Optimal classification methods for mapping agricultural tillage practices

Abstract The classification of agricultural tillage systems has proven challenging in the past using traditional classification methods due to the similarity of spectral reflectance signatures of soils and senescent crop residues. In this study, five classification methods were examined to determine the most suitable classification algorithm for the identification of no-till (NT) and traditional tillage (TT) cropping methods: minimum distance (MD), Mahalanobis distance, Maximum Likelihood (ML), spectral angle mapping (SAM), and the cosine of the angle concept (CAC). A Landsat ETM+ image acquired over southern Michigan and northern Indiana was used to test these classification methods. Each classification method was validated with 293 ground truth sampling locations collected commensurate with the satellite overpass. Classification accuracy was then assessed using error matrix analysis, Kappa statistics, and tests for statistical significance. The results indicate that of the classification routines examined, the two spectral angle methods were superior to the others. The cosine of the angle concept algorithm outperformed all the other classification routines for tillage practice identification and mapping, yielding an overall accuracy of 97.2% (Kappa=0.959).

[1]  Prasanna H. Gowda,et al.  Mapping tillage practices with landstat thematic mapper based logistic regression models , 2001 .

[2]  Prasanna H. Gowda,et al.  Using Thematic Mapper Data to Identify Contrasting Soil Plains and Tillage Practices , 1997 .

[3]  P. Deschamps,et al.  Description of a computer code to simulate the satellite signal in the solar spectrum : the 5S code , 1990 .

[4]  H. Mcnairn,et al.  Mapping Corn Residue Cover on Agricultural Fields in Oxford County, Ontario, Using Thematic Mapper , 1993 .

[5]  Jeanne B. Etheridge,et al.  AREA ESTIMATION OF CROPS BY DIGITAL ANALYSIS OF LANDSAT DATA. , 1978 .

[6]  Rick L. Lawrence,et al.  Documenting no-till and conventional till practices using Landsat ETM+ imagery and logistic regression , 2002 .

[7]  B. Kartikeyan,et al.  A segmentation approach to classification of remote sensing imagery , 1998 .

[8]  J. Chen,et al.  Classification by progressive generalization: A new automated methodology for remote sensing multichannel data , 1998 .

[9]  M. Schaepman,et al.  Retrieving sup-pixel land cover composition through an effective integration of the spatial, spectral, and temporal dimensions of MERIS imagery , 2005 .

[10]  N. S. Rebello,et al.  Supervised and Unsupervised Spectral Angle Classifiers , 2002 .

[11]  William D. Philpot,et al.  The effects of a complex environment on crop separability with landsat TM , 1989 .

[12]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[13]  D. Albert.  Regional landscape ecosystems of Michigan, Minnesota and Wisconsin: a working map and classification. , 1995 .

[14]  W. Cohen,et al.  Land cover mapping in an agricultural setting using multiseasonal Thematic Mapper data , 2001 .

[15]  R. Leemans,et al.  Comparing global vegetation maps with the Kappa statistic , 1992 .

[16]  S. Magnussen.  Calibrating photo-interpreted forest cover types and relative species compositions to their ground expectations , 1997 .

[17]  Hans Tømmervik,et al.  Monitoring vegetation changes in Pasvik (Norway) and Pechenga in Kola Peninsula (Russia) using multitemporal Landsat MSS/TM data , 2003 .

[18]  E. Moran,et al.  Deforestation in North-Central Yucatan 1985-1995) : Mapping secondary succession of forest and agricultural land use in Sotuta using the cosine of the angle concept , 1999 .

[19]  D. Myers,et al.  Status and trends in suspended-sediment discharges, soil erosion, and conservation tillage in the Maumee River Basin–Ohio, Michigan, and Indiana , 2000 .

[20]  Hamza Erol,et al.  A new supervised classification method for quantitative analysis of remotely-sensed multi-spectral data , 1998 .

[21]  G. Robertson,et al.  Greenhouse gases in intensive agriculture: contributions of individual gases to the radiative forcing of the atmosphere , 2000, Science.

[22]  R. G. Oderwald,et al.  Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. , 1983 .