Tensor‐CA: A high‐performance cellular automata model for land use simulation based on vectorization and GPU

Abstract

With the ability to understand linkages and feedbacks between land use dynamics and human–land relationships, cellular automata (CA) are extensively applied in land use/cover change (LUCC) simulation. However, with complex transition rules and a growing volume of spatial data, conventional serial CA models cannot meet the demands of efficient computation. In this article, a Tensor‐CA model using vectorization and Graphics Processing Unit (GPU) technology based on a tensor computation framework for optimizing multiple LUCC simulations is presented. Complex transition rules of LUCC‐CA models are vectorized and formalized to tensor operations which are effectively solved by GPU. The proposed Tensor‐CA model was applied to LUCC simulations in the Pearl River Delta of China. The experimental results indicate that the proposed model effectively improved the performance compared to Serial‐CA, Parallel‐CA, and GPU‐CA.

VST-PCA: A Land Use Change Simulation Model Based on Spatiotemporal Feature Extraction and Pre-Allocation Strategy

“…where I t k is the inertia coefficient for type k at the t-th iteration, I t−1 k is the coefficient at the (t − 1)th iteration, D t−1 k represents the difference between the allocation demand and the target demand for type k at the (t − 1)th iteration, and D t−2 k represents the difference at the (t − 2)th iteration. When the evolutionary trend matches the macro demand, the inertia coefficient remains unchanged; otherwise, the inertia coefficient will be dynamically adjusted to correct the development trend in subsequent iterations [45].…”

A high‐performance cellular automata model for urban expansion simulation based on convolution and graphic processing unit

“…However, the logical structure of these GPU-based CA models is too complex to conveniently implement and maintain (Xia et al, 2018;Zhuang et al, 2022). Consequently, Xia et al (2018) proposed vectorized CA, which enhances the computational efficiency of CA by the idea of matrix operation.…”

“…Consequently, Xia et al (2018) proposed vectorized CA, which enhances the computational efficiency of CA by the idea of matrix operation. Zhuang et al (2022) combined vectorization and GPU technology to further improve the computational efficiency of vectorized CA.…”

“…However, the logical structure of these GPU‐based CA models is too complex to conveniently implement and maintain (Xia et al., 2018; Zhuang et al., 2022). Consequently, Xia et al.…”

“…Zhuang et al. (2022) combined vectorization and GPU technology to further improve the computational efficiency of vectorized CA. In the vectorized CA, the neighborhood space is constructed through translation operations of the cell space, and transform the calculation of the neighborhood effect into the vectorization addition operation of each layer in the neighborhood space.…”