Mechanics and its Applications

SN - 0378-4371

ER -