As an important spatiotemporal simulation approach and an effective tool for developing and examining spatial optimization strategies (e.g., land allocation and planning), geospatial cellular automata (CA) models often require multiple data layers and consist of complicated algorithms in order to deal with the complex dynamic processes of interest and the intricate relationships and interactions between the processes and their driving factors. Also, massive amount of data may be used in CA simulations as high-resolution geospatial and non-spatial data are widely available. Thus, geospatial CA models can be both computationally intensive and data intensive, demanding extensive length of computing time and vast memory space. Based on a hybrid parallelism that combines processes with discrete memory and threads with global memory, we developed a parallel geospatial CA model for urban growth simulation over the heterogeneous computer architecture composed of multiple central processing units (CPUs) and graphics processing units (GPUs). Experiments with the datasets of California showed that the overall computing time for a 50-year simulation dropped from 13,647 seconds on a single CPU to 32 seconds using 64 GPU/CPU nodes. We conclude that the hybrid parallelism of geospatial CA over the emerging heterogeneous computer architectures provides scalable solutions to enabling complex simulations and optimizations with massive amount of data that were previously infeasible, sometimes impossible, using individual computing approaches.

Heterogeneous computer architectures are the emerging and future trend in computer engineering but lead to major challenges in algorithm redesign and software re-engineering. This article reviews the evolutional trend in hardware advancement and discusses how to utilize multiple modern graphics processing units (GPUs) and central processing units (CPUs) to accelerate geospatial computation. In particular, we deployed the supercomputing power of Keeneland to demonstrate the significant performance improvement in spatial interpolation using Kriging which is computing intensive over large data. It is concluded that heterogeneous computer system can exemplify an apparent acceleration when a larger scale of spatial data is processed.

This paper introduces how to automatically derive a minimum set of viewpoints for maximum coverage over a large scale of digital terrain data. This is a typical data and computation-intensive research covering a series of geocomputation tasks that have not been implemented efficiently or optimally in prior works. This paper introduces a three-step computational solution to resolve the problem. For any given digital elevation model (DEM) data, automatic generation of control viewpoints is the first step through map algebra calculation and hydrological modeling approaches. For each viewpoint, the viewshed calculation then has to be implemented. The combined viewshed derived from the viewshed of all viewpoints establishes the maximum viewshed coverage of the given DEM. Finally, detecting the minimum set of viewpoints for the maximum coverage is a Non-deterministic Polynomial-time hard problem. The outcome of the computation has broader societal impacts since the research questions and solutions can be adapted into real-world application and decision-making practice, such as the distribution, optimization and management of telecommunication infrastructure and wildfire observation towers, and military tactics and operations dependent upon landscape and terrain features.

Supervised image classification has been widely utilized in a variety of remote sensing applications. When large volume of satellite imagery data and aerial photos are increasingly available, high-performance image processing solutions are required to handle large scale of data. This paper introduces how maximum likelihood classification approach is parallelized for implementation on a computer cluster and a graphics processing unit to achieve high performance when processing big imagery data. The solution is scalable and satisfies the need of change detection, object identification, and exploratory analysis on large-scale high-resolution imagery data in remote sensing applications.

Constructing an embedding space for musical instrument sounds that can meaningfully represent new and unseen instruments is important for downstream music generation tasks such as multi-instrument synthesis and timbre transfer. The framework of Automatic Speaker Verification (ASV) provides us with architectures and evaluation methodologies for verifying the identities of unseen speakers, and these can be repurposed for the task of learning and evaluating a musical instrument sound embedding space that can support unseen instruments. Borrowing from state-of-the-art ASV techniques, we construct a musical instrument recognition model that uses a SincNet front-end, a ResNet architecture, and an angular softmax objective function. Experiments on the NSynth and RWC datasets show our model’s effectiveness in terms of equal error rate (EER) for unseen instruments, and ablation studies show the importance of data augmentation and the angular softmax objective. Experiments also show the benefit of using a CQT-based filterbank for initializing SincNet over a Mel filterbank initialization. Further complementary analysis of the learned embedding space is conducted with t-SNE visualizations and probing classification tasks, which show that including instrument family labels as a multi-task learning target can help to regularize the embedding space and incorporate useful structure, and that meaningful information such as playing style, which was not included during training, is contained in the embeddings of unseen instruments.