Incorporating spatial autocorrelation with neural networks in empirical land-use change models

Hone-Jay Chu, Chen Fa Wu, Yu Pin Lin

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Land-use data can accurately reflect spatial pattern dependence (ie, spatial autocorrelation) and a nonlinear relationship with driving variables. In this study landuse dynamics in the Paochiao Watershed, Taiwan are forcast for the next fifteen years by incorporating artificial neural networks with spatial autocorrelation (Auto-ANNs) into the conversion of land use and its effects (CLUE-s) model. In addition to spatial autocorrelations of land use, Auto-ANNs-CLUE-s considers the nonlinear relationships between driving factors and land-use patterns. Results of a three-map comparison indicate that the Auto-ANNs-CLUE-s model has a better overall performance than Autologistic-CLUE-s. The Auto-ANNs-CLUE-s is highly applicable for all resolutions from multiresolution validation. The results of landscape metrics demonstrate the prevalence of urban sprawl in the study area. The proposed model is an alternative means of improving land use and environmental planning.

Original languageEnglish
Pages (from-to)384-404
Number of pages21
JournalEnvironment and Planning B: Planning and Design
Volume40
Issue number3
DOIs
Publication statusPublished - 2013 Jan 1

Fingerprint

Autocorrelation
Land use
neural network
autocorrelation
land use change
land use
Neural networks
environmental planning
urban sprawl
land use planning
artificial neural network
Watersheds
Taiwan
effect
watershed
Planning
performance

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Environmental Science(all)

Cite this

@article{8d0a1c8de7914ed0a5533b00701a5535,
title = "Incorporating spatial autocorrelation with neural networks in empirical land-use change models",
abstract = "Land-use data can accurately reflect spatial pattern dependence (ie, spatial autocorrelation) and a nonlinear relationship with driving variables. In this study landuse dynamics in the Paochiao Watershed, Taiwan are forcast for the next fifteen years by incorporating artificial neural networks with spatial autocorrelation (Auto-ANNs) into the conversion of land use and its effects (CLUE-s) model. In addition to spatial autocorrelations of land use, Auto-ANNs-CLUE-s considers the nonlinear relationships between driving factors and land-use patterns. Results of a three-map comparison indicate that the Auto-ANNs-CLUE-s model has a better overall performance than Autologistic-CLUE-s. The Auto-ANNs-CLUE-s is highly applicable for all resolutions from multiresolution validation. The results of landscape metrics demonstrate the prevalence of urban sprawl in the study area. The proposed model is an alternative means of improving land use and environmental planning.",
author = "Hone-Jay Chu and Wu, {Chen Fa} and Lin, {Yu Pin}",
year = "2013",
month = "1",
day = "1",
doi = "10.1068/b37116",
language = "English",
volume = "40",
pages = "384--404",
journal = "Environment and Planning B: Planning and Design",
issn = "0265-8135",
publisher = "Pion Ltd.",
number = "3",

}

Incorporating spatial autocorrelation with neural networks in empirical land-use change models. / Chu, Hone-Jay; Wu, Chen Fa; Lin, Yu Pin.

In: Environment and Planning B: Planning and Design, Vol. 40, No. 3, 01.01.2013, p. 384-404.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Incorporating spatial autocorrelation with neural networks in empirical land-use change models

AU - Chu, Hone-Jay

AU - Wu, Chen Fa

AU - Lin, Yu Pin

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Land-use data can accurately reflect spatial pattern dependence (ie, spatial autocorrelation) and a nonlinear relationship with driving variables. In this study landuse dynamics in the Paochiao Watershed, Taiwan are forcast for the next fifteen years by incorporating artificial neural networks with spatial autocorrelation (Auto-ANNs) into the conversion of land use and its effects (CLUE-s) model. In addition to spatial autocorrelations of land use, Auto-ANNs-CLUE-s considers the nonlinear relationships between driving factors and land-use patterns. Results of a three-map comparison indicate that the Auto-ANNs-CLUE-s model has a better overall performance than Autologistic-CLUE-s. The Auto-ANNs-CLUE-s is highly applicable for all resolutions from multiresolution validation. The results of landscape metrics demonstrate the prevalence of urban sprawl in the study area. The proposed model is an alternative means of improving land use and environmental planning.

AB - Land-use data can accurately reflect spatial pattern dependence (ie, spatial autocorrelation) and a nonlinear relationship with driving variables. In this study landuse dynamics in the Paochiao Watershed, Taiwan are forcast for the next fifteen years by incorporating artificial neural networks with spatial autocorrelation (Auto-ANNs) into the conversion of land use and its effects (CLUE-s) model. In addition to spatial autocorrelations of land use, Auto-ANNs-CLUE-s considers the nonlinear relationships between driving factors and land-use patterns. Results of a three-map comparison indicate that the Auto-ANNs-CLUE-s model has a better overall performance than Autologistic-CLUE-s. The Auto-ANNs-CLUE-s is highly applicable for all resolutions from multiresolution validation. The results of landscape metrics demonstrate the prevalence of urban sprawl in the study area. The proposed model is an alternative means of improving land use and environmental planning.

UR - http://www.scopus.com/inward/record.url?scp=84878466908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878466908&partnerID=8YFLogxK

U2 - 10.1068/b37116

DO - 10.1068/b37116

M3 - Article

VL - 40

SP - 384

EP - 404

JO - Environment and Planning B: Planning and Design

JF - Environment and Planning B: Planning and Design

SN - 0265-8135

IS - 3

ER -