Urban flooding is a major natural disaster that poses a serious threat to the urban environment. It is highly demanded that the flood extent can be mapped in near real-time for disaster rescue and relief missions, reconstruction efforts, and financial loss evaluation. Many efforts have been taken to identify the flooding zones with remote sensing data and image processing techniques. Unfortunately, the near real-time production of accurate flood maps over impacted urban areas has not been well investigated due to three major issues. (1) Satellite imagery with high spatial resolution over urban areas usually has nonhomogeneous background due to different types of objects such as buildings, moving vehicles, and road networks. As such, classical machine learning approaches hardly can model the spatial relationship between sample pixels in the flooding area. (2) Handcrafted features associated with the data are usually required as input for conventional flood mapping models, which may not be able to fully utilize the underlying patterns of a large number of available data. (3) High-resolution optical imagery often has varied pixel digital numbers (DNs) for the same ground objects as a result of highly inconsistent illumination conditions during a flood. Accordingly, traditional methods of flood mapping have major limitations in generalization based on testing data. To address the aforementioned issues in urban flood mapping, we developed a patch similarity convolutional neural network (PSNet) using satellite multispectral surface reflectance imagery before and after flooding with a spatial resolution of 3 meters. We used spectral reflectance instead of raw pixel DNs so that the influence of inconsistent illumination caused by varied weather conditions at the time of data collection can be greatly reduced. Such consistent spectral reflectance data also enhance the generalization capability of the proposed model. Experiments on the high resolution imagery before and after the urban flooding events (i.e., the 2017 Hurricane Harvey and the 2018 Hurricane Florence) showed that the developed PSNet can produce urban flood maps with consistently high precision, recall, F1 score, and overall accuracy compared with baseline classification models including support vector machine, decision tree, random forest, and AdaBoost, which were often poor in either precision or recall. The study paves the way to fuse bi-temporal remote sensing images for near real-time precision damage mapping associated with other types of natural hazards (e.g., wildfires and earthquakes).

Near realtime flood mapping in densely populated urban areas is critical for emergency response. The strong heterogeneity of urban areas poses a big challenge for accurate near realtime flood mapping. However, previous studies on automatic methods for urban flood mapping perform infeasible in near realtime or fail to generalize well to other floods, for several reasons. First, multitemporal pixel-wise flood mapping requires accurate image registration, hindering the efficiency of large-scale processing. Although automatic image registration has been investigated, precisely coregistered multitemporal image sequence requires time-consuming fine tuning. Additionally, the floods may lead to the loss of many corresponding image points across multitemporal images for accurate coregistration. Second, existing unsupervised methods generally rely on hand-crafted features for floodwater detection. Such features may not well represent the patterns of floodwaters in different areas due to inconsistent weather conditions, illumination, and floodwater spectra. This article proposes a self-supervised learning framework for patch-wise urban flood mapping using bitemporal multispectral satellite imagery. Patch-wise change vector analysis is used with patch features learned through a self-supervised autoencoder to produce patch-wise change maps showing potentially flood-affected areas. Postprocessing including spectral and spatial filtering is applied to these patch-wise change maps to remove nonflood related changes. Final flood maps and parameter sensitivities were evaluated using several performance metrics. Two flood events from areas with differing degrees of urbanization were considered: Hurricane Harvey flood (2017) in Houston, Texas, and Hurricane Florence flood (2018) in Lumberton, North Carolina. The proposed method shows strong performance for self-supervised urban flood mapping.

Natural hazards have been resulting in severe damage to our cities, and flooding is one of the most disastrous in the U.S and worldwide. Therefore, it is critical to develop efficient methods for risk and damage assessments after natural hazards, such as flood depth estimation. Existing works primarily leverage photos and images capturing flood scenes to estimate flood depth using traditional computer vision and machine learning techniques. However, the advancement of deep learning (DL) methods make it possible to estimate flood depth more accurate. Therefore, based on state-of-the-art DL technique (i.e., Mask R-CNN) and publicly available images from the Internet, this study aims to investigate and improve the flood depth estimation. Specifically, human objects are detected and segmented from flooded images to infer the floodwater depth. This study provides a new framework to extract critical information from large accessible online data for rescue teams or even robots to carry out appropriate plans for disaster relief and rescue missions in the urban area, shedding lights on the real-time detection of the flood depth.

Advances in deep learning and computer vision are making significant contributions to flood mapping, particularly when integrated with remotely sensed data. Although existing supervised methods, especially deep convolutional neural networks, have proved to be effective, they require intensive manual labeling of flooded pixels to train a multi-layer deep neural network that learns abstract semantic features of the input data. This research introduces a novel weakly supervised approach for pixel-wise flood mapping by leveraging multi-temporal remote sensing imagery and image processing techniques (e.g., Normalized Difference Water Index and edge detection) to create weakly labeled data. Using these weakly labeled data, a bi-temporal U-Net model is then proposed and trained for flood detection without the need for time-consuming and labor-intensive human annotations. Using floods from Hurricanes Florence and Harvey as case studies, we evaluated the performance of the proposed bi-temporal U-Net model and baseline models, such as decision tree, random forest, gradient boost, and adaptive boosting classifiers. To assess the effectiveness of our approach, we conducted a comprehensive assessment that (1) covered multiple test sites with varying degrees of urbanization, and (2) utilized both bi-temporal (i.e., pre- and post-flood) and uni-temporal (i.e., only post-flood) input. The experimental results showed that the proposed framework of weakly labeled data generation and the bi-temporal U-Net could produce near real-time urban flood maps with consistently high precision, recall, f1 score, IoU score, and overall accuracy compared with baseline machine learning algorithms.

Wildfires cause substantial damage and present considerable risks to both natural ecosystem and human societies. A precise and prompt evaluation of wildfire-induced damage is crucial for effective post-fire management and restoration. Considerable advancements have been made in monitoring and mapping fire-affected areas through feature engineering and machine learning techniques. However, existing methods often exhibit several limitations, such as complicated and time-intensive procedures on manual labeling, and a primary focus on binary classification, which only distinguishes between burned and non-burned areas. In response, this study develops a wildfire burn severity assessment model, Bi-RAUnet-NBR, which can not only accurately identify fire-affected areas, but also assess the burn severity levels (low, moderate, and high) within those areas. Built upon the standard U-Net architecture, the proposed Bi-RAUnet-NBR first incorporates bi-temporal Sentinel 2 remote sensing imagery, captured before and after a wildfire, which enables the model to better distinguish burned areas from the background and identify the severity level of the resulting burns. Additionally, it further enhances the standard U-Net architecture by fusing additional spectral layers, such as the Normalized Burn Ratio (NBR) derived from post- and pre-fire images, therefore informing the detection of burn areas. Moreover, Bi-RAUnet-NBR also integrates attention mechanism, enabling the model to pay more attention to meaningful features and burn areas, and residual blocks in the decoder module, which not only significantly improves segmentation results but also enhances training stability and prevents the issue of vanishing gradients. The experimental results demonstrate the superiority of the proposed model in both multi-class and binary mapping of wildfire burn areas, achieving an overall accuracy (OA) over 95%. Furthermore, it outperforms baseline algorithms, including support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost), and fully convolutional network (FCN), with an average improvement of 18% in F1-score and 15% in mean intersection over union (mIoU).

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks.