Spatial scale is a fundamental issue for geographical phenomena because the size of the spatial unit adopted for analysis can have a significant effect on aggregated spatial data and the corresponding analytical results. There exists much research on the scale issue of spatial distribution data while a few has paid attention to the scale effect on spatial interactions. Big geo-data with micro-level individual movements provide an unprecedented opportunity to explore spatial interactions from the bottom up and to understand the scale effect from the perspective of interaction patterns. In this paper, we introduced an empirical framework to explore spatial interaction data across scales. By incorporating two data sets of taxi trajectories in Beijing and Shanghai, we aggregated the taxi O-D trips under multiple regular grids with different cell sizes and analyzed the properties of spatial interactions in three aspects: the statistical distribution, the distance decay mechanism, and the structure pattern. Our research demonstrated the feasibility of analyzing spatial interactions from a multi-scale view and offered a basic empirical framework for future geographical research that is interested in scale and spatial interactions.

This paper proposes a model to extract feature information quickly and accurately identifying what cannot be achieved through traditional methods of remote sensing image classification. First, process the selected Landsat-8 remote sensing data, including radiometric calibration, geometric correction, optimal band combination, and image cropping. Add the processed remote sensing image to the normalized geographic auxiliary information, digital elevation model (DEM), and normalized difference vegetation index (NDVI), working together to build a neural network that consists of three levels based on the structure of back-propagation neural and extended delta bar delta (BPN-EDBD) algorithm, determining the parameters of the neural network to constitute a good classification model. Then determine classification and standards via field surveys and related geographic information; select training samples BPN-EDBD for algorithm learning and training and, if necessary, revise and improve its parameters using the BPN-EDBD classification algorithm to classify the remote sensing image after pretreatment and DEM data and NDVI as input parameters and output classification results, and run accuracy assessment. Finally, compare with traditional supervised classification algorithms, while adding different auxiliary geographic information to compare classification results to study the advantages and disadvantages of BPN-EDBD classification algorithm.

In this paper, a hybrid wavelet neural network (HWNN) model is developed for effectively forecasting rainfall with the data of antecedent monthly rainfalls, the ant colony optimization algorithm (ACO) is combined with particle swarm optimization algorithm (PSO) to improve performance of...