Spatial heterogeneity has been regarded as an important issue in space–time prediction. Although some statistical methods of space–time predictions have been proposed to address spatial heterogeneity, the linear assumption makes it difficult for these methods to predict geographical processes accurately because geographical processes always involve complicated nonlinear characteristics. An extreme learning machine (ELM) has the advantage of approximating nonlinear relationships with a rapid learning speed and excellent generalization performance. However, determining how to incorporate spatial heterogeneity into an ELM to predict space–time data is an urgent problem. For this purpose, a new method called geographically weighted ELM (GWELM) is proposed to address spatial heterogeneity based on an ELM in this article. GWELM is essentially a locally varying ELM in which the parameters are regarded as functions of spatial locations, and geographically weighted least squares is applied to estimate the parameters in a local model. The proposed method is used to analyze two groups of different data sets, and the results demonstrate that the GWELM method is superior to the comparative method, which is also developed to address spatial heterogeneity.
Basin-wide sediment transport affects estimates of basin sediment yield, which is a fundamental scientific issue in drainage basin studies. Many studies have been conducted to examine erosion and deposition rates in drainage networks. In this study, we proposed a new approach using grain-size standard deviation model of sedimentary samples from different geomorphological units for numerical analysis and paleo-climate interpretation in the Shiyang River drainage basin, arid China. 1043 sedimentary samples were obtained from the upper reaches, the midstream alluvial plain and the terminal lake area; chronological frames were established based on 58 radiocarbon ages. Grain-size standard deviation model was introduced to examine sediment components according to grain-size and transport forces. In addition, transient paleo-climate simulations, including the Community Climate System Model version 3 and the Kiel models, were synthesized, as well as the results from PMIP 3.0 project, to detect the long-term climate backgrounds. Totally, we found four major common components, including fine particulates (<2 μm), fine silt (2–20 μm), sandy silt (20–200 μm), coarse sand (>200 μm), from basin-wide sedimentary samples. The fine particulates and fine silt components exist in all the sedimentary facies, showing long-term airborne aerosol changes and its transport by suspended load. There are some differences in ranges of sandy silt and coarse sand components, due to lake and river hydrodynamics, as well as the distance with the Gobi Desert. Paleo-climate simulations have shown that the strong Asian summer monsoon during the transition of the Last Deglaciation and Holocene was conducive to erosion and transport of basin-wide suspended load, also enhancing sediment sorting effects due to strong lake hydrodynamics. Our findings provide a new approach in research of long-term basin-wide sediment transport processes.
A large part of the world’s coastlines consists of sandy beaches and dunes that may undergo dramatic changes during storms. Extreme storm events in some cases dominate the erosion history of the coastline and may have dramatic impacts on densely populated coastal areas. Policy, research and historical background are essential elements that need to be interconnected for effective coastal planning and management.
This book discusses this framework, with
Water Wells and Boreholes focuses on wells that are used for drinking, industry, agriculture or other supply purposes. Other types of wells and boreholes are also covered, including boreholes for monitoring groundwater level and groundwater quality. This fully revised second edition updates and expands the content of the original book whilst maintaining its practical emphasis. The book follows a life-cycle approach to water wells, from identifying