DExtER Lab, School of Civil and Environmental Engineering, A-11 Building, North Campus, IIT Mandi, Mandi, Himachal Pradesh, India, 175075.
Environ Sci Pollut Res Int. 2024 May;31(21):30569-30591. doi: 10.1007/s11356-024-33094-3. Epub 2024 Apr 12.
Mizoram (India) is part of UNESCO's biodiversity hotspots in India that is primarily populated by tribes who engage in shifting agriculture. Hence, the land use land cover (LULC) pattern of the state is frequently changing. We have used Landsat 5 and 8 satellite images to prepare LULC maps from 2000 to 2020 in every 5 years. The atmospherically corrected images were pre-processed for removal of cloud cover and then classified into six classes: waterbodies, farmland, settlement, open forest, dense forest, and bare land. We applied four machine learning (ML) algorithms for classification, namely, random forest (RF), classification and regression tree (CART), minimum distance (MD), and support vector machine (SVM) for the images from 2000 to 2020. With 80% training and 20% testing data, we found that the RF classifier works best with the most accuracy than other classifiers. The average overall accuracy (OA) and Kappa coefficient (KC) from 2000 to 2020 were 84.00% and 0.79 when the RF classifier was used. When using SVM, CART, and MD, the average OA and KC were 78.06%, 0.73; 78.60%, 0.72; and 73.32%, 0.65, respectively. We utilised three methods of topographic correction, namely, C-correction, SCS (sun canopy sensor) correction, and SCS + C correction to reduce the misclassification due to shadow effects. SCS + C correction worked best for this region; hence, we prepared LULC maps on SCS + C corrected satellite image. Hence, we have used RF classifier for LULC preparation demi-decadal from 2000 to 2020. The OA for 2000, 2005, 2010, 2015, and 2020 was found to be 84%, 81%, 81%, 85%, and 89%, respectively, using RF. The dense forest decreased from 2000 to 2020 with an increase in open forest, settlement, and agriculture; nevertheless, when Farmland was low, there was an increase in the barren land. The results were significantly improved with the topographic correction, and misclassification was quite less.
印度米佐拉姆邦是教科文组织印度生物多样性热点地区的一部分，主要由从事轮作农业的部落居住。因此，该邦的土地利用/土地覆被（LULC）模式经常发生变化。我们使用 Landsat 5 和 8 卫星图像，每 5 年从 2000 年到 2020 年编制 LULC 地图。对大气校正后的图像进行预处理以去除云层，然后将其分为六类：水体、农田、住区、阔叶林、密林和裸地。我们应用了四种机器学习（ML）算法进行分类，即随机森林（RF）、分类回归树（CART）、最小距离（MD）和支持向量机（SVM），用于 2000 年至 2020 年的图像。使用 80%的训练数据和 20%的测试数据，我们发现 RF 分类器的准确性优于其他分类器。使用 RF 分类器时，2000 年至 2020 年的平均总体精度（OA）和 Kappa 系数（KC）分别为 84.00%和 0.79。当使用 SVM、CART 和 MD 时，平均 OA 和 KC 分别为 78.06%和 0.73、78.60%和 0.72、73.32%和 0.65。我们利用了三种地形校正方法，即 C 校正、SCS（太阳冠层传感器）校正和 SCS+C 校正，以减少阴影效应引起的分类错误。SCS+C 校正对该地区最为有效；因此，我们在 SCS+C 校正后的卫星图像上制作了 LULC 地图。因此，我们在 2000 年至 2020 年期间使用 RF 分类器进行了每十年一次的 LULC 编制。使用 RF 时，2000 年、2005 年、2010 年、2015 年和 2020 年的 OA 分别为 84%、81%、81%、85%和 89%。阔叶林从 2000 年到 2020 年减少，而阔叶林、住区和农业用地增加；然而，当农田减少时，荒地增加。地形校正后，结果得到了显著改善，分类错误也大大减少。
Zotero 插件