With increasing volumes of hyper-spectral, multi-source data, there is a high demand for automation and simplification of the process for advanced remote sensing classification research. We present a novel geospatial modeler tool. With flexible modeling and data analysis function, this tool provides an easy environment for scientist and educators for remote sensing community.

The tool is designed toward a generic framework for external packages integration. Three major components are graphic modeler, algorithm toolbox, and result viewer. Developed in a modular fashion, it incorporates algorithms written with languages which are widely used in remote sensing application, including Python, R, Matlab, and C (GDAL/OGR executables). This tool has features such as data loading and transformation, preprocessing, modeling, validation and visualization. Geospatial data processing routines are already available, and the ease of model building and program development makes it straightforward to implement new algorithms and to assess the results. Collecting data visualization routines into the package will make them readily available for evaluation for particular applications.

As part effort of the GAABS project, we demonstrate the abilities of HUBzero to host the tool. The tool is deployed and configured at GeoHub server. A synergy effect in the simple flexible tool framework and a powerful fabric of RS/GIS libraries and applications in HUBzero can be observed. We extend the HUBzero platform by integration with IData service. Input and output data, and algorithms are readily shared across network, which allow researches in cooperative environment.

1. M. Crawford, D. Tuia, and H. Yang, (2013), “Active learning: Any value for classification of remotely sensed data?” in Proc. IEEE, vol. 101, no. 3, pp. 593–608, Mar. 2013.
2. McLennan, M., & Kennell, R. (2010). HUBzero: A platform for dissemination and collaboration in computational science and engineering. Computing in Science Engineering, 12(2), 48-53.
3. Parallels Holdings Ltd. (2011). OpenVZ project website. Retrieved 3/19, 2011, from http://wiki.openvz.org/Main_Page
4. ArcGIS Help 10.2. A quick tour of using iterators. Retrieved 30.4.2014 Available:http://resources.arcgis.com/en/help/main/10.2/index.html#// 002w0000001w000000
5. Quantum GIS Development Team, (2011). Quantum GIS Geographic Information System.Open Source Geospatial Foundation Project. Available at: http://qgis.osgeo.org
6. Olaya, V. and Gimenez, J.C., (2011). SEXTANTE, a versatile open–source library for spatial data analysis.
7. Zhao, L., Song, C. X., Lee, J., Kim, J. R., Feng, W., Merwade, V., & Villoria, N. B. (2011, November). Bring integrated GIS data and modeling capabilities into HUBzero platform. In Proceedings of the ACM SIGSPATIAL Second International Workshop on High Performance and Distributed Geographic Information Systems (pp. 30-33). ACM.
8. GDAL Development Team (2011). GDAL { Geospatial Data Abstraction Library, Version 1.7.3. Open Source Geospatial Foundation. URL http://www.gdal.org/.
9. Dobesova, Z. (2014). DATA FLOW DIAGRAMS IN GEOGRAPHIC INFORMATION SYSTEMS: A SURVEY.14th SGEM GeoConference on Informatics, Geoinformatics and Remote Sensing,1(SGEM2014 Conference Proceedings, ISBN 978-619-7105-10-0/ISSN 1314-2704, June 19-25, 2014, Vol. 1), 705-712.

Wei Wan
 

Wei Wan

Researchers should cite this work as follows:

• Wei Wan (2016), "Geospatial Modeler," https://mygeohub.org/resources/geomodeler.

  BibTex | EndNote

1. Remote Sensing