One-Class Classification of Natural Vegetation Using Remote Sensing: A Review

Advances in remote sensing (RS) technology recent years have increased the interest including RS data into one-class classifiers (OCCs). However, this integration is complex given interdisciplinary issues involved. In context, review highlights advances and current challenges integrating OCCs to map vegetation classes. A systematic was performed for period 2013–2020. total of 136 articles were analyzed based on 11 topics 30 attributes that address ecological issues, properties data, tools parameters used classify natural vegetation. The results highlight several use OCCs: (i) mapping potential actual areas, (ii) long-term monitoring classes, (iii) generation multiple variables, (iv) availability open-source (v) reduction plotting effort, (vi) quantification over-detection. Recommendations related also suggested: increasing visibility available following good classification practices, bridging gap between spatial resolution site extent, classifying plant communities.