Classification of sugarcane varieties with harmonized Sentinel-2 and Landsat-8/9 data using parametric and non-parametric methods

Remote sensing data has been successfullyused to enhance sugarcanemonitoring and management, in topicssuch as yield estimation, health anomaly detection, orvariety classification. Specifically, variety classification is an essential objectivefor optimizing crop management, as it can guidestrategies such as plant renovation, pest control, or yield estimation. A literature review allowed identifyingthat the integration of diversesatellite platforms to enhance time series for sugarcane variety classification has not been explored.This strategy can improve the temporal density of available imagery in our study area, Costa Rica, with frequent cloud cover. Therefore, ourresearchproposedto classify six sugarcane varietiesusing anadditive approach (aggregating them in four variety groups)andemploying parametric and non-parametric algorithms on harmonized data from Sentinel-2 and Landsat-8/9. Validation was done at both pixel and plot scales. Thebest classifications were achieved using green and near infrared bands, along with the Enhanced Bloom Indexand Normalized Difference Infrared Indexvegetation indices. Regarding temporal dynamics, the most relevant months were September, November, and December, corresponding to advanced growth cycle stages.Support Vector Machine and Random Forest provided the best classification accuracies. At the pixel scale, the overall accuracy of all groups exceeded 0.86, with a slight decrease as the number of varieties increased. When validation was done at plot scale, the overall accuracyremained above 0.89 in all the groups. These achievementsweresuitableand valuableforsugarcane sustainable planning anddecision-making.