Population dynamics in Yangtze River Delta: A neural-network and spatial statistical analysis

  • Chao Wang
  • , Runhe Shi*
  • , Wei Wei
  • , Chaoshun Liu
  • , Tao Qi
  • , Wei Gao
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Population dynamics has major impacts on regional ecosystem and socioeconomic development. Its prediction has become a key step for assessing ecosystems and socioeconomic development. Using the population data of Yangtze River Delta, a model created by Back Propagation (BP) neural network were adapted to probe and describe the dynamic evolution, and the Moran Index was used in analyzing spatial autocorrelation quantitatively. The predicted population result is quietly similar to the real situation. Population increasing represents a stable trend from 2003 to 2007 and slowed down in last two years. The population distribution pattern calculated through global Moran index barely varies, and most cities in the middle and north of the study area reveal a High-High (HH) pattern. This paper provides scientific basis for further coordinated development, comprehensive revitalization and government policy.

Original languageEnglish
Title of host publicationRemote Sensing and Modeling of Ecosystems for Sustainability IX
DOIs
StatePublished - 2012
EventRemote Sensing and Modeling of Ecosystems for Sustainability IX - San Diego, CA, United States
Duration: 16 Aug 201216 Aug 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8513
ISSN (Print)0277-786X

Conference

ConferenceRemote Sensing and Modeling of Ecosystems for Sustainability IX
Country/TerritoryUnited States
CitySan Diego, CA
Period16/08/1216/08/12

Keywords

  • BP neural network
  • Global Moran Index
  • Population distribution pattern
  • Population dynamics change

Fingerprint

Dive into the research topics of 'Population dynamics in Yangtze River Delta: A neural-network and spatial statistical analysis'. Together they form a unique fingerprint.

Cite this