文献类型：期刊文献

英文题名：Environmental modeling of impacts of agricultural land changes using Markov chain and machine learning (case study: Shanghai metropolis, China)

作者：Yao, Zigang[1];Li, Wenmo[2];Pang, Yan[3]

机构：[1]East China Univ Sci & Technol, Sch Art Design & Media, Shanghai 200237, Peoples R China;[2]Shanghai Urban Construct Vocat Coll, Sch Architecture & Environm Arts, Shanghai 201999, Peoples R China;[3]Shanghai Tongzeng Planning & Architectural Design, Shanghai 200092, Peoples R China

年份：2024

卷号：38

期号：4

起止页码：353

外文期刊名：INTERNATIONAL AGROPHYSICS

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001308971500001)】；

语种：英文

外文关键词：Agricultural land changes; thermal radiation; emissivity; normalized difference vegetation index; normalized difference build-up index; normalized difference water index

摘要：Learning about potential land uses is necessary to make the best use of land resources due to ongoing temporal change caused by human activity. The study uses Landsat 5 and 8 images to investigate changes in land cover, especially agricultural land, in Shanghai, China over the last 20 years in 5-year intervals due to urbanization. Also, through the calculation of environmental indices of the earth's surface, such as normalized difference vegetation index, normalized difference built-up index, normalized difference water index, emissivity, thermal radiance, and land surface temperature, the changes in their values in relation to the land cover changes were investigated. To capture the nature of the changes that have occurred, three other major land covers, such as urban, vegetation, and water classes, were also monitored in parallel with agricultural lands. Land cover and land surface temperature changes were also predicted for 2030 using the Markov chain method and GBM machine learning. Based on the results from 2002 to 2020, the agricultural and other land covers of this city underwent significant changes, and most of the agricultural lands have been lost in favor of the urban expansion. Consequently, the class for urban and impervious areas, has grown by 33.87%, making the class with the largest overall positive growth and, on the other hand, the agricultural land class, which had the largest negative growth at 57%, had a fall. Moreover, despite the increase of 10.5% in 2020 in the class of vegetated areas, the urban area's water class, water body class, has grown by 16.4%. The land cover prediction map predicts areas in water body class and urban and impervious areas to rise, while agricultural land class and vegetated areas will contract. The normalized * Corresponding author e-mail: py77@sina.com **Ministry of Education's Program for Planning Funds in Humanities and Social Sciences Research-Research on Development Strategies for Characteristic Historical and Cultural Towns inthe Grand Canal Cultural Belt (Shandong, Jiangsu, and Zhejiang Sections), 20YJAZH121. Major Project of the National Social Science Fund-Study on the Investigation, Arrangement, Protection and Utilization ofTraditional Village Resources Associated with Taiwan Province,21&ZD215. Shanghai Summit Discipline in Design. difference vegetation index index shows a 58.54% decline, while the normalized difference built-up index and normalized difference water index indices and land surface temperature values increase. There is a strong correlation between the normalized difference vegetation index, normalized difference built-up index, normalized difference water index, and thermal radiance indices. The results of prediction and estimation of land cover and surface temperature also indicate reduction of agricultural land for the benefit of increasing urban land and a parallel increase in land surface temperature in 2030. The results of this research can represent the changes that have occurred and their effects as well as a roadmap for planning and policymaking in the future of Shanghai's environment for managers and planners.