Modelling and Predicting Multiple Land Use/Land Cover Changes Using SimWeight Method with Choice Approach among Existing Options

Land use change models are increasingly being used to evaluate the effect of land change on climate and biodiversity. This study was conducted to identify the land cover changes during ۱۹۹۶ to ۲۰۰۶ and to predict the future changes (for ۲۰۲۶) using satellite imagery in the Massachusetts region of the United States using a Similarity-Weighted instance-based Machine Learning (SimWeight) method. To increase the efficiency and optimization of the model, the efficient features have been selected using Cramer's V test. In this regard, the study area was classified into ۱۸ classes. As a result, the analysis showed a decreasing trend of ۳.۸۴% by grasslands, while bare lands have increased by ۹.۷۸% and unconsolidated shore by ۹.۵%; as well as the other land uses have changed slightly between ۱۹۹۶ and ۲۰۰۶. Accordingly, Land-use/Land-cover changes have been predicted using the Similarity-Weighted instance-based Machine Learning (SimWeight) and Markov chain model by selecting from the available options using the Cramer's V test for ۲۰۲۶. The accuracy of this method using the ۲۰۱۶ data had an overall accuracy of ۸۹.۳۱% and a Kappa index of ۰.۷۶۴۰. The results of this study showed rapid changes in land use for future years. The conversion of forest land into other lands, especially grassland and pasture, was the most important change in land cover in the future. Therefore, planning for the protection and restoration of the forest should be a key plan for decision-makers in the study area.

Keywords:

Land-use Change Prediction , SimWeight , Cramer’s V , Markov Chain