Comparison of three updating models for real time forecasting: a case study of flood forecasting at the middle reaches of the Huai River in East China

Self Cite

Free water storage capacity, an important characteristic of land surface related to runoff process, has a significant influence on runoff generation and separation. It is thus necessary to derive reasonable spatial distribution of free water storage capacity for rainfall-runoff simulation, especially in distributed modeling. In this paper, a topographic index based approach is proposed for the derivation of free water storage capacity spatial distribution. The topographic index, which can be obtained from digital elevation model (DEM), are used to establish a functional relationship with free water storage capacity in the proposed approach. In this case, the spatial variability of free water storage capacity can be directly estimated from the characteristics of watershed topography. This approach was tested at two medium sized watersheds, including Changhua and Chenhe, with the drainage areas of 905 km2 and 1395 km2, respectively. The results show that locations with larger values of free water storage capacity generally correspond to locations with higher topographic index values, such as riparian region. The estimated spatial distribution of free water storage capacity is also used in a distributed, grid-based Xinanjiang model to simulate 10 flood events for Chenhe Watershed and 17 flood events for Changhua Watershed. Our analysis indicates that the proposed approach based on topographic index can produce reasonable spatial variability of free water storage capacity and is more suitable for flood simulation.

Section: Parameterization Of W M and S M In The Xaj Modelmentioning

confidence: 99%

Derivation of the Spatial Distribution of Free Water Storage Capacity Based on Topographic Index

Tong

Yao

et al. 2018

Self Cite

“…Among these three aspects for data assimilation, error updating can describe the difference between the observations and the model predictions to produce reliable forecasts; thus, it is a frequently used technique in operational flood forecasting [29,30]. Furthermore, inaccurate input data, model parameters, and output variables from the real-time flood forecasting hydrological models necessitate a hybrid approach, such as coupling the hydrological model with an error correction model [31]. Therefore, inspired by the significant power of LSTM networks in modeling dynamics and dependencies of sequential data, we combined LSTM neural networks and the k-nearest neighbor (KNN) algorithm [32] as a way of learning from historical data to predict sequential discharge using an updating technique that learns from the errors of the LSTM simulation results.…”

Section: Introductionmentioning

confidence: 99%

“…KNN has been used as the error prediction model in real-time flood forecasting. In the application of the KNN algorithm in flood prediction, the distance between feature vectors (e.g., meteorological inputs) is compared to selected k-nearest neighbors similar to the present hydrological process; then, the error is estimated at the forecast time to update the flood forecasts of hydrological models [31]. Kan [36] adopted the ensemble feed-forward neural network (ENN) incorporating partial mutual information for input variable selection, and KNN was employed for discharge error forecasting.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Applicability of LSTM-KNN Model for Real-Time Flood Forecasting in Different Climate Zones in China

Liu

Huang

et al. 2020

Self Cite

Flow forecasting is an essential topic for flood prevention and mitigation. This study utilizes a data-driven approach, the Long Short-Term Memory neural network (LSTM), to simulate rainfall–runoff relationships for catchments with different climate conditions. The LSTM method presented was tested in three catchments with distinct climate zones in China. The recurrent neural network (RNN) was adopted for comparison to verify the superiority of the LSTM model in terms of time series prediction problems. The results of LSTM were also compared with a widely used process-based model, the Xinanjiang model (XAJ), as a benchmark to test the applicability of this novel method. The results suggest that LSTM could provide comparable quality predictions as the XAJ model and can be considered an efficient hydrology modeling approach. A real-time forecasting approach coupled with the k-nearest neighbor (KNN) algorithm as an updating method was proposed in this study to generalize the plausibility of the LSTM method for flood forecasting in a decision support system. We compared the simulation results of the LSTM and the LSTM-KNN model, which demonstrated the effectiveness of the LSTM-KNN model in the study areas and underscored the potential of the proposed model for real-time flood forecasting.

“…Topography has a significant role on the forming and distribution of flooding [28][29][30]. Elevation and slope are generally used to quantify topographic variation.…”

Section: Introductionmentioning

confidence: 99%

Analysis and GIS Mapping of Flooding Hazards on 10 May 2016, Guangzhou, China

Lyu

Wang

Shen

et al. 2016

Abstract:On 10 May 2016, Guangdong Province, China, suffered a heavy rainstorm. This rainstorm flooded the whole city of Guangzhou. More than 100,000 people were affected by the flooding, in which eight people lost their lives. Subway stations, cars, and buses were submerged. In order to analyse the influential factors of this flooding, topographical characteristics were mapped using Digital Elevation Model (DEM) by the Geographical Information System (GIS) and meteorological conditions were statistically summarised at both the whole city level and the district level. To analyse the relationship between flood risk and urbanization, GIS was also adopted to map the effect of the subway system using the Multiple Buffer operator over the flooding distribution area. Based on the analyses, one of the significant influential factors of flooding was identified as the urbanization degree, e.g., construction of a subway system, which forms along flood-prone areas. The total economic loss due to flooding in city centers with high urbanization has become very serious. Based on the analyses, the traditional standard of severity of flooding hazards (rainfall intensity grade) was modified. Rainfall intensity for severity flooding was decreased from 50 mm to 30 mm in urbanized city centers. In order to protect cities from flooding, a "Sponge City" planning approach is recommended to increase the temporary water storage capacity during heavy rainstorms. In addition, for future city management, the combined use of GIS and Building Information Modelling (BIM) is recommended to evaluate flooding hazards.