The construction of spatial weight matrix based on discrete points through building a searching area for each point

In this paper, we present an algorithm to construct a spatial weight matrix by employing the threshold method to measure the spatial connectivity among discrete spatial points. This method can save searching costs by building a searching area for each point when we set values for each element of the weight matrix, and achieve optimization in the process of constructing a spatial weight matrix. The algorithm presented here has been implemented with Python programming language. A sample of 6122 discrete points of the aerosol optical thickness is used to test the efficiency of the algorithm through figuring out the dataset´s spatial autocorrelation indices.