Abstract
Advances in remote sensing (RS) technology in recent years have increased the interest in including RS data into one-class classifiers (OCCs). However, this integration is complex given the interdisciplinary issues involved. In this context, this review highlights the advances and current challenges in integrating RS data into OCCs to map vegetation classes. A systematic review was performed for the period 2013–2020. A total of 136 articles were analyzed based on 11 topics and 30 attributes that address the ecological issues, properties of RS data, and the tools and parameters used to classify natural vegetation. The results highlight several advances in the use of RS data in OCCs: (i) mapping of potential and actual vegetation areas, (ii) long-term monitoring of vegetation classes, (iii) generation of multiple ecological variables, (iv) availability of open-source data, (v) reduction in plotting effort, and (vi) quantification of over-detection. Recommendations related to interdisciplinary issues were also suggested: (i) increasing the visibility and use of available RS variables, (ii) following good classification practices, (iii) bridging the gap between spatial resolution and site extent, and (iv) classifying plant communities.
Highlights
Integrating remote sensing (RS) data into one-class classifiers (OCCs) to map natural vegetation is a multidisciplinary issue: (i) the RS community highlights the emergence of new sensors and new variables derived from the RS data; (ii) the ecological community is interested in the potential of RS data to improving monitoring of vegetation classes but stresses the need to understand clearly how each classifier works
The literature search was based on expert definition of 79 keywords that were classified into three topics: RS, OCCs, and natural vegetation
The size of the study site is crucial for OCCs: the larger the size and variety of environments considered, the more transferable the classification will be to other parts of the world [17]
Summary
Integrating RS data into OCCs to map natural vegetation is a multidisciplinary issue: (i) the RS community highlights the emergence of new sensors and new variables derived from the RS data; (ii) the ecological community is interested in the potential of RS data to improving monitoring of vegetation classes but stresses the need to understand clearly how each classifier works In this context, the objectives of this study are: (i) to review the recent state-of-the-art on the use of remote sensing data for one-class classification of natural vegetation at three hierarchical levels (land cover, plant community, and plant species classes); (ii) to review the state-of-the-art on the tools and parameters used to apply OCCs; and (iii) to highlight the advances achieved in classification of natural vegetation using OCCs, the challenges to be addressed, and further research to be conducted. A systematic review was performed for the period 2013–2020
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have