International Journal of Applied Earth Observation and Geoinformation
High quality land use/land cover (LULC) data with fine spatial resolution and frequent temporal coverage are indispensable for revealing detail information of the Earth’s surface, characterizing LULC of the area, predicting the plausible land use changes, and assessing the viability and impacts of any development plans. While airborne imagery has high spatial resolution, it only provides limited temporal coverage over time. The LULC data from historical remote sensing images, such as those from Landsat, have frequent coverages over a long temporal period, but their spatial resolutions are low.
This paper presents a spatio-temporal Cokriging method to sharpen LULC data and predict the trends of land use change. A set of time-series coarse resolution LULC maps and one frame of high spatial resolution airborne imagery of the Upper Mill Creek Watershed were used to illustrate the utility of our method. By explicitly describing the spatio-temporal dependence within and between different datasets, modelling the Anderson classification codes using spatial, temporal, and cross-covariance structures, and transforming the Anderson integer classification code to class probability, our method was able to resolve the differences between multi-source spatio-temporal LULC data, generate maps with sharpened and detailed land features, characterize the spatial and temporal LULC changes, reveal the trend of LULC change, and create a quality dataset invaluable for monitoring, assessing, and modelling LULC changes.
Land use, Change detection, Sharpening algorithm, Multispectral, Classification
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Urban and Regional Planning
Bo Yang, Susanna T.Y. Tong, and Rong Fan. "Sharpening land use maps and predicting the trends of land use change using high resolution airborne image: A geostatistical approach" International Journal of Applied Earth Observation and Geoinformation (2019): 141-152. https://doi.org/10.1016/j.jag.2019.03.010