作者: Di Yang , Chiung-Shiuan Fu , Audrey C. Smith , Qiang Yu
DOI: 10.1080/10095020.2017.1371385
关键词: Distribution (economics) 、 Scale (map) 、 Data science 、 Random forest 、 Cartography 、 Computer science 、 Land cover 、 Training (civil) 、 Collaborative mapping 、 Volunteered geographic information 、 Task (project management)
摘要: AbstractA land-use map at the regional scale is a heavy computation task yet critical to most landowners, researchers, and decision-makers, enabling them make informed decisions for varying objectives. There are two major difficulties in generating land classification maps scale: necessity of large data-sets training points expensive cost terms both money time. Volunteered Geographic Information opens new era mapping visualizing physical world by providing an open-access database valuable georeferenced information collected volunteer citizens. As one well-known VGI initiatives, OpenStreetMap (OSM), contributes not only road network distribution but also potential using these data justify delineate patterns. Whereas, large-scale approaches – including national scales confuse “land cover” “land-use”, or build up based on modeled la...