| Popis: |
Moraes, D., Benevides, P., Costa, H., Moreira, F. D., & Caetano, M. (2022). Exploring Different Levels of Class Nomenclature in Random Forest Classification of Sentinel-2 Data. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium: Proceedings (pp. 2279-2282). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS46834.2022.9883798--------- Funding:The work has been supported by project foRESTER (PCIF ISSI/0102/20 17), SCAPEFIRE (PCIF IMOS/0046/ 2017) and by Centro de Investigçãao em Gestae de Informação (MagIC), all funded by the Portuguese Foundation for Science and Technology (FCT). Value-added data processed by CNES for the Theia data centre www.theia-land.fr using Copernicus products. The processing uses algorithms developed by Theia's Scientific Expertise Centres. The current land cover mapping paradigm relies on automatic classification of satellite images, with supervised methods being the most used, implying training data to have a crucial role. Aspects such as training sample size and quality should be carefully considered. This paper proposes assessing the use of a detailed class nomenclature to reinforce class diversity in the training sample. A Random Forest (RF) classification of Sentinel-2 multi-temporal data was conducted. Additionally, the effect of sample size and class distribution were evaluated. The results indicate that the use of a detailed nomenclature provided better results in terms of classification accuracy. With respect to sample distribution, adopting class sizes proportional to their occurrence in a reference land cover map exhibited superior performance in comparison to an equal size approach. The effect of sample size on classification performance was limited, as previous studies with RF suggested. authorsversion published |
