The spatial plan program for Makassar City and the surrounding area called Mamminasata (Makassar, Maros, Sungguminasa, and Takalar) was created by the Indonesian Government. The program regulates the proportion of land cover, but predictions about land cover changes were not considered. Therefore, in this study, we predict what the land cover may be in 2031 using the multi-layer perceptron neural network and the Markov chain methods. For this purpose, image composite, support vector machine classifier, and change detection were applied to a time series of satellite data. Visual validation showed the hot-spots of land cover changes related to population density, and statistical validation scored 0.99 and 0.78 in no information kappa and grid-cell level location kappa, respectively. The model was performed to predict land cover in 2031, and the predicted result was then compared with the spatial plan using an overlapping method. The results showed that built-up area, dryland agriculture, and wetland agriculture occupied two, twenty, and eight percent of the protected zone, respectively. Meanwhile, fifteen percent of the development zone was covered by forest, mainly in the eastern part of Mamminasata. The result can be used to help the Government decide future plans for the Mamminasata area.

中文翻译：

---

预测印度尼西亚Mamminasata地区的土地覆盖变化，以评估空间规划

望加锡市及其周边地区称为Mamminasata（Makassar，Maros，Sungguminasa和Takalar）的空间规划方案是由印度尼西亚政府制定的。该计划规定了土地覆盖的比例，但未考虑土地覆盖变化的预测。因此，在这项研究中，我们使用多层感知器神经网络和马尔可夫链方法预测了2031年的土地覆盖。为此，将图像合成，支持向量机分类器和变化检测应用于卫星数据的时间序列。视觉验证显示了与人口密度有关的土地覆被变化的热点，统计验证在无信息卡伯和网格单元水平位置卡伯分别为0.99和0.78。该模型用于预测2031年的土地覆盖，然后使用重叠法将预测结果与空间规划进行比较。结果表明，建成区，旱地农业和湿地农业分别占保护区的百分之二，百分之二十和百分之八。同时，开发区的15％被森林覆盖，主要在Mamminasata东部。结果可用于帮助政府确定Mamminasata地区的未来计划。