Flood Extent Mapping: An Integrated Method Using Deep Learning and Region Growing Using UAV Optical Data

Abstract

Flooding occurs frequently and causes loss of lives, and extensive damages to infrastructure and the environment. Accurate and timely mapping of flood extent to ascertain damages is critical and essential for relief activities. Recently, deep-learningbased approaches, including convolutional neural network (CNN) has shown promising results for flood extent mapping. However, these methods cannot extract floods underneath vegetation canopy using the optical imagery. This article attempts to address this problem by introducing an integrated CNN and region growing (RG) method for the mapping of both visible and underneath vegetation flooded areas. The CNN-based classifier is used to extract flooded areas from the optical images, whereas, the RG method is applied to estimate the extent of floods underneath vegetation that are not visible from imagery using the digital elevation model. A data augmentation technique is applied for training the CNN-based classifier to improve the classification results. The results show that the data augmentation can enhance the accuracy of image classification and the proposed integrated method efficiently detects floods in both the visible and the areas covered by vegetation, which is essential to supporting effective flood emergency response and recovery activities. Index Terms-Convolutional neural network (CNN), flood mapping, LiDAR, region growing (RG), remote sensing. I. INTRODUCTIONF LOODING is one of the catastrophic and frequently occurring natural disasters that cause extensive damages to life, infrastructure, and the environment. In many countries, the severity and frequency of flooding have increased in recent years due to extreme weather such as hurricanes, and the expansion of urbanization. Generating accurate and timely inundation maps is essential for regional and federal agencies to manage rescue operations and assess damages effectively [1]-[2].

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

“…Satellite data is the most used input for flood inundation applications (e.g., Sarker et al, 2019;Peng et al, 2019;Nogueira et al, 2017). Other input data sources include unmanned aerial vehicles data (UAV) (e.g., Gebrehiwot et al, 2019;Ichim and Popescu, 2020), hydrographs (e.g., Hou et al, 2021) and DEMs (e.g., Hashemi-Beni and Gebrehiwot, 2021;Muñoz et al, 2021). Inundation maps produced by 3D numerical models are also used as target prediction (Muñoz et al, 2021) remote sensing data that represent a flood event seen from above.…”

Light-Weight Semantic Segmentation Network for UAV Remote Sensing Images

“…To conduct the comparison with other approaches, we use the same training set and validation set as papers [44]. The training set includes 11 patches of images (1,3,5,7,13,17,21,23,26,32,37), and the validation set includes 5 patches (11,15,28,30,40).…”

“…In terms of flexibility, the UAVs supports a controllable flight path to get multi-temporal data without the restriction of revisit interval of the platform. It is especially important in tasks that require a rapid response, such as natural disaster damage assessment [3]- [5], automatic warning system [6] and traffic analysis [7]- [9]. In addition, as shown in Fig.…”

Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification

“…Therefore, their generalization capabilities and their abilities to find efficient features that can be considered to various geographic areas and time frames are limited [10]. DLM methods, when properly trained on large training data sets, have shown excellent generalization capabilities in many research fields, including several remote sensing applications such as food security monitoring [11], hybrid data-driven earth observation modelling [12], and flood mapping from high-resolution optical data [13]. We consider these achievements in the aforementioned fields and believe that deep neural networks (DNNs) may also show performance improvement in automatic sea ice classification [14], [15].…”