RT Journal Article
SR Electronic
T1 Mapping tillage practices with landstat thematic mapper based logistic regression models
JF Journal of Soil and Water Conservation
FD Soil and Water Conservation Society
SP 91
OP 96
VO 56
IS 2
A1 P. H. Gowda
A1 B. J. Dalzell
A1 D. J. Mulla
A1 F. Kollman
YR 2001
UL http://www.jswconline.org/content/56/2/91.abstract
AB Tillage information is crucial in environmental modeling as it has a direct impact on sediment delivery, phosphorus loss, and water holding capacity of agricultural soils. Remote sensing techniques can provide information about tillage practices over large areas. In this study, six Thematic Mapper (TM)-based logistic regression models proposed by van Deventer et al. (1997) were used to distinguish conventional and conservation tillage practices in the Lower Minnesota River watershed located in southern Minnesota. Accuracy assessments of tillage maps derived from Landsat TM data were made using field data collected by the Natural Resources Conservation Service (NRCS). Regression models were easy to use, cost and time effective, and produced reasonably accurate tillage maps. The percentage correct and kappa (k) values varied from 42–77% and 0.03–0.51, respectively, with best values for logistic regression models that use TM band 5 or the difference between TM band 3 and 5 images. This approach is promising for the rapid collection of tillage information on individual fields over large areas.