Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data

Regional Landslide Susceptibility Zonation(LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression(LR), Artificial Neural Networks(ANN) and Support Vector Machine(SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis(LDA), receiver operating characteristic(ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadilyincreasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes. Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.

Multi-path routing algorithm in WSN using an improvedparticle swarm optimization

To slove the problems of constrained energy and unbalanced load of wireless sensor network(WSN)nodes,a multipath load balancing routing algorithm based on neighborhood subspace cooperation is proposed.The algorithm adopts the improved particle swarm optimization(PSO)algorithm,takes the shortest distance and minimum energy consumption as optimization target and divides the nodes in one-hop neighborhood near the base station area into different regions.Furthermore,the algorithm designs a fitness function to find the best node in each region as a relay node and forward the data in parallel through the different paths of the relay nodes.The simulation results show that the proposed algorithm can reduce energy consumption and average end-to-end delay,balance network load and prolong network lifetime effectively.

Buffer allocation method of serial production lines based on improved ant colony optimization algorithm

Buffer influences the performance of production lines greatly.To solve the buffer allocation problem(BAP) in serial production lines with unreliable machines effectively,an optimization method is proposed based on an improved ant colony optimization(IACO) algorithm.Firstly,a problem domain describing buffer allocation is structured.Then a mathematical programming model is established with an objective of maximizing throughput rate of the production line.On the basis of the descriptions mentioned above,combining with a two-opt strategy and an acceptance probability rule,an IACO algorithm is built to solve the BAP.Finally,the simulation experiments are designed to evaluate the proposed algorithm.The results indicate that the IACO algorithm is valid and practical.

The Concept of MDSA （Macro Demand Spatial Approach） on Spatial Demand Forecasting for Main Development Area in Transmission Planning

MDSA （macro demand spatial approach） is an approach introduced in long time electricity demand forecasting considering location. It will be used at transmission planning and policy decision on electricity infrastructure development in a region. In the model, MDSA combined with PCA （principal component analysis） and QA （qualitative analysis） to determine main development area in region and the variables that affecting electricity demand in there. Main development area is an area with industrial domination as a driver of economic growth. The electricity demand driver variables are different for type of electricity consumer. However, they will be equal for main development areas. The variables which have no significant effect can be reduced by using PCA. The generated models tested to assess whether it still at the range of confidence level of electricity demand forecasting. At the case study, generated model for main development areas at South Sumatra Subsystem as a part of Sumatra Interconnection System is still in the range of confidence level. Thus, MDSA can be proposed as alternative approach in transmission planning that considering location.

Regionalization Methodology Systems of Aquatic Ecosystems in China and the Case Study of Huaihe River Basin

本文提出的水生态区划方法体系包括指导思想、基本原则、分区方法、命名与编码规则几个部分。其核心指导思想是科学发展观及人与自然和谐的理念;基本原则有区域相关性原则、协调原则、主导功能原则和分及区划原则;分区方法、命名与编码规则则随分区等级和研究尺度而异。本文采用2级分区的思路,提出了全国水生态区划分方案,包括6个水生态一级区和34个水生态二级区。基于以下3类7种水生态服务功能:水生态保育类(包括水源涵养、水土保持和物种保护),水生态调控类(包括洪水调蓄和生境维持),水生态服务类(包括产品提供和景观保障),以淮河流域为例,将3级水生态区划方法应用于流域尺度。在实例区共划分出2个水生态一级区、3个水生态二级区和21个水生态三级区。

20世纪以来美国土地用途管制发展历程的回顾与展望

本文主要回顾了美国土地用途管制的发展历程,从20世纪上半叶的区划(法),经由二战后的理性规划和1970年代的历史保护和美学管制,发展到1990年代的新都市主义和形态条例。进入21世纪后,随着生态环境保护日益成为主流,美国土地用途管制正逐渐向19世纪去中心化的传统回归。

Planning Method of Non-Development Zone in Southern Jiangyin

Jiangyin was the earliest to conduct Non-development zone planning and has attracted the attention of people all over China because it is regarded as the Chinese version of Smart Growth. The planning process is as follows. Based on SPOT and TM satellite remote sensing images develop a regional land use map with high precision using artificial interpretation methods. Then, according to the relationship between anti-development suitability and disasters, agriculture, ecology, built-up area distribution and other geographical factors, generate a comprehensive evaluation chart of anti-development suitability using GIS analysis, such as buffer analysis and overlay analysis. Later, with a regional land use map and anti-development suitability evaluation chart, using the principle of ecological security network and learning from the management experience of nature reserves, draw the scope of Non-development zone and core area. Last, put forward a series of protective measures for the above Non-development zone, that is only allowed to develop agriculture and tourism, strictly restricted industrial projects and urban real estate activities, and all existing industrial factories must be moved to planned industrial parks. This is good practice whereby local governments keep land resources for future generations and more advanced than an urban expansion strategy. This method is very useful for promoting land use layout optimization in Southern Jiangsu Developed Areas.

An iterative interval analysis method based on Kriging-HDMR for uncertainty problems

In recent years,growing attention has been paid to the interval investigation of uncertainty problems.However,the contradiction between accuracy and efficiency always exists.In this paper,an iterative interval analysis method based on Kriging-HDMR(IIAMKH)is proposed to obtain the lower and upper bounds of uncertainty problems considering interval variables.Firstly,Kriging-HDMR method is adopted to establish the meta-model of the response function.Then,the Genetic Algorithm&Sequential Quadratic Programing(GA&SQP)hybrid optimization method is applied to search for the minimum/maximum values of the meta-model,and thus the corresponding uncertain parameters can be obtained.By substituting them into the response function,we can acquire the predicted interval.Finally,an iterative process is developed to improve the accuracy and stability of the proposed method.Several numerical examples are investigated to demonstrate the effectiveness of the proposed method.Simulation results indicate that the presented IIAMKH can obtain more accurate results with fewer samples.