The objective of this study was comparative study of artificial neural networks (ANN) and wavelet artificial neural networks (WANN) for time-series groundwater depth data (GWD) forecasting with various curve fractal dimensions. The paper offered a better method of revealing the change characteristics of GWD. Time series prediction based on ANN algorithms is fundamentally difficult to capture the data change details, when the time-series GWD data changes are more complex. For this purpose, Wavelet analysis and fractal theory methods are proposed to link to ANN models in predicting GWD and analysis the change characteristics. The trend and random components were separated from the original time-series GWD using wavelet methods. The fractal dimension is convenient for quantitatively describing the irregularity or randomness of time series data. Three types of training algorithms for ANN and WANN models using a Mallat decomposition algorithm were investigated as case study at three sites in the Ganzhou region of northwest China to find an optimal model that is suitable for certain characteristics of time-series GWD data. The simulation results indicate that both WANN and ANN models with the Bayesian regularization algorithm are accurate in reproducing GWD at sites with smaller fractal dimensions. However, WANN models alone are suitable for sites at which the fractal dimension of the wavelet decomposition detail components is larger. Prediction error is also greater when the fractal dimension is larger.
Monsoon and arid regions in the Asia-Africa-Australia (A-A-A) realm occupy more than 60% of the total area of these continents. Geological evidence showed that significant changes occurred to the A-A-A environments of the monsoon and arid regions, the land-ocean configuration in the Eastern Hemisphere, and the topography of the Tibetan Plateau in the Cenozoic. Motivated by this background, numerical experiments for 5 typical geological periods during the Cenozoic were conducted using a coupled ocean-atmosphere general circulation model to systemically explore the formations and evolutionary histories of the Cenozoic A-A-A monsoon and arid regions under the influences of continental drift and plateau uplift. Results of the numerical experiments indicate that the timings and causes of the formations of monsoon and arid regions in the A-A-A realm were very different. The northern and southern African monsoons existed during the mid-Paleocene, while the South Asian monsoon appeared in the Eocene after the Indian Subcontinent moved into the tropical Northern Hemisphere. In contrast, the East Asian monsoon and northern Australian monsoon were established much later in the Miocene. The establishment of the tropical monsoons in northern and southern Africa, South Asia, and Australia were determined by both the continental drift and seasonal migration of the Inter-Tropical Convergence Zone (ITCZ), while the position and height of the Tibetan Plateau were the key factor for the establishment of the East Asian monsoon. The presence of the subtropical arid regions in northern and southern Africa, Asia, and Australia depended on the positions of the continents and the control of the planetary scale subtropical high pressure zones, while the arid regions in the Arabian Peninsula and West Asia were closely related to the retreat of the Paratethys Sea. The formation of the mid-latitude arid region in the Asian interior, on the other hand, was the consequence of the uplift of the Tibetan Plateau. These results from this study provide insight to the important roles played by the earth's tectonic boundary conditions in the formations and evolutions of regional climates during geological times.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.