NARX neural network approach for the monthly prediction of groundwater levels in Sylhet Sadar,Bangladesh

Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of groundwater resources. In this study, a new nonlinear autoregressive with exogenous inputs(NARX) network has been applied to simulate monthly groundwater levels in a well of Sylhet Sadar at a local scale. The Levenberg-Marquardt(LM) and Bayesian Regularization(BR) algorithms were used to train the NARX network, and the results were compared to determine the best architecture for predicting monthly groundwater levels over time. The comparison between LM and BR showed that NARX-BR has advantages over predicting monthly levels based on the Mean Squared Error(MSE), coefficient of determination(R~2), and Nash-Sutcliffe coefficient of efficiency(NSE). The results show that BR is the most accurate method for predicting groundwater levels with an error of ± 0.35 m. This method is applied to the management of irrigation water source, which provides important information for the prediction of local groundwater fluctuation at local level during a short period.     

Use of an artificial neural network for analysis of the susceptibility to landslides at Boun,Korea

The purpose of this study was to develop landslide susceptibility analysis techniques using artificial neural networks and to apply the resulting techniques to the study area of Boun in Korea. Landslide locations were identified in the study area from interpretation of aerial photographs and field survey data. A spatial database of the topography, soil type, timber cover, geology, and land cover was constructed and the landslide-related factors were extracted from the spatial database. Using these factors, the susceptibility to landslides was analyzed by artificial neural network methods. The results of the landslide susceptibility maps were compared and verified using known landslide locations at another area, Yongin, in Korea. A Geographic Information System (GIS) was used to analyze efficiently the vast amount of data and an artificial neural network turned out to be an effective tool to analyze the landslide susceptibility.     

人工神经网络及其在短期气候预测中的应用

从业务实际出发，提出了面向短期气候预测的神经网络。选用主分量作为网络的输入和输出，大大减少了输入输出节点数，重点突出了大尺度影响变化关系，提高了实际预报的稳定性；用全局寻优的SA算法取代经典BP算法，使网络学习训练更充分，知识获取更全面；针对业务实际设计代价函数，保证了网络学习训练能适应短期气候预测业务的要求，学习目的更明确，针对性更强。     

Human genome behaviour: a powerful mechanism for optimizing the use of space technology in surveying networks design

An approach based on the behaviour of human genome is developed to efficiently provide a general framework for optimizing the use of space technology in surveying networks design. The developed approach attempts to apply the successful self-organizing principles based upon the biological evolution to artificial intelligence. It mimics the phenomena of natural selection observed in nature to achieve its goals by continuously adopting a population of candidate solutions and improving its performance over successive generations. The goal of adaptation is to find the best solution that optimizes the design of a surveying network based on the use of satellite observations. This network can be defined as a set of stations, co-ordinated by a series of sessions formed by placing receivers on the stations. The problem is to search for the best order for observing these sessions to give the best observation schedule at minimum cost. The obtained results prove the effectiveness of the developed technique in term of solution quality and computational efforts. The Corresponding Author in formed me that his address is likely to change soon. Please contact me, leick@spatial.maine.edu for the latest on this change.     

A comparative study of ANN and Neuro-fuzzy for the prediction of dynamic constant of rockmass

Physico-mechanical properties of rocks have great significance in all operational parts in mining activities, from exploration to final dispatch of material. Compressional wave velocity (p-wave velocity) and anisotropic behaviour of rocks are two such properties which help to understand the rock response under varying stress conditions. They also influence the breakage mechanism of rock. There are different methods to determine thep-wave velocity and anisotropyin situ and in the laboratory. These methods are cumbersome and time consuming. Fuzzy set theory, Fuzzy logic and Neural Networks techniques seem very well suited for typical geotechnical problems. In conjunction with statistics and conventional mathematical methods, hybrid methods can be developed that may prove to be a step forward in modeling geotechnical problems. Here, we have developed and compared two different models, Neuro-fuzzy systems (combination of fuzzy and artificial neural network systems) and Artificial neural network systems, for the prediction of compressional wave velocity.     

Landslide hazard and risk mapping at catchment scale in the Arno River basin

We present the methodologies adopted and the outcomes obtained in the analysis of landslide risk in the basin of the Arno River (Central Italy) in the framework of a project sponsored by the Basin Authority of the Arno River, started in the year 2002 and completed at the beginning of 2005. In particular, a complete set of methods and applications for the assessment of landslide susceptibility and risk are described and discussed. A new landslide inventory of the whole area was realized, using conventional (aerial-photo interpretation and field surveys) and non-conventional methods (e.g. remote sensing techniques such as DInSAR and PS-InSAR). The great majority of the mapped mass movements are rotational slides (75%), solifluctions and other shallow slow movements (17%) and flows (5%), while soil slips, and other rapid landslides, seem less frequent everywhere within the basin. The relationships between landslide characteristics and environmental factors have been assessed through statistical analysis. As expected, the results show a strong control of land cover, lithology and morphology on landslide occurrence. The landslide frequency-size distribution shows a typical scaling behaviour already underlined in other landslide inventories worldwide. The assessment of landslide hazard in terms of probability of occurrence in a given time, based for mapped landslides on direct and indirect observations of the state of activity and recurrence time, has been extended to landslide-free areas through the application of statistical methods implemented in an artificial neural network (ANN). Unique conditions units (UCU) were defined by the map overlay of landslide preparatory factors (lithology, land cover, slope gradient, slope curvature and upslope contributing area) and afterwards used to construct a series of model vectors for the training and test of the ANN. Various different ANNs were selected throughout the basin, until each UCU was assigned a degree of membership to a susceptibility and a hazard class. Model validation confirms that prediction results are very good, with an average percentage of correctly recognized mass movements of about 85%. The analysis also revealed the existence of a large number of unmapped mass movements, thus contributing to the completeness of the final inventory. Temporal hazard was estimated via the translation of state of activity in recurrence time and hence probability of occurrence. The following intersection of hazard values with vulnerability and exposure figures, obtained by reclassification of digital vector mapping at 1:10,000 scale, lead to the definition of risk values for each terrain unit for different periods of time into the future. The final results of the research are now undergoing a process of integration and implementation within land planning and risk prevention policies and practices at local and national level.     

Application of grey correlation method to evaluate potential groundwater recharge sites

Artificial recharge is a practical tool available for increasing the groundwater storage capacity. The efficiency of artificial recharge is related to various hydrogeological factors of the target area. In this study, a variable saturated groundwater flow model, FEMWATER, was used to evaluate the arrival times of recharged water that infiltrates from an artificial recharge pond to the groundwater table under various hydrogeological conditions. Forty-five arrival times were generated by FEMWATER. The relationships between the arrival times and hydrogeological factors used in the simulation of FEMWATER were analyzed by the grey correlation method. The results show the order of importance of the factors as they influence the arrival time. In order from high to low importance, they are α, D _g, θ _e, D _p, K _S and β. D _g and D _p are interpreted as the potential for movement of the recharge water; θ_e is the water storage capacity of soil, and K _S represents the ability of soil to transport water. α and β describe the characteristic curve of the unsaturated soil. The method was applied to evaluate a suitable site for artificial recharge in the Yun-Lin area. Grey correlation analysis was performed to obtain the grey correlation grade using the minimum arrival time as a reference sequence. An index is proposed herein to determine the recharge efficiency of 20 sampling sites. A contour mapping of index values at the 20 sampling sites identified three areas for artificial aquifer recharge in Yun-Lin. Area A in the upper plain is considered more appropriate for groundwater recharge than areas B and C in the coast.     

上海菜区人工模拟暴雨入渗试验研究初报

根据水量平衡原理,采用人工模拟降雨入渗实验装置,对上海新老菜区土壤进行不同墒情状态下的多种雨强人工模拟降雨入渗试验,获取了上海菜区代表性土壤的暴雨入渗过程动态实验数据和入渗基本参数,并分析了土壤水分变化规律,可作为上海菜区开展暴雨雨涝灾情评估的依据,对类似土壤条件的长江流域平原地区菜田,也有一定的参考价值。     

人工神经网络西太平洋副热带高压预报业务系统

本文应用常规500hpa资料,结合具有较稠密、高分辨的“TOVS”资料（卫星信息资料）,分析、归纳了西太平洋副热带高压大幅度北移、南蓝（120°E脊线）的经验规则,在此基础上选择了具有最优下降因子的BP算法。在人工神经网络的结构方面设计了神经网络的前处理功能,将众多的单因子经基于专家系统的前处理模块,归纳的规则,作为网络的输入端,经网络学习、训练、迭代获得了较快的收敛速度和较高的历史拟合率,建立了“人工神经网络西太平洋副热带高压预报业务系统”