SPATIO-TEMPORAL CHANGE MODELING OF LULC: A SEMANTIC KRIGING APPROACH

• Main Authors: S. Bhattacharjee, S. K. Ghosh
• Format: Article
• Language: English
• Published: Copernicus Publications 2015-07-01
• Series: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• Online Access: http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-4-W2/177/2015/isprsannals-II-4-W2-177-2015.pdf

Spatio-temporal land-use/ land-cover (<i>LULC</i>) change modeling is important to forecast the future <i>LULC</i> distribution, which may facilitate natural resource management, urban planning, etc. The spatio-temporal change in <i>LULC</i> trend often exhibits non-linear behavior, due to various dynamic factors, such as, human intervention (e.g., urbanization), environmental factors, etc. Hence, proper forecasting of <i>LULC</i> distribution should involve the study and trend modeling of historical data. Existing literatures have reported that the meteorological attributes (e.g., <i>NDVI</i>, <i>LST</i>, <i>MSI</i>), are semantically related to the terrain. Being influenced by the terrestrial dynamics, the temporal changes of these attributes depend on the <i>LULC</i> properties. Hence, incorporating meteorological knowledge into the temporal prediction process may help in developing an accurate forecasting model. This work attempts to study the change in inter-annual <i>LULC</i> pattern and the distribution of different meteorological attributes of a region in Kolkata (a metropolitan city in India) during the years 2000-2010 and forecast the future spread of <i>LULC</i> using <i>semantic kriging</i> (<i>SemK</i>) approach. A new variant of time-series <i>SemK</i> is proposed, namely <i>Rev-SemK</i>_ts to capture the multivariate semantic associations between different attributes. From empirical analysis, it may be observed that the augmentation of semantic knowledge in spatio-temporal modeling of meteorological attributes facilitate more precise forecasting of <i>LULC</i> pattern.