A traffic flow data processing and forecasting framework based on Spark is designed, and it can complete the efficient cleaning, statistics, storage and query of traffic flow data. A multi-order spatial weight matrix STARIMA model is used to predict the traffic flow, and it can verify the efficiency of data processing and the support for the prediction. By comparative experiments, the results show that the traffic flow data processing framework is efficient, and it is suitable for realizing complex data cleaning and mining algorithms and establishing data support for the prediction model. The traffic flow prediction model optimizes the multi-order spatial weight matrix, and it takes both efficiency and accuracy into consideration. The prediction results can provide reference for traffic guidance.
It is difficult to monitor land surface soil moisture in high temporal and spatial resolution within a wide range for lack of ground observation data when the satellite is passing over. To solve this problem, a new integrated approach termed as “soil moisture retrieval with combined active and passive microwave remote sensing observation” was proposed. AMSR-E soil moisture product is compensated as “high temporal resolution observation control data” and soil moisture benchmark is retrieved together with ASAR alternating polarization mode data. Then both of them are integrated to build up a co-inversion model for soil moisture retrieval. This approach applies to areas where the land surface roughness is small and vegetation index (NDVI) is low. The approach is evaluated in Weibei Upland of Shaanxi Province. According to the regression analysis based on AIEM (advanced integrated equation model), the correlation coefficient between compensated AMSR-E soil moisture and downscaled ASAR backscattering coefficient was approximately 0.81. Verification analysis with the in-situ data of Fengxiang County in the study area shows that the soil moisture retrieved with combined active and passive microwave remote sensing observation displays a correlation coefficient of 0.92, and the root mean square errors (RMSE) of the soil volumetric moisture is 0.025. It indicates that the approach is credible and the soil moisture retrieval results could be used in simulating regional crop growth under water-limited environments.