Search

Geospatial cellular automata (Geo-CA) models have encountered challenges in computing efficiency and scalability when conducting large-scale land use change simulation applications. Parallel computing has proven to be effective to address these challenges. However, parallelization strategies for existing parallel Geo-CA models are always optimized for specific models and lack applicability to others. Besides, most parallel Geo-CA models focus on parallelizing land use change simulations, ignoring land use transition rule mining. Moreover, there is a lack of effective parallel strategies for demand-constrained land use change simulation on distributed heterogeneous architectures. This study proposes a parallel framework on hybrid parallel computing architectures applicable for raster-based Geo-CA models to enhance their computing efficiency and scalability while maintaining simulation accuracy. The framework provides parallelization strategies for both the land use transition rule mining for multiple land use types and the demand-constrained land use change simulation on distributed heterogeneous architectures. The framework was employed to parallelize two contemporary Geo-CA models, i.e., PLUS and MCCA. Experiments showed that the parallelized models achieved significant improvements in computing efficiency and scalability, confirming the effectiveness of the proposed framework for large-scale land use change simulation studies. [ABSTRACT FROM AUTHOR]

Parallel computing on distributed heterogeneous architectures (e.g. computing clusters with multiple CPUs and GPUs) can significantly improve the computational efficiency and scalability of complicated algorithms, but it is theoretically and technically complex. Parallel raster processing libraries reduce the development complexity of parallel raster algorithms by hiding parallel computing details; however, no existing library sufficiently utilizes distributed heterogeneous computing resources. A general-purpose raster processing library (mcRPL) combining multi-process parallelism and multi-thread parallelism is proposed to enable parallel raster processing on distributed heterogeneous architectures with multiple CPUs and GPUs. Additionally, an adaptive hardware assignment strategy is proposed to fully utilize available processors in various hardware environments. A series of task-processing strategies are adopted to aim toward maximizing the utilization of the computing capacity of involved processors. Experiments revealed that two raster algorithms parallelized using mcRPL for spatiotemporal data fusion and land-use change simulation were 170.7- and 143.2-fold faster than original serial algorithms using 8 and 16 GPUs, respectively. While hiding the details of mixed parallelism and reducing the development complexity, mcRPL provides user-friendly interfaces for the development of parallel raster algorithms to enhance computational performance and enable large-scale raster computing tasks with extensive data volumes. [ABSTRACT FROM AUTHOR]