Mozambique Flood (2019) Caused by Tropical Cyclone Idai Monitored From Sentinel-1 and Sentinel-2 Images
Jinyun Guo, Yujie Luan, Zhen Li, Xin Liu, Chengming Li, Xiaotao Chang
Abstract
The tropical cyclone Idai caused severe floods in Mozambique in March 2019. Sentinel-1 and Sentinel-2 images are processed to monitor the flood disaster in Pungue River and Buzi River by combining the object-based image analysis approach and the decision tree algorithm. Water is preliminarily extracted from Sentinel-1 image, and shadows of mountain and buildings in the study area are extracted from Sentinel-2 image. Mountain shadow is extracted based on the decision tree classification rules constructed by the digital elevation model and the index model, while building shadow is extracted by constructing the decision tree classification rules using the features of objects. Water extraction results are combined with shadows to eliminate confusing shadows in the preliminary extraction to obtain the accurate flood extent. Sentinel-2 images are used to classify land use types in multiple periods before and after the flood and analyze the disaster by combining with the change information of the water. Land use type changes are analyzed and predicted with the CA-Markov model. The results show that the maximum submerged area was 3.5 times of the normal water area, and that most areas were submerged for more than 10 days. The area between Pungue River and Buzi River were severely affected, where a large number of crops and villages were submerged. Grassland and cropland were the most seriously submerged. The overall accuracy of extracted water results ranges from 86% to 92%. The results indicated that the combining method can effectively suppress the influence of shadows on water extraction results.