Font Size: a A A

Application Of BP Neural Network Supported By Cloud Computing Platform In Flood Disaster Loss Assessment

Posted on:2018-09-20Degree:MasterType:Thesis
Country:ChinaCandidate:W ZhangFull Text:PDF
GTID:2348330518961602Subject:Cartography and Geographic Information System
Abstract/Summary:PDF Full Text Request
Flood disaster is one of the most serious natural disasters in China.Its high frequency,wide influence range and large economic loss have seriously restricted the development of our national economy.Therefore,it is necessary to make an effective assessment of the economic loss of flood disaster.However,in recent years,due to the increase of human activities,the data types and the number of floods have been increasing,which may lead to the problems such as time-consuming and difficult training in the application of traditional BP neural network in flood disaster assessment.Considering the superiority and practicability of the cloud computing platform in dealing with large amounts of data,the research on the existing flood damage assessment has not been applied in the cloud computing platform.Therefore,it is of practical significance to study the application of BP neural network supported by cloud computing platform in flood disaster assessment.In this paper,a county in the Poyang Lake area of Jiangxi Province is selected as the research area.The main contents are as follows:Firstly,this paper introduces the current research situation of flood disaster assessment and related technology,and expounds the key technology used in this paper: Hadoop distributed computing framework and BP neural network,which provide the theoretical basis for the application of flood disaster assessment.Secondly,we use the method of mathematical statistics to collect and collate the original data,combine the flood disaster theory to select the flood impact factor which can reflect the flood disaster,and obtain the calculated sample data and test data according to the flood impact factor.Then,based on the basic structure of BP neural network algorithm,the algorithm is divided into two parts: the first part is the network learning part and the other part is the weight adjustment part.According to the algorithm of the split,respectively,in the Map function and Reduce function to achieve,get the cloud computing platform to support the Mapreduce-bp algorithm;Finally,according to the Mapreduce-bp algorithm,the flood risk assessment model of Mapreduce-bp neural network is established.The model is used to study the economic losses of floods in 2013,and the final results are obtained.The results of this study show that the Mapreduce-bp flood damage assessment model supported by the cloud computing platform can accurately and quickly estimate the economic loss value of the flood disaster.Therefore,the model can effectively evaluate the flood damage in the case of large data Provide new solutions.
Keywords/Search Tags:flood damage assessment, Hadoop, MapReduce, BP neural network
PDF Full Text Request
Related items