Prediction of surface air temperatures by neural network, example based on three-year temperature monitoring at Spořilov station

L. Bodri, V. Čermák

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Artificial time-delay feed-forward neural networks (NN) with one hidden layer and error back-propagation learning are used to predict surface air temperatures (SAT) for six hours up to one day. The networks were trained and tested with the use of data covering a total of 26280 hours (three years) monitored in the period 1998-2000 in location Spořilov (suburban area of Prague). The NN models provided a good fit with the measured data. Phase diagrams as well as the results of the variability studies of SAT revealed a fundamental difference between summer temperatures (April-September) and winter temperatures (October-March). Results of the trial runs indicated that NN models perform better when both periods are trained separately. The results show that relatively simple neural networks, with an adequate choice of the input data, can achieve reasonably good accuracy in one-lag as well as in multi-lag predictions. For the "summer" period the total errors give 0.055 and/or 0.044 mean accuracy of predicted values in training and testing sets, respectively. Similarly high mean accuracy of the simulated values of 0.057 and 0.065 was obtained for the training and testing sets in the winter season. Similarly good results with the mean error of 0.028 were obtained for the summer period of the year 2001, which were used for additional testing (see Appendix). Higher accuracy obtained for the year 2001 is due to the fact, that warm temperature extremes, which are generally predicted with less accuracy, did not occurred in the summer 2001.

Original languageEnglish
Pages (from-to)173-184
Number of pages12
JournalStudia Geophysica et Geodaetica
Volume47
Issue number1
DOIs
Publication statusPublished - 2003

Fingerprint

surface temperature
air temperature
stations
summer
Neural networks
Monitoring
air
monitoring
Air
prediction
predictions
time lag
temperature
winter
Testing
education
Temperature
suburban areas
back propagation
suburban area

ASJC Scopus subject areas

  • Geochemistry and Petrology
  • Geophysics

Cite this

@article{5df4812e06f3423f833155a3fe1f9124,
title = "Prediction of surface air temperatures by neural network, example based on three-year temperature monitoring at Spořilov station",
abstract = "Artificial time-delay feed-forward neural networks (NN) with one hidden layer and error back-propagation learning are used to predict surface air temperatures (SAT) for six hours up to one day. The networks were trained and tested with the use of data covering a total of 26280 hours (three years) monitored in the period 1998-2000 in location Spořilov (suburban area of Prague). The NN models provided a good fit with the measured data. Phase diagrams as well as the results of the variability studies of SAT revealed a fundamental difference between summer temperatures (April-September) and winter temperatures (October-March). Results of the trial runs indicated that NN models perform better when both periods are trained separately. The results show that relatively simple neural networks, with an adequate choice of the input data, can achieve reasonably good accuracy in one-lag as well as in multi-lag predictions. For the {"}summer{"} period the total errors give 0.055 and/or 0.044 mean accuracy of predicted values in training and testing sets, respectively. Similarly high mean accuracy of the simulated values of 0.057 and 0.065 was obtained for the training and testing sets in the winter season. Similarly good results with the mean error of 0.028 were obtained for the summer period of the year 2001, which were used for additional testing (see Appendix). Higher accuracy obtained for the year 2001 is due to the fact, that warm temperature extremes, which are generally predicted with less accuracy, did not occurred in the summer 2001.",
author = "L. Bodri and V. Čerm{\'a}k",
year = "2003",
doi = "10.1023/A:1022211924646",
language = "English",
volume = "47",
pages = "173--184",
journal = "Studia Geophysica et Geodaetica",
issn = "0039-3169",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Prediction of surface air temperatures by neural network, example based on three-year temperature monitoring at Spořilov station

AU - Bodri, L.

AU - Čermák, V.

PY - 2003

Y1 - 2003

N2 - Artificial time-delay feed-forward neural networks (NN) with one hidden layer and error back-propagation learning are used to predict surface air temperatures (SAT) for six hours up to one day. The networks were trained and tested with the use of data covering a total of 26280 hours (three years) monitored in the period 1998-2000 in location Spořilov (suburban area of Prague). The NN models provided a good fit with the measured data. Phase diagrams as well as the results of the variability studies of SAT revealed a fundamental difference between summer temperatures (April-September) and winter temperatures (October-March). Results of the trial runs indicated that NN models perform better when both periods are trained separately. The results show that relatively simple neural networks, with an adequate choice of the input data, can achieve reasonably good accuracy in one-lag as well as in multi-lag predictions. For the "summer" period the total errors give 0.055 and/or 0.044 mean accuracy of predicted values in training and testing sets, respectively. Similarly high mean accuracy of the simulated values of 0.057 and 0.065 was obtained for the training and testing sets in the winter season. Similarly good results with the mean error of 0.028 were obtained for the summer period of the year 2001, which were used for additional testing (see Appendix). Higher accuracy obtained for the year 2001 is due to the fact, that warm temperature extremes, which are generally predicted with less accuracy, did not occurred in the summer 2001.

AB - Artificial time-delay feed-forward neural networks (NN) with one hidden layer and error back-propagation learning are used to predict surface air temperatures (SAT) for six hours up to one day. The networks were trained and tested with the use of data covering a total of 26280 hours (three years) monitored in the period 1998-2000 in location Spořilov (suburban area of Prague). The NN models provided a good fit with the measured data. Phase diagrams as well as the results of the variability studies of SAT revealed a fundamental difference between summer temperatures (April-September) and winter temperatures (October-March). Results of the trial runs indicated that NN models perform better when both periods are trained separately. The results show that relatively simple neural networks, with an adequate choice of the input data, can achieve reasonably good accuracy in one-lag as well as in multi-lag predictions. For the "summer" period the total errors give 0.055 and/or 0.044 mean accuracy of predicted values in training and testing sets, respectively. Similarly high mean accuracy of the simulated values of 0.057 and 0.065 was obtained for the training and testing sets in the winter season. Similarly good results with the mean error of 0.028 were obtained for the summer period of the year 2001, which were used for additional testing (see Appendix). Higher accuracy obtained for the year 2001 is due to the fact, that warm temperature extremes, which are generally predicted with less accuracy, did not occurred in the summer 2001.

UR - http://www.scopus.com/inward/record.url?scp=0038758815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038758815&partnerID=8YFLogxK

U2 - 10.1023/A:1022211924646

DO - 10.1023/A:1022211924646

M3 - Article

VL - 47

SP - 173

EP - 184

JO - Studia Geophysica et Geodaetica

JF - Studia Geophysica et Geodaetica

SN - 0039-3169

IS - 1

ER -