Chinese researchers have proposed a novel hybrid deep-learning model to address streamflow forecasting for water catchment areas at a global scale, with a view to improving flood prediction, according to a recent research article published in the journal The Innovation.
Streamflow and flood forecasting remains one of the long-standing challenges in hydrology. Traditional physically based models are hampered by sparse parameters and complex calibration procedures particularly in ungauged catchments.
More than 95 percent of small and medium-sized water catchments in the world lack monitoring data, according to the Chinese Academy of Sciences (CAS).
Researchers from the Institute of Mountain Hazards and Environment of the CAS used the datasets of more than 2,000 catchments around the world to conduct model training in order to cope with streamflow forecasting at a global scale for all gauged and ungauged catchments.
The distribution of these catchments was significantly different, ensuring the diversity of data.
The results show that the forecasting accuracy of the model was higher than traditional hydrological models and other AI models.
The study demonstrated the potential of deep-learning methods to overcome the lack of hydrologic data and deficiencies in physical model structure and parameterization, the research article noted.
China to expedite building modern eco
Cold Harbin a hot tourism destination for holiday
Over 5 bln USD of tentative deals inked at east China digital trade expo
US seeks information from Tesla on how it developed and verified whether Autopilot recall worked
China sets up expert advisory committee for lunar samples
New advances inspire China's deep space exploration
Oklahoma State hires Olympic gold medalist David Taylor as wrestling coach
China sees expansion in 5G network coverage
Lizzo has all eyes on her in puzzling 'vase dress' with bowl
China's autonomous driving enters fast lane with commercial operations