Evaluation and machine learning improvement of global hydrological model-based flood simulations

A warmer climate is expected to accelerate global hydrological cycle, causing more intense precipitation and floods. Despite recent progress in global flood risk assessment, the accuracy and improvement of global hydrological models (GHMs)-based flood simulation is insufficient for most applications. Here we compared flood simulations from five GHMs under the Inter-Sectoral Impact Model Intercomparison Project 2a (ISIMIP2a) protocol, against those calculated from 1032 gauging stations in the Global Streamflow Indices and Metadata Archive for the historical period 1971–2010. A machine learning approach, namely the long short-term memory units (LSTM) was adopted to improve the GHMs-based flood simulations within a hybrid physics- machine learning approach (using basin-averaged daily mean air temperature, precipitation, wind speed and the simulated daily discharge from GHMs-CaMa-Flood model chain as the inputs of LSTM, and observed daily discharge as the output value). We found that the GHMs perform reasonably well in terms of amplitude of peak discharge but are relatively poor in terms of their timing. The performance indicated great discrepancy under different climate zones. The large difference in performance between GHMs and observations reflected that those simulations require improvements. The LSTM used in combination with those GHMs was then shown to drastically improve the performance of global flood simulations (especially in terms of amplitude of peak discharge), suggesting that the combination of classical flood simulation and machine learning techniques might be a way forward for more robust and confident flood risk assessment

Climate change · Climate model · Climatology · Coupled model intercomparison project · Drainage basin · Flood forecasting · Flood myth · Global warming · Meteorology · Precipitation · Streamflow · Water cycle · Computer Science · Environmental Science · Flood Risk Assessment and Management · Hydrology and Drought Analysis · Hydrology and Watershed Management Studies · Geology

• Challenges and opportunities in precision irrigation decision-support systems for center pivots

  Open Access•Jingwen Zhang, Kaiyu Guan et al.•Environmental Research Letters•2021

  Añadir item

• Hybrid modeling of evapotranspiration

  Open Access•Reda ElGhawi, Basil Kraft et al.•Environmental Research Letters•2023

  Añadir item

• Effects of cryospheric hydrological processes on future flood inundation and the subsequent socioeconomic exposures in Central Asia

  Open Access•Ning Wang, Fubao Sun et al.•Environmental Research Letters•2022

  Añadir item

• Global hydrological models continue to overestimate river discharge

  Open Access•Stefanie Heinicke, Jan Volkholz et al.•Environmental Research Letters•2024

  Añadir item

• Extreme precipitation induced concurrent events trigger prolonged disruptions in regional road networks

  Open Access•Raviraj Dave, Srikrishnan Siva Subramanian et al.•Environmental Research Letters•2021

  Añadir item

• Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US

  Open Access•Goutam Konapala, Shih‐Chieh Kao et al.•Environmental Research Letters•2020

  Añadir item

• A review of deep learning and machine learning techniques for hydrological inflow forecasting

  Open Access•Sarmad Dashti Latif, Ali Najah Ahmed•Environment Development and…•2023

  Añadir item

• The ERA‐Interim reanalysis

  Open Access•Dick Dee, D P Dee et al.•Quarterly Journal of the Royal…•2011

  Añadir item

• Deep learning and process understanding for data-driven Earth system science

  Open Access•Markus Reichstein, Gustau Camps-Valls et al.•Nature•2019

  Añadir item

• A simple hydrologically based model of land surface water and energy fluxes for general circulation models

  Open Access•Xu Liang, Dennis P Lettenmaier et al.•Journal of Geophysical Research:…•1994

  Añadir item

• Agricultural green and blue water consumption and its influence on the global water system

  Open Access•Stefanie Rost, Dieter Gerten et al.•Water Resources Research•2008

  Añadir item

• The impacts of climate change on river flood risk at the global scale

  Open Access•Nigel W Arnell, Simon N Gosling•Climatic Change•2016

  Añadir item

• Global depletion of groundwater resources

  Open Access•Yoshihide Wada, Ludovicus P H van Beek et al.•Geophysical Research Letters•2010

  Añadir item

• Long Short-Term Memory

  Sepp Hochreiter, Jurgen Schmidhuber•Neural Computation•1997

  Añadir item

• The critical role of the routing scheme in simulating peak river discharge in global hydrological models

  Open Access•Fang Zhao, Ted Veldkamp et al.•Environmental Research Letters•2017

  Añadir item

• Intercomparison of global river discharge simulations focusing on dam operation—multiple models analysis in two case-study river basins, Missouri–Mississippi and Green–Colorado

  Open Access•Yoshimitsu Masaki, Naota Hanasaki et al.•Environmental Research Letters•2017

  Añadir item

• Multimodel uncertainty changes in simulated river flows induced by human impact parameterizations

  Open Access•Xingcai Liu, Qiuhong Tang et al.•Environmental Research Letters•2017

  Añadir item

• Human impact parameterizations in global hydrological models improve estimates of monthly discharges and hydrological extremes

  Open Access•Ted Veldkamp, Fang Zhao et al.•Environmental Research Letters•2018

  Añadir item

• Sources of uncertainty in hydrological climate impact assessment

  Open Access•Fred F Hattermann, Thomas Vetter et al.•Environmental Research Letters•2017

  Añadir item