Land Use/Land Cover Mapping Based on GEE for the Monitoring of Changes in Ecosystem Types in the Upper Yellow River Basin over the Tibetan Plateau

Abstract

The upper Yellow River basin over the Tibetan Plateau (TP) is an important ecological barrier in northwestern China. Effective LULC products that enable the monitoring of changes in regional ecosystem types are of great importance for their environmental protection and macro-control. Here, we combined an 18-class LULC classification scheme based on ecosystem types with Sentinel-2 imagery, the Google Earth Engine (GEE) platform, and the random forest method to present new LULC products with a spatial resolution of 10 m in 2018 and 2020 for the upper Yellow River Basin over the TP and conducted monitoring of changes in ecosystem types. The results indicated that: (1) In 2018 and 2020, the overall accuracy (OA) of LULC maps ranged between 87.45% and 93.02%. (2) Grassland was the main LULC first-degree class in the research area, followed by wetland and water bodies and barren land. For the LULC second-degree class, the main LULC was grassland, followed by broadleaf shrub and marsh. (3) In the first-degree class of changes in ecosystem types, the largest area of progressive succession (positive) was grassland–shrubland (451.13 km2), whereas the largest area of retrogressive succession (negative) was grassland–barren (395.91 km2). In the second-degree class, the largest areas of progressive succession (positive) were grassland–broadleaf shrub (344.68 km2) and desert land–grassland (302.02 km2), whereas the largest areas of retrogressive succession (negative) were broadleaf shrubland–grassland (309.08 km2) and grassland–bare rock (193.89 km2). The northern and southwestern parts of the study area showed a trend towards positive succession, whereas the south-central Huangnan, northeastern Gannan, and central Aba Prefectures showed signs of retrogressive succession in their changes in ecosystem types. The purpose of this study was to provide basis data for basin-scale ecosystem monitoring and analysis with more detailed categories and reliable accuracy.

Machine Learning-Based Wetland Vulnerability Assessment in the Sindh Province Ramsar Site Using Remote Sensing Data

“…The rapid population growth revealed by the LandScan data analysis has clear implications on the land use and land cover modifications surrounding Khinjhir Lake wetland. The 29 million increase in regional population from 11 million to 29 million between 2000 and 2020 aligns closely with the doubling of the built-up area from 2% to 4% over the same period as estimated by the random forest LULC classification model [70,71]. This significant population influx and associated development activities contribute to urban expansion into wetland areas, as evidenced by the steady rise in the built-up land cover class.…”

Untitled

“…S. Feng et al (2022) utilized the Google Earth Engine (GEE) platform to conduct land use classification in a large area with a complex workflow, achieving fast and accurate results. The pixel-based Random Forest (RF) classification method was used for land use classification, which yielded overall accuracy above 87% and kappa coefficient 0.88 that met the requirements.…”

Karst of Gunung Sewu Land Use and Land Covers Dynamics: Spatio-Temporal Analysis

“…To achieve the research objectives, we initially deployed the Google Earth Engine (GEE) as the primary instrument. GEE contains the raw dataset and analytical tools that provide most of the data used in the research (Feng et al, 2022). From the explanatory stage using the quantitative data, the discussion is broadened to a qualitative descriptive elaboration.…”