REFINEMENT OF CROPLAND DATA LAYER USING MACHINE LEARNING
- 1Center for Spatial Science and Systems, George Mason University, Fairfax, VA 22030, USA
- 2Research and Development Division, U.S. Department of Agriculture National Agricultural Statistics Service, Washington, DC 20250, USA
- 3Research and Development Division, U.S. Department of Agriculture National Agricultural Statistics Service, Washington, DC 20250, USA
Keywords: Cropland Data Layer, Machine Learning, Misclassification Correction, Crop Sequence Modeling, Raster Map Refinement
Abstract. As the most widely used crop-specific land use data, the Cropland Data Layer (CDL) product covers the entire Contiguous United States (CONUS) at 30-meter spatial resolution with very high accuracy up to 95% for major crop types (i.e., Corn, Soybean) in major crop area. However, the quality of early-year CDL products were not as good as the recent ones. There are many erroneous pixels in the early-year CDL product due to the cloud cover of the original Landsat images, which affect many follow-on researches and applications. To address this issue, we explore the feasibility of using machine learning technology to refine and correct misclassified pixels in the historical CDLs in this study. An end-to-end deep learning-based framework for restoration of misclassified pixels in CDL image is developed and tested. By feeding the CDL time series into the artificial neural network, a crop sequence model is trained and the misclassified pixels in an original CDL map can be restored. In the experiment with the 2005 CDL data of the State of Illinois, the misclassified pixels over Agricultural Statistics Districts (ASD) #1760 were corrected with a reasonable accuracy (> 85%). The findings suggest that the proposed method provides a low-cost and reliable way to refine the historical CDL data, which can be potentially scaled up to the entire CONUS.