<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>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.</p>
</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.

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

University of Jember, Faculty of Agricultural

University of Jember, Faculty of Agricultural Technology

University of Bojonegoro, Faculty of Sains and Engineering

University of Gresik, Faculty of Engineering

Environmental & Socio-economic Studies

This work is licensed under the Creative Commons Attribution 4.0 International License.

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...

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

Publié en ligne: 13 mars 2024

Pages: 69 - 80

Reçu: 14 août 2023

Accepté: 06 févr. 2024

DOI: https://doi.org/10.2478/environ-2024-0007

Mots clés
LULC change, random forest algorithm, Sentinel, East Java

© 2024 Marga Mandala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

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

Publié en ligne: 13 mars 2024

Pages: 69 - 80

Reçu: 14 août 2023

Accepté: 06 févr. 2024

DOI: https://doi.org/10.2478/environ-2024-0007

Mots clésLULC change, random forest algorithm, Sentinel, East Java

© 2024 Marga Mandala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
LULC change, random forest algorithm, Sentinel, East Java