Application of stacking hybrid machine learning algorithms in delineating multi-type flooding in Bangladesh.

Floods are among the most devastating natural hazards in Bangladesh. The country experiences multi-type floods (i.e., fluvial, flash, pluvial, and surge floods) every year. However, areas prone to multi-type floods have not yet been assessed on a national scale. Here, we used locally weighted linear regression (LWLR), random subspace (RSS), reduced error pruning tree (REPTree), random forest (RF), and M5P model tree algorithms in a hybrid ensemble to assess multi-type flood probabilities at a national scale in Bangladesh. We used historical flood data (1988-2020), remote sensing images (e.g., MODIS, Landsat 5-8, and Sentinel-1), and topography, hydrogeology, and environmental datasets to train and validate the proposed algorithms. According to the results, the stacking ensemble machine learning LWLR-RF algorithm performed better than the other algorithms in predicting flood probabilities, with R2 = 0.967-0.999, MAE = 0.022-0.117, RMSE = 0.029-0.148, RAE = 4.48-23.38%, and RRSE = 5.8829.69% for the training and testing datasets. Furthermore, true skill statistics (TSS: 0.929-0.967), corrected classified instances (CCI: 96.45-98.35), area under the curve (AUC: 0.983-0.997), and Gini coefficients (0.966-0.994) were computed to validate the constructed (LWLR-RF) multi-type flood probability maps. The maps constructed via the LWLR-RF algorithm revealed that the proportions of different categories of flooding areas in Bangladesh are fluvial flooding 1.50%, 5.71%, 12.66%, and 13.77% of the total land area; flash floods of 4.16%, 8.90%, 11.11%, and 5.07%; pluvial flooding: 5.72%, 3.25%, 5.07%, and 0.90%; and surge flooding, 1.69%, 1.04%, 0.52%, and 8.64% of the total land area, respectively. These percentages represent low, medium, high, and very high probabilities of flooding. The findings can guide future flood risk management and sustainable land-use planning in the study area.

Erosion during extreme flood events dominates Holocene canyon evolution in northeast Iceland.

Extreme flood events have the potential to cause catastrophic landscape change in short periods of time (10(0) to 10(3) h). However, their impacts are rarely considered in studies of long-term landscape evolution (>10(3) y), because the mechanisms of erosion during such floods are poorly constrained. Here we use topographic analysis and cosmogenic (3)He surface exposure dating of fluvially sculpted surfaces to determine the impact of extreme flood events within the Jökulsárgljúfur canyon (northeast Iceland) and to constrain the mechanisms of bedrock erosion during these events. Surface exposure ages allow identification of three periods of intense canyon cutting about 9 ka ago, 5 ka ago, and 2 ka ago during which multiple large knickpoints retreated large distances (>2 km). During these events, a threshold flow depth was exceeded, leading to the toppling and transportation of basalt lava columns. Despite continuing and comparatively large-scale (500 m(3)/s) discharge of sediment-rich glacial meltwater, there is no evidence for a transition to an abrasion-dominated erosion regime since the last erosive event because the vertical knickpoints have not diffused over time. We provide a model for the evolution of the Jökulsárgljúfur canyon through the reconstruction of the river profile and canyon morphology at different stages over the last 9 ka and highlight the dominant role played by extreme flood events in the shaping of this landscape during the Holocene.

Road network disruptions during extreme flooding events and their impact on the access to emergency medical services: A spatiotemporal vulnerability analysis.

The impact of extreme floods can be significant, affecting humans, the environment and any type of human-built infrastructure. A further consequence of flooding is restricted access to medical facilities, including constraints to access more dedicated emergency medical services (EMS). To date, there has been a lack of investigation into EMS accessibility dynamics during extreme floods. The objective of this study is to gain a deeper understanding of the spatiotemporal changes in accessibility-based vulnerability related to EMS during a representative extreme flood event, which was simulated over a period of six days. The study assesses the spatial accessibility of EMS centres to populations located within 15-, 30-, 45-, and 60-minute travel time thresholds in Canton Bern, Switzerland, and applies floating catchment area method. The dynamic aspects of EMS access vulnerability during extreme floods were assessed in two different ways. Firstly, the ratios between accessibility change and accessibility under normal conditions in 1 km grid cells were calculated at hourly moments, t. Subsequently, the resulting values were used to calculate the average vulnerability score. Secondly, percentage changes of affected populations were evaluated for different accessibility classes during the flood event and under all-time high static flood conditions. Varied spatial patterns of accessibility were generally observed with respect to the road network and population distributions in the hilly and mountainous landscape. Extending evaluations to consider temporal dynamics revealed a complex pattern of accessibility gains and losses in different regions of the study area, including those where no direct flood impacts occurred on the road network. The application of a static, all-time high flood condition resulted in an overestimation of accessibility limits to EMS centres. While this overestimation was not considered to be critical, the application of a spatiotemporal accessibility-based vulnerability analysis method to EMS is considered to be more holistic. Insights from this study can be used to evaluate the effectiveness of EMS risk management plans with respect to evolving extreme flood scenarios.

Impact evaluation of geomorphic changes caused by extreme floods on inundation area considering geomorphic variations and land use types.

Extreme floods caused by dam breaches, dike breaches, and rainstorms cause significant erosion and deposition in the flooded area. Furthermore, geomorphic changes have various impacts on different land use types, which is an important aspect extreme flood outcomes. The impact type and degree depend on geomorphic variations and land characteristics. However, neither the amount of geomorphic variations nor its impact on the inundation area have been fully understood. Firstly, we propose the use of a numerical simulation method to calculate erosion and deposition depths of the whole inundation area caused by extreme floods. Secondly, combined with the characteristics of erosion, deposition, and land use types, the impact type of geomorphic changes on different land use types were divided into positive, negative, and negligible impacts, and the impact degree was expressed by two indices of impact grade and impact score. In addition, the calculation methods of the two indices were put forward. Then, we propose a method for evaluating the impacts of geomorphic changes on the whole inundation area from five aspects of mesh, land use type, overall erosion region, overall deposition region, and overall inundation area. Combined with the simulation of the flood process caused by dam breach of Luhun Reservoir in China, this method was verified, and the results showed that: (a) geomorphic changes had a negative impact on 94.7% of the inundation area, and only part of the water bodies were positively affected and the towns were not affected, accounting for 2.1% and 3.2% respectively; (b) the negative impact degree of each land use type in descending order was grassland, town, cropland, forest, shrubland and water body; and (c) the area of deposition was larger than that of erosion, whereas the severity of negative impact was opposite.

What is a bad flood? Local perspectives of extreme floods in the Peruvian Amazon.

The annual flood cycle is integral to rural life and livelihoods in riparian Amazonia. Livelihoods are built around the flood cycle, which facilitates transportation and affects soil fertility and fish migrations. Flood extremes, however, can have devastating impacts for riverine populations, yet there is minimal understanding of what distinguishes a 'normal' flood from a 'bad' flood, or flooding as integral to riverine settlement from flooding as environmental hazard. We address this limitation by drawing upon hydrograph data and field data collected in a riverine village in the Peruvian Amazon. We define four extreme flood types based on height, duration, and timing of onset, and illustrate how they each create a unique combination of negative and positive implications. We discuss the integral role of fishing to floodplain livelihoods during the flood season, and the implications of flood extremes for health, safety, and food provision. The article proposes a more nuanced conceptualization of flooding in riverine Amazonia to better inform policies and practices aimed at supporting local populations during extreme floods.

Coupling hydroclimate-hydraulic-sedimentation models to estimate flood inundation and sediment transport during extreme flood events under a changing climate.

Extreme flood events are disastrous and can cause serious damages to society. Flood frequency obtained based on historical flow records may also be changing under future climate conditions. The associated flood inundation and environmental transport processes will also be affected. In this study, an integrated numerical modeling framework is proposed to investigate the inundation and sedimentation during multiple flood events (2,5,10, 20, 50, 100, 200-year) under future climate change scenarios in a watershed system in northern California, USA. The proposed modeling framework couples physical models of various spatial resolution: kilometers to several hundred kilometers climatic processes, hillslope scale hydrological processes in a watershed, and centimeters to meters scale hydrodynamic and sediment transport processes in a riverine system. The modeling results show that compared to the flows during historical periods, extreme events become more extreme in the 21st century and higher flows tend to be larger and smaller flows tend to be smaller in the system. Flood inundation in the study area, especially during 200-year events, is projected to increase in the future. More sediment will be trapped as the flow increases and the deposition will also increase in the settling basin. Sediment trap efficiency values are within 37.5-65.4% for the historical conditions, within 32.4-68.8% in the first half of the 21st century, and within 34.9-69.3% in the second half of the 21st century. The results highlight the impact of climate change on extreme flood events, the resulting sedimentation, and reflected the importance of incorporating the coupling of physical models into the adaptive watershed and river system management.

Geological record of extreme floods and anthropogenic impacts on an industrialised bay: The inner Abra of Bilbao (northern Spain).

The Bilbao estuary is one of the most polluted areas on the northern coast of Spain, owing to the direct disposal of urban effluents and wastewaters from mining and industrial activities that has occurred during the last 170 years. Recent sediment records collected from the inner Abra of Bilbao bay were examined using a multidisciplinary approach including geochemical, micropaleontological and isotopic proxies to evaluate heavy metal contamination (Pb, Zn and Cd), ecological condition (benthic foraminifera), and sediment accumulation variability (210Pb). Results evidenced the interplay of both human activities and extreme weather events. Most contaminated materials are buried below a thin layer (1-21 cm) of cleaner sediments which have been deposited since contaminant discharges have substantially decreased, due to industrial reconversion and environmental regulations. However, the fingerprint left in the sedimentary record by the catastrophic floods of 1983 confirms the potential of natural events for sediment relocation, showing catastrophic events may endanger recently-achieved environmental improvements in historically contaminated coastal areas.

River ecosystem resilience to extreme flood events.

Floods have a major influence in structuring river ecosystems. Considering projected increases in high-magnitude rainfall events with climate change, major flooding events are expected to increase in many regions of the world. However, there is uncertainty about the effect of different flooding regimes and the importance of flood timing in structuring riverine habitats and their associated biotic communities. In addition, our understanding of community response is hindered by a lack of long-term datasets to evaluate river ecosystem resilience to flooding. Here we show that in a river ecosystem studied for 30 years, a major winter flood reset the invertebrate community to a community similar to one that existed 15 years earlier. The community had not recovered to the preflood state when recurrent summer flooding 9 years later reset the ecosystem back to an even earlier community. Total macroinvertebrate density was reduced in the winter flood by an order of magnitude more than the summer flood. Meiofaunal invertebrates were more resilient to the flooding than macroinvertebrates, possibly due to their smaller body size facilitating greater access to in-stream refugia. Pacific pink salmon escapement was markedly affected by the winter flood when eggs were developing in redds, compared to summer flooding, which occurred before the majority of eggs were laid. Our findings inform a proposed conceptual model of three possible responses to flooding by the invertebrate community in terms of switching to different states and effects on resilience to future flooding events. In a changing climate, understanding these responses is important for river managers to mitigate the biological impacts of extreme flooding effects.

The impact of flooding on aquatic ecosystem services.

Flooding is a major disturbance that impacts aquatic ecosystems and the ecosystem services that they provide. Predicted increases in global flood risk due to land use change and water cycle intensification will likely only increase the frequency and severity of these impacts. Extreme flooding events can cause loss of life and significant destruction to property and infrastructure, effects that are easily recognized and frequently reported in the media. However, flooding also has many other effects on people through freshwater aquatic ecosystem services, which often go unrecognized because they are less evident and can be difficult to evaluate. Here, we identify the effects that small magnitude frequently occurring floods (< 10-year recurrence interval) and extreme floods (> 100-year recurrence interval) have on ten aquatic ecosystem services through a systematic literature review. We focused on ecosystem services considered by the Millennium Ecosystem Assessment including: (1) supporting services (primary production, soil formation), (2) regulating services (water regulation, water quality, disease regulation, climate regulation), (3) provisioning services (drinking water, food supply), and (4) cultural services (aesthetic value, recreation and tourism). The literature search resulted in 117 studies and each of the ten ecosystem services was represented by an average of 12 ± 4 studies. Extreme floods resulted in losses in almost every ecosystem service considered in this study. However, small floods had neutral or positive effects on half of the ecosystem services we considered. For example, small floods led to increases in primary production, water regulation, and recreation and tourism. Decision-making that preserves small floods while reducing the impacts of extreme floods can increase ecosystem service provision and minimize losses.