An official website of the United States government
Flood events have become intense and more frequent due to heavy rainfall and hurricanes caused by global warming. Accurate floodwater extent maps are essential information sources for emergency management agencies and flood relief programs to direct their resources to the most affected areas. Synthetic Aperture Radar (SAR) data are superior to optical data for floodwater mapping, especially in vegetated areas and in forests that are adjacent to urban areas and critical infrastructures. Investigating floodwater mapping with various available SAR sensors and comparing their performance allows the identification of suitable SAR sensors that can be used to map inundated areas in different land covers, such as forests and vegetated areas. In this study, we investigated the performance of polarization configurations for flood boundary delineation in vegetated and open areas derived from Sentinel1b, C-band, and Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) L-band data collected during flood events resulting from Hurricane Florence in the eastern area of North Carolina. The datasets from the sensors for the flooding event collected on the same day and same study area were processed and classified for five landcover classes using a machine learning method—the Random Forest classification algorithm. We compared the classification results of linear, dual, and full polarizations of the SAR datasets. The L-band fully polarized data classification achieved the highest accuracy for flood mapping as the decomposition of fully polarized SAR data allows land cover features to be identified based on their scattering mechanisms.
more »
« less
This content will become publicly available on July 17, 2026
Flood detection using PolSAR decomposition, feature selection, and deep learning
Accurate identification of inundated areas is crucial for mitigating the impacts of flooding, which causes numerous casualties and significant economic losses. While polarimetric synthetic aperture radar (PolSAR) data have been utilized to detect inundated regions, the information contained within PolSAR features remains severely underutilized. We introduce a novel approach that involves extracting a large number of PolSAR features through various PolSAR decomposition techniques, selecting the most important ones using the decision tree–recursive feature elimination (DT-RFE) method, and ultimately detecting inundation using a convolutional neural network (CNN) model. The hybrid DT-RFE–CNN model was trained and tested over a region in southeastern North Carolina during Hurricane Florence on September 18, 2018, using PolSAR features derived from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). In terms of flood-mapping efficacy, the DT-RFE–CNN model outperformed a CNN model that used only PolSAR data across all metrics in both the training and testing stages. The performance of the trained DT-RFE–CNN model was evaluated by testing it over the same region for four more days (September 19, 20, 22, and 23, 2018); it achieved an average accuracy, precision, recall, F1 score, and intersection-over-union of 0.9304, 0.9089, 0.9584, 0.9324, and 0.8738, respectively, outperforming both the classical Otsu method and the FT-Transformer model using features selected by DT-RFE. Finally, we assessed the model’s generalizability by mapping another significant flood event, caused by Hurricane Harvey in Texas between August and September 2017. Based on the results, the hybrid model can accurately detect flooding, even in regions on which it has not been trained. Thus, the proposed method can facilitate flood monitoring and response efforts.
more »
« less
- Award ID(s):
- 2327253
- PAR ID:
- 10644237
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Gondwana research
- ISSN:
- 1878-0571
- Subject(s) / Keyword(s):
- Flood detection deep learning UAVSAR PolSAR decomposition
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Flooding during extreme weather events damages critical infrastructure, property, and threatens lives. Hurricane María devastated Puerto Rico (PR) on 20 September 2017. Sixty-four deaths were directly attributable to the flooding. This paper describes the development of a hydrologic model using the Gridded Surface Subsurface Hydrologic Analysis (GSSHA), capable of simulating flood depth and extent for the Añasco coastal flood plain in Western PR. The purpose of the study was to develop a numerical model to simulate flooding from extreme weather events and to evaluate the impacts on critical infrastructure and communities; Hurricane María is used as a case study. GSSHA was calibrated for Irma, a Category 3 hurricane, which struck the northeastern corner of the island on 7 September 2017, two weeks before Hurricane María. The upper Añasco watershed was calibrated using United States Geological Survey (USGS) stream discharge data. The model was validated using a storm of similar magnitude on 11–13 December 2007. Owing to the damage sustained by PR’s WSR-88D weather radar during Hurricane María, rainfall was estimated in this study using the Weather Research Forecast (WRF) model. Flooding in the coastal floodplain during Hurricane María was simulated using three methods: (1) Use of observed discharge hydrograph from the upper watershed as an inflow boundary condition for the coastal floodplain area, along with the WRF rainfall in the coastal flood plain; (2) Use of WRF rainfall to simulate runoff in the upper watershed and coastal flood plain; and (3) Similar to approach (2), except the use of bias-corrected WRF rainfall. Flooding results were compared with forty-two values of flood depth obtained during face-to-face interviews with residents of the affected communities. Impacts on critical infrastructure (water, electric, and public schools) were evaluated, assuming any structure exposed to 20 cm or more of flooding would sustain damage. Calibration equations were also used to improve flood depth estimates. Our model included the influence of storm surge, which we found to have a minimal effect on flood depths within the study area. Water infrastructure was more severely impacted by flooding than electrical infrastructure. From these findings, we conclude that the model developed in this study can be used with sufficient accuracy to identify infrastructure affected by future flooding events.more » « less
-
null (Ed.)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).more » « less
-
Abstract High‐power large‐aperture radar instruments are capable of detecting thousands of meteor head echoes within hours of observation, and manually identifying every head echo is prohibitively time‐consuming. Previous work has demonstrated that convolutional neural networks (CNNs) accurately detect head echoes, but training a CNN requires thousands of head echo examples manually identified at the same facility and with similar experiment parameters. Since pre‐labeled data is often unavailable, a method is developed to simulate head echo observations at any given frequency and pulse code. Real instances of radar clutter, noise, or ionospheric phenomena such as the equatorial electrojet are additively combined with synthetic head echo examples. This enables the CNN to differentiate between head echoes and other phenomena. CNNs are trained using tens of thousands of simulated head echoes at each of three radar facilities, where concurrent meteor observations were performed in October 2019. Each CNN is tested on a subset of actual data containing hundreds of head echoes, and demonstrates greater than 97% classification accuracy at each facility. The CNNs are capable of identifying a comprehensive set of head echoes, with over 70% sensitivity at all three facilities, including when the equatorial electrojet is present. The CNN demonstrates greater sensitivity to head echoes with higher signal strength, but still detects more than half of head echoes with maximum signal strength below 20 dB that would likely be missed during manual detection. These results demonstrate the ability of the synthetic data approach to train a machine learning algorithm to detect head echoes.more » « less
-
Numerous algorithms have been developed to automate the process of delineating water surface maps for flood monitoring and mitigation purposes by using multiple sources such as satellite sensors and digital elevation model (DEM) data. To better understand the causes of inaccurate mapping information, we aim to demonstrate the advantages and limitations of these algorithms through a case study of the 2022 Madagascar flooding event. The HYDRAFloods toolbox was used to perform preprocessing, image correction, and automated flood water detection based on the state-of-the-art Edge Otsu, Bmax Otsu, and Fuzzy Otsu algorithms for the satellite images; the FwDET tool was deployed upon the cloud computing platform (Google Earth Engine) for rapid estimation of flood area/depth using the digital elevation model (DEM) data. Generated surface water maps from the respective techniques were evaluated qualitatively against each other and compared with a reference map produced by the European Union Copernicus Emergency Management Service (CEMS). The DEM-based maps show generally overestimated flood extents. The satellite-based maps show that Edge Otsu and Bmax Otsu methods are more likely to generate consistent results than those from Fuzzy Otsu. While the synthetic-aperture radar (SAR) data are typically favorable over the optical image under undesired weather conditions, maps generated based on SAR data tend to underestimate the flood extent as compared with reference maps. This study also suggests the newly launched Landsat-9 serves as an essential supplement to the rapid delineation of flood extents.more » « less
