Regression estimation techniques with remote sensing: a review and case study

With the relatively recent widespread availability of operational fine spatial resolution imagery from satellites, there is more opportunity to conduct spatial sampling with combinations of spatial resolution data. This method is generally called regression estimation. Regression estimation consists of first using a coarser spatial resolution sensor over a large area. For selected samples, a second delineation is done with a finer spatial resolution system which is presumed to be more accurate. A statistical comparison of the two estimates for the selected sample areas is made and if a suitable relationship exists, a correction factor can be determined and applied to the full study area. This manuscript reviews the regression estimation process and provides a case study. The case study used the technique to determine the extent of the winter rice crop in Bangladesh with Landsat data and statistics provided for local administrative units by agricultural agents.

[1]  H. Schreuder,et al.  The Alaska four-phase forest inventory sampling design using remote sensing and ground sampling , 1995 .

[2]  R. Colwell.  Remote sensing of the environment , 1980, Nature.

[3]  F. Deppe,et al.  Forest Area Estimation Using Sample Surveys and Landsat MSS and TM Data , 1998 .

[4]  D. S. Gilmer,et al.  Enumeration of prairie wetlands with Landsat and aircraft data , 1980 .

[5]  Eric F. Lambin,et al.  Estimation of tropical forest area from coarse spatial resolution data: A two-step correction function for proportional errors due to spatial aggregation , 1995 .

[6]  H. Eva,et al.  Remote Sensing of Biomass Burning in Tropical Regions: Sampling Issues and Multisensor Approach , 1998 .

[7]  Robert H. Fraser,et al.  Validation and Calibration of Canada-Wide Coarse-Resolution Satellite Burned-Area Maps , 2004 .

[8]  A. Winsor.  Sampling techniques. , 2000, Nursing times.

[9]  M. A. Moreira,et al.  Wheat-area estimation using digital LANDSAT MSS data and aerial photographs , 1986 .

[10]  F. J. Gallego.  Remote sensing and land cover area estimation , 2004 .

[11]  C. Rueda,et al.  Crop area estimates through remote sensing: stability of the regression correction , 1993 .

[12]  Francis A. Roesch,et al.  A Comparison of Various Estimators for Updating Forest Area Coverage Using AVHRR and Forest Inventory Data , 1995 .

[13]  Ned Horning,et al.  Determining the rate of forest conversion in Mato Grosso, Brazil, using Landsat MSS and AVHRR data , 1987 .

[14]  Onisimo Mutanga,et al.  Merging Double Sampling with Remote Sensing for a Rapid Estimation of Fuelwood , 2004 .

[15]  R. Nelson.  Regression and ratio estimators to integrate AVHRR and MSS data , 1989 .

[16]  New Multi-Stage Sampling Techniques Using Space and Aircraft Imagery for Forest Inventory , 1969 .

[17]  Thomas J. Stohlgren,et al.  Assessing the accuracy of Landsat Thematic Mapper classification using double sampling , 1998 .