NASA Evolutionary Programming Analytic Center (NEPAC): requirements survey

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

We are creating a new method to develop satellite-based chlorophyll-a algorithms using a machine learning (ML) approach called Genetic Programming. This NASA Advanced Information Systems Technology (AIST) project, called the NASA Evolutionary Programming Analytic Center (NEPAC), will create a web-based Graphical User Interface (GUI) to allow Earth Scientists without prior ML experience to configure and apply an objective, fast and efficient ML application to formulate new satellite algorithms. NEPAC is initially focusing on generating Chl-a algorithms to reduce current Chl-a product uncertainties and anneal the estimation across multiple ocean color satellite missions. Community input is essential to ensure that the GUI utility contains the necessary tools/options to meet the science community’s needs. Thus, we are asking for your help in filling the “NEPAC Requirements” survey.

What variables do you think would help improve a satellite-based chlorophyll-a algorithm?

Satellite over-pass time and viewing angle

Sea surface temperature (SST)

Sea surface salinity

Phytoplankton size distribution

CDOM, non-algal particle information

Bathymetric information for shallow water

Other:

What tools or options would you prefer for in situ data QA/QC, and the estimation of errors and biases?

What performance metrics should be included in the comparison and selection of improved algorithms?

Relative errors/relative percent differences

Absolute errors/percent differences

Biases

Biased/unbiased root mean square errors

Coefficient of variation

R-squared

Regression slopes and intercepts

Other:

What suggestions do you have in developing an algorithm that would be capable of annealing multiple instruments/datasets to create more robust Climate Data Records, etc.?

Would outputting the full population of GP algorithms be useful for ensemble-type algorithm estimates?

What other ocean color satellite data products would you like to develop algorithms for in the future?

Phytoplankton accessory pigments, such as phycocyanin, phycoerythrin, chlorophyll b, c, carotenoids, etc.

Phytoplankton functional types

Primary productivity

Carbon dynamics/cycle

Other:

What kinds of features in the NEPAC web application would make it more appealing and helpful?

Access to different data archives

Choices in computing resources

Post-processing of algorithms into usable computer code

Other:

Would you like to serve as a beta-tester for the GUI application?

Yes

Maybe

Clear selection

Other suggestions or comments

Name

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy

Forms