Predictions of the maximum amplitude for solar cycle 23 and its subsequentbehavior using nonlinear methods

Two nonlinear methods are employed for the prediction of the maximum amplit ude for solar cycle 23 and its declining behavior. First, a new heuristic m ethod based on the second derivative of the (conveniently smoothed) sunspot data is proposed. The curvature of the smoothed sunspot data at cycle mini mum appears to correlate (R similar or equal to 0.92) with the cycle's late r-occurring maximum amplitude. Secondly, in order to predict the near-maxim um and declining activity of solar cycle 23, a neural network analysis of t he annual mean sunspot time series is also performed. The results of the pr esent study are then compared with some other recent predictions.