Land use land cover (LULC) change has become a crucial topic that needs to be addressed when the studying global and local sustainable development. In this research, time-series of Sentinel-2 images from 2019 to 2020 are used to derive LULC change in Mu Cang Chai (MCC) and Van Yen (VY) districts, Yen Bai province, Vietnam. We identified seven main land cover types and collected reference data from visual interpretation using Google Earth. The random forest (RF) classification algorithm is applied to construct the classified LULC map in these regions of Yen Bai province. The classification accuracy of the method is evaluated using producer’s accuracy, user’s accuracy, overall accuracy, and Kappa coefficient. We obtain a high overall accuracy (90.7%) with a corresponding Kappa coefficient of 0.85 for the classification in 2019. In the case of 2020, overall classification accuracy reaches about 91.1% and 0.87 of the Kappa coefficient. Then, the LULC change area in the period 2019–2020 of the study area is evaluated and discussed by using the transition matrix of LULC.
Random Forest Analysis of Land Use and Land Cover Change Using Sentinel-2 Data in Van Yen, Yen Bai Province, Vietnam
Truong, Xuan Quang;Yordanov, Vasil;Brovelli, Maria Antonia;
2023-01-01
Abstract
Land use land cover (LULC) change has become a crucial topic that needs to be addressed when the studying global and local sustainable development. In this research, time-series of Sentinel-2 images from 2019 to 2020 are used to derive LULC change in Mu Cang Chai (MCC) and Van Yen (VY) districts, Yen Bai province, Vietnam. We identified seven main land cover types and collected reference data from visual interpretation using Google Earth. The random forest (RF) classification algorithm is applied to construct the classified LULC map in these regions of Yen Bai province. The classification accuracy of the method is evaluated using producer’s accuracy, user’s accuracy, overall accuracy, and Kappa coefficient. We obtain a high overall accuracy (90.7%) with a corresponding Kappa coefficient of 0.85 for the classification in 2019. In the case of 2020, overall classification accuracy reaches about 91.1% and 0.87 of the Kappa coefficient. Then, the LULC change area in the period 2019–2020 of the study area is evaluated and discussed by using the transition matrix of LULC.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
