Classification of rainfall variability by using artificial neural networks

International Journal of Climatology - Tập 21 Số 11 - Trang 1401-1414 - 2001
Silas Michaelides1, Constantinos S. Pattichis2, Georgia Kleovoulou2
1Meteorological Service, Nicosia, Cyprus
2Dept. of Computer Science, University of Cyprus, Cyprus

Tóm tắt

AbstractIn this paper, the usefulness of artificial neural networks (ANNs) as a suitable tool for the study of the medium and long‐term climatic variability is examined. A method for classifying the inherent variability of climatic data, as represented by the rainfall regime, is investigated. The rainfall recorded at a climatological station in Cyprus over a long time period has been used in this paper as the input for various ANN and cluster analysis models. The analysed rainfall data cover the time span 1917–1995. Using these values, two different procedures were followed for structuring the input vectors for training the ANN models: (a) each 1‐year subset consisting of the 12 monthly elements, and (b) each 2‐year subset consisting of the 24 monthly elements. Several ANN models with a varying number of output nodes have been trained, using an unsupervised learning paradigm, namely, the Kohonen's self‐organizing feature maps algorithm. For both the 1‐ and 2‐year subsets, 16 classes were empirically considered as the optimum for computing the prototype classes of weather variability for this meteorological parameter. The classification established by using the ANN methodology is subsequently compared with the classification generated by using cluster analysis, based on the agglomerative hierarchical clustering algorithm. To validate the classification results, the rainfall distributions for the more recent years 1996, 1997 and 1998 were utilized. The respective 1‐ and 2‐year distributions for these years were assigned to particular classes for both the ANN and cluster analysis procedures. Compared with cluster analysis, the ANN models were more capable of detecting even minor characteristics in the rainfall waveshapes investigated, and they also performed a more realistic categorization of the available data. It is suggested that the proposed ANN methodology can be applied to more climatological parameters, and with longer cycles. Copyright © 2001 Royal Meteorological Society

Từ khóa


Tài liệu tham khảo

Arbib MA, 1995, The Handbook of Brain Theory and Neural Networks

10.1175/1520-0450(1994)033<0909:CCOAII>2.0.CO;2

10.1007/BF00868190

Bulsari AB, 1996, Solving Engineering Problems with Neural Networks

Demuth H, 1994, MATLAB Neural Network Toolbox User's Guide

Duda RO, 1973, Pattern Classification and Scene Analysis

10.1175/1520-0477(1992)073<0049:NPCAN>2.0.CO;2

Everitt B, 1977, Cluster Analysis

10.1016/S0168-1923(97)00051-8

Furlan D, 1997, The climate of southeast Europe, 185

10.1016/S0165-1684(97)00203-X

Hartignan JA, 1975, Clustering Algorithms

Haykin S, 1994, Neural Networks—A Comprehensive Foundation

Kalogirou SA, 1997, A time series reconstruction of precipitation records using artificial neural networks, 2409

Kalogirou SA, 1998, Proceedings Fourth International Conference on Engineering Applications of Neural Networks, 383

10.1109/5.58325

10.1007/978-3-642-97610-0

10.1016/0022-1694(87)90059-X

10.1016/0022-1694(88)90086-8

10.1175/1520-0469(1969)26<636:APARBN>2.0.CO;2

Luo FL, 1997, Applied Neural Networks for Signal Processing

Maheras P, 1984, Application of the methods of factorial analysis for the study of the organization of the rhythm of the monthly precipitation values in Athens, Zeitschrift fur Meteorologie, 34, 100

10.1175/1520-0450(1996)035<0617:ANNFTP>2.0.CO;2

Micheli‐Tzanakou E, 1995, The Biomedical Engineering Handbook, 917

10.1175/1520-0469(1998)055<0465:AAARTS>2.0.CO;2

Norusis MJ, 1993, SPSS for Windows Professional Statistics Release 6.0

10.1175/1520-0477(1992)073<0995:TAIOSI>2.0.CO;2

Sanchez‐Sinencio E, 1992, Artificial Neural Gibraltar Networks, Paradigms, Applications and Hardware Implementations

Schizas CN, 1994, Forecasting minimum temperature with short time‐length data using artificial neural networks, Neural Network World, 2, 219

Taha MF, 1981, The climates of the Near East, 183

10.1029/97JC03414

10.1175/1520-0493(1989)117<2230:ANLAWF>2.0.CO;2

10.1007/978-3-642-65629-3_3

Thông tin
Thông tin xuất bản

International Journal of Climatology

Tập 21 Số 11

1401-1414

Thông tin tác giả