Identification of minimal timespan problem for recurrent neural networks with application to cyclone wind-intensity prediction

Time series prediction relies on past data points to make robust predictions. The span of past data points is important for some applications since prediction will not be possible unless the minimal timespan of the data points is available. This is a problem for cyclone wind-intensity prediction, where prediction needs to be made as a cyclone is identified. This paper presents an empirical study on minimal timespan required for robust prediction using Elman recurrent neural networks. Two different training methods are evaluated for training Elman recurrent network that includes cooperative coevolution and backpropagation-though time. They are applied to the prediction of the wind intensity in cyclones that took place in the South Pacific over past few decades. The results show that a minimal timespan is an important factor that leads to the measure of robustness in prediction performance and strategies should be taken in cases when the minimal timespan is needed.

[1]  J.N.K. Liu,et al.  A neural network regression model for tropical cyclone forecast , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[2]  S. Chaudhuri,et al.  Track and intensity forecast of tropical cyclones over the North Indian Ocean with multilayer feed forward neural nets , 2015 .

[3]  Risto Miikkulainen,et al.  Accelerated Neural Evolution through Cooperatively Coevolved Synapses , 2008, J. Mach. Learn. Res..

[4]  Nikolay I. Nikolaev,et al.  Recursive Bayesian Recurrent Neural Networks for Time-Series Modeling , 2010, IEEE Transactions on Neural Networks.

[5]  Mengjie Zhang,et al.  On the issue of separability for problem decomposition in cooperative neuro-evolution , 2012, Neurocomputing.

[6]  Kenneth A. De Jong,et al.  A Cooperative Coevolutionary Approach to Function Optimization , 1994, PPSN.

[7]  Chandan Roy,et al.  Cyclone track forecasting based on satellite images using artificial neural networks , 2009 .

[8]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[9]  Gwo-Fong Lin,et al.  A hybrid neural network model for typhoon-rainfall forecasting , 2009 .

[10]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[11]  Charles R. Sampson,et al.  Statistical, 5-Day Tropical Cyclone Intensity Forecasts Derived from Climatology and Persistence , 2003 .

[12]  K. Emanuel.  Increasing destructiveness of tropical cyclones over the past 30 years , 2005, Nature.

[13]  Lewis F. Richardson,et al.  Weather Prediction by Numerical Process , 1922 .

[14]  Rohitash Chandra,et al.  Cooperative neuro-evolution of Elman recurrent networks for tropical cyclone wind-intensity prediction in the South Pacific region , 2015, 2015 IEEE Congress on Evolutionary Computation (CEC).

[15]  Mark DeMaria,et al.  An Updated Statistical Hurricane Intensity Prediction Scheme (SHIPS) for the Atlantic and Eastern North Pacific Basins , 1999 .

[16]  Kalyanmoy Deb,et al.  A Computationally Efficient Evolutionary Algorithm for Real-Parameter Optimization , 2002, Evolutionary Computation.

[17]  Wu Meng,et al.  Application of Support Vector Machines in Financial Time Series Forecasting , 2007 .

[18]  Jukka Saarinen,et al.  Time Series Prediction with Multilayer Perception, FIR and Elman Neural Networks , 1996 .

[19]  S. Chaudhuri,et al.  Predictability of landfall location and surge height of tropical cyclones over North Indian Ocean (NIO) , 2014, Natural Hazards.

[20]  Rohitash Chandra,et al.  Application of cooperative neuro-evolution of Elman recurrent networks for a two-dimensional cyclone track prediction for the south pacific region , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[21]  Mengjie Zhang,et al.  Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction , 2012, Neurocomputing.

[22]  Wei Du,et al.  Time series forecasting by neural networks: A knee point-based multiobjective evolutionary algorithm approach , 2014, Expert Syst. Appl..

[23]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[24]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[25]  M. Samuelides.  Neural Identification of Controlled Dynamical Systems and Recurrent Networks , 2005 .

[26]  Carlo Combi,et al.  Data mining with Temporal Abstractions: learning rules from time series , 2007, Data Mining and Knowledge Discovery.

[27]  Long Jin,et al.  A Nonlinear Artificial Intelligence Ensemble Prediction Model for Typhoon Intensity , 2008 .