You must login before you can run this tool.
Category
Published on
Abstract
The Fine-scale Land Allocation Tool, FLAT, is an interface developed based on an econometric framework that uses pixel level (e.g., 5 arc-minute) independent variables (agronomic data in the examples installed with the tool) and aggregate dependent variables (land use statistics at the regional level in the examples) to develop predictions of the dependent variables (cropland allocations in the examples) at the pixel level (Song et al., 2016).
FLAT is an open source tool. Users can upload their own data files of independent and dependent variables and GAMS script that implements an estimation approach, or use the default datasets and scripts. Default datasets include state/province level cropland harvested area data for maize, soybeans, and wheat, and pixel level land attributes data for the Americas. The default models predict cropland area at the 5 arc-minute pixel level for the Americas. All default datasets, programming scripts, and result files can be downloaded. FLAT provides mapping options so that the users can view and download the predicted crop fractions shown on a map by selecting the region and crop of interest.
Credits
The authors are grateful for helpful comments and suggestions from Thomas Hertel. FLAT development is supported in part by USDA grant Agreement #58300010058 and Purdue grant #105651.
References
Song, J., Delgado, M. S., Preckel, P. V., and Villoria, N. B. (2016). “Pixel Level Cropland Allocation and the Marginal Impacts of Biophysical Factors,” under review.
Graphical user interface was created by:
Jingyu Song, Michael S. Delgado, Paul V. Preckel, Shandian Zhe, Ian J. Campbell, Lan Zhao, Carol Song. (2016). “FLAT in the Cloud,” https://mygeohub..org/resources/flat
Citations
Jingyu Song, Michael S. Delgado, Paul V. Preckel, Shandian Zhe, Ian J. Campbell, Lan Zhao, Carol Song. (2016).
Cite this work
Researchers should cite this work as follows: