Land serves as a vital production resource, and therefore land planning plays an important role in sustainable land-use design. Iran includes large areas of the world's drylands, many of which are used as rangelands, and where the population has increased by 60% from 1985 to 2016. Further population increase in Iran would probably require more land resources to be allocated for human needs. However, the pace and patterns of these changes remain unclear. The aim of this study was to map land-cover change from 1985 to 2016 and predict future land-cover change in the Zayandehrood ecologic sub-basins of Central Iran. By using multiseasonal LANDSAT imagery, we mapped land-cover change with a Random Forest classifier for 1985, 1998, and 2016 with an overall accuracy of 80% for each period. Classification results revealed that from 1985 to 2016 residential areas doubled and industrial areas increased at the expense of rangelands. Our study also revealed cropland expansion at the expense of rangelands, cropland abandonment, and contraction of croplands due to residential and industrial development. Prediction of changes by 2036 with a multilayer perceptron neural network and Markov chain analysis showed further expansion of industries and residencies, particularly near the Ghamashlu Wildlife Refuge. Despite the partial restoration of rangelands in some parts of the world, our study provides evidence of ongoing rangeland degradation in Iran due to conversion to other land uses. Therefore, the study underscores the importance of sustainable land management of already cultivated areas and the development of strategies for the protection of global rangelands.

中文翻译：

---

牧场的命运：揭示过去并预测伊朗中部旱地从 1985 年到 2036 年的土地覆盖转变

土地是重要的生产资源，因此土地规划在可持续土地利用设计中发挥着重要作用。伊朗包括世界上大片旱地，其中许多被用作牧场，人口从 1985 年到 2016 年增加了 60%。伊朗人口的进一步增加可能需要分配更多的土地资源来满足人类需求。然而，这些变化的速度和模式仍不清楚。本研究的目的是绘制 1985 年至 2016 年的土地覆盖变化图，并预测伊朗中部 Zayandehrood 生态子盆地未来的土地覆盖变化。通过使用多季节 LANDSAT 图像，我们使用随机森林分类器绘制了 1985、1998 和 2016 年的土地覆盖变化，每个时期的总体准确度为 80%。分类结果显示，从 1985 年到 2016 年，住宅区翻了一番，工业区以牺牲牧场为代价而增加。我们的研究还揭示了耕地扩张以牺牲牧场、耕地废弃以及住宅和工业发展导致的耕地收缩为代价。使用多层感知器神经网络和马尔可夫链分析预测到 2036 年的变化表明工业和居住地进一步扩张，特别是在 Ghamashlu 野生动物保护区附近。尽管世界某些地区的牧场已部分恢复，但我们的研究提供的证据表明，由于转换为其他土地用途，伊朗的牧场正在退化。所以，