Browser-Based Remote Data Analysis and Visualization

Computer models and remote sensing missions often generate datasets that are too large to store and analyze on desktop computers or even on local compute clusters. A traditional approach to exploring such datasets is to run the analysis program on a remote machine and display the output on the desktop computer via X windows. The tunneling option of the secure shell connection can be used to facilitate remote display of graphics generated by analysis software like Matlab, IDL, NCL etc. More recently, purely browser–based visualization tools are becoming more popular for graphical data analysis and visualization. These tools extend beyond desktop and laptop computers to the realm of mobile devices. Javascript toolkits like d3.js support powerful in-browser display options. Web services like plotly not only display plots, but also allow them to be easily shared with others. For data analysis using languages like Python and R, the IPython Notebook tool now supports powerful inline graphics and widgets that can be viewed remotely in a browser. This presentation will survey different alternatives that are currently available for browser-based remote visualization and discuss the pros and cons of these approaches.