Geoweaver

PI: ZIHENG SUN, GEORGE MASON UNIVERSITY 

Geoweaver is a web system allowing users to easily compose and execute full-stack deep learning workflows by taking advantage of online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries. It is a perfect alternative to SSH client (e.g., Putty), FTP client, and scientific workflow software.

Through the ESIP Lab project, the team succeeded in:

• turning large-scale distributed deep network into manageable modernized workflows;
• boosting higher utilization ratio of the existing cyberinfrastructures by separating scientists from tedious technical details;
• enhancing the frequency and accuracy of classified land cover land use maps for agricultural purposes;
• enabling the tracking of provenance by recording the execution logs in structured tables to evaluate the quality of the result maps;
• prove the effectiveness of operationally using large-scale distributed deep learning models in classifying Landsat image time series

PUBLICATIONS:

• Ziheng Sun, et al, Crop Mapping by Deep Neural Network and Cyberinfrastructure, ISPRS Journal of Photogrammetry and Remote Sensing, under review.
• Ziheng Sun, et al, Advanced Cyberinfrastructure for Intercomparison and Validation of Climate Models, Environmental Modelling and Software, under review.
• Ziheng Sun, et al, Advanced Geospatial Cyberinfrastructure for Pulling GIScience into AI Phase, in preparation.
• “Aha” Moments Abound at ESIP’s Custom Bootcamp

PRESENTATIONS:

• Presentations and posters on Figshare.

AWARDS:

• 2018 InnoCentive Challenge Winner