Use of Multi-Frequency SAR anOptical Data for Crop Area Classification in Preparation for the NISAR Cropland Products

An algorithm for classifying crop areas from multi-frequency Synthetic Aperture Radar (SAR) and optical data is evaluated for the upcoming NASA ISRO SAR (NISAR) mission and its active crop-area products. Two time-series of L-band ALOS-2 and C-band Sentinel-1A images over an agricultural region in the Southern United States are used as input, as well as higher-resolution Planet optical data. Since existing landcover maps are available with at least one-year delay, training and validation sets of crop/non-crop polygons are derived with the Planet images. Classification results show that the 80% requirement on the NISAR science accuracy is achievable only with L-band HV input and with a resolution of 100m. In comparison, HH polarized images do not meet this target. The spatial resolution is a key factor: 100m is necessary to accomplish the 80% goal, while 10m do not produce the desired accuracy. Unlike the previous study reporting that C-band performs better than L-band, we found otherwise in this study. This suggests that the performance likely depends on the site of interest and crop types. Alternative to the SAR images, the Normalized Difference Vegetation Index (NDVI) from Planet data is not effective either as an input to the classification algorithm or as a ground truth for training the algorithm itself. The reason is that NDVI becomes saturated and temporally static, thus rendering crop pixels misclassified as non-crop ones.