A NEW APPROACH FOR MAPPING LAND USE / LAND COVER USING GOOGLE EARTH ENGINE: A COMPARISON OF COMPOSITION IMAGES
نویسندگان
چکیده
Abstract. In view of the increase in human activities, climate change and related hazards, land use cover (LULC) mapping is becoming a fundamental part process any development or hazard prevention project. From this perspective, we propose new approach for LULC using Machine learning algorithms by comparing result five composition methods based on Google Earth Engine city Tetouan - Morocco. To achieve goal, considering Sentinel S2 L2 imageries as source data , datasets were derived to make classification generating aggregating functions (median mean max min mode). Then very high resolution (VHR) satellite images provided comes next step that involves selecting samples are divided into classes (barren land, water surface, vegetation, forest, urban areas), which will be further split two parts: 70% training -used feed machine (support vector (SVM), random forest (RF) regression trees (CART))- 30% testing evaluating models accuracy assessments. The results all indicate SVM algorithm has highest its performance better than other (RF CART). average overall RF CART was 87.99% 87.81% 84.72% respectively. Furthermore, each algorithm, comparison between different composites indicates composite most suitable mapping. Finally, GEE proven an effective rapid method mapping, especially with compositional imagery can assist decision makers future planning risk prevention.
منابع مشابه
Investigation of land use changes in Gorganrood catchment using Google Earth Engine platform
The purpose of this study is to investigate landuse changes in Gorganrood basin in 2001, 2010 and 2019. Using Landsat and Product-Modes satellite images, used maps were prepared using the classification method of random forest algorithm in Google Earth Engine. Satellite imagery was classified into eight classes including forest, cropland, shrubland, grassland, wetland, urban, barren, and water....
متن کاملMapping land cover change over continental Africa using Landsat and Google Earth Engine cloud computing
Quantifying and monitoring the spatial and temporal dynamics of the global land cover is critical for better understanding many of the Earth's land surface processes. However, the lack of regularly updated, continental-scale, and high spatial resolution (30 m) land cover data limit our ability to better understand the spatial extent and the temporal dynamics of land surface changes. Despite the...
متن کاملExploring the Use of Google Earth Imagery and Object-Based Methods in Land Use/Cover Mapping
Google Earth (GE) releases free images in high spatial resolution that may provide some potential for regional land use/cover mapping, especially for those regions with high heterogeneous landscapes. In order to test such practicability, the GE imagery was selected for a case study in Wuhan City to perform an object-based land use/cover classification. The classification accuracy was assessed b...
متن کاملLand cover land use mapping and change detection analysis using geographic information system and remote sensing
Land cover/land use categories are relevant components in land management. Understanding how land cover/land use change over time is necessary to assess the consequences of humans and natural stressors on the earth’s environment and resources. The aim of the study was to map and monitor the spatial and temporal change in land cover/land use for the periods of 1977, 1991 and 2016 and to predict ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
سال: 2023
ISSN: ['1682-1777', '1682-1750', '2194-9034']
DOI: https://doi.org/10.5194/isprs-archives-xlviii-4-w6-2022-343-2023