Is Apache Spark scalable to seismic data analytics and computations?

Abstract

High Performance Computing (HPC) has been a dominated technology used in seismic data processing at the petroleum industry. However, with the increasing data size and varieties, traditional HPC focusing on computation meets new challenges. Researchers are looking for new computing platforms with a balance of both performance and productivity, as well as featured with big data analytics capability. Apache Spark is a new big data analytics platform that supports more than map/reduce parallel execution mode with good scalability and fault tolerance. In this paper, we try to answer the question that if Apache Spark is scalable to process seismic data with its in-memory computation and data locality features. We use a few typical seismic data processing algorithms to study the performance and productivity. Our contributions include customized seismic data distributions in Spark, extraction of commonly used templates for seismic data processing algorithms, and performance analysis of several typical seismic processing algorithms.