Land use and land cover change in East Java from 2015 to 2021: Use optical imagery and Google Earth engine

M. Mandala, I. Indarto, N. N. Rodhi, Akhmad Andi Saputra, Farid Lukman Hakim
{"title":"Land use and land cover change in East Java from 2015 to 2021: Use optical imagery and Google Earth engine","authors":"M. Mandala, I. Indarto, N. N. Rodhi, Akhmad Andi Saputra, Farid Lukman Hakim","doi":"10.2478/environ-2024-0007","DOIUrl":null,"url":null,"abstract":"\n This study analysed the changes in land use and land cover (LULC) in East Java Province by comparing two LULC maps interpreted from optical imagery. The images captured from 2015 to 2017 were selected to represent the initial LULC maps. Then, the images collected from 2020 to 2021 were considered the recent LULC maps. The input imagery was prepared using the Google Earth engine (GEE). The Random Forest algorithm was used for classification. In this study, eight significant LULC classes were categorised, i.e., built-up area (BU), heterogeneous-agricultural land (HAL), bare soil (BS), paddy field (PF), open water (OW), vegetation (VG), shrubland (SH), and wetland (WL). Next, the training samples were interpreted from Google Earth Pro. Then, the GEE satellite base map and the ground control points (GCPs) were collected. The collected GCPs were split into 70% training and 30% validation data. The results showed that significant LULC Change was more marked in the most urbanised areas (in and around the big cities), followed by LULC change in and around medium towns and rural areas. Four classes experienced an area increase, i.e., BU (+30.23%), HAL (+30.77%), BS (+24.52%), and PF (+14.36%). As a consequence, the other four classes compensated for the increase, i.e., OW (−32.79%), VG (−25.72%), SH (−6.59%), and WL (−25.53%). Regional development from 2015 to 2021 has increased built-up areas. Conversely, the development has reduced OW, VG, SH, and WL. The LULC changes have significantly changed the natural landscape to a human-dominated one.","PeriodicalId":517968,"journal":{"name":"Environmental & Socio-economic Studies","volume":"19 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental & Socio-economic Studies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2478/environ-2024-0007","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This study analysed the changes in land use and land cover (LULC) in East Java Province by comparing two LULC maps interpreted from optical imagery. The images captured from 2015 to 2017 were selected to represent the initial LULC maps. Then, the images collected from 2020 to 2021 were considered the recent LULC maps. The input imagery was prepared using the Google Earth engine (GEE). The Random Forest algorithm was used for classification. In this study, eight significant LULC classes were categorised, i.e., built-up area (BU), heterogeneous-agricultural land (HAL), bare soil (BS), paddy field (PF), open water (OW), vegetation (VG), shrubland (SH), and wetland (WL). Next, the training samples were interpreted from Google Earth Pro. Then, the GEE satellite base map and the ground control points (GCPs) were collected. The collected GCPs were split into 70% training and 30% validation data. The results showed that significant LULC Change was more marked in the most urbanised areas (in and around the big cities), followed by LULC change in and around medium towns and rural areas. Four classes experienced an area increase, i.e., BU (+30.23%), HAL (+30.77%), BS (+24.52%), and PF (+14.36%). As a consequence, the other four classes compensated for the increase, i.e., OW (−32.79%), VG (−25.72%), SH (−6.59%), and WL (−25.53%). Regional development from 2015 to 2021 has increased built-up areas. Conversely, the development has reduced OW, VG, SH, and WL. The LULC changes have significantly changed the natural landscape to a human-dominated one.
2015 至 2021 年东爪哇的土地利用和土地覆被变化:使用光学图像和谷歌地球引擎
本研究通过比较两幅由光学图像解读的土地利用和土地覆被地图,分析了东爪哇省土地利用和土地覆被的变化。2015年至2017年拍摄的图像被选为初始土地利用和土地覆被图。然后,2020 年至 2021 年采集的图像被视为近期的 LULC 地图。输入图像使用谷歌地球引擎(GEE)制作。采用随机森林算法进行分类。本研究对八个重要的 LULC 类别进行了分类,即建成区(BU)、异质农业用地(HAL)、裸土(BS)、水田(PF)、开阔水域(OW)、植被(VG)、灌木林地(SH)和湿地(WL)。然后,从谷歌地球专业版对训练样本进行解释。然后,收集 GEE 卫星底图和地面控制点(GCP)。收集到的地面控制点分为 70% 的训练数据和 30% 的验证数据。结果显示,城市化程度最高的地区(大城市及其周边地区)的土地利用、土地利用变化更为明显,其次是中等城镇及其周边地区和农村地区。有四个等级的面积有所增加,即 BU(+30.23%)、HAL(+30.77%)、BS(+24.52%)和 PF(+14.36%)。因此,其他四个等级弥补了增长,即 OW(-32.79%)、VG(-25.72%)、SH(-6.59%)和 WL(-25.53%)。从 2015 年到 2021 年的区域发展增加了建成区面积。相反,发展却减少了 OW、VG、SH 和 WL。LULC 的变化极大地改变了自然景观,使之成为人类主导的景观。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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