期刊
出版社
ELSEVIER
DOI: 10.1016/j.jag.2020.102264
关键词
Random Forest; Samples cleansing; Training sample; Agricultural mapping; Food security
Crop type mapping is important for food security applications, and supervised classification methods are commonly used for generating data from satellite images. Various solutions like transfer learning, temporal-spectral signatures, re-utilization of inventories, and crowdsourcing are applied to generate samples for coarser classifications, but rarely for generating crop type samples. This study proposes a method that leverages phenology information to automatically generate crop samples, showing promising results for classes with reduced inter-class similarity. However, the method may not perform as well for crops with high inter-class similarity, particularly in regions with imbalanced crop samples. Despite its shortcomings, the proposed methodology offers a viable option for generating crop samples in regions with limited ground labels.
Crop type mapping is relevant to a wide range of food security applications. Supervised classification methods commonly generate these data from satellite image time-series. Yet, their successful implementation is hindered by the lack of training samples. Solutions like transfer learning, development of temporal-spectral signatures of the target classes, re-utilization of existing inventories, or crowdsourcing initiatives are commonly applied to generate samples for thematically coarser classifications. These methods are rarely used for generating crop types samples. In this study, we leverage the phenology information of existing data inventories using Time-Weighted Dynamic Time Warping (TWDTW) to address the problem of automatic crop sample generation in two target areas. Resulting labeled samples are refined using proximity measures obtained from Random Forests (RF). Sentinel-2 time-series are used to obtain phenology information from two study areas. The proposed methodology achieved promising results for classes with a reduced inter-classes similarity such as sugar beets (user's accuracy, UA, of 98% and producer's accuracy, PA, of 100%) or grains (UA of 98% and PA of 90%). The crops with a high inter-classes similarity yielded less satisfactory results. Potatoes, for example, obtained a high PA of 95%, but a UA of only 36% because of the spectral-temporal similarity with maize. The methodology works well for areas with balanced crop samples. Yet, it favors prevalent classes in areas with imbalanced crops at the expense of a low accuracy for the minority crops. Despite these shortcomings, the proposed methodology offers a viable option to generate crop samples in regions with few ground labels.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据