MERGING RANDOM FOREST CLASSIFICATION WITH AN OBJECT-ORIENTED APPROACH FOR ANALYSIS OF AGRICULTURAL LANDS

Machine learning algorithms recently have made major advances, with decision tree classifiers gaining wide acceptance. Boosting and bagging of decision trees have added to the predictive capabilities of these approaches. Object-oriented (O-O) analyses have been developed during this same period, offering important improvements in classification over pixel-based approaches under certain conditions. Classification algorithms for O-O approaches, however, have been fairly limited and generally have not incorporated new statistical approaches used for pixel-based classifications. One of the most promising new classification algorithms is Random Forest (Breiman-Cutler) classification (RF). We incorporated RF into an O-O classification of Landsat-based imagery for mapping agricultural lands in north-central Montana, USA. The Definiens multi-resolution segmentation algorithm was used to generate fieldbased objects. RF was used to classify land management (tillage, conservation reserve, crop/fallow) based on reference data from >400 field sites. Object-based attributes included factors such as average spectral response, spectral variability, texture, and shape characteristics. Accuracy was assessed using “out-of-bag” estimates in RF. This classification approach was able to efficiently and accurately merge RF with an object-oriented approach for improved classifications.

[1]  Limin Yang,et al.  Derivation of a tasselled cap transformation based on Landsat 7 at-satellite reflectance , 2002 .

[2]  Rick L. Lawrence,et al.  Predicting tillage practices and agricultural soil disturbance in north central Montana with Landsat imagery , 2006 .

[3]  A. J. Stern,et al.  Remote sensing of crop residue cover and soil tillage intensity , 2006 .

[4]  K. Green,et al.  Using objext-oriented classification of ADS40 data to map the benthic habitats of the state of texas , 2007 .

[5]  R. Lawrence,et al.  Mapping wetlands and riparian areas using Landsat ETM+ imagery and decision-tree-based models , 2006, Wetlands.

[6]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[7]  C. Tucker,et al.  Satellite remote sensing of primary production , 1986 .

[8]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Frieke Van Coillie,et al.  Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in Flanders, Belgium , 2007 .

[10]  K. Price,et al.  Mapping Land Cover in a High Plains Agro-ecosystem Using a Multidate Landsat Thematic Mapper Modeling Approach , 1997 .

[11]  Rick L. Lawrence,et al.  Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) , 2006 .

[12]  Kevin P. Price,et al.  Mapping conservation reserve program (CRP) grasslands using multi‐seasonal thematic mapper imagery , 1998 .

[13]  K. Navulur Multispectral Image Analysis Using the Object-Oriented Paradigm , 2006 .

[14]  D. Towery,et al.  Conservation Tillage and Plant Biotechnology : How New Technologies Can Improve the Environment By Reducing the Need to Plow , 2002 .

[15]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[16]  Thomas Blaschke,et al.  A comparison of three image-object methods for the multiscale analysis of landscape structure , 2003 .

[17]  Gyanesh Chander,et al.  Revised Landsat-5 Thematic Mapper Radiometric Calibration , 2007, IEEE Geoscience and Remote Sensing Letters.

[18]  James E. McMurtrey,et al.  Remote sensing of crop residue cover and soil tillage intensity , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[19]  Rick L. Lawrence,et al.  Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis , 2004 .

[20]  R. Lawrence Rule-Based Classification Systems Using Classification and Regression Tree (CART) Analysis , 2001 .

[21]  W. Cao,et al.  The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXVIII-4/C7 CLASSIFICATION OF HIGH RESOLUTION OPTICAL AND SAR FUSION IMAGE USING FUZZY KNOWLEDGE AND OBJECT-ORIENTED PARADIGM , 2010 .

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

[23]  S. Franklin,et al.  OBJECT-BASED ANALYSIS OF IKONOS-2 IMAGERY FOR EXTRACTION OF FOREST INVENTORY PARAMETERS , 2006 .

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.