Development of Flood Monitoring Index for daily flood risk evaluation: case studies in Fiji

Moishin, Mohammed; Deo, Ravinesh C.; Prasad, Ramendra; Raj, Nawin; Abdulla, Shahab

doi:10.1007/s00477-020-01899-6

Cited by 19 publications

(21 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another limitation of the study is in terms of the . has been previously applied in Fiji and has shown suitability as a means of quantifying floods [7]. Therefore, it was acceptable to develop based forecasting system for Fiji.…”

Section: F Discussionmentioning

confidence: 99%

“…This makes the flood index a practical tool to determine the flood state solely using daily rainfall data that is advantageous in regions without sophisticated flood monitoring technologies. In a previous paper, applied in Fiji was shown to be an effective tool for flood monitoring at short timescales [7]. In many other related works [5,6,[27][28][29], has already been adopted for flood monitoring studies but none of these studies have built a deep learning forecast model using the .…”

Section: B Theoretical Overviewmentioning

confidence: 99%

“…In this equation, ( denote the standard deviation and mean of the yearly maximum daily during the study period. The duration, severity and intensity of floods can be successively determined using equations presented in earlier studies [7]…”

Section: Flood Index Computationmentioning

confidence: 99%

“…This approach represents the standardized form of 'Effective Precipitation' (PE) based on the rationale that a flood event on any particular day is dependent on the current and the previous day's precipitation with the effect of previous day's precipitation on current day's flood state gradually reducing due to the effect of hydrological factors [4]. has been applied at various locations globally and is generally accepted as an accurate data-driven mechanism to monitor flood state and, to determine the duration, severity, and intensity of flood situations [5][6][7][8]. However, as a flood monitoring index, cannot be currently used to determine the flood state ahead of time unless a predictive model for this index is built and tested.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm

et al. 2021

Self Cite

View full text Add to dashboard Cite

Efficient, robust, and accurate early flood warning is a pivotal decision support tool that can help save lives and protect the infrastructure in natural disasters. This research builds a hybrid deep learning (ConvLSTM) algorithm integrating the predictive merits of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network to design and evaluate a flood forecasting model to forecast the future occurrence of flood events. Derived from precipitation dataset, the work adopts a Flood Index (), in form of a mathematical representation, to capture the gradual depletion of water resources over time, employed in a flood monitoring system to determine the duration, severity, and intensity of any flood situation. The newly designed predictive model utilizes statistically significant lagged , improved by antecedent and real-time rainfall data to forecast the next daily value. The performance of the proposed ConvLSTM model is validated against 9 different rainfall datasets in flood prone regions in Fiji which faces flood-driven devastations almost annually. The results illustrate the superiority of ConvLSTM-based flood model over the benchmark methods, all of which were tested at the 1-day, 3-day, 7-day, and the 14-day forecast horizon. For instance, the Root Mean Squared Error (RMSE) for the study sites were 0.101, 0.150, 0.211 and 0.279 for the four forecasted periods, respectively, using ConvLSTM model. For the next best model, the RMSE values were 0.105, 0.154, 0.213 and 0.282 in that same order for the four forecast horizons. In terms of the difference in model performance for individual stations, the Legate-McCabe Efficiency Index (LME) were 0.939, 0.898, 0.832 and 0.726 for the four forecast horizons, respectively. The results demonstrated practical utility of ConvLSTM in accurately forecasting and its potential use in disaster management and risk mitigation in the current phase of extreme weather events.

show abstract

Section: F Discussionmentioning

confidence: 99%

Section: B Theoretical Overviewmentioning

confidence: 99%

Section: Flood Index Computationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Balogun et al (2020) utilized geographic information system and remote sensing data from Malaysia to generate flood susceptibility maps, applying Fuzzy-Analytic Network Process flood models. Moishin et al (2020) investigated fluvial flood risk in Fiji developing a flood index based on current and antecedent day's precipitation. Talukdar et al (2020) gathered historical flood data related to the Teesta River basin in Bangladesh and employed ensemble machine learning algorithms to predict flooding sites and flood susceptible zones.…”

Section: Introductionmentioning

confidence: 99%

Social Media Integration of Flood Data: A Vine Copula-Based Approach

Ansell¹,

Valle²

2021

Preprint

View full text Add to dashboard Cite

Floods are the most common and among the most severe natural disasters in many countries around the world. As global warming continues to exacerbate sea level rise and extreme weather, governmental authorities and environmental agencies are facing the pressing need of timely and accurate evaluations and predictions of flood risks. Current flood forecasts are generally based on historical measurements of environmental variables at monitoring stations. In recent years, in addition to traditional data sources, large amounts of information related to floods have been made available via social media. Members of the public are constantly and promptly posting information and updates on local environmental phenomena on social media platforms. Despite the growing interest of scholars towards the usage of online data during natural disasters, the majority of studies focus exclusively on social media as a stand-alone data source, while its joint use with other type of information is still unexplored. In this paper we propose to fill this gap by integrating traditional historical information on floods with data extracted by Twitter and Google Trends. Our methodology is based on vine copulas, that allow us to capture the dependence structure among the marginals, which are modelled via appropriate time series methods, in a very flexible way. We apply our methodology to data related to three different coastal locations in the South cost of the UK. The results show that our approach, based on the integration of social media data, outperforms traditional methods, providing a more accurate evaluation and prediction of flood events.

show abstract

Spatio temporal hydrological extreme forecasting framework using LSTM deep learning model

Anshuka

Chandra

Buzacott

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Hydrological extremes occupy a large spatial extent, with a temporal sequence, both of which can be influenced by a range of climatological and geographical phenomena. Understanding the key information in the spatial and temporal domain is essential to make accurate forecasts. The capabilities of deep learning methods can be applied in such instances due to their enhanced ability in learning complex relationships. Given its success in other domains, this study presents a framework that features a long short-term memory deep learning model for spatio temporal hydrological extreme forecasting in the South Pacific region. The data consists of satellite rainfall estimates and sea surface temperature (SST) anomalies. We use the satellite rainfall estimate to calculate the effective drought index (EDI), an indicator of hydrological extreme events. The framework is developed to forecast monthly EDI using three different approaches: (i) univariate (ii) multivariate with neighbouring spatial points (iii) multivariate with neighbouring spatial points and the eigenvector values of SST. Additionally, better identification of extreme wet events is noted with the inclusion of the eigenvector values of SST. By establishing the framework for the multivariate approach in two forms, it is evident that the model accuracy is contingent on understanding the dominant feature which influences precipitation regimes in the Pacific. The framework can be used to better understand linear and non-linear relationships within multi-dimensional data in other study regions, and provide long-term climate outlooks.

show abstract

Development of Flood Monitoring Index for daily flood risk evaluation: case studies in Fiji

Cited by 19 publications

References 15 publications

Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm

Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm

Social Media Integration of Flood Data: A Vine Copula-Based Approach

Spatio temporal hydrological extreme forecasting framework using LSTM deep learning model

Contact Info

Product

Resources

About