Enhanced urban functional land use map with free and open-source data

The study aims at developing an applicable methodology to produce the functional land-use map using only free and open-source data.Top-view Sentinel image and ground-view Open Street Map(OSM)data are chosen due to their extensive availability.The three-stage framework,including object-based image analysis,OSM data cleaning,and ontology-based decision fusion,is proposed and implemented with open-source tools.We applied the developed approach to districts 1,4,and 7 of HoChiMinh city,representing the complexities of the dynamic change in big cities.The result showed a good functional land use map with 78.70%overall accuracy.The outcome presents the mismatch between the data-driven approach and human knowledge,which can be improved by ontology-based fusion with OSM data.The ontology-based framework comprises the common urban land-use classes and OSM attributes,which can be applied and extended in other urban areas.Additional text attributes may be applicable only locally and can be modified in our open-source framework.Object-based image analysis takes advantage of Google Earth Engine computing power,whereas ontology-based processing works well on a local computer.In future studies,adopted natural language processing to pre-process OSM data and ontology-based fusion will be implemented on the cloud-computing platform to enhance computational efficiency.