Flood Risk Mapping by Remote Sensing Data and Random Forest Technique

Prediction of flood sensitivity based on Logistic Regression, eXtreme Gradient Boosting, and Random Forest modeling methods

Floods are one of the most destructive disasters that cause loss of life and property worldwide every year. In this study, the aim was to find the best-performing model in flood sensitivity assessment and analyze key characteristic factors, the spatial pattern of flood sensitivity was evaluated using three machine learning (ML) models: Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF). Suqian City in Jiangsu Province was selected as the study area, and a random sample dataset of historical flood points was constructed. Fifteen different meteorological, hydrological, and geographical spatial variables were considered in the flood sensitivity assessment, 12 variables were selected based on the multi-collinearity study. Among the results of comparing the selected ML models, the RF method had the highest AUC value, accuracy, and comprehensive evaluation effect, and is a reliable and effective flood risk assessment model. As the main output of this study, the flood sensitivity map is divided into five categories, ranging from very low to very high sensitivity. Using the RF model (i.e., the highest accuracy of the model), the high-risk area covers about 44% of the study area, mainly concentrated in the central, eastern, and southern parts of the old city area.

Use of remote sensing techniques to assess water storage variations and flood-related inflows for the Hawizeh wetland

High spatial and temporal resolution remote sensing data are becoming readily available. This has made the use of remote sensing to monitor and quantify spatiotemporal changes in surface waters feasible and efficient. In this paper, remote sensing techniques based on spectral indices were used to assess the changes in submerged areas and water storage in the Hawizeh marsh (south of Iraq) during the 2019 flood. Two water indices, the Normalized Difference Water Index (NDWI) and Normalized Difference Moisture Index (NDMI), were used for this purpose. Water indices have been frequently utilized to detect water bodies because of their particular spectral properties in the visible and infrared spectrum. Non-measured flood-related flows into the marsh have also been estimated by applying the water balance approach. The accuracy assessment of the water areas extracted by the remote sensing indices showed an acceptable degree of reliability, which reflected positively on the water inflow calculations. As the Hawizeh is a transboundary marsh shared by Iraq and Iran, remote sensing techniques allowed for the estimation of difficult-to-measure inflows from the Iranian side. The results of the water balance revealed that the inflows from the Iranian side to the marsh during the 5 months of the flood made up approximately 41.2% of the total water volume entering the marsh. The study demonstrated the feasibility of using uncomplicated water extraction methods that depend on remote sensing data to monitor hydrological changes in the Hawizeh wetland that lack sufficient data.

Multi-hazard exposure mapping under climate crisis using random forest algorithm for the Kalimantan Islands, Indonesia

Numerous natural disasters that threaten people's lives and property occur in Indonesia. Climate change-induced temperature increases are expected to affect the frequency of natural hazards in the future and pose more risks. This study examines the consequences of droughts and forest fires on the Indonesian island of Kalimantan. We first create maps showing the eleven contributing factors that have the greatest impact on forest fires and droughts related to the climate, topography, anthropogenic, and vegetation. Next, we used RF to create single and multi-risk maps for forest fires and droughts in Kalimantan Island. Finally, using the Coupled Model Intercomparison Project (CMIP6) integrated evaluation model, a future climate scenario was applied to predict multiple risk maps for RCP-SSP2-4.5 and RCP-SSP5-8.5 in 2040-2059 and 2080-2099. The probability of a 22.6% drought and a 21.7% forest fire were anticipated to have an influence on the study's findings, and 2.6% of the sites looked at were predicted to be affected by both hazards. Both RCP-SSP2-4.5 and RCP-SSP5-8.5 have an increase in these hazards projected for them. Researchers and stakeholders may use these findings to assess risks under various mitigation strategies and estimate the spatial behavior of such forest fire and drought occurrences.

Monitoring Dewatering Fish Spawning Sites in the Reservoir of a Large Hydropower Plant in a Lowland Country Using Unmanned Aerial Vehicles

This paper presents research concerning dewatered areas in the littoral zones of the Kaunas hydropower plant (HPP) reservoir in Lithuania. It is a multipurpose reservoir that is primarily used by two large hydropower plants for power generation. As a result of the peaking operation regime of the Kaunas HPP, the large quantity of water that is subtracted and released into the reservoir by the Kruonis pumped storage hydropower plant (PSP), and the reservoir morphology, i.e., the shallow, gently sloping littoral zone, significant dewatered areas can appear during drawdown operations. This is especially dangerous during the fish spawning period. Therefore, reservoir operation rules are in force that limit the operation of HPPs and secure other reservoir stakeholder needs. There is a lack of knowledge concerning fish spawning locations, how they change, and what areas are dewatered at different stages of HPP operation. This knowledge is crucial for decision-making and efficient reservoir storage management in order to simultaneously increase power generation and protect the environment. Current assessments of the spawning sites are mostly based on studies that were carried out in the 1990s. Surveying fish spawning sites is typically a difficult task that is usually carried out by performing manual bathymetric measurements due to the limitations of sonar in such conditions. A detailed survey of a small (approximately 5 ha) area containing several potential spawning sites was carried out using Unmanned Aerial Vehicles (UAV) equipped with multispectral and conventional RGB cameras. The captured images were processed using photogrammetry and analyzed using various techniques, including machine learning. In order to highlight water and track changes, various indices were calculated and assessed, such as the Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), Visible Atmospherically Resistant Index (VARI), and Normalized Green-Red Difference Index (NGRDI). High-resolution multispectral images were used to analyze the spectral footprint of aquatic macrophytes, and the possibility of using the results of this study to identify and map potential spawning sites over the entire reservoir (approximately 63.5 km²) was evaluated. The aim of the study was to investigate and implement modern surveying techniques to improve usage of reservoir storage during hydropower plant drawdown operations. The experimental results show that thresholding of the NGRDI and supervised classification of the NDWI were the best-performing methods for the shoreline detection in the fish spawning sites.

Spatial Prediction of Current and Future Flood Susceptibility: Examining the Implications of Changing Climates on Flood Susceptibility Using Machine Learning Models

The main aim of this study was to predict current and future flood susceptibility under three climate change scenarios of RCP2.6 (i.e., optimistic), RCP4.5 (i.e., business as usual), and RCP8.5 (i.e., pessimistic) employing four machine learning models, including Gradient Boosting Machine (GBM), Random Forest (RF), Multilayer Perceptron Neural Network (MLP-NN), and Naïve Bayes (NB). The study was conducted for two watersheds in Canada, namely Lower Nicola River, BC and Loup, QC. Three statistical metrics were used to validate the models: Receiver Operating Characteristic Curve, Figure of Merit, and F1-score. Findings indicated that the RF model had the highest accuracy in providing the flood susceptibility maps (FSMs). Moreover, the provided FSMs indicated that flooding is more likely to occur in the Lower Nicola River watershed than the Loup watershed. Following the RCP4.5 scenario, the area percentages of the flood susceptibility classes in the Loup watershed in 2050 and 2080 have changed by the following percentages from the year 2020 and 2050, respectively: Very Low = -1.68%, Low = -5.82%, Moderate = +6.19%, High = +0.71%, and Very High = +0.6% and Very Low = -1.61%, Low = +2.98%, Moderate = -3.49%, High = +1.29%, and Very High = +0.83%. Likewise, in the Lower Nicola River watershed, the changes between the years 2020 and 2050 and between the years 2050 and 2080 were: Very Low = -0.38%, Low = -0.81%, Moderate = -0.95%, High = +1.72%, and Very High = +0.42% and Very Low = -1.31%, Low = -1.35%, Moderate = -1.81%, High = +2.37%, and Very High = +2.1%, respectively. The impact of climate changes on future flood-prone places revealed that the regions designated as highly and very highly susceptible to flooding, grow in the forecasts for both watersheds. The main contribution of this study lies in the novel insights it provides concerning the flood susceptibility of watersheds in British Columbia and Quebec over time and under various climate change scenarios.

Flood Hazard Assessment and Mapping: A Case Study from Australia's Hawkesbury-Nepean Catchment

Floods are among the costliest natural hazards, in Australia and globally. In this study, we used an indicator-based method to assess flood hazard risk in Australia's Hawkesbury-Nepean catchment (HNC). Australian flood risk assessments are typically spatially constrained through the common use of resource-intensive flood modelling. The large spatial scale of this study area is the primary element of novelty in this research. The indicators of maximum 3-day precipitation (M3DP), distance to river-elevation weighted (DREW), and soil moisture (SM) were used to create the final Flood Hazard Index (FHI). The 17-26 March 2021 flood event in the HNC was used as a case study. It was found that almost 85% of the HNC was classified by the FHI at 'severe' or 'extreme' level, illustrating the extremity of the studied event. The urbanised floodplain area in the central-east of the HNC had the highest FHI values. Conversely, regions along the western border of the catchment had the lowest flood hazard risk. The DREW indicator strongly correlated with the FHI. The M3DP indicator displayed strong trends of extreme rainfall totals increasing towards the eastern catchment border. The SM indicator was highly variable, but featured extreme values in conservation areas of the HNC. This study introduces a method of large-scale proxy flood hazard assessment that is novel in an Australian context. A proof-of-concept methodology of flood hazard assessment developed for the HNC is replicable and could be applied to other flood-prone areas elsewhere.

A Machine Learning-Based Surrogate Model for the Identification of Risk Zones Due to Off-Stream Reservoir Failure

Approximately 70,000 Spanish off-stream reservoirs, many of them irrigation ponds, need to be evaluated in terms of their potential hazard to comply with the new national Regulation of the Hydraulic Public Domain. This requires a great engineering effort to evaluate different scenarios with two-dimensional hydraulic models, for which many owners lack the necessary resources. This work presents a simplified methodology based on machine learning to identify risk zones at any point in the vicinity of an off-stream reservoir without the need to elaborate and run full two-dimensional hydraulic models. A predictive model based on random forest was created from datasets including the results of synthetic cases computed with an automatic tool based on the two-dimensional numerical software Iber. Once fitted, the model provided an estimate on the potential hazard considering the physical characteristics of the structure, the surrounding terrain and the vulnerable locations. Two approaches were compared for balancing the dataset: the synthetic minority oversampling and the random undersampling. Results from the random forest model adjusted with the random undersampling technique showed to be useful for the estimation of risk zones. On a real application test the simplified method achieved 91% accuracy.

Regional Flood Frequency Analysis of the Sava River in South-Eastern Europe

Regional flood frequency analysis (RFFA) is a powerful method for interrogating hydrological series since it combines observational time series from several sites within a region to estimate risk-relevant statistical parameters with higher accuracy than from single-site series. Since RFFA extreme value estimates depend on the shape of the selected distribution of the data-generating stochastic process, there is need for a suitable goodness-of-distributional-fit measure in order to optimally utilize given data. Here we present a novel, least-squares-based measure to select the optimal fit from a set of five distributions, namely Generalized Extreme Value (GEV), Generalized Logistic, Gumbel, Log-Normal Type III and Log-Pearson Type III. The fit metric is applied to annual maximum discharge series from six hydrological stations along the Sava River in South-eastern Europe, spanning the years 1961 to 2020. Results reveal that (1) the Sava River basin can be assessed as hydrologically homogeneous and (2) the GEV distribution provides typically the best fit. We offer hydrological-meteorological insights into the differences among the six stations. For the period studied, almost all stations exhibit statistically insignificant trends, which renders the conclusions about flood risk as relevant for hydrological sciences and the design of regional flood protection infrastructure.

Water Body Mapping Using Long Time Series Sentinel-1 SAR Data in Poyang Lake

Mapping water bodies with a high accuracy is necessary for water resource assessment, and mapping them rapidly is necessary for flood monitoring. Poyang Lake is the largest freshwater lake in China, and its wetland is one of the most important in the world. Poyang Lake is affected by floods from the Yangtze River basin every year, and the fluctuation of the water area and water level directly or indirectly affects the ecological environment of Poyang Lake. Synthetic Aperture Radar (SAR) is particularly suitable for large-scale water body mapping, as SAR allows data acquisition regardless of illumination and weather conditions. The two-satellite Sentinel-1 constellation, providing C-Band SAR data, passes over the Poyang Lake about five times a month. With its high temporal-spatial resolution, the Sentinel-1 SAR data can be used to accurately monitor the water body. After acquiring all the Sentinel-1 (1A and 1B) SAR data, to ensure the consistency of data processing, we propose the use of a Python and SeNtinel Application Platform (SNAP)-based engine (SARProcMod) to process the data and construct a Poyang Lake Sentinel-1 SAR dataset with a 10 m resolution. To extract water body information from Sentinel-1 SAR data, we propose an automatic classification engine based on a modified U-Net convolutional neural network (WaterUNet), which classifies all data using artificial sample datasets with a high validation accuracy. The results show that the maximum and minimum water areas in our study area were 2714.08 km2 on 20 July 2020, and 634.44 km2 on 4 January 2020. Compared to the water level data from the Poyang gauging station, the water area was highly correlated with the water level, with the correlation coefficient being up to 0.92 and the R2 from quadratic polynomial fitting up to 0.88; thus, the resulting relationship results can be used to estimate the water area or water level of Poyang Lake. According to the results, we can conclude that Sentinel-1 SAR and WaterUNet are very suitable for water body monitoring as well as emergency flood mapping.

Extraction of Broad-Leaved Tree Crown Based on UAV Visible Images and OBIA-RF Model: A Case Study for Chinese Olive Trees

Chinese olive trees (Canarium album L.) are broad-leaved species that are widely planted in China. Accurately obtaining tree crown information provides important data for evaluating Chinese olive tree growth status, water and fertilizer management, and yield estimation. To this end, this study first used unmanned aerial vehicle (UAV) images in the visible band as the source of remote sensing (RS) data. Second, based on spectral features of the image object, the vegetation index, shape, texture, and terrain features were introduced. Finally, the extraction effect of different feature dimensions was analyzed based on the random forest (RF) algorithm, and the performance of different classifiers was compared based on the features after dimensionality reduction. The results showed that the difference in feature dimensionality and importance was the main factor that led to a change in extraction accuracy. RF has the best extraction effect among the current mainstream machine learning (ML) algorithms. In comparison with the pixel-based (PB) classification method, the object-based image analysis (OBIA) method can extract features of each element of RS images, which has certain advantages. Therefore, the combination of OBIA and RF algorithms is a good solution for Chinese olive tree crown (COTC) extraction based on UAV visible band images.

A Flood Risk Management Model to Identify Optimal Defence Policies in Coastal Areas Considering Uncertainties in Climate Projections

Coastal areas are particularly vulnerable to flooding from heavy rainfall, sea storm surge, or a combination of the two. Recent studies project higher intensity and frequency of heavy rains, and progressive sea level rise continuing over the next decades. Pre-emptive and optimal flood defense policies that adaptively address climate change are needed. However, future climate projections have significant uncertainty due to multiple factors: (a) future CO2 emission scenarios; (b) uncertainties in climate modelling; (c) discount factor changes due to market fluctuations; (d) uncertain migration and population growth dynamics. Here, a methodology is proposed to identify the optimal design and timing of flood defense structures in which uncertainties in 21st century climate projections are explicitly considered probabilistically. A multi-objective optimization model is developed to minimize both the cost of the flood defence infrastructure system and the flooding hydraulic risk expressed by Expected Annual Damage (EAD). The decision variables of the multi-objective optimization problem are the size of defence system and the timing of implementation. The model accounts for the joint probability density functions of extreme rainfall, storm surge and sea level rise, as well as the damages, which are determined dynamically by the defence system state considering the probability and consequences of system failure, using a water depth–damage curve related to the land use (Corine Land Cover); water depth due to flooding are calculated by hydraulic model. A new dominant sorting genetic algorithm (NSGAII) is used to solve the multi-objective problem optimization. A case study is presented for the Pontina Plain (Lazio Italy), a coastal region, originally a swamp reclaimed about a hundred years ago, that is rich in urban centers and farms. A set of optimal adaptation policies, quantifying size and timing of flood defence constructions for different climate scenarios and belonging to the Pareto curve obtained by the NSGAII are identified for such a case study to mitigate the risk of flooding and to aid decision makers.

Rapid and automatic burned area detection using sentinel-2 time-series images in google earth engine cloud platform: a case study over the Andika and Behbahan Regions, Iran

For proper forest management, accurate detection and mapping of burned areas are needed, yet the practice is difficult to perform due to the lack of an appropriate method, time, and expense. It is also critical to obtain accurate information about the density and distribution of burned areas in a large forest and vegetated areas. For the most efficient and up-to-date mapping of large areas, remote sensing is one of the best technologies. However, the complex image scenario and the similar spectral behavior of classes in multispectral satellite images may lead to many false-positive mistakes, making it challenging to extract the burned areas accurately. This research aims to develop an automated framework in the Google Earth Engine (GEE) cloud computing platform for detecting burned areas in Andika and Behbahan, located in the south and southwest of Iran, using Sentinel-2 time-series images. After importing the images and applying the necessary preprocessing, the Sentinel-2 Burned Areas Index (BAIS2) was used to create a map of the Primary Burned Areas (PBA). Detection accuracy was then improved by masking out disturbing classes (vegetation and water) on the PBA map, which resulted in Final Burned Areas (FBA). The unimodal method is used to calculate the ideal thresholds of indices to make the proposed method automatic. The final results demonstrated that the proposed method performed well in both homogeneous and heterogeneous areas for detecting the burned areas. Based on a test dataset, maps of burned areas were produced in the Andika and Behbahan regions with an overall accuracy of 90.11% and 92.40% and a kappa coefficient of 0.87 and 0.88, respectively, which were highly accurate when compared to the BAIS2, Normalized Burn Ratio (NBR), Normalized Difference Vegetation Index (NDVI), Mid-Infrared Bispectral Index (MIRBI), and Normalized Difference SWIR (NDSWIR) indices. Based on the results, accurate determination of vegetation classes and water zones and eliminating them from the map of burned areas led to a considerable increase in the accuracy of the obtained final map from the BAIS2 spectral index.

Publicly Available Data-Based Flood Risk Assessment Methodology: A Case Study for a Floodplain in Poland

Flood risk assessment is used to estimate the expected consequences and probability of a flood. It leads to the strengthening of resilience through appropriate preparation for an event of a specific scale. The methodology described in this paper was developed by the authors for the purposes of flood risk assessment in Poland, introduced to and applied on an actual example. It is based on simple calculations and a comparison of the results with a template. All of the data required for calculation came from freely available sources. Therefore, it is essential to evaluate the effectiveness of the flood risk assessment methodology in improving construction safety and identifying the factors that influence its implementation. The approach presented in this article is based on implementation of the parameters of floods, describing the characteristics of the exposed area and human vulnerability, among other factors, to the national risk assessment methodology, and then using it to determine the directions of activities aimed at reducing the risk of flooding. Simultaneously, assessment of these parameters might not be related directly to flood threats, but rather to the broader approach to risk assessment, including other threats. As a result of the application of the described methodology, it was estimated that the flood risk in the studied area is catastrophic, which requires immediate decisions of people responsible for safety.