Spatial-Temporal Pattern of Land Use and SDG15 Assessment in the Bohai Rim Region Based on GEE and RF Algorithms

Abstract

The United Nations has proposed Sustainable Development Goal 15 (SDG15), which emphasizes the importance of sustainable land development. This study aims to use remote sensing data to build spectral index feature dataset based on Google Earth Engine platform, dig deep spectral features of ground objects, and use random forest algorithm to extract land use type distribution data in the Bohai Rim region from 2000 to 2020. Meanwhile, combined with land use transfer map and landscape pattern index, the spatio-temporal pattern of land use was quantitatively analyzed. Finally, the sustainable development level of land was evaluated quantitatively from three aspects: forest resource sustainability, wetland resource sustainability and land system sustainability. The results show that : (1) The overall accuracy and kappa coefficient of land use classification achieved by GEE and the RF algorithm were 0.94 and 0.92, respectively. (2) From 2000 to 2020, the main land use type in the study area is cropland, accounting for 33% of the total, and the impervious has significantly expanded, increasing by 9588.01 square kilometers, mainly from cropland, barren and water. (3) In relation to SDG15, forest resources exhibited poor stability, wetland resources demonstrated a steady recovery, SDG15.3.1 revealed that the problems of land degradation exist in various provinces and cities around the Bohai Sea, and the stability of land system is poor between 2000 and 2020. This paper can provide a valuable reference for land use management and ecological remediation in the Bohai Rim region.

Analyzing Spatial–Temporal Characteristics and Influencing Mechanisms of Landscape Changes in the Context of Comprehensive Urban Expansion Using Remote Sensing

“…Therefore, various types of remote sensing data are widely used in the study of urban problems [47,48]. Since remote sensing data can provide continuous land cover/use data, a large number of studies have been conducted to analyze urban landscape change based on remote sensing data [42,[49][50][51]. In this study, landscape index and its driving factors were extracted from multi-source remote sensing data to help realize long-term and large-scale landscape pattern research.…”