Spatial Validation of Land Use Change Models Using Multiple Assessment Techniques: A Case Study of Transition Potential Models

摘要: Using land use and cover change (LUCC) models for the urban growth planning, environmental assessment, decision-making needs establishment of an appropriate level confidence in their performance. The objective this research is to explore importance using multiple assessment techniques order fairly evaluate performance models. An application conducted by Land Change Modeler Ecological Sustainability (LCM) which empirical transition potential model. LCM applied model agricultural developed areas Rennes metropolitan area (France). demand estimated Markov Chain model; whereas, map implemented Multi-Layer Perceptron Neural Network (MLP) method based on historical changes driving variables. assessed a variety most commonly used validation techniques. At study level, correctness disagreement analysis shows that performs better at predicting amount than allocation areas. Additionally, landscape metrics reveal tends predict fragmented form, seems evident because large number individual patches. municipality error budget performance, varies highly between different subareas, be improved. Moreover, cross-tabulation both observed predicted transitions reveals values does not perfectly fit change; solely limited with high potential.