Objectives The evaluation of heterogeneity is essential for domain decomposition in parallel geocomputation. According to the theory of geospatial domain, the assessment of heterogeneity can be transformed to the computational intensity (CI) modelling, thus the key of domain decomposition is feature extraction and computational intensity prediction. However, the existing methods rely on expert knowledge for feature extraction and CI modelling of geospatial domain, suffering from poor feature applicability, complex modelling process and low model accuracy. In order to relieve the dependence on expert knowledge and achieve accurate computational intensity prediction, a computational intensity prediction and decomposition method for geospatial domain based on artificial intelligence (AI) deep learning is proposed.

Methods We use convolutional neural network (CNN) to capture the features of geospatial domain automatically, and a fully connected layer is used to predict the computational intensity. An added component is developed to match the geospatial domain and the input of CNN.

Results Spatial intersection on vector data is implemented to compare the proposed method and traditional methods. The results demonstrate the advantages of the proposed method in terms of the usability and parallel performance.

Conclusions The proposed method optimizes computational intensity prediction and domain decomposition from data science perspective, which provides a reference on how AI deep learning can be used in high-performance geocomputation.