SBIR-STTR Award

Machine-Learning & QMU for Multi-Fidelity Analysis of Scramjet Operability
Award last edited on: 2/27/2018

Sponsored Program
SBIR
Awarding Agency
NASA : GSFC
Total Award Amount
$878,978
Award Phase
2
Solicitation Topic Code
A1.10
Principal Investigator
Amirreza Saghafian

Company Information

Cascade Technologies Inc

2445 Faber Place Suite 100
Palo Alto, CA 94303
Location: Single
Congr. District: 16
County: Santa Clara

Phase I

Contract Number: NNX17CL46P
Start Date: 6/9/2017    Completed: 12/8/2017
Phase I year
2017
Phase I Amount
$124,941
Continuum Analytics proposes a Python-based open-source data analysis machine learning pipeline toolkit for satellite data processing, weather and climate data processing, and machine learning and prediction with optional proprietary cluster management tools for streamlined deployment for cloud providers and on-premises clusters. The innovative software will empower scientists and analysts to readily and seamlessly construct and test workflows that transparently and scalably perform calculations across cluster nodes for data-driven discovery. The simple API for homogenous processing of images, mosaics and tiles further improves ease of use for rapid testing and prototyping of analyses paradigms for multiple extremely large data sets. Today, NASA researchers must create, debug, and tune custom workflows for each analysis. Creation and modification of custom workflows is fragile, non-portable, and consumes time that could be better spent on advancing scientific discovery. The Phase I work plan will demonstrate that it is feasible to easily create and compose data manipulations and analytics from a variety of sources with a portable, reproducible, extensible process that can be deployed on a wide variety of systems and software. This is a major improvement over the current state-of-the-art because of reduced workflow creation time, portability of deployment and use, extensibility, and robustness.

Phase II

Contract Number: N/A
Start Date: 00/00/00    Completed: 00/00/00
Phase II year
2018
Phase II Amount
$754,037
Today, NASA researchers must create, debug, and tune custom workflows for each analysis. Creation and modification of custom workflows is fragile, non-portable and consumes time that could be better spent on advancing scientific discovery. The Phase I open source software Ensemble Learning Models (ELM) provides composable, portable, reproducible, and extensible machine learning pipelines with easy-to-configure parallelization, with tools specifically for satellite data processing, weather and climate data processing, and machine learning and prediction. This is a major advancement over the current state-of-the-art because of reduced workflow creation time, parallelization, portability of deployment and use, extensibility, and robustness. Phase II will extend the Phase I work with more options useful to NASA missions, such as advanced ensemble fitting and prediction tools, feature engineering options for 3-D and 4-D arrays, and a web-based map user interface. Phase II will also harden and extend ELM to make ELM's easy-to-use large data ensemble methods accessible to industry outside of NASA, increasing the potential user base in a variety of domains.