ABSTRACT The increase of Land Surface Temperature (LST) and the formation of heat island in megacities have become an emerging environmental concern. The main objective of this study is to predict the intensity of Tehran’s heat island in the year 2033 based on historical changes of land cover and LST. For this purpose, Landsat satellite images were integrated with meteorological stations’ measurements from 1985 to 2017. The Cellular Automata-Markov (CA-Markov) and Artificial Neural Network (ANN) models were used to predict the land cover changes and to the modelling of the Surface Urban Heat Island Intensity (SUHII), Surface Urban Heat Island Ratio Index (SUHRI) was used. Subsequently, using statistical analysis of the effect of historical land cover changes on LST variations, SUHII for 2033 was predicted. Our findings show that within this period, the built-up lands increased significantly from 39% in 1985 to 65% in 2017. The intensity of heat island increased with an increase in the value of SUHII from 0.02 to 0.19. Our predictive analysis reveals that the intensity of the Tehran’s heat island will increase to 0.32 by 2033. Our conclusions draw attentions to the increasing LST now and in the future in Tehran so that urban planners and local authorities take adequate actions for controlling its environmental impacts.

中文翻译：

---

模拟城市地表热岛强度并预测新兴模式：Landsat 多时相图像和德黑兰作为案例研究

摘要 地表温度（LST）的升高和大城市热岛的形成已成为一个新兴的环境问题。本研究的主要目的是根据土地覆盖和LST的历史变化预测2033年德黑兰热岛的强度。为此，Landsat 卫星图像与 1985 年至 2017 年气象站的测量结果相结合。使用元胞自动机-马尔可夫 (CA-Markov) 和人工神经网络 (ANN) 模型来预测土地覆盖变化和建模使用地表城市热岛强度 (SUHII)、地表城市热岛比率指数 (SUHRI)。随后，利用历史土地覆盖变化对 LST 变化影响的统计分析，预测了 2033 年的 SUHII。我们的研究结果表明，在此期间，建成用地比例从1985年的39%显着增加到2017年的65%。热岛强度随着SUHII值从0.02增加到0.19而增加。我们的预测分析表明，到 2033 年，德黑兰的热岛强度将增加到 0.32。我们的结论引起人们对德黑兰现在和未来 LST 增加的关注，以便城市规划者和地方当局采取适当的行动来控制其对环境的影响。