More Like this

1. A national scale big data analytics pipeline to assess the potential impacts of flooding on critical infrastructures and communities

   https://doi.org/https://doi.org/10.1016/j.envsoft.2020.104828  

   Donratanapata, N. ; Samadi, S ; Vidal, J.M. ; Sadeghi Tabas, S. ( August 2020 , Environmental modelling software)

   With the rapid development of the Internet of Things (IoT) and Big Data infrastructure, crowdsourcing techniques have emerged to facilitate data processing and problem solving particularly for flood emergences purposes. A Flood Analytics Information System (FAIS) has been developed as a Python Web application to gather Big Data from multiple servers and analyze flooding impacts during historical and real-time events. The application is smartly designed to integrate crowd intelligence, machine learning (ML), and natural language processing of tweets to provide flood warning with the aim to improve situational awareness for flood risk management. FAIS, a national scale prototype, combines flood peak rates and river level information with geotagged tweets to identify a dynamic set of at-risk locations to flooding. The prototype was successfully tested in real-time during Hurricane Dorian flooding as well as for historical event (Hurricanes Florence) across the Carolinas, USA where the storm made extensive disruption to infrastructure and communities. 

   more » « less
2. A national scale big data analytics pipeline to assess the potential impacts of flooding on critical infrastructures and communities

   https://doi.org/https://doi.org/10.1016/j.envsoft.2020.104828828  

   N.Donratanapat, S.Samadi ( August 2020 , Environmental modelling software)

   With the rapid development of the Internet of Things (IoT) and Big Data infrastructure, crowdsourcing techniques have emerged to facilitate data processing and problem solving particularly for flood emergences purposes. A Flood Analytics Information System (FAIS) has been developed as a Python Web application to gather Big Data from multiple servers and analyze flooding impacts during historical and real-time events. The application is smartly designed to integrate crowd intelligence, machine learning (ML), and natural language processing of tweets to provide flood warning with the aim to improve situational awareness for flood risk management. FAIS, a national scale prototype, combines flood peak rates and river level information with geotagged tweets to identify a dynamic set of at-risk locations to flooding. The prototype was successfully tested in real-time during Hurricane Dorian flooding as well as for historical event (Hurricanes Florence) across the Carolinas, USA where the storm made extensive disruption to infrastructure and communities. 

   more » « less
3. A National Scale Real Time Data Analytics Application for Assessing the Potential Impacts of Flooding on Communities

   Samadi, S. ( January 2019 , the American Geophysical Union)

   Successive hurricane events have brought new challenges to human life, critical infrastructure and the environment in the United States. This study introduced Flood Analytics Information System (FAIS) as a national scale data analytics application for real-time flood data collection and analysis. FAIS has been Beta tested across a mixed urban and rural basin in the Carolinas where Hurricane Florence made extensive damages and disruption. Our research aim was to develop and test an integrated solution based on real time Big data for stakeholder map-based dashboard visualizations that can be applicable to other countries and a range of weather-driven emergency situations. The prototype successfully identifies a dynamic set of at-risk locations using web-based river level and flood information. The list of prioritized locations can be updated every 15 minutes, as the environmental information and condition change. FAIS will be extended to collect data from other countries and other kinds of weather-related hazards such as snowstorms and wildfires. 

   more » « less
4. Co-evolution of wetland landscapes, flooding, and human settlement in the Mississippi River Delta Plain

   https://doi.org/10.1007/s11625-016-0374-4  

   Twilley, Robert R. ; Bentley, Samuel J. ; Chen, Qin ; Edmonds, Douglas A. ; Hagen, Scott C. ; Lam, Nina S.-N. ; Willson, Clinton S. ; Xu, Kehui ; Braud, DeWitt ; Hampton Peele, R. ; et al ( May 2016 , Sustainability Science)

   Abstract River deltas all over the world are sinking beneath sea-level rise, causing significant threats to natural and social systems. This is due to the combined effects of anthropogenic changes to sediment supply and river flow, subsidence, and sea-level rise, posing an immediate threat to the 500–1,000 million residents, many in megacities that live on deltaic coasts. The Mississippi River Deltaic Plain (MRDP) provides examples for many of the functions and feedbacks, regarding how human river management has impacted source-sink processes in coastal deltaic basins, resulting in human settlements more at risk to coastal storms. The survival of human settlement on the MRDP is arguably coupled to a shifting mass balance between a deltaic landscape occupied by either land built by the Mississippi River or water occupied by the Gulf of Mexico. We developed an approach to compare 50 % L:W isopleths (L:W is ratio of land to water) across the Atchafalaya and Terrebonne Basins to test landscape behavior over the last six decades to measure delta instability in coastal deltaic basins as a function of reduced sediment supply from river flooding. The Atchafalaya Basin, with continued sediment delivery, compared to Terrebonne Basin, with reduced river inputs, allow us to test assumptions of how coastal deltaic basins respond to river management over the last 75 years by analyzing landward migration rate of 50 % L:W isopleths between 1932 and 2010. The average landward migration for Terrebonne Basin was nearly 17,000 m (17 km) compared to only 22 m in Atchafalaya Basin over the last 78 years (p\0.001), resulting in migration rates of 218 m/year (0.22 km/year) and\0.5 m/year, respectively. In addition, freshwater vegetation expanded in Atchafalaya Basin since 1949 compared to migration of intermediate and brackish marshes landward in the Terrebonne Basin. Changes in salt marsh vegetation patterns were very distinct in these two basins with gain of 25 % in the Terrebonne Basin compared to 90 % decrease in the Atchafalaya Basin since 1949. These shifts in vegetation types as L:W ratio decreases with reduced sediment input and increase in salinity also coincide with an increase in wind fetch in Terrebonne Bay. In the upper Terrebonne Bay, where the largest landward migration of the 50 % L:W ratio isopleth occurred, we estimate that the wave power has increased by 50–100 % from 1932 to 2010, as the bathymetric and topographic conditions changed, and increase in maximum storm-surge height also increased owing to the landward migration of the L:W ratio isopleth. We argue that this balance of land relative to water in this delta provides a much clearer understanding of increased flood risk from tropical cyclones rather than just estimates of areal land loss. We describe how coastal deltaic basins of the MRDP can be used as experimental landscapes to provide insights into how varying degrees of sediment delivery to coastal deltaic floodplains change flooding risks of a sinking delta using landward migrations of 50 % L:W isopleths. The nonlinear response of migrating L:W isopleths as wind fetch increases is a critical feedback effect that should influence human river-management decisions in deltaic coast. Changes in land area alone do not capture how corresponding landscape degradation and increased water area can lead to exponential increase in flood risk to human populations in low-lying coastal regions. Reduced land formation in coastal deltaic basins (measured by changes in the land:water ratio) can contribute significantly to increasing flood risks by removing the negative feedback of wetlands on wave and storm-surge that occur during extreme weather events. Increased flood risks will promote population migration as human risks associated with living in a deltaic landscape increase, as land is submerged and coastal inundation threats rise. These system linkages in dynamic deltaic coasts define a balance of river management and human settlement dependent on a certain level of land area within coastal deltaic basins (L). 

   more » « less
5. Data-Driven Flood Alert System (FAS) Using Extreme Gradient Boosting (XGBoost) to Forecast Flood Stages

   https://doi.org/10.3390/w14050747  

   Sanders, Will ; Li, Dongfeng ; Li, Wenzhao ; Fang, Zheng N. ( March 2022 , Water)

   Heavy rainfall leads to severe flooding problems with catastrophic socio-economic impacts worldwide. Hydrologic forecasting models have been applied to provide alerts of extreme flood events and reduce damage, yet they are still subject to many uncertainties due to the complexity of hydrologic processes and errors in forecasted timing and intensity of the floods. This study demonstrates the efficacy of using eXtreme Gradient Boosting (XGBoost) as a state-of-the-art machine learning (ML) model to forecast gauge stage levels at a 5-min interval with various look-out time windows. A flood alert system (FAS) built upon the XGBoost models is evaluated by two historical flooding events for a flood-prone watershed in Houston, Texas. The predicted stage values from the FAS are compared with observed values with demonstrating good performance by statistical metrics (RMSE and KGE). This study further compares the performance from two scenarios with different input data settings of the FAS: (1) using the data from the gauges within the study area only and (2) including the data from additional gauges outside of the study area. The results suggest that models that use the gauge information within the study area only (Scenario 1) are sufficient and advantageous in terms of their accuracy in predicting the arrival times of the floods. One of the benefits of the FAS outlined in this study is that the XGBoost-based FAS can run in a continuous mode to automatically detect floods without requiring an external starting trigger to switch on as usually required by the conventional event-based FAS systems. This paper illustrates a data-driven FAS framework as a prototype that stakeholders can utilize solely based on their gauging information for local flood warning and mitigation practices. 

   more » « less