A neural network tool for analyzing trends in rainfall

Rainfall, like all other natural phenomena is highly unpredictable. Traditionally, principal component analysis and spectral analysis are used to understand trends in rainfall over long periods. In this paper, we present a new method that appears to be better than existing methods to understand the long-term behavior of rainfall phenomena. Using a case study on the rainfall in Kerala State, the southern part of Indian Peninsula, we show that a new kind of neural network known as the adaptive basis function network is a promising tool for climatic studies, especially rainfall analysis. The paper also reveals that in spite of the fluctuations resulting from the nonlinearity in the system, the trends in the rainfall pattern in Kerala state have remained unaffected over the past 87 years from 1893 to 1980. We also successfully filter out the chaotic part of the system and illustrate that its effects are marginal over long-term predictions.

[1]  Ninan Sajeeth Philip,et al.  Adaptive basis function for artificial neural networks , 2002, Neurocomputing.

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  The Relation between Indian Monsoon Rainfall, the Southern Oscillation, and Hemispheric Air and Sea Temperature: 1884–1984 , 1987 .

[4]  Henry F. Diaz,et al.  Prediction of all‐India summer monsoon rainfall with regional and large‐scale parameters , 1988 .

[5]  Erode Subramanian Raja Gopal.  Statistical Mechanics and Properties of Matter: Theory and Applications , 1974 .

[6]  市村 浩.  E.S.Raja Gopal : Statistical Mechanics and Properties of Matter ; Theory and Applications, Ellis Horwood, Chichester and John Wiley & Sons, New York, 1974, vii+302ページ, 23.5×16cm, 10,170円 , 1976 .

[7]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[8]  A. Chowdhury,et al.  Variations in meteorological floods during summer monsoon over India , 2021, MAUSAM.

[9]  H A Ceccatto,et al.  Predicting Indian monsoon rainfall: a neural network approach , 1994 .

[10]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[11]  S. V. Singh,et al.  Possibility of Predicting Indian Monsoon Rainfall on Reduced Spatial and Temporal Scales , 1992 .

[12]  M. A. Kraaijveld.  Small Sample Behavior of Multi-Layer Feedforward Network Classifiers: Theoretical and Practical Aspects , 1993 .

[13]  S. K. Jadhav,et al.  The southern oscillation and its relation to the monsoon rainfall , 1984 .

[14]  D. A. Mooley,et al.  Cyclic Fluctuations in the Flood Area and Relationship with the Double (Hale) Sunspot Cycle , 1981 .

[15]  H. Annamalai,et al.  Intrinsic problems in the seasonal prediction of the Indian summer monsoon rainfall , 1995 .

[16]  B. Parthasarathy,et al.  Indian rainfall in relation to the sunspot cycle: 1871–1978 , 1984 .

[17]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.