Modeling land use/cover change based on LCM model for a semi-arid area in the Latian Dam Watershed (Iran)

• Published in: Environmental monitoring and assessment Vol. 195; no. 3; p. 363
• Main Authors: Shafie, Banafsheh, Javid, Amir Hossein, Behbahani, Homa Irani, Darabi, Hassan, Lotfi, Farhad Hosseinzadeh
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.03.2023; Springer Nature B.V
• Subjects: Accumulation; Accuracy; Atmospheric Protection/Air Quality Control/Air Pollution; Conservation of Natural Resources - methods; Dynamic models; Earth and Environmental Science; Ecology; Ecotoxicology; Environment; Environmental Management; Environmental monitoring; Environmental Monitoring - methods; Environmental science; Iran; Land use; Landsat; Landscape preservation; Modelling; Monitoring/Environmental Analysis; Multilayer perceptrons; Multilayers; Neural networks; Open spaces; Orchards; Public policy; Reflectance; Regional development; Regional planning; Remote sensing; Risk reduction; Satellite imagery; Semi arid areas; Sustainable Development; Time series; Watersheds; Iran; Land Change Modeler; Artificial neural network; LULC change; Multi-layer perceptron
• ISSN: 0167-6369; 1573-2959
• DOI: 10.1007/s10661-022-10876-1

The monitoring and modeling of changes, based on a time-series LULC approach, is fundamental for planning and managing regional environments. The current study analyzed the LULC changes as well as estimated future scenarios for 2027 and 2037. To achieve accuracy in predicting LULC changes, the Land Change Modeler (LCM) was used for the Latian Dam Watershed, which is located approximately in the northeast of Tehran. The LULC time-series technique was specified utilizing four atmospherically endorsed surface reflectance Landsat images for the years t 1 (1987), t 2 (1998), t 3 (2007), and t 4 (2017) to authenticate the LULC predictions, so to obtain estimates for t 5 (2027) and t 6 (2037). The LULC classes identified in the watershed were water bodies, build-up areas, vegetated areas, and bare lands. The dynamic modeling of the LULC was based on a multi-layer perceptron (MLP), the neural network in LCM, which presented good results with an average accuracy rate equivalent to 84.89 percent. The results of the LULC change analysis showed an increase in the build-up area and a decrease in bare lands and vegetated areas within the duration of the study period. The results of this research could help in the formulation of public policies designed to conserve environmental resources in the Latian Dam Watershed and, consequently, minimize the risks of the fragmentation of orchards and vegetated areas. Also, careful regional planning ensuring the preservation of natural landscapes and open spaces is critical to creating a resilient regional environment and sustainable development.