Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention

Floods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the complexity of the traditional lumped model and distributed model, the hydrologic parameter calibration process is full of difficulties, leading to a long development cycle of a reasonable hydrologic prediction model. Even for modern data-driven models, the spatial distribution characteristics of the rainfall data are also not fully mined. Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction. Through well-designed experiments, the forecasting effect of flood peak value and flood arrival time is verified. Furthermore, compared with the LSTM model and BIGRU model without spatial feature extraction, the advantages of spatiotemporal feature fusion are highlighted. The specific performance is that the RMSE (the root means square error) and R2(coefficient of determination) of the GA-RNN model have been significantly improved. Finally, we conduct experiments on the observed ten rainfall events in the history of the target watershed. According to the hydrological prediction specifications, the model can be evaluated as a Class B flood forecasting model.

Download Full-text

Improving operational flood ensemble prediction by the assimilation of satellite soil moisture: comparison between lumped and semi-distributed schemes

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-11-10635-2014 ◽

2014 ◽

Vol 11 (9) ◽

pp. 10635-10681 ◽

Cited By ~ 3

Author(s):

C. Alvarez-Garreton ◽

D. Ryu ◽

A. W. Western ◽

C.-H. Su ◽

W. T. Crow ◽

...

Keyword(s):

Spatial Distribution ◽

Soil Moisture ◽

Distributed Model ◽

Ensemble Prediction ◽

Streamflow Prediction ◽

Flood Prediction ◽

Lumped Model ◽

Model Soil ◽

Main Driver ◽

Semi Arid

Abstract. Assimilation of remotely sensed soil moisture data (SM–DA) to correct soil water stores of rainfall-runoff models has shown skill in improving streamflow prediction. In the case of large and sparsely monitored catchments, SM–DA is a particularly attractive tool. Within this context, we assimilate active and passive satellite soil moisture (SSM) retrievals using an ensemble Kalman filter to improve operational flood prediction within a large semi-arid catchment in Australia (>40 000 km2). We assess the importance of accounting for channel routing and the spatial distribution of forcing data by applying SM–DA to a lumped and a semi-distributed scheme of the probability distributed model (PDM). Our scheme also accounts for model error representation and seasonal biases and errors in the satellite data. Before assimilation, the semi-distributed model provided more accurate streamflow prediction (Nash–Sutcliffe efficiency, NS = 0.77) than the lumped model (NS = 0.67) at the catchment outlet. However, this did not ensure good performance at the "ungauged" inner catchments. After SM–DA, the streamflow ensemble prediction at the outlet was improved in both the lumped and the semi-distributed schemes: the root mean square error of the ensemble was reduced by 27 and 31%, respectively; the NS of the ensemble mean increased by 7 and 38%, respectively; the false alarm ratio was reduced by 15 and 25%, respectively; and the ensemble prediction spread was reduced while its reliability was maintained. Our findings imply that even when rainfall is the main driver of flooding in semi-arid catchments, adequately processed SSM can be used to reduce errors in the model soil moisture, which in turn provides better streamflow ensemble prediction. We demonstrate that SM–DA efficacy is enhanced when the spatial distribution in forcing data and routing processes are accounted for. At ungauged locations, SM–DA is effective at improving streamflow ensemble prediction, however, the updated prediction is still poor since SM–DA does not address systematic errors in the model.

Download Full-text

Improving operational flood ensemble prediction by the assimilation of satellite soil moisture: comparison between lumped and semi-distributed schemes

Hydrology and Earth System Sciences ◽

10.5194/hess-19-1659-2015 ◽

2015 ◽

Vol 19 (4) ◽

pp. 1659-1676 ◽

Cited By ~ 65

Author(s):

C. Alvarez-Garreton ◽

D. Ryu ◽

A. W. Western ◽

C.-H. Su ◽

W. T. Crow ◽

...

Keyword(s):

Spatial Distribution ◽

Soil Moisture ◽

Distributed Model ◽

Ensemble Prediction ◽

Generation Process ◽

Streamflow Prediction ◽

Flood Prediction ◽

Lumped Model ◽

Model Soil ◽

Semi Arid

Abstract. Assimilation of remotely sensed soil moisture data (SM-DA) to correct soil water stores of rainfall-runoff models has shown skill in improving streamflow prediction. In the case of large and sparsely monitored catchments, SM-DA is a particularly attractive tool. Within this context, we assimilate satellite soil moisture (SM) retrievals from the Advanced Microwave Scanning Radiometer (AMSR-E), the Advanced Scatterometer (ASCAT) and the Soil Moisture and Ocean Salinity (SMOS) instrument, using an Ensemble Kalman filter to improve operational flood prediction within a large (> 40 000 km2) semi-arid catchment in Australia. We assess the importance of accounting for channel routing and the spatial distribution of forcing data by applying SM-DA to a lumped and a semi-distributed scheme of the probability distributed model (PDM). Our scheme also accounts for model error representation by explicitly correcting bias in soil moisture and streamflow in the ensemble generation process, and for seasonal biases and errors in the satellite data. Before assimilation, the semi-distributed model provided a more accurate streamflow prediction (Nash–Sutcliffe efficiency, NSE = 0.77) than the lumped model (NSE = 0.67) at the catchment outlet. However, this did not ensure good performance at the "ungauged" inner catchments (two of them with NSE below 0.3). After SM-DA, the streamflow ensemble prediction at the outlet was improved in both the lumped and the semi-distributed schemes: the root mean square error of the ensemble was reduced by 22 and 24%, respectively; the false alarm ratio was reduced by 9% in both cases; the peak volume error was reduced by 58 and 1%, respectively; the ensemble skill was improved (evidenced by 12 and 13% reductions in the continuous ranked probability scores, respectively); and the ensemble reliability was increased in both cases (expressed by flatter rank histograms). SM-DA did not improve NSE. Our findings imply that even when rainfall is the main driver of flooding in semi-arid catchments, adequately processed satellite SM can be used to reduce errors in the model soil moisture, which in turn provides better streamflow ensemble prediction. We demonstrate that SM-DA efficacy is enhanced when the spatial distribution in forcing data and routing processes are accounted for. At ungauged locations, SM-DA is effective at improving some characteristics of the streamflow ensemble prediction; however, the updated prediction is still poor since SM-DA does not address the systematic errors found in the model prior to assimilation.

Download Full-text

Accuracy Validation of Flood Forecasting Method Based on Time Series Analysis Using Observed Water Level and Rainfall Data

10.5194/egusphere-egu2020-12604 ◽

2020 ◽

Author(s):

Naoki Koyama ◽

Tadashi Yamada

Keyword(s):

Time Series ◽

Time Series Analysis ◽

Water Level ◽

First Grade ◽

Flood Forecasting ◽

Rainfall Data ◽

Flood Prediction ◽

Series Analysis ◽

Level Data ◽

Water Level Data

The aim of this paper is to verify the accuracy of the real-time flood prediction model, using the time-series analysis. Forecast information of water level is important information that encourages residents to evacuate. Generally, flood forecasting is conducted by using runoff analysis. However, in developing countries, there are not enough hydrological data in a basin. Therefore, this study assumes where poor hydrologic data basin and evaluates it through reproducibility and prediction by using time series analysis which statistical model with the water level data and rainfall data. The model is applied to the one catchment of the upper Tone River basin, one of the first grade river in Japan. This method is possible to reproduce hydrograph, if the observation stations exist several points in the basin. And using the estimated parameters from past flood events, we can apply this method to predict the water level until the flood concentration time which the reference point and observation station. And until this time, the peak water level can be predicted with the accuracy of several 10cm. Prediction can be performed using only water level data, but by adding rainfall data, prediction can be performed for a longer time.

Download Full-text

A Study on the Improvement of Flood Forecasting Techniques in Urban Areas by Considering Rainfall Intensity and Duration

Water ◽

10.3390/w11091883 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1883 ◽

Cited By ~ 2

Author(s):

Choo ◽

Jo ◽

Yun ◽

Lee

Keyword(s):

Water Level ◽

Urban Areas ◽

Prediction Method ◽

Flood Forecasting ◽

Flood Damage ◽

Rainfall Data ◽

Runoff Simulation ◽

Flood Prediction ◽

Prediction Techniques ◽

Impervious Areas

Frequent localized torrential rains, excessive population density in urban areas, and increased impervious areas have led to massive flood damage that has been causing overloading of drainage systems (watersheds, reservoirs, drainage pump sites, etc.). Flood concerns are raised around the world in the events of rain. Flood forecasting, a typical nonstructural measure, was developed to help prevent repetitive flood damage. However, it is difficult to apply flood prediction techniques using training processes because training needs to be applied at every usage. Other techniques that use predicted rainfall data are also not appropriate for small watershed, such as single drainage area. Thus, in this paper, a flood prediction method is proposed by improving four criteria (50% water level, 70% water level, 100% water level, and first flooding of water pipes) in an attempt to reduce flooding in urban areas. The four criteria nodes are generated using a rainfall runoff simulation with synthetic rainfall at various durations. When applying real-time rainfall data, these nodes have the advantage of simple application. The improved flood nomograph made in this way is expected to help predict and prepare for rainstorms that can potentially cause flood damage.

Download Full-text

Calibrations of Low-Cost Air Pollution Monitoring Sensors for CO, NO2, O3, and SO2

Sensors ◽

10.3390/s21010256 ◽

2021 ◽

Vol 21 (1) ◽

pp. 256

Author(s):

Pengfei Han ◽

Han Mei ◽

Di Liu ◽

Ning Zeng ◽

Xiao Tang ◽

...

Keyword(s):

Random Forest ◽

Linear Regression ◽

Short Term Memory ◽

Hot Spot ◽

Low Cost ◽

Field Evaluation ◽

Pollution Monitoring ◽

Coefficient Of Determination ◽

Air Pollution Monitoring ◽

National Monitoring

Pollutant gases, such as CO, NO2, O3, and SO2 affect human health, and low-cost sensors are an important complement to regulatory-grade instruments in pollutant monitoring. Previous studies focused on one or several species, while comprehensive assessments of multiple sensors remain limited. We conducted a 12-month field evaluation of four Alphasense sensors in Beijing and used single linear regression (SLR), multiple linear regression (MLR), random forest regressor (RFR), and neural network (long short-term memory (LSTM)) methods to calibrate and validate the measurements with nearby reference measurements from national monitoring stations. For performances, CO > O3 > NO2 > SO2 for the coefficient of determination (R2) and root mean square error (RMSE). The MLR did not increase the R2 after considering the temperature and relative humidity influences compared with the SLR (with R2 remaining at approximately 0.6 for O3 and 0.4 for NO2). However, the RFR and LSTM models significantly increased the O3, NO2, and SO2 performances, with the R2 increasing from 0.3–0.5 to >0.7 for O3 and NO2, and the RMSE decreasing from 20.4 to 13.2 ppb for NO2. For the SLR, there were relatively larger biases, while the LSTMs maintained a close mean relative bias of approximately zero (e.g., <5% for O3 and NO2), indicating that these sensors combined with the LSTMs are suitable for hot spot detection. We highlight that the performance of LSTM is better than that of random forest and linear methods. This study assessed four electrochemical air quality sensors and different calibration models, and the methodology and results can benefit assessments of other low-cost sensors.

Download Full-text

Long Short Term Memory Modelling Approach for Flood Prediction: An Application in Deduru Oya Basin of Sri Lanka

2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer) ◽

10.1109/icter51097.2020.9325438 ◽

2020 ◽

Author(s):

W.A.M. Prabuddhi ◽

B.L.D. Seneviratne

Keyword(s):

Sri Lanka ◽

Short Term Memory ◽

Short Term ◽

Flood Prediction ◽

Term Memory ◽

Long Short Term Memory ◽

Memory Modelling ◽

Modelling Approach

Download Full-text

Driver Drowsiness Estimation Based on Factorized Bilinear Feature Fusion and a Long-Short-Term Recurrent Convolutional Network

Information ◽

10.3390/info12010003 ◽

2020 ◽

Vol 12 (1) ◽

pp. 3

Author(s):

Shuang Chen ◽

Zengcai Wang ◽

Wenxin Chen

Keyword(s):

Short Term Memory ◽

Feature Fusion ◽

Detection Methods ◽

Video Frame ◽

Estimation Model ◽

Short Term ◽

Convolutional Network ◽

Drowsiness Detection ◽

Driver Drowsiness ◽

Time Information

The effective detection of driver drowsiness is an important measure to prevent traffic accidents. Most existing drowsiness detection methods only use a single facial feature to identify fatigue status, ignoring the complex correlation between fatigue features and the time information of fatigue features, and this reduces the recognition accuracy. To solve these problems, we propose a driver sleepiness estimation model based on factorized bilinear feature fusion and a long- short-term recurrent convolutional network to detect driver drowsiness efficiently and accurately. The proposed framework includes three models: fatigue feature extraction, fatigue feature fusion, and driver drowsiness detection. First, we used a convolutional neural network (CNN) to effectively extract the deep representation of eye and mouth-related fatigue features from the face area detected in each video frame. Then, based on the factorized bilinear feature fusion model, we performed a nonlinear fusion of the deep feature representations of the eyes and mouth. Finally, we input a series of fused frame-level features into a long-short-term memory (LSTM) unit to obtain the time information of the features and used the softmax classifier to detect sleepiness. The proposed framework was evaluated with the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results showed that this method had better stability and robustness compared with other methods.

Download Full-text

Test on Flood Prediction-Model Using Artificial Neural Network for ShiiLiAn Hydrologic Station on MinChiang,China

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.39.555 ◽

2010 ◽

Vol 39 ◽

pp. 555-561 ◽

Cited By ~ 1

Author(s):

Qing Hua Luan ◽

Yao Cheng ◽

Zha Xin Ima

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Flood Control ◽

Back Propagation ◽

Forecast Model ◽

Flood Forecast ◽

Back Propagation Algorithm ◽

Nonlinear Method ◽

Flood Prediction ◽

Artificial Neural

The establishing of a precise simulation model for runoff prediction in river with several tributaries is the difficulty of flood forecast, which is also one of the difficulties in hydrologic research. Due to the theory of Artificial Neural Network, using Back Propagation algorithm, the flood forecast model for ShiLiAn hydrologic station in Minjiang River is constructed and validated in this study. Through test, the result shows that the forecast accuracy is satisfied for all check standards of flood forecast and then proves the feasibility of using nonlinear method for flood forecast. This study provides a new method and reference for flood control and water resources management in the local region.

Download Full-text

A two-stage analogue model for real-time urban flood forecasting

10.5194/egusphere-egu21-15645 ◽

2021 ◽

Author(s):

Chris Onof ◽

Yuting Chen ◽

Li-Pen Wang ◽

Amy Jones ◽

Susana Ochoa Rodriguez

Keyword(s):

Real Time ◽

Flood Forecasting ◽

Image Feature ◽

Two Stage ◽

Analogue Model ◽

Flood Prediction ◽

Urban Flood ◽

Radar Images ◽

Proposed Model ◽

Flood Maps

In this work a two-stage (rainfall nowcasting + flood prediction) analogue model for real-time urban flood forecasting is presented. The proposed approach accounts for the complexities of urban rainfall nowcasting while avoiding the expensive computational requirements of real-time urban flood forecasting.The model has two consecutive stages:<ul><li>(1) Rainfall nowcasting: 0-6h lead time ensemble rainfall nowcasting is achieved by means of an analogue method, based on the assumption that similar climate condition will define similar patterns of temporal evolution of the rainfall. The framework uses the NORA analogue-based forecasting tool (Panziera et al., 2011), consisting of two layers. In the first layer, the 120 historical atmospheric (forcing) conditions most similar to the current atmospheric conditions are extracted, with the historical database consisting of ERA5 reanalysis data from the ECMWF and the current conditions derived from the US Global Forecasting System (GFS). In the second layer, twelve historical radar images most similar to the current one are extracted from amongst the historical radar images linked to the aforementioned 120 forcing analogues. Lastly, for each of the twelve analogues, the rainfall fields (at resolution of 1km/5min) observed after the present time are taken as one ensemble member. Note that principal component analysis (PCA) and uncorrelated multilinear PCA methods were tested for image feature extraction prior to applying the nearest neighbour technique for analogue selection.</li> <li>(2) Flood prediction: we predict flood extent using the high-resolution rainfall forecast from Stage 1, along with a database of pre-run flood maps at 1x1 km2 solution from 157 catalogued historical flood events. A deterministic flood prediction is obtained by using the averaged response from the twelve flood maps associated to the twelve ensemble rainfall nowcasts, where for each gridded area the median value is adopted (assuming flood maps are equiprobabilistic). A probabilistic flood prediction is obtained by generating a quantile-based flood map. Note that the flood maps were generated through rolling ball-based mapping of the flood volumes predicted at each node of the InfoWorks ICM sewer model of the pilot area.</li> </ul>The Minworth catchment in the UK (~400 km2) was used to demonstrate the proposed model. Cross&#8209;assessment was undertaken for each of 157 flooding events by leaving one event out from training in each iteration and using it for evaluation. With a focus on the spatial replication of flood/non-flood patterns, the predicted flood maps were converted to binary (flood/non-flood) maps. Quantitative assessment was undertaken by means of a contingency table. An average accuracy rate (i.e. proportion of correct predictions, out of all test events) of 71.4% was achieved, with individual accuracy rates ranging from 57.1% to 78.6%). Further testing is needed to confirm initial findings and flood mapping refinement will be pursued.The proposed model is fast, easy and relatively inexpensive to operate, making it suitable for direct use by local authorities who often lack the expertise on and/or capabilities for flood modelling and forecasting.References: Panziera et al. 2011. NORA&#8211;Nowcasting of Orographic Rainfall by means of Analogues. Quarterly Journal of the Royal Meteorological Society. 137, 2106-2123.

Download Full-text

Simulation of karst floods with a hydrological model improved by meteorological model coupling

Journal of Hydrometeorology ◽

10.1175/jhm-d-21-0088.1 ◽

2021 ◽

Keyword(s):

Flood Control ◽

Underground Structure ◽

Wrf Model ◽

Precipitation Forecast ◽

Karst Area ◽

Peak Time ◽

Flood Prediction ◽

Meteorological Model ◽

Flood Peak ◽

Flood Warning

Abstract Karst basins are prone to rapid flooding because of their geomorphic complexity and exposed karst landforms with low infiltration rates. Accordingly, simulating and forecasting floods in karst regions can provide important technical support for local flood control. The study area, the Liujiang karst river basin, is the most well-developed karst area in South China, and its many mountainous areas lack rainfall gauges, limiting the availability of precipitation information. Quantitative precipitation forecast (QPF) from the Weather Research and Forecasting model (WRF) and quantitative precipitation estimation (QPE) from remote sensing information by an artificial neural network cloud classification system (PERSIANN-CCS) can offer reliable precipitation estimates. Here, the distributed Karst-Liuxihe (KL) model was successfully developed from the terrestrial Liuxihe model, as reflected in improvements to its underground structure and confluence algorithm. Compared with other karst distributed models, the KL model has a relatively simple structure and small modeling data requirements, which are advantageous for flood prediction in karst areas lacking hydrogeological data. Our flood process simulation results suggested that the KL model agrees well with observations and outperforms the Liuxihe model. The average Nash coefficient, correlation coefficient, and water balance coefficient increased by 0.24, 0.19, and 0.20, respectively, and the average flood process error, flood peak error, and peak time error decreased by 13%, 11%, and 2 hours, respectively. Coupling the WRF model and PERSIANN-CCS with the KL model yielded a good performance in karst flood simulation and prediction. Notably, coupling the WRF and KL models effectively predicted the karst flood processes and provided flood prediction results with a lead time of 96 hours, which is important for flood warning and control.

Download Full-text