气候变化领域集成服务门户(CCPortal): Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians

CCPortal

DOI	10.1016/j.rse.2020.112103
	Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians
	Grabska E.; Frantz D.; Ostapowicz K.
发表日期	2020
ISSN	00344257
卷号	251
英文摘要	Information about forest stand species distribution is essential for biodiversity modelling, forest disturbances, fire hazard and drought monitoring, biomass and carbon estimation, detection of non-native and invasive species, as well as for planning forest management strategies. High temporal and spectral resolution remote sensing data from the Sentinel-2 mission enables the derivation of accurate and timely maps of tree species in forests in a cost-efficient way. However, there is still a lack of studies regarding forest stand species mapping for large areas like the Polish Carpathian Mountains (approx. 20,000 km2). In this study, we aimed to develop a workflow to obtain forest stand species maps with machine learning algorithms applied to multi-temporal Sentinel-2 products and environmental data at regional scale. Using variable importance techniques - Variable Importance Using Random Forests (VSURF) and Recursive Feature Elimination (RFE) - we assessed three Sentinel-2 Best Available Pixel composites (April, July and October), eight annual spectral-temporal metrics (STM; mean, minimum, maximum, standard deviation, range, first quartile, third quartile and interquartile range), and four environmental topographic variables (elevation, slope, aspect, distance to water bodies), i.e. 114 variables in total. Following a variable importance assessment, we produced maps of eleven tree species with the use of three Machine Learning algorithms: Random Forest (RF), Support Vector Machines (SVM) and Extreme Gradient Boosting (XGB) on nine different variable subsets, i.e. in total 27 classifications. The results showed that SVM outperformed the other two classifiers - the highest overall accuracy exceeded 85% for SVM classification of all variables (86.9%), and 64 variables (85.6%). Including elevation information improved the accuracies. From the best five classifications we created a final ensemble map (overall accuracy of 86.6%) and a precision map based on the Simpson Index, which indicates where the five models agree. This ensemble approach allowed us to determine that the lowest precision occurred in foothills and basins with lower forest cover, in the areas with lack of good quality imagery, and at the borders of stands with homogenous species composition. On the other hand, the highest precision occurred in regions with homogenous stands with high forest and canopy cover. The study demonstrates the potential of Sentinel-2 imagery and topographic data in mapping forest stand species in large mountainous areas with high accuracy. Furthermore, it demonstrates the usefulness of the ensemble approach, which enables to assess the classification precision. © 2020 Elsevier Inc.
英文关键词	Classification; Ensemble; Extreme gradient boosting; Mountains; Random forest; Support vector machines; Vegetation
语种	英语
scopus关键词	Adaptive boosting; Biodiversity; Biohazards; Decision trees; Forestry; Mapping; Random forests; Remote sensing; Support vector machines; Classification precision; Inter quartile ranges; Management strategies; Recursive feature elimination; Species composition; Species distributions; Temporal and spectral resolutions; Variable importances; Learning systems; accuracy assessment; algorithm; biodiversity; classification; forest management; machine learning; management practice; precision; satellite data; satellite imagery; Sentinel; stand structure; vegetation cover; vegetation mapping; Carpathians
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/179108
作者单位	Institute of Geography & Spatial Management, Faculty of Geography & Geology, Jagiellonian University in Kraków, Gronostajowa 730-387, Poland; Department of Forest Resources Management, Faculty of Forestry, University of Agriculture in Krakow, Al. 29 Listopada 46, Krakow, 31-425, Poland; Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, Berlin, 10099, Germany; Department of Environmental Science, Policy & Management, University of California, Berkeley, 326 Mulford Hall, Berkeley, CA 94720, United States
推荐引用方式 GB/T 7714	Grabska E.,Frantz D.,Ostapowicz K.. Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians[J],2020,251.
APA	Grabska E.,Frantz D.,&Ostapowicz K..(2020).Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians.Remote Sensing of Environment,251.
MLA	Grabska E.,et al."Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians".Remote Sensing of Environment 251(2020).