Mapping, Monitoring, and Prediction of Floods Due to Ice Jam and Snowmelt with Operational Weather Satellites

Goldberg, Mitchell D.; Li, Sanmei; Lindsey, Daniel T.; Sjoberg, W.; Zhou, Lihang; Sun, Donglian

doi:10.3390/rs12111865

Cited by 12 publications

(5 citation statements)

References 36 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2020, Goldberg et al [12] used operational weather satellites to discuss mapping, assessing, and forecasting floods generated by snowmelt and ice jams. It was anticipated that satellite-based flood forecasts would enable more quantitative forecasts on the breakdown timing and areas of floods caused by ice jams and snowmelt when combined with temperature readings.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Weights S and S * are provided as the input solution to the CHHSSO method. Equation (12) defines the given objective ob of CHHSSO, and er denotes the error between predicted and actual value. As per this work, the flood is predicted, and the difference between the target value and the predicted value is estimated during the error calculation.…”

Section: Training Phase: Combined Harris Hawks Shuffled Shepherd Opti...mentioning

confidence: 99%

“…The assessment of the deep hybrid model for flood prediction with CHHSSO-based training (DHMFP) is performed over deep belief networks (DBN), recurrent neural networks (RNN), long short term memory (LSTM), support vector machines (SVM), bidirectional gated recurrent units (Bi-GRU), shuffled shepherd optimization algorithm (SSOA), Harris hawks optimization (HHO), COOT, arithmetic optimization algorithm (AOA), change detection (CD) approach [12], and fully convolutional neural networks (FCNN) [19], regarding accuracy, NPV, FPR, and so on. To further illustrate the effectiveness of the DHMFP, statistical analysis, an ablation study, and segmentation accuracy are performed and tested.…”

Section: Accuracy =mentioning

confidence: 99%

See 2 more Smart Citations

Optimized Deep Learning Model for Flood Detection Using Satellite Images

Stateczny,

Praveena,

Krishnappa

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection models, deep learning techniques are extensively used in flood control. Therefore, a novel deep hybrid model for flood prediction (DHMFP) with a combined Harris hawks shuffled shepherd optimization (CHHSSO)-based training algorithm is introduced for flood prediction. Initially, the input satellite image is preprocessed by the median filtering method. Then the preprocessed image is segmented using the cubic chaotic map weighted based k-means clustering algorithm. After that, based on the segmented image, features like difference vegetation index (DVI), normalized difference vegetation index (NDVI), modified transformed vegetation index (MTVI), green vegetation index (GVI), and soil adjusted vegetation index (SAVI) are extracted. The features are subjected to a hybrid model for predicting floods based on the extracted feature set. The hybrid model includes models like CNN (convolutional neural network) and deep ResNet classifiers. Also, to enhance the prediction performance, the CNN and deep ResNet models are fine-tuned by selecting the optimal weights by the combined Harris hawks shuffled shepherd optimization (CHHSSO) algorithm during the training process. This hybrid approach decreases the number of errors while improving the efficacy of deep neural networks with additional neural layers. From the result study, it clearly shows that the proposed work has obtained sensitivity (93.48%), specificity (98.29%), accuracy (94.98%), false negative rate (0.02%), and false positive rate (0.02%) on analysis. Furthermore, the proposed DHMFP–CHHSSO displays better performances in terms of sensitivity (0.932), specificity (0.977), accuracy (0.952), false negative rate (0.0858), and false positive rate (0.036), respectively.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Training Phase: Combined Harris Hawks Shuffled Shepherd Opti...mentioning

confidence: 99%

Section: Accuracy =mentioning

confidence: 99%

See 1 more Smart Citation

Optimized Deep Learning Model for Flood Detection Using Satellite Images

Stateczny,

Praveena,

Krishnappa

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Over the years, these models have been successfully applied in a variety of applications to solve ice-related problems. These include ice-jam flood hydrology and frequency analyses [17], flood risk analyses [18,19], regulation impact studies [20,21], operational flood forecasting [22,23] and climate change impact analyses [24][25][26]. Each model has some advantages and limitations; therefore, an experienced modeler can apply the most appropriate model based on the suitability of the study site, data availability and application of the analysis.…”

Section: Introductionmentioning

confidence: 99%

Exploring the Potential of Zoning Regulation for Reducing Ice-Jam Flood Risk Using a Stochastic Modelling Framework

Das

2021

Water

View full text Add to dashboard Cite

Ice-jam floods pose a serious threat to many riverside communities in cold regions. Ice-jam-related flooding can cause loss of human life, millions of dollars in property damage, and adverse impacts on ecology. An effective flood management strategy is necessary to reduce the overall risk in flood-prone areas. Most of these strategies require a detailed risk-based management study to assess their effectiveness in reducing flood risk. Zoning regulation is a sustainable measure to reduce overall flood risk for a flood-prone area. Zoning regulation is a specified area in a floodplain where certain restrictions apply to different land uses (e.g., development or business). A stochastic framework was introduced to evaluate the effectiveness of a potential zoning regulation. A stochastic framework encompasses the impacts of all the possible expected floods instead of a more traditional approach where a single design flood is incorporated. The downtown area of Fort McMurray along the Athabasca River was selected to explore the impact of zoning regulation on reducing expected annual damages (EAD) from ice-jam flooding. The results show that a hypothetical zoning regulation for a certain area in the town of Fort McMurray (TFM) can be effective in substantially reducing the level of EAD. A global sensitivity analysis was also applied to understand the impacts of model inputs on ice-jam flood risk using a regional sensitivity method. The results show that model boundary conditions such as river discharge, the inflowing volume of ice and ice-jam toe locations are highly sensitive to ice-jam flood risk.

show abstract

“…Even though high-resolution SAR data (10-30 m) can provide very valuable surface information under almost all sky conditions, it usually has limited spatial coverage and a long revisit time (6-12 days) [35]. Recently, geostationary satellites, GOES-R series with a 5 min temporal resolution, allowing us to capture some clear sky observations, have been utilized to help mitigate the cloud contamination problem [36,37]. Multi-day composite VIIRS flood maps have been used to filter the cloud contamination and obtain the maximum flood extent; they are very useful for flood damage assessment after the flooding events [36].…”

Section: Introductionmentioning

confidence: 99%

Assessment of the Catastrophic Asia Floods and Potentially Affected Population in Summer 2020 Using VIIRS Flood Products

Goldberg²,

Sjoberg³

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Since 2 June 2020, unusual heavy and continuous rainfall from the Asian summer monsoon rainy season caused widespread catastrophic floods in many Asian countries, including primarily the two most populated countries, China and India. To detect and monitor the floods and estimate the potentially affected population, data from sensors aboard the operational polar-orbiting satellites Suomi National Polar-Orbiting Partnership (S-NPP) and National Oceanic and Atmospheric Administration (NOAA)-20 were used. The Visible Infrared Imaging Radiometer Suite (VIIRS) with a spatial resolution of 375 m available twice per day aboard these two satellites can observe floodwaters over large spatial regions. The flood maps derived from the VIIRS imagery provide a big picture over the entire flooding regions, and demonstrate that, in July, in China, floods mainly occurred across the Yangtze River, Hui River and their tributaries. The VIIRS 5-day composite flood maps, along with a population density dataset, were combined to estimate the population potentially exposed (PPE) to flooding. We report here on the procedure to combine such data using the Zonal Statistic Function from the ArcGIS Spatial Analyst toolbox. Based on the flood extend for July 2020 along with the population density dataset, the Jiangxi and Anhui provinces were the most affected regions with more than 10 million people in Jingdezhen and Shangrao in Jiangxi province, and Fuyang and Luan in Anhui province, and it is estimated that about 55 million people in China might have been affected by the floodwaters. In addition to China, several other countries, including India, Bangladesh, and Myanmar, were also severely impacted. In India, the worst inundated states include Utter Pradesh, Bihar, Assam, and West Bengal, and it is estimated that about 40 million people might have been affected by severe floods, mainly in the northern states of Bihar, Assam, and West Bengal. The most affected country was Bangladesh, where one third of the country was underwater, and the estimated population potentially exposed to floods is about 30 million in Bangladesh.

show abstract

Mapping, Monitoring, and Prediction of Floods Due to Ice Jam and Snowmelt with Operational Weather Satellites

Cited by 12 publications

References 36 publications

Optimized Deep Learning Model for Flood Detection Using Satellite Images

Optimized Deep Learning Model for Flood Detection Using Satellite Images

Exploring the Potential of Zoning Regulation for Reducing Ice-Jam Flood Risk Using a Stochastic Modelling Framework

Assessment of the Catastrophic Asia Floods and Potentially Affected Population in Summer 2020 Using VIIRS Flood Products

Contact Info

Product

Resources

About