Application of change detection techniques driven by expert opinions for small-area studies in developing countries

IF 2.7 Q2 MULTIDISCIPLINARY SCIENCES
Tanaka A. Mbendana , Anesu D. Gumbo , Simbarashe Jombo , Ephias Mugari , Evison Kapangaziwiri
{"title":"Application of change detection techniques driven by expert opinions for small-area studies in developing countries","authors":"Tanaka A. Mbendana ,&nbsp;Anesu D. Gumbo ,&nbsp;Simbarashe Jombo ,&nbsp;Ephias Mugari ,&nbsp;Evison Kapangaziwiri","doi":"10.1016/j.sciaf.2025.e02594","DOIUrl":null,"url":null,"abstract":"<div><div>Rapid urbanisation in developing countries, fuelled by population growth and rural-to-urban migration, poses significant challenges for service delivery in under-resourced municipalities. Dangamvura Township in Mutare, Zimbabwe, exemplifies this issue, potentially overwhelming the City of Mutare services. Resource limitations have hindered the quantification of these changes. This study assesses changes in land use and land cover (LULC) in Dangamvura Township, Mutare, Zimbabwe, between 2010 and 2022, using stakeholder-driven methods, Google Earth Pro (GEP) and machine learning in R. A four-tier methodology was applied integrating R and expert validation through GEP to classify and quantify changes in LULC. The analysis identified built-up areas, cropland, and bare land as the main LULC classes. The results from R showed that built-up areas expanded from 3.74 km² in 2010 to 8.64 km² in 2022, the bare land decreased from 3.10 km² to 1.42 km², and the cropland declined from 6.06 km² to 2.84 km². GEP assessments indicated an increase in built-up areas from 5.08 km² to 8.91 km², a reduction in bare land from 3.57 km² to 1.97 km², and a decrease in cropland from 4.25 km² to 2.02 km² over the same period. These findings highlight significant urban expansion and declining agricultural and undeveloped land. The disparities between the R statistical software and the GEP results underscore the importance of integrating expert opinions to validate classifications, particularly in small-area studies with spatial heterogeneity. The results provide valuable insights for urban planning and decision-making, highlighting the need for adaptive strategies to manage urban growth and infrastructure development. The tiered methodology demonstrates the potential of combining advanced remote sensing tools with local knowledge to achieve robust LULC assessments in resource-limited settings, guiding sustainable urban planning and informing policy interventions to address challenges associated with rapid urbanisation in resource-limited countries.</div></div>","PeriodicalId":21690,"journal":{"name":"Scientific African","volume":"27 ","pages":"Article e02594"},"PeriodicalIF":2.7000,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientific African","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S246822762500064X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Rapid urbanisation in developing countries, fuelled by population growth and rural-to-urban migration, poses significant challenges for service delivery in under-resourced municipalities. Dangamvura Township in Mutare, Zimbabwe, exemplifies this issue, potentially overwhelming the City of Mutare services. Resource limitations have hindered the quantification of these changes. This study assesses changes in land use and land cover (LULC) in Dangamvura Township, Mutare, Zimbabwe, between 2010 and 2022, using stakeholder-driven methods, Google Earth Pro (GEP) and machine learning in R. A four-tier methodology was applied integrating R and expert validation through GEP to classify and quantify changes in LULC. The analysis identified built-up areas, cropland, and bare land as the main LULC classes. The results from R showed that built-up areas expanded from 3.74 km² in 2010 to 8.64 km² in 2022, the bare land decreased from 3.10 km² to 1.42 km², and the cropland declined from 6.06 km² to 2.84 km². GEP assessments indicated an increase in built-up areas from 5.08 km² to 8.91 km², a reduction in bare land from 3.57 km² to 1.97 km², and a decrease in cropland from 4.25 km² to 2.02 km² over the same period. These findings highlight significant urban expansion and declining agricultural and undeveloped land. The disparities between the R statistical software and the GEP results underscore the importance of integrating expert opinions to validate classifications, particularly in small-area studies with spatial heterogeneity. The results provide valuable insights for urban planning and decision-making, highlighting the need for adaptive strategies to manage urban growth and infrastructure development. The tiered methodology demonstrates the potential of combining advanced remote sensing tools with local knowledge to achieve robust LULC assessments in resource-limited settings, guiding sustainable urban planning and informing policy interventions to address challenges associated with rapid urbanisation in resource-limited countries.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Scientific African
Scientific African Multidisciplinary-Multidisciplinary
CiteScore
5.60
自引率
3.40%
发文量
332
审稿时长
10 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信