Distributed long-term hourly streamflow predictions using deep learning – A case study for State of Iowa

Xiang, Zhongrun; Demir, İbrahim

doi:10.1016/j.envsoft.2020.104761

Cited by 75 publications

(25 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kratzert et al [184] performed a study using Long Short Term Memory (LSTM) ANN over 241 catchments and showed the ability of this DL approach to learn long-term dependencies between the inputs and the output of the model (e.g., those related to modelling storage effects) along with the possibility to transfer process understanding from the regional to the local scale. Recently, Xiang and Demir [185] proposed the use of DL for extending the forecast horizon until five days on an hourly basis with promising results. Because there is a very recent interest on the application of DL for discharge forecasting, it has been tested by using only spatially distributed rainfall derived from dense rain gauges.…”

Section: Flash Flood Modelling Approaches Using Radar Datamentioning

confidence: 99%

The Role of Weather Radar in Rainfall Estimation and Its Application in Meteorological and Hydrological Modelling—A Review

et al. 2021

View full text Add to dashboard Cite

Radar-based rainfall information has been widely used in hydrological and meteorological applications, as it provides data with a high spatial and temporal resolution that improve rainfall representation. However, the broad diversity of studies makes it difficult to gather a condensed overview of the usefulness and limitations of radar technology and its application in particular situations. In this paper, a comprehensive review through a categorization of radar-related topics aims to provide a general picture of the current state of radar research. First, the importance and impact of the high temporal resolution of weather radar is discussed, followed by the description of quantitative precipitation estimation strategies. Afterwards, the use of radar data in rainfall nowcasting as well as its role in preparation of initial conditions for numerical weather predictions by assimilation is reviewed. Furthermore, the value of radar data in rainfall-runoff models with a focus on flash flood forecasting is documented. Finally, based on this review, conclusions of the most relevant challenges that need to be addressed and recommendations for further research are presented. This review paper supports the exploitation of radar data in its full capacity by providing key insights regarding the possibilities of including radar data in hydrological and meteorological applications.

show abstract

Section: Flash Flood Modelling Approaches Using Radar Datamentioning

confidence: 99%

The Role of Weather Radar in Rainfall Estimation and Its Application in Meteorological and Hydrological Modelling—A Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Due to the lack of systematic and standardized data collection on disasters, long-term planning becomes a critical challenge for decision-makers [39]. The standardized data and information [40] is a critical need for improving hydrological data management [41], remote sensing and monitoring [42], data analytics [43], and forecast and modeling studies [44][45][46]. Information generated through optimized data structures can support informed decision for flood management and control [47], preparedness [48], prevention [49], recovery, and response to future flood events and can be utilized for these applications.…”

Section: Flood Inventory Specificationmentioning

confidence: 99%

A comprehensive flood event specification and inventory: 1930–2020 Turkey case study

Haltaş

Yildirim

Oztas³

et al. 2021

International Journal of Disaster Risk Reduction

Self Cite

View full text Add to dashboard Cite

Flooding is one of the most frequent natural disasters that have significant impact on communities in terms of loss of life, direct and indirect economic losses, and disruption of daily life. Decision makers often consult flood data inventories to make more informed decisions on the development of flood mitigation plans to protect flood prone communities. A comprehensive inventory that covers multiple aspects of a flood event is critical to identify vulnerable regions, historical trends, and mitigate possible flood impacts. This study proposes an integrated flood data specification to support multi-stakeholder use cases, community-based sustainable domain specific maintenance, and crowdsourced data collection and expansion. The specification is designed based on comprehensive review of existing global and national repositories, literature, needs and requirements of stakeholders. The specification is designed to cover environmental, economic, and demographic impact, hydraulic, hydrologic, and meteorological features, and detailed location information of a flood event. As a case study, a flood event inventory was compiled for Turkey between 1930-2020 using existing national and global data sources and digitized media archives. A total of 2,101 flood events with 64 data attributes have been collected over the last 90 years. An initial statistical analysis of the inventory is also presented for the seasonal and regional characteristics of flooding in Turkey.

show abstract

“…Water resource management and hydrological modeling using physically based or data-driven (i.e. artificial neural networks) approaches [15][16][17] need high-resolution DEM for accurate hydrological predictions [18]. Besides advanced hydrological modeling, monitoring and geographic analysis such as watershed delineation [19,20] and stage height measurements [21] benefit from DEMs.…”

Section: Introductionmentioning

confidence: 99%

D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

2021

Self Cite

View full text Add to dashboard Cite

Digital elevation model (DEM) is a critical data source for variety of applications such as road extraction, hydrological modeling, flood mapping, and many geospatial studies. The usage of high-resolution DEMs as inputs in many application areas improves the overall reliability and accuracy of the raw dataset. The goal of this study is to develop a machine learning model that increases the spatial resolution of DEM without additional information. In this paper, a GAN based model (D-SRGAN), inspired by single image super-resolution methods, is developed and evaluated to increase the resolution of DEMs. The experiment results show that D-SRGAN produces promising results while constructing 3 feet high-resolution DEMs from 50 feet low-resolution DEMs. It outperforms common statistical interpolation methods and neural network algorithms.This study shows that it is possible to use the power of artificial neural networks to increase the resolution of the DEMs. The study also demonstrates that approaches from single image super-resolution can be applied for DEM super-resolution.

show abstract

Distributed long-term hourly streamflow predictions using deep learning – A case study for State of Iowa

Abstract: • Developed Neural Runoff Model (NRM) using deep learning for 120 hours streamflow forecasts. • NRM on 125 USGS stations in Iowa outperforms other machine learning methods. • NRM shows effectiveness in integrating stage level data for runoff forecasts.

Cited by 75 publications

References 35 publications

The Role of Weather Radar in Rainfall Estimation and Its Application in Meteorological and Hydrological Modelling—A Review

The Role of Weather Radar in Rainfall Estimation and Its Application in Meteorological and Hydrological Modelling—A Review

A comprehensive flood event specification and inventory: 1930–2020 Turkey case study

D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

Contact Info

Product

Resources

About