Cloud detection of satellite images is an important preprocessing step for remote sensing applications due to the adverse effect of clouds on data analysis. With the development of machine learning methods, an increasing number of studies have applied the state-of-art technology to detect clouds in satellite imagery. However, machine learning-based cloud detection methods are often limited by a small number of training samples with insufficient representativeness. To improve the robustness of cloud detection, developing a method to automatically construct a reliable training sample database is a meaningful issue. This paper explores a hybrid Erosion morphology processing and Disagreement-based Semi-supervised Learning model (EDSL) to refine cloud samples generated by the widely-used Fmask algorithm. Experimental results show that the sample accuracy after refinement could be improved from the original Fmask cloud masks. Further, the random forest model trained by the sample database after EDSL refinement achieves comparable accuracy but higher efficiency with Fmask algorithm, thus proving the effectiveness of the above method.

The development of geospatial big data makes it possible to study traffic congestion issues through floating car data (FCD). FCD can help predict the traffic congestion bottlenecks and provide corresponding solutions to address traffic problems. However, few studies have focused on the distribution and changes in traffic congestion bottlenecks throughout a mega-city. This study proposes an index calculation and clustering (ICC) model by integrating PageRank and clustering algorithms via multisource data, including rainfall data, FCD and OpenStreetMap data. We selected Shenzhen, the largest developed city in South China, as the study area. The results demonstrate that there are three peak periods of citizen travel: 8:00-10:00, 14:00-16:00, and 18:00-20:00. Road speeds after rainfall decrease, and traffic congestion areas increase. The results also quantitatively analyzed the differences of traffic congestion between work day and rest day. The proposed ICC model can offer a thorough understanding of urban traffic congestion areas, which can help policy makers optimize alleviation strategies.