A hybrid neural network-based technique to improve the flow forecasting of physical and data-driven models: Methodology and case studies in Andean watersheds

Farfán, Juan F.; Palacios, Karina; Ulloa, Jacinto; Avilés, Álex

doi:10.1016/j.ejrh.2019.100652

Cited by 25 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the coefficients of determination (r = 0.87; p < 0.01) and Nash decreased (Figure 10a); this can be attributed to inadequate representation of GCM datasets for estimating extreme streamflows (Figure 10a). The decrease in the GR2M model's performance has also been observed in other studies [64].…”

Section: Hydrological Modeling Of the Daule Riversupporting

confidence: 84%

See 1 more Smart Citation

Impacts of Climate Change on the Precipitation and Streamflow Regimes in Equatorial Regions: Guayas River Basin

Ilbay-Yupa

Ilbay

Zubieta

et al. 2021

Water

View full text Add to dashboard Cite

The effects of climate change projected for 2050 to 2079 relative to the 1968–2014 reference period were evaluated using 39 CMIP5 models under the RCP8.5 emissions scenario in the Guayas River basin. The monthly normalized precipitation index (SPI) was used in this study to assess the impact of climate change for wet events and droughts from a meteorological perspective. The GR2M model was used to project changes in the streamflow of the Daule River. The climate projection was based on the four rigorously selected models to represent the climate of the study area. On average, an increase in temperature (~2 °C) and precipitation (~6%) is expected. A 7% increase in precipitation would result in a 10% increase in streamflow for flood periods, while an 8% decrease in precipitation could result in approximately a 60% reduction in flow for dry periods. The analysis of droughts shows that they will be more frequent and prolonged in the highlands (Andes) and the middle part of the basin. In the future, wet periods will be less frequent but of greater duration and intensity on the Ecuadorian coast. These results point to future problems such as water deficit in the dry season but also increased streamflow for floods during the wet season. This information should be taken into account in designing strategies for adaptation to climate change.

show abstract

Section: Hydrological Modeling Of the Daule Riversupporting

confidence: 84%

“…X2 determines runoff on output (Q) and the water exchange between surface and subsurface processes [63]. This model has been used in an Andean basin south of Ecuador and adequately represents flow dynamics but overestimates low flows [64].…”

Section: Hydrological Modeling By Gr2mmentioning

confidence: 99%

Impacts of Climate Change on the Precipitation and Streamflow Regimes in Equatorial Regions: Guayas River Basin

Ilbay-Yupa

Ilbay

Zubieta

et al. 2021

Water

View full text Add to dashboard Cite

show abstract

“…It is also necessary to analyze the impacts of afforestation on water availability due to climate change, and the impact of vegetation cover on the quality of the simulation. Finally, future work on small catchments will include hybrid modeling (lumped hydrological modeling and machine learning) [115] and the use of machine learning techniques [110] to evaluate their efficiency performance in the simulation of maximum and minimum flows.…”

Section: Discussionmentioning

confidence: 99%

Comparison of Three Daily Rainfall-Runoff Hydrological Models Using Four Evapotranspiration Models in Four Small Forested Watersheds with Different Land Cover in South-Central Chile

Flores

Rodrı́guez

Yépez

et al. 2021

Water

View full text Add to dashboard Cite

We used the lumped rainfall–runoff hydrologic models Génie Rural à 4, 5, 6 paramètres Journalier (GR4J, GR5J and GR6J) to evaluate the most robust model for simulating discharge on four forested small catchments (<40 ha) in south-central Chile. Different evapotranspiration methods were evaluated: Oudin, Hargreaves–Samani and Priestley–Taylor. Oudin’s model allows the achievement of the highest efficiencies in the flow simulation. The more sensitive parameters for each model were identified through a Generalized Probability Uncertainty Estimation (GLUE) model. Our results demonstrate that the three hydrological models were capable of efficiently simulating flow in the four study catchments. However, the GR6J model obtained the most satisfactory results in terms of simulated to measured streamflow closeness. In general, the three models tended to underestimate peak flow, as well as underestimate and overestimate flow events in most of the in situ observations, according to the probability of non-exceedance. We also evaluated the models’ performance in a simulation of summer discharge due to the importance of downstream water supply in the months of greatest scarcity. Again, we found that GR6J obtained the most efficient simulations.

show abstract

“…More details about the application of ANN to ensemble modeling can be found in Andraos and Najem (2020); Farfán et al. (2020); Li et al. (2018).…”

Section: Methodsmentioning

confidence: 99%

Assessing the Effects of Climate Change on Compound Flooding in Coastal River Areas

Bermúdez

Farfán

Willems

et al. 2021

Water Resources Research

View full text Add to dashboard Cite

Globally, floods are the most common natural hazard and have major economic, social, and ecological impacts on communities (CRED & UNISDR, 2015). Coastal river areas concentrate population, infrastructure, and economic activity, all of these highly vulnerable to floods (Koks et al., 2015). The effects of global warming in such already flood-prone areas raise concerns about future flood conditions, making imperative the need for reliable methods for their analysis (Seneviratne et al., 2012) and innovative approaches to their planning and management. These challenges, however, have been insufficiently addressed by regulations and policies. In the European Union (EU), the EU Floods Directive (2007/60/CE) and the Water Framework Directive (2000/60/ EC) establish the framework for assessing and managing flood risks. It defines a cycle that includes a preliminary assessment to identify areas at risk of flooding, the creation of flood hazard and risk maps, and the establishment of flood risk management plans focused on prevention, protection, and preparedness. It also establishes that these steps need to be reviewed every 6 years, and acknowledges the need to take into account the likely impact of climate change on the magnitude and frequency of floods. The European Water Framework Directive does not go beyond these procedural obligations, leaving open the question as to which methodological approaches are most appropriate for such flood risk assessments.The prediction of flooding in coastal river areas is not an easy task due to the complexity and interaction of the underlying physical processes. Elevated water levels in coastal reaches originate from the interaction of several coastal and inland drivers, such as storm surge and river discharge. These flood drivers are often not independent since they share a common meteorological forcing. For example, the combined effects of low atmospheric pressure and strong winds associated with synoptic-scale storms can induce storm surges along the coast. Concurrently, or in close succession, heavy precipitation increases freshwater runoff, and as a result leads to high river discharge. Elevated sea levels can block or slow down river drainage into the sea, leading to increased upstream water levels. Compared to flood events caused by a single driver, compound floods can usually be expected to yield higher impacts, as evidenced, for example, in the recent floods in Ravenna (Italy) (Bevacqua et al., 2017) or in the Hurricane Harvey Flood in Houston Area (Valle-Levinson

show abstract

A hybrid neural network-based technique to improve the flow forecasting of physical and data-driven models: Methodology and case studies in Andean watersheds

Cited by 25 publications

References 30 publications

Impacts of Climate Change on the Precipitation and Streamflow Regimes in Equatorial Regions: Guayas River Basin

Impacts of Climate Change on the Precipitation and Streamflow Regimes in Equatorial Regions: Guayas River Basin

Comparison of Three Daily Rainfall-Runoff Hydrological Models Using Four Evapotranspiration Models in Four Small Forested Watersheds with Different Land Cover in South-Central Chile

Assessing the Effects of Climate Change on Compound Flooding in Coastal River Areas

Contact Info

Product

Resources

About