SSSAJ
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
 QUICK SEARCH:   [advanced]


     


Published online 11 January 2008
Published in Soil Sci Soc Am J 72:186-193 (2008)
DOI: 10.2136/sssaj2007.0028
© 2008 Soil Science Society of America
677 S. Segoe Rd., Madison, WI 53711 USA
This Article
Right arrow Abstract Freely available
Right arrow Full Text Free
Right arrow Full Text (PDF) Free
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Chen, F.
Right arrow Articles by Luvall, J. C.
Right arrow Search for Related Content
PubMed
Right arrow Articles by Chen, F.
Right arrow Articles by Luvall, J. C.
Agricola
Right arrow Articles by Chen, F.
Right arrow Articles by Luvall, J. C.
Related Collections
Right arrow Carbon Sequestration
Right arrow Remote Sensing

Mapping Soil Organic Carbon Concentration for Multiple Fields with Image Similarity Analysis

Feng Chena,*, David E. Kissela, Larry T. Westa, W. Adkinsa, Doug Rickmanb and J. C. Luvallb

a Dep. of Crop and Soil Sciences, Univ. of Georgia, Athens, GA 30602
b Global Hydrology and Climate Center, NASA, Huntsville, AL 35806


Figure 1
View larger version (133K):
[in this window]
[in a new window]

 
Fig. 1. The 10 crop fields selected from the NASA Advanced Thermal and Land Applications Sensor (ATLAS) data. Soil samples in circles were used for model development and those in stars were used for model validation. Fields in Group 1 (Flds 1, 2, and 3) are shown with red boundaries and Fields in Group 2 (Flds 4, 5, 6, and 7) are shown with yellow boundaries. The two groups were used for mapping soil organic C concentrations.

 

Figure 2
View larger version (17K):
[in this window]
[in a new window]

 
Fig. 2. The architecture of a typical multilayer perception network.

 

Figure 3
View larger version (12K):
[in this window]
[in a new window]

 
Fig. 3. Input, output, and the architecture of the Ward neural network system (WNNS). The input and output are part of the algorithm structure. In the WNNS, PP is the preprocessor, BP1 to BP3 are the three multilayer perception networks, and RC is the result combination.

 

Figure 4
View larger version (59K):
[in this window]
[in a new window]

 
Fig. 4. Maps of soil organic C (SOC) concentrations for the seven fields sampled. The points in Field 2 were locations selected for examining the consistence between the maps developed with the field-by-field approach and the approach using similarity analysis.

 

Figure 5
View larger version (12K):
[in this window]
[in a new window]

 
Fig. 5. The linear relationships between measured and predicted soil organic C (SOC) concentration for the two groups of fields. The dash lines are 1:1.

 

Figure 6
View larger version (11K):
[in this window]
[in a new window]

 
Fig. 6. The linear relationship between predicted soil organic C (SOC) concentrations with the field-by-field approach and the approach using similarity analysis for Field 2. The dash line is 1:1.

 





HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
The SCI Journals Agronomy Journal Crop Science
Journal of Natural Resources
and Life Sciences Education
Vadose Zone Journal
Journal of Plant Registrations Journal of
Environmental Quality
The Plant Genome
Copyright © 2008 by the Soil Science Society of America.