NASA Home Page Goddard Space Flight Center Home Page
NASA Logo - Goddard Space Flight Center   + Visit NASA.gov
a directory of Earth science data and services Global Change Master Directory Web site
header 2 bullet Links bullet FAQ bullet Contact Us bullet Site Map
Home Data Sets Data Services Learn about GCMD_legacy's portal collaborations. Add new dataset or dataservice records to GCMD_legacy What's New Participate Calendar About GCMD_legacy
 
Record Search Query: ServiceParameters>DATA MANAGEMENT/DATA HANDLING>DATA MINING

SMILEY (Satellite-image Miner and Interface Language for EOSDIS, Yet-another)Data Analysis Tool
Entry ID: SMILEY
[ Update this Record ]


Summary
Abstract: SMILEY (Satellite-image Miner and Interface Language for
EOSDIS, Yet-another) is a data mining and viewing system
developed in the NDSU DataSURG laboratory (Data System User
and Research Group) under funding provided by the USDA, NSF
and DARPA. Further development of SMILEY is ongoing. In the
last year, SMILEY has been enhanced with zooming and isolating
capabilities, more sophisticated data management capabilities
and enhanced data mining components. Two new data-mining tools
are under development and are being integrated with the SMILEY
interface.

One of the tools is an association rule-miner. An association
rule is of the form X implies Y, such as values of red, green
and blue in an image imply a certain level of grain
yield. Each rule has two measures of value: support and
confidence. The support of the rule X implies Y is the union
of X and Y, or the percent pixels in the image that satisfy X
implies Y. The confidence is the percent pixels that satisfy
the rule (the support) divided by the number of pixels that
satisfy X. Support indicates the frequency of the occurring
patterns and confidence denotes the strength of implication in
the rule. The rule-miner will find all rules that exceed a
minimum support and confidence. Once a rule is found the tool
can then visualize it (Figure 4.4-1). We have used this tool
to bracket ranges in the visible and near infrared spectrum
that correspond to different levels of yield. Rule
visualization from SMILEY of the form Blue[0,127] and Green
[128,191] implies a high corn grain yield [192,255] using data
from a high altitude aerial photo of the BMP corn field in the
OITA and an on-the-go yield monitoring map of the same field
. The light grey color represents the pixels that satisfy the
rule with a support of 56% and a confidence of 81%.

The second tool will employ spectral analysis to analyze
patterns in the image. A spatial Fourier analysis is
performed, transforming the data from the space domain to the
frequency domain. The data is then displayed as an area or
radial power spectrum. This technique may be valuable in
determining whether spatial data is becoming more or less
variable, such as when the crop canopy begins to fill or after
a pattern from plant stresses forms.

(Summary addapted from "http://www.umac.org/")

Related URL
Link: VIEW PROJECT HOME PAGE
Description: We develop products and services for Agriculture, for Natural
Resource Management, and for K-12 Education, using satellite
imagery and other spatial technologies. We also provide
information and educational outreach services to the general
public with respect to regional impacts of environmental and
climatic change. We provide products, services, and
information to the general public by operating as a Public
Access Resource Center, or PARC, focused principally on the
agriculture, natural resource management, and education
communities.

As a consortium, UMAC is led by the University of North
Dakota, and includes participants from academia, industry,
and government located throughout North Dakota, South Dakota,
Montana, Wyoming, and Idaho.

UMAC operates as a consortium, meaning we provide a way for
participants from a range of partnering institutions to work
together in our areas of common interest. In doing so, we
benefit from each other's expertise and resources and
therefore strengthen each of our own institutions
accordingly. One of the parnters is ESIP (Earth Science
Information Partners, http://www.esipfed.org).
Service Citation
Title: SMILEY (Satellite-image Miner and Interface Language for EOSDIS, Yet-another)Data Analysis Tool
URL: http://www.umac.org/
ISO Topic Category
FARMING
ECONOMY
GEOSCIENTIFIC INFORMATION
IMAGERY/BASE MAPS/EARTH COVER
Service Provider
Upper Midwest Aerospace Consortium, University of North Dakota

Service Provider Personnel
Name: GEORGE SEIELSTAD
Phone: (701) 777-4755
Fax: (701) 777-2940
Email: gseielst at aero.und.edu
Contact Address:
Upper Midwest Aerospace Consortium
Odegard School of Aerospace Sciences
University of North Dakota
University & Tulane Drive
City: Grand Forks
Province or State: ND USA
Postal Code: 58202-9007
Country: USA
Personnel
TYLER B. STEVENS
Role: SERF AUTHOR
Phone: (301) 614-6898
Fax: 301-614-5268
Email: Tyler.B.Stevens at nasa.gov
Contact Address:
NASA Goddard Space Flight Center
Global Change Master Directory
City: Greenbelt
Province or State: MD
Postal Code: 20771
Country: USA
Creation and Review Dates
SERF Creation Date:
SERF Last Revision Date: 2007-04-13
[ Update this Record ]
USA dot gov - The U.S. Government's Official Web Portal NASA
Webmaster:  Monica Holland
Responsible NASA Official:  Lola Olsen
Last Updated:  April 2014