Rapid Flood Mapping Research Articles

2024 IEEE GRSS Data Fusion Contest: Rapid Flood Mapping [Technical Committees

2024 IEEE GRSS Data Fusion Contest: Rapid Flood Mapping [Technical Committees

Automated floodwater depth estimation using large multimodal model for rapid flood mapping

Automated floodwater depth estimation using large multimodal model for rapid flood mapping

Optimizing Height Above Nearest Drainage parameters to enable rapid flood mapping in North Carolina

Surface water flooding represents a significant hazard for many infrastructure systems. For example, residential, commercial, and industrial properties, water and wastewater treatment facilities, private drinking water wells, stormwater systems, or transportation networks are often impacted (i.e., in terms of damage or functionality) by flooding events. For large scale events, knowing where to prioritize recovery resources can be challenging. To help communities throughout North Carolina manage flood disaster responses, near real-time state-wide rapid flood mapping methods are needed. In this study, Height Above Nearest Drainage (HAND) concepts are combined with National Water Model river discharges to enable rapid flood mapping throughout North Carolina. The modeling system is calibrated using USGS stage-discharge relationships and FEMA 100-year flood maps. The calibration process ultimately provides spatially distributed channel roughness values to best match the available datasets. Results show that the flood mapping system, when calibrated, provides reasonable estimates of both river stage (or corresponding water surface elevations) and surface water extents. Comparing HAND to FEMA hazard maps both in Wake County and state-wide shows an agreement of 80.1% and 76.3%, respectively. For the non-agreement locations, flood extents tend to be overestimated as compared to underestimated, which is preferred in the context of identifying potentially impacted infrastructure systems. Future research will focus on developing transfer relationships to estimate channel roughness values for locations that lack the data needed for calibration.

An efficient urban flood mapping framework towards disaster response driven by weakly supervised semantic segmentation with decoupled training samples

Despite the proven effectiveness of data-driven deep learning techniques in urban flood mapping, the availability of annotation data remains a critical factor impeding their timeliness in real applications. Recent progress in weakly supervised semantic segmentation (WSSS) presents promising solutions for addressing this limitation. To accomplish prompt and accurate flood mapping in complex urban areas from high-resolution remote sensing images to support disaster management and response, this study makes contributions in three key aspects: weak training data generation, the improvement of WSSS algorithm, and the construction of benchmark datasets. Firstly, we present a novel yet efficient weak training data generation strategy by decoupling the acquisition of positive and negative samples. This strategy enables the rapid generation of block-level weak annotations assisted by pre-flood river data or the segment anything model (SAM) for zero-shot segmentation, thereby alleviating the burden of weak data labeling. Secondly, to enhance the flood detection results in complex urban landscapes based on low-cost weak labels, we design an end-to-end WSSS framework incorporating tree filtering-based structure constraints and a perturbed dual-branch cross self-distillation mechanism. Lastly, to evaluate the performance of the proposed approach, we constructed two large aerial imagery datasets, namely Calgary-Flood and Huston-Flood. These datasets encompass diverse urban land covers and include challenging scenarios with extensive shadows, providing a robust benchmark for evaluating our method against various urban environments. Experimental results demonstrate that our weak data annotation strategy substantially enhances efficiency. Additionally, the proposed WSSS framework exhibits superior performance in comparison to existing state-of-the-art methods, particularly in terms of edge delineation and algorithmic stability. The advancements in weak data annotation strategy, end-to-end model architecture, and benchmark dataset development in this study collectively exploit the potential of the weakly supervised paradigm for rapid flood mapping in urgent situations. The datasets and code will be publicly available at (https://github.com/YJ-He/Flood_Mapping_WSSS).

The Spatial Planning in Purworejo Regency-based Flood Hazard using Sentinel-1A Imagery

Flood disasters in Indonesia increased by 23% over a period of 70 years. In Central Java Province, the incidence of floods has also experienced a significant increase, including flooding in Purworejo Regency. Floods in Purworejo Regency occur in almost every rainy season in the same location. In 2020 and 2021, floods hit the same 13 villages. The utilization of the Sentinel-1A Imagery technology can quickly and accurately visualize the distribution of locations where there are indications of flood inundation. This research aims to do rapid flood mapping for spatial planning. The method used in this research is the processing of Sentinel-1A imagery, flood mapping in Purworejo Regency, validation test of processed Saentinel-1A imagery, and flood analysis with the Purworejo Regency Spatial Planning. The Sentinel-1A data processing is in the form of a combination process between Composite RGB and the Change Detection and Thresholding (CDAT) method. Sentinel-1A imagery was taken at two different times, namely when there was a flood and when there was no flood. The Flood Map Processed by Saentinel-1A imagery will be verified and validated. The validity test results using the Kappa coefficient are 0.841, and the accuracy value is 94%. The Kappa coefficient value and accuracy show that the flooding results from the Saentinel-1A image processing are valid and accurate. The results of the analysis between spatial planning and flood inundation in Purworejo Regency are > 50% of the flooded areas in the form of paddy fields and plantations.

A multi-system comparison of forecast flooding extent using a scale-selective approach

Abstract Fluvial flood forecasting systems increasingly couple river discharge to a flood map library or a real-time hydrodynamic model to provide forecast flood maps to humanitarian agencies. The forecast flood maps can be linked to potential impacts to inform forecast-based financing schemes. We investigate a new application of scale-selective verification by evaluating three flood forecasting systems. Two simulation library systems, Flood Foresight (30 m) and GloFAS Rapid Flood Mapping (1,000 m) and one hydrodynamically modelled system, the Bangladesh Flood Forecasting and Warning Centre (FFWC) Super Model (300 m), all made predictions of flooding extent at different spatial scales (grid lengths, in brackets) for the Jamuna River flood, Bangladesh, July 2020. The flood maps are validated against synthetic-aperture-radar-derived observations of flooding using a scale-selective approach that can compare directly across different spatial scales. At short forecast lead times, the Super Model outperforms the other systems. Near to the Bangladesh border, the trans-boundary benefits of the two global systems are evident. We find that scale-selective methods can quantify the skill of systems operating at different spatial scales so that the benefits and limitations can be evaluated. Multi-system comparison of flood maps is important for improving impact-based forecasts and ensuring funds and response activities are appropriately targeted.

MAPPING NEWLY INUNDATED AREAS IN POST-FLOOD LANDSAT IMAGES USING THRESHOLDING TECHNIQUES

Abstract. Identifying newly inundated areas following flood events is essential for planning rescue missions. These maps must be generated quickly as the spatial extent of the inundated areas might change during a single flood event. Several methods exist for generating such maps and several rely on one or more geospatial data to exclude existing waterbodies in an affected area. In this study, we tested a rapid flood mapping method that uses a pair of pre- and post-flood satellite images on seven sites throughout the US. We derived Normalized Difference Water Index (NDWI) and Modified NDWI (MNDWI) images from pre- and post-flood Landsat images and identified the optimal threshold values that highlighted newly inundated areas at these sites. The accuracy of the inundation maps was determined using manually interpreted verification data from the pairs of satellite images. Image analysts have identified the optimal threshold values between 25 and 40 minutes. Maps of newly inundated areas derived from differencing MNDWI and NDWI images had higher overall accuracy > 93%. Results obtained in this study confirms the utility of this rapid flood mapping technique to identify inundated areas using pre- and post-flood satellite images.

Rapid Flood Mapping Using Statistical Sampling Threshold Based on Sentinel-1 Imagery in the Barito Watershed, South Kalimantan Province, Indonesia

Flood disasters occur frequently in Indonesia and can cause property damage and even death. This research aimed to provide rapid flood mapping based on remote sensing data by using a cloud platform. In this study, the Google Earth Engine cloud platform was used to quickly detect major floods in the Barito watershed in South Kalimantan province, Indonesia. The data used in this study were Sentinel-1 images before and after the flood event, and surface reflectance of Sentinel-2 images available on the Google Earth Engine platform. Flooding is detected using the threshold method. In this study, we determined the threshold using the Otsu method and statistical sampling thresholds (SST). Four SST scenarios were used in this study, combining the mean and standard deviation of the difference backscatter of Sentinel-1 images. The results of this study showed that the second SST scenario could classify floods with the highest accuracy of 73.2%. The inundation area determined by this method was 4,504.33 km2. The first, third and fourth SST scenarios and the Otsu method could reduce the flood load with an overall accuracy of 48.37%, 43.79%, 55.5% and 68.63%, respectively. The SST scenario is considered to be a reasonably good method for rapid flood detection using Sentinel-1 satellite imagery. This rapid detection method can be applied to other areas to detect flooding. This information can be quickly produced to help stakeholders determine appropriate flood management strategies.

Rapid assessment of riverine flood inundation in Chenab floodplain using remote sensing techniques

IntroductionAfter flood occurrences, remote sensing images provide crucial information formapping flood inundation extent. Optical satellite images can be utilized to generate flooded area maps when the flooded areas are free from clouds.Materials and MethodsIn this study flooded area was calculated using a variety of water indices and classification algorithms, calculated on Landsat data. Pre-flood, during flood, and post-flood satellite data were collected for in-depth flood investigation. The delineation of inundated areas was done using the Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), and Water Ratio Index (WRI). In order to detect and compare flooded areas with water indices, the supervised maximum likelihood algorithm was also used for land use and land cover mapping.ResultsThe results of the investigation allowed for a flooded area and recession. The analysis revealed that the flooded area covered about 68% of the study area, and remained standing for seven weeks. We used the misclassified areas approach, as determined, using the classified results, to improve the results of the flooded areas, generated through the use of each of the 3 water indices. The result showed that the MNDWI images showed better accuracy of above 90%, which reflects the reliability of the results.ConclusionThis proposed remote sensing (RS) technique provides a basis for the identification of inundated areas with less misclassified areas, which enable an emergency response to be targeted, for newly flooded areas. Thus, the present study provides a novel rapid flood mapping perspective and provides a considerable contribution to flood monitoring.

Flood mapping based on open-source remote sensing data using an efficient band combination system

Flood mapping is an essential component of planning flood mitigation. The availability of remote sensing data makes rapid flood mapping possible. This article develops an accurate method for rapid flood mapping using satellite imagery. Sentinel-2 imagery was tested by acquiring data before and after a flood event in a lowland area. Flooding extraction was performed using the newly developed Flood Inundation Extraction Index (FIEI) and compared to the Modified Normalized Difference Water Index (MNDWI), the most commonly used index. Based on the choice of threshold, the results are divided into flooded and non-flooded areas. Evaluation of the performance accuracy based on the total and kappa coefficients showed that the FIEI approach is more accurate than the MNDWI approach.

Flood mapping based on open-source remote sensing data using an efficient band combination system

Flood mapping is an essential component of planning flood mitigation. The availability of remote sensing data makes rapid flood mapping possible. This article develops an accurate method for rapid flood mapping using satellite imagery. Sentinel-2 imagery was tested by acquiring data before and after a flood event in a lowland area. Flooding extraction was performed using the newly developed Flood Inundation Extraction Index (FIEI) and compared to the Modified Normalized Difference Water Index (MNDWI), the most commonly used index. Based on the choice of threshold, the results are divided into flooded and non-flooded areas. Evaluation of the performance accuracy based on the total and kappa coefficients showed that the FIEI approach is more accurate than the MNDWI approach.

Combining SAR images with land cover products for rapid urban flood mapping

Synthetic Aperture Radar (SAR) is an indispensable source of data for mapping and monitoring flood hazards, thanks to its ability to image the Earth’s surface in all weather conditions and at all times. Through cloud computing platforms such as Google Earth Engine (GEE), SAR imagery can be used in near-real time for rapid flood mapping. This has facilitated the disaster response community to make informed decisions in flood hazard interventions and management plans. However, rapid urban flood mapping using SAR is challenging, due to the complex land cover configuration in urban environments, coupled with complicated backscattering mechanisms. Here, we propose a novel method to utilise SAR imagery and land use-land cover (LULC) products for rapid urban flood mapping. Our approach uses a Land Cover Product to segment the study area into LULC types and differentiate each type with respect to whether double bounce is expected to occur during the flooding events. The normalised difference index was derived using a multi-temporal SAR image stack, and the threshold segmentation method was adopted for flood mapping. In addition, DEM and Surface Water datasets were employed to refine the flood extraction results using a morphological correction approach. We assessed the method quantitatively using two use cases: the 2017 Houston and 2022 Coraki flood events. Based on fine spatial resolution optical imagery, the proposed method achieved an accuracy of 92.7% for the August 2017 Houston flood mapping task and 89% for the March 2022 Coraki flood mapping task, which not only represents at least 13% in accuracy compared to non-LCP based flood extraction method, but also provides strong capability for rapid flood mapping in urban settings.

Evaluation of SAR and Optical Data for Flood Delineation Using Supervised and Unsupervised Classification

Precise and accurate delineation of flooding areas with synthetic aperture radar (SAR) and multi-spectral (MS) data is challenging because flooded areas are inherently heterogeneous as emergent vegetation (EV) and turbid water (TW) are common. We addressed these challenges by developing and applying a new stepwise sequence of unsupervised and supervised classification methods using both SAR and MS data. The MS and SAR signatures of land and water targets in the study area were evaluated prior to the classification to identify the land and water classes that could be delineated. The delineation based on a simple thresholding method provided a satisfactory estimate of the total flooded area but did not perform well on heterogeneous surface water. To deal with the heterogeneity and fragmentation of water patches, a new unsupervised classification approach based on a combination of thresholding and segmentation (CThS) was developed. Since sandy areas and emergent vegetation could not be classified by the SAR-based unsupervised methods, supervised random forest (RF) classification was applied to a time series of SAR and co-event MS data, both combined and separated. The new stepwise approach was tested for determining the flood extent of two events in Italy. The results showed that all the classification methods applied to MS data outperformed the ones applied to SAR data. Although the supervised RF classification may lead to better accuracies, the CThS (unsupervised) method achieved precision and accuracy comparable to the RF, making it more appropriate for rapid flood mapping due to its ease of implementation.

Global Flood Mapper: a novel Google Earth Engine application for rapid flood mapping using Sentinel-1 SAR

Global Flood Mapper: a novel Google Earth Engine application for rapid flood mapping using Sentinel-1 SAR

Flood Detection in Urban Areas Using Satellite Imagery and Machine Learning

Urban flooding poses risks to the safety of drivers and pedestrians, and damages infrastructures and lifelines. It is important to accommodate cities and local agencies with enhanced rapid flood detection skills and tools to better understand how much flooding a region may experience at a certain period of time. This results in flood management orders being announced in a timely manner, allowing residents and drivers to preemptively avoid flooded areas. This research combines information received from ground observed data derived from road closure reports from the police department, with remotely sensed satellite imagery to develop and train machine-learning models for flood detection for the City of San Diego, CA, USA. For this purpose, flooding information are extracted from Sentinel 1 satellite imagery and fed into various supervised and unsupervised machine learning models, including Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classifier (MLC), to detect flooded pixels in images and evaluate the performance of these ML models. Moreover, a new unsupervised machine learning framework is developed which works based on the change detection (CD) approach and combines the Otsu algorithm, fuzzy rules, and iso-clustering methods for urban flood detection. Results from the performance evaluation of RF, SVM, MLC and CD models show 0.53, 0.85, 0.75 and 0.81 precision measures, 0.9, 0.85, 0.85 and 0.9 for recall values, 0.67, 0.85, 0.79 and 0.85 for the F1-score, and 0.69, 0.87, 0.83 and 0.87 for the accuracy measure, respectively, for each model. In conclusion, the new unsupervised flood image classification and detection method offers better performance with the least required data and computational time for enhanced rapid flood mapping. This systematic approach will be potentially useful for other cities at risk of urban flooding, and hopefully for detecting nuisance floods, by using satellite images and reducing the flood risk of transportation design and urban infrastructure planning.

Assessing Surface Water Flood Risks in Urban Areas Using Machine Learning

Urban flooding is a devastating natural hazard for cities around the world. Flood risk mapping is a key tool in flood management. However, it is computationally expensive to produce flood risk maps using hydrodynamic models. To this end, this paper investigates the use of machine learning for the assessment of surface water flood risks in urban areas. The factors that are considered in machine learning models include coordinates, elevation, slope gradient, imperviousness, land use, land cover, soil type, substrate, distance to river, distance to road, and normalized difference vegetation index. The machine learning models are tested using the case study of Exeter, UK. The performance of machine learning algorithms, including naïve Bayes, perceptron, artificial neural networks (ANNs), and convolutional neural networks (CNNs), is compared based on a spectrum of indicators, e.g., accuracy, F-beta score, and receiver operating characteristic curve. The results obtained from the case study show that the flood risk maps can be accurately generated by the machine learning models. The performance of models on the 30-year flood event is better than 100-year and 1000-year flood events. The CNNs and ANNs outperform the other machine learning algorithms tested. This study shows that machine learning can help provide rapid flood mapping, and contribute to urban flood risk assessment and management.

Rapid Flood Mapping based on Remote Sensing Cloud Computing and Sentinel-1

Flood is a natural disaster with the highest frequency and the widest influence range in the world, which seriously restricts human survival and economic development. Obtaining flood inundation range quickly and accurately has important practical significance for flood disaster assessment, rescue and resource allocation. Based on Google Earth Engine cloud platform and Sentinel-1 radar images, a quick flood inundation range extraction model is constructed and applied to the analysis of severe floods in Matala District, Sri Lanka in May 2017. The results show that the flood in Matala area is mainly concentrated in the south and southwest, and the surface water area has expanded by 5 times, among which the flood area in Thihagoda district is the most serious, accounting for 29.28% of the total area. The model has high efficiency and strong feasibility, which can be widely used in flood emergency monitoring.

Rapid monitoring of cyclone induced flood through an automated approach using multi–temporal Earth Observation (EO) images in RSS CloudToolbox platform

ABSTRACT The new era of cloud platform technologies opens up many opportunities for near real-time dissemination of disaster information to the end-users. The present study utilizes the European Space Agency (ESA) Research and Service Support (RSS) CloudToolbox platform to monitor the spatio-temporal dynamics of a flood event. A collective flood monitoring framework is formulated to rapidly assess cyclone-induced flood in the CloudToolbox platform. The outputs of the framework are spatio-temporal maps of flood extent, depth, and hot spot zones. The framework utilizes Earth Observation (EO) images such as optical and C-band Synthetic Aperture Radar (SAR) images and an automatic Kittler and Illingworth thresholding algorithm for rapid flood mapping. The temporal flood depth maps are created with the Floodwater Depth Estimation Tool (FwDET) which requires only two input parameters, viz. flood extent, and Digital Elevation Model (DEM). Subsequently, flood hotspot zones are also identified. We tested the flood monitoring framework on Amphan cyclone-induced flood event at both regional and local levels. The spatio-temporal flood extent, depth, and hot spot maps are generated for the Amphan cyclone event and a 97% overall accuracy is achieved at the local level. The entire process took less than one hour for regional and local level analysis.

Fully Convolutional Neural Network for Rapid Flood Segmentation in Synthetic Aperture Radar Imagery

Rapid response to natural hazards, such as floods, is essential to mitigate loss of life and the reduction of suffering. For emergency response teams, access to timely and accurate data is essential. Satellite imagery offers a rich source of information which can be analysed to help determine regions affected by a disaster. Much remote sensing flood analysis is semi-automated, with time consuming manual components requiring hours to complete. In this study, we present a fully automated approach to the rapid flood mapping currently carried out by many non-governmental, national and international organisations. We design a Convolutional Neural Network (CNN) based method which isolates the flooded pixels in freely available Copernicus Sentinel-1 Synthetic Aperture Radar (SAR) imagery, requiring no optical bands and minimal pre-processing. We test a variety of CNN architectures and train our models on flood masks generated using a combination of classical semi-automated techniques and extensive manual cleaning and visual inspection. Our methodology reduces the time required to develop a flood map by 80%, while achieving strong performance over a wide range of locations and environmental conditions. Given the open-source data and the minimal image cleaning required, this methodology can also be integrated into end-to-end pipelines for more timely and continuous flood monitoring.

GEE4FLOOD: rapid mapping of flood areas using temporal Sentinel-1 SAR images with Google Earth Engine cloud platform

The present state of the art technologies for flood mapping are typically tested on small geographical regions due to limitation of resources, which hinders the implementation of real-time flood management activities. We proposed a unified framework (GEE4FLOOD) for rapid flood mapping in Google Earth Engine (GEE) cloud platform. With the unexpected spells of extreme rainfall in August 2018, many parts of Kerala state in India experienced a major disastrous flood. Therefore, we tested the GEE4FLOOD processing chain on August 2018 Kerala flood event. GEE4FLOOD utilizes multitemporal Sentinel-1 synthetic aperture radar images available in GEE catalog and an automatic Otsu’s thresholding algorithm for flood mapping. It also utilizes other remote sensing datasets available in GEE catalog for permanent water body mask creation and result validation. The ground truth data collected during the Kerala flood indicates promising accuracy with 82% overall accuracy and 78.5% accuracy for flood class alone. In addition, the entire process from data fetching to flood map generation at a varying geographical extent (district to state level) took ∼2 to 4 min.