A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps

Y. Tulunay; E. T. Şenalp; Ş Öz; L. I. Dorman; E. Tulunay; S. S. Menteş; M. E. Akcan

doi:10.5194/angeo-26-3945-2008

A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps

Y. Tulunay, E. T. Şenalp^*, Ş Öz, L. I. Dorman, E. Tulunay, S. S. Menteş, M. E. Akcan

^*Corresponding author for this work

Department of Meteorological Engineering

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

Atmospheric processes are highly nonlinear. A small group at the METU in Ankara has been working on a fuzzy data driven generic model of nonlinear processes. The model developed is called the Middle East Technical University Fuzzy Neural Network Model (METU-FNN-M). The METU-FNN-M consists of a Fuzzy Inference System (METU-FIS), a data driven Neural Network module (METU-FNN) of one hidden layer and several neurons, and a mapping module, which employs the Bezier Surface Mapping technique. In this paper, the percent cloud coverage (%CC) and cloud top temperatures (CTT) are forecast one month ahead of time at 96 grid locations. The probable influence of cosmic rays and sunspot numbers on cloudiness is considered by using the METU-FNN-M.

Original language	English
Pages (from-to)	3945-3954
Number of pages	10
Journal	Annales Geophysicae
Volume	26
Issue number	12
DOIs	https://doi.org/10.5194/angeo-26-3945-2008
Publication status	Published - 24 Nov 2008

Keywords

Interplanetary physics (Cosmic rays; Energetic particles; Instruments and techniques)

Access to Document

10.5194/angeo-26-3945-2008

Cite this

@article{c43c35182f214389ad57cdd1a7650207,

title = "A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps",

abstract = "Atmospheric processes are highly nonlinear. A small group at the METU in Ankara has been working on a fuzzy data driven generic model of nonlinear processes. The model developed is called the Middle East Technical University Fuzzy Neural Network Model (METU-FNN-M). The METU-FNN-M consists of a Fuzzy Inference System (METU-FIS), a data driven Neural Network module (METU-FNN) of one hidden layer and several neurons, and a mapping module, which employs the Bezier Surface Mapping technique. In this paper, the percent cloud coverage (%CC) and cloud top temperatures (CTT) are forecast one month ahead of time at 96 grid locations. The probable influence of cosmic rays and sunspot numbers on cloudiness is considered by using the METU-FNN-M.",

keywords = "Interplanetary physics (Cosmic rays; Energetic particles; Instruments and techniques)",

author = "Y. Tulunay and {\c S}enalp, {E. T.} and {\c S} {\"O}z and Dorman, {L. I.} and E. Tulunay and Mente{\c s}, {S. S.} and Akcan, {M. E.}",

year = "2008",

month = nov,

day = "24",

doi = "10.5194/angeo-26-3945-2008",

language = "English",

volume = "26",

pages = "3945--3954",

journal = "Annales Geophysicae",

issn = "0992-7689",

publisher = "Copernicus Publications",

number = "12",

}

TY - JOUR

T1 - A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps

AU - Tulunay, Y.

AU - Şenalp, E. T.

AU - Öz, Ş

AU - Dorman, L. I.

AU - Tulunay, E.

AU - Menteş, S. S.

AU - Akcan, M. E.

PY - 2008/11/24

Y1 - 2008/11/24

N2 - Atmospheric processes are highly nonlinear. A small group at the METU in Ankara has been working on a fuzzy data driven generic model of nonlinear processes. The model developed is called the Middle East Technical University Fuzzy Neural Network Model (METU-FNN-M). The METU-FNN-M consists of a Fuzzy Inference System (METU-FIS), a data driven Neural Network module (METU-FNN) of one hidden layer and several neurons, and a mapping module, which employs the Bezier Surface Mapping technique. In this paper, the percent cloud coverage (%CC) and cloud top temperatures (CTT) are forecast one month ahead of time at 96 grid locations. The probable influence of cosmic rays and sunspot numbers on cloudiness is considered by using the METU-FNN-M.

AB - Atmospheric processes are highly nonlinear. A small group at the METU in Ankara has been working on a fuzzy data driven generic model of nonlinear processes. The model developed is called the Middle East Technical University Fuzzy Neural Network Model (METU-FNN-M). The METU-FNN-M consists of a Fuzzy Inference System (METU-FIS), a data driven Neural Network module (METU-FNN) of one hidden layer and several neurons, and a mapping module, which employs the Bezier Surface Mapping technique. In this paper, the percent cloud coverage (%CC) and cloud top temperatures (CTT) are forecast one month ahead of time at 96 grid locations. The probable influence of cosmic rays and sunspot numbers on cloudiness is considered by using the METU-FNN-M.

KW - Interplanetary physics (Cosmic rays; Energetic particles; Instruments and techniques)

UR - http://www.scopus.com/inward/record.url?scp=79551641517&partnerID=8YFLogxK

U2 - 10.5194/angeo-26-3945-2008

DO - 10.5194/angeo-26-3945-2008

M3 - Article

AN - SCOPUS:79551641517

SN - 0992-7689

VL - 26

SP - 3945

EP - 3954

JO - Annales Geophysicae

JF - Annales Geophysicae

IS - 12

ER -

A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this