The EnMAP Contest: Developing and Comparing Classification Approaches for the Environmental Mapping and Analysis Programme - Dataset and First results

Abstract. The Environmental Mapping and Analysis Programme EnMAP is a hyperspectral satellite mission, supposed to be launched into space in the near future. EnMAP is designed to be revolutionary in terms of spectral resolution and signal-to-noise ratio. Nevertheless, it will provide a relatively high spatial resolution also. In order to exploit the capacities of this future mission, its data have been simulated by other authors in previous work. EnMAP will differ from other spaceborne and airborne hyperspectral sensors. Thus, the assumption that the standard classification algorithms from other sensors will perform best for EnMAP as well cannot by upheld since proof. Unfortunately, until today, relatively few studies have been published to investigate classification algorithms for EnMAP. Thus, the authors of this study, who have provided some insights into classifying simulated EnMAP data before, aim to encourage future studies by opening the EnMAP contest. The EnMAP contest consists in a benchmark dataset provided for algorithm development, which is presented herein. For demonstrative purposes, this report also represents two classification results which have already been realized. It furthermore provides a roadmap for other scientists interested in taking part in the EnMAP contest.

[1]  Jon Atli Benediktsson,et al.  Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Timo Stuffler,et al.  EnMAP A Hyperspectral Sensor for Environmental Mapping and Analysis , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[3]  Uwe Weidner,et al.  Classification in High-Dimensional Feature Spaces—Assessment Using SVM, IVM and RVM With Focus on Simulated EnMAP Data , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

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

[6]  Patrick Hostert,et al.  Estimating Fractional Shrub Cover Using Simulated EnMAP Data: A Comparison of Three Machine Learning Regression Techniques , 2014, Remote. Sens..

[7]  Uwe Weidner,et al.  Design of a Spectral–Spatial Pattern Recognition Framework for Risk Assessments Using Landsat Data—A Case Study in Chile , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Uwe Weidner,et al.  Support Vector Machines for Vegetation Classification – A Revision , 2010 .

[9]  Mandy Eberhart,et al.  Decision Forests For Computer Vision And Medical Image Analysis , 2016 .

[10]  Mahesh Pal,et al.  Support vector machine‐based feature selection for land cover classification: a case study with DAIS hyperspectral data , 2006 .

[11]  H. Kaufmann,et al.  Hyperspectral imaging—An advanced instrument concept for the EnMAP mission (Environmental Mapping and Analysis Programme) , 2009 .

[12]  Patrick Hostert,et al.  Environmental Mapping and Analysis Program (EnMAP) - Recent Advances and Status , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[13]  Uwe Weidner,et al.  Contribution to the Assessment of Segmentation Quality for Remote Sensing Applications , 2008 .

[14]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem☆ , 2008 .

[15]  Luis Guanter,et al.  EeteS—The EnMAP End-to-End Simulation Tool , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  U. Benz,et al.  The EnMAP hyperspectral imager—An advanced optical payload for future applications in Earth observation programmes , 2006 .

[17]  Christian Heipke,et al.  EVALUATION OF AUTOMATIC ROAD EXTRACTION , 2007 .

[18]  Luis Guanter,et al.  Simulation of Optical Remote-Sensing Scenes With Application to the EnMAP Hyperspectral Mission , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Stefan Kaiser,et al.  Simulation of Spatial Sensor Characteristics in the Context of the EnMAP Hyperspectral Mission , 2010, IEEE Transactions on Geoscience and Remote Sensing.