Frameworks: Deep Learning Cyber-Infrastructure for the Exploration of High Dimensional Multimodal Data

The BisQue Deep Learning (BDL) cyberinfrastructure (CI) project is set to transform scientific research across multiple fields, including materials science, environmental science, and bioimaging. Utilizing cutting-edge deep learning and computer vision techniques, the BDL CI offers a scalable, user-friendly platform for the management and analysis of vast, complex datasets.

This initiative tackles significant challenges such as meticulous data curation, specialized domain expertise, and the need for scalable solutions for high-dimensional data. By facilitating scientific discovery and innovation, the BDL CI significantly enhances national scientific capabilities. Furthermore, it supports education and diversity through comprehensive training programs, making advanced analytical tools accessible to a wider research community and thereby promoting the progress of science.

The BDL-CI provides a sophisticated cloud-based service with an intuitive web interface designed for analyzing extensive, unstructured datasets. It supports advanced functionalities such as spatio-temporal annotations, object detection, segmentation, localization, classification, and tracking, all underpinned by a robust database backend that ensures data integrity and provenance.

The infrastructure is built for scalability and efficiency, supporting dynamic resource allocation, complex workflow orchestration, and high-volume data management. Core deliverables include a comprehensive software infrastructure tailored for multimodal imaging data, detailed documentation, a suite of deep learning workflows, and an accessible interface for discovering and utilizing data and models.

This project, driven by a multidisciplinary team from UC Santa Barbara, UC Riverside, and the Smithsonian Institution, ensures broad access and long-term sustainability through strategic collaborations and the integration of community feedback into ongoing development.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.