Identification and mapping of various habitats with sufficient spatial details are essential to support environmental planning and management. Considering the complexity of diverse habitat types in a heterogeneous landscape, a context-dependent mapping framework is expected to be superior to traditional classification techniques. With the aim to produce a territory-wide habitat map in Hong Kong, a three-stage mapping procedure was developed to identify 21 habitats by combining very-high-resolution satellite images, geographic information system (GIS) layers and knowledge-based modification rules. In stage 1, several classification methods were tested to produce initial results with 11 classes from a WorldView-2/3 image mosaic using a combination of spectral, textural, topographic and geometric variables. In stage 2, modification rules were applied to refine the classification results based on contextual properties and ancillary data layers. Evaluation of the classified maps showed that the highest overall accuracy was obtained from pixel-based random forest classification (84.0%) and the implementation of modification rules led to an average 8.8% increase in the accuracy. In stage 3, the classification scheme was expanded to all 21 habitats through the adoption of additional rules. The resulting habitat map achieved >80% accuracy for most of the evaluated classes and >70% accuracy for the mixed habitats when validated using field-collected points. The proposed mapping framework was able to utilize different information sources in a systematic and controllable workflow. While transitional mixed habitats were mapped using class membership probabilities and a soft classification method, the identification of other habitats benefited from the hybrid use of remote-sensing classification and ancillary data. Adaptive implementation of classification procedures, development of appropriate rules and combination with spatial data are recommended when producing an integrated and accurate map.
|Number of pages||67|
|Early online date||24 Dec 2021|
|Publication status||Published - 24 Dec 2021|
Bibliographical noteWe thank LM Chu (School of Life Sciences, CUHK), David Lau, Joyce Siu (Shiu Ying Hu Herbarium, CUHK), Leo Ng, Martin Lee (Earth System Science Programme, CUHK) and all helpers for their assistance in field data collection. This work was supported by the Agriculture, Fisheries and Conservation Department and the Planning Department of the HKSAR Government.
We thank the editors and anonymous reviewers for their helpful comments on this manuscript.
- Multi-stage approach
- post-classification modification
- habitat mapping