Effectiveness of Semi-Supervised Learning and Multi-Source Data in Detailed Urban Landuse Mapping with a Few Labeled Samples

Identification and Evaluation of the Polycentric Urban Structure: An Empirical Analysis Based on Multi-Source Big Data Fusion

Identifying and evaluating polycentric urban spatial structure is essential for understanding and optimizing current urban development. In order to accurately identify the urban centers of the Guangdong–Hong Kong–Macao Greater Bay Area (GBA), this study firstly fused nighttime light data, POI data, and population migration data based on wavelet transform, then identified the polycentric spatial structure of the GBA by carrying out cluster and outlier analysis, and evaluated the level of different urban centers byconducting geographical weighted regression analysis. Using data fusion, we identified 4579.81 km² of the urban poly-center area in the GBA, with an identification accuracy of 93.22%. Although the number and spatial extent of the identified urban poly-centers are consistent with the GBA development plan outline, the poly-center level evaluation results are inconsistent with the development plan, which shows there are great differences in actual development levels among different cities in the GBA. By identifying and grading the polycentric spatial structure of the GBA, this study accurately analyzed the current spatial distribution and could provide policy implications for the GBA’s future development and planning.

Land Use and Land Cover Mapping Using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A Comparison of Two Composition Methods

Accurate and real-time land use/land cover (LULC) maps are important to provide precise information for dynamic monitoring, planning, and management of the Earth. With the advent of cloud computing platforms, time series feature extraction techniques, and machine learning classifiers, new opportunities are arising in more accurate and large-scale LULC mapping. In this study, we aimed at finding out how two composition methods and spectral–temporal metrics extracted from satellite time series can affect the ability of a machine learning classifier to produce accurate LULC maps. We used the Google Earth Engine (GEE) cloud computing platform to create cloud-free Sentinel-2 (S-2) and Landsat-8 (L-8) time series over the Tehran Province (Iran) as of 2020. Two composition methods, namely, seasonal composites and percentiles metrics, were used to define four datasets based on satellite time series, vegetation indices, and topographic layers. The random forest classifier was used in LULC classification and for identifying the most important variables. Accuracy assessment results showed that the S-2 outperformed the L-8 spectral–temporal metrics at the overall and class level. Moreover, the comparison of composition methods indicated that seasonal composites outperformed percentile metrics in both S-2 and L-8 time series. At the class level, the improved performance of seasonal composites was related to their ability to provide better information about the phenological variation of different LULC classes. Finally, we conclude that this methodology can produce LULC maps based on cloud computing GEE in an accurate and fast way and can be used in large-scale LULC mapping.