AUTOMATED UPDATING OF FOREST COVER MAPS FROM CLOUD-FREE SENTINEL-2 MOSAIC IMAGES USING OBJECT-BASED IMAGE ANALYSIS AND MACHINE LEARNING METHODS
| Autor: | Misganu Debella-Gilo, Bjørn Tobias Borchsenius, Johannes Breidenbach, Knut Bjørkelo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
lcsh:Applied optics. Photonics
0106 biological sciences 010504 meteorology & atmospheric sciences Computer science Machine learning computer.software_genre lcsh:Technology 01 natural sciences Software Robustness (computer science) Aerial image 0105 earth and related environmental sciences Contextual image classification lcsh:T business.industry lcsh:TA1501-1820 Resource map Field (geography) Random forest lcsh:TA1-2040 Multilayer perceptron Artificial intelligence lcsh:Engineering (General). Civil engineering (General) business computer 010606 plant biology & botany |
| Zdroj: | V-3 2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol V-3-2020, Pp 803-807 (2020) |
| ISSN: | 2194-9050 |
| Popis: | Planning sustainable use of land resources and environmental monitoring benefit from accurate and detailed forest information. The basis of accurate forest information is data on the spatial extent of forests. In Norway land resource maps have been carefully created by field visits and aerial image interpretation for over four decades with periodic updating. However, due to prioritization of agricultural and built-up areas, and high requirements with respect to the map accuracy, forest areas and outfields have not been frequently updated. Consequently, in some part of the country, the map has not been updated since its first creation in the 1960s. The Sentinel-2 satellite acquires images with high spatial and temporal resolution which provides opportunities for creating cloud-free mosaic images over areas that are often covered with clouds. Here, we combine object-based image analysis with machine learning methods in an automated framework to map forest area in Sentinel-2 mosaic images. The images are segmented using the eCogntion™ software. Training data are collected automatically from the existing land resource map and filtered using height and greenness information so that the training samples certainly represent their respective classes. Two machine learning algorithms, namely Random Forest (RF) and the Multilayer Perceptron Neural Network (MLP), are then trained and validated before mapping forest area. The effects of including and excluding some features on the classification accuracy is investigated. The results show that the method produces forest cover map at very high accuracy (up to 97%). The MLP performs better than the RF algorithm both in classification accuracy and in robustness against inclusion and exclusion of features. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|