Evaluation of residential land use compatibilities using a density-based IOWA operator and an ANFIS-based model: A case study of Tehran, Iran

• Pahlavani, Parham ^[1] ; Sheikhian, Hossein ^[1] ; Bigdeli, Behnaz ^[2]
  1. [1] University of Tehran

     University of Tehran

     Irán

     
  2. [2] School of Civil Engineering, Shahrood University of Technology, Shahrood, Iran
• Localización: Land use policy: The International Journal Covering All Aspects of Land Use, ISSN 0264-8377, ISSN-e 1873-5754, Nº. 90, 2020
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • The world is rapidly urbanized in the recent decades and urban areas are dealing with enormous changes and demands in utilizing the land units. To prevent incongruous land development, a seamless land use control planning tool, impowered by a decision support system is an imperative part of development management. This study focuses on evaluating the suitability of existing land uses through a spatial decision support system. Although the problem involves various criteria as well as expert judgments, we dealt with a multi-criteria group decision making problem. The proposed methodology consists of two main sections: density-based induced ordered weighted averaging (D-IOWA) operator as a group decision making section to combine expert opinions on the problem, and an adaptive neuro-fuzzy resonance system (ANFIS) to define the compatibility of the land uses in their surrounding environment. Expert opinions were aggregated by the D-IOWA operator and the ANFIS model was trained and then applied to the rest of the data to generate the compatibility map of the residential areas. An accuracy of 81%, and a root mean square error of 0.44 were observed. Maximum 15% variation in the outputs was observed in the sensitivity analysis. In addition to the performance measurements of the model, some other models were implemented and compared with the ANFIS model. The comparisons concluded that most of the models provided acceptable accuracies while the ANFIS model acquired the best results and confirmed to be used in similar circumstances. This study confirmed that a multi-criteria decision-making system supported by an accurate classification system can provide a basis for a detailed and accurate distribution of land use across the land unit.