Modelling land use and land cover changes in the Lower Neretva Region

Abstract

It has been shown that simulation models are reliable tools for predicting land changes, which contributes to better understanding and management of human impact on the environment. Land use and land cover changes in the Lower Neretva Region between 1990 and 2035 have been analysed and modelled in this study. The final simulation model of future changes was created based on cellular automata and artificial neural networks, implemented in the MOLUSCE plugin for QGIS. In addition, a test simulation model for 2020 was created, which showed high accuracy. Input variables for the final simulation model included a digital elevation model (DEM), slope, distance from water bodies, distance from built-up areas, and population density by settlement in 2011 and 2021. According to the results, forests and grasslands will expand and occupy almost 45% of the area. A slight increase in built-up and agricultural areas is expected, while swamps, water bodies, and sparse vegetation areas will decrease.

A Two-Layer SD-ANN-CA Model Framework for Multi-Typed Land Use and Land Cover Change Prediction under Constraints: Case Study of Ya’an City Area, Western China

“…With the advent of machine-learning techniques, Artificial Neural Networks (ANN) have proven to be a powerful tool to tackle unprecedented, large-scale, influential challenges [35,36] and are known for the perceptron and recognition logic for establishing essential knowledge about driving factors that could make target patterns happen, which can provide the necessary basis to set evolvement process rules for CA models [12,37]. The application of the ANN-CA algorithm became quite popular in the literature, especially in China and other developing countries with more rapid LUCC change and more competition between different land use/land cover types [38][39][40][41][42]. Significantly higher kappa coefficients are obtained in this research, ranging from 0.81 to 0.94, indicating better performance of ANN-CA when formulating future LUCC scenarios.…”