Your current location:HOME >business >Researchers develop deep 正文
TIME:2024-05-08 17:50:23 Source: Internet compilationEdit:business
Chinese researchers have proposed a novel hybrid deep-learning model to address streamflow forecasti
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.
Britain's most notorious inmate Charles Bronson puts his parole bid in jeopardy after punch2024-05-08 17:30
Myanmar’s junta moves Aung San Suu Kyi to house arrest, report says — Radio Free Asia2024-05-08 17:05
Jontay Porter banned from NBA after gambling probe2024-05-08 16:58
What is cloud seeding? Step2024-05-08 16:46
Hidden agenda behind hype of China's 'overcapacity problem'2024-05-08 16:20
Supreme Court makes it easier to sue for job discrimination over forced transfers2024-05-08 16:17
OJ Simpson was chilling with a beer on a couch before Easter, lawyer says2024-05-08 16:11
Massive rockfall hits luxury development site in Cornwall earmarked for seven £1m new homes2024-05-08 15:26
PGA Championship invites 7 LIV players to get top 100 in the world2024-05-08 15:07
Pilot who died last week in Indiana plane crash was Purdue student, authorities say2024-05-08 15:04
China Cruise Shipping Conference opens in Shenzhen2024-05-08 17:25
Hillary Clinton and Malala Yousafzai producing. An election nigh. ‘Suffs’ has timing on its side2024-05-08 17:21
'I was afraid for my life' — Orlando Bloom puts himself in peril for new TV series2024-05-08 17:21
Edmunds: Avoid these 3 mistakes when buying a used car sight unseen2024-05-08 17:07
Too much water, and not enough: Brazil's flooded south struggles to find basic goods2024-05-08 17:07
Asian Americans more likely to believe in climate change: AP2024-05-08 16:44
'I was afraid for my life' — Orlando Bloom puts himself in peril for new TV series2024-05-08 16:07
A neglected burial ground for migrants on Greek island of Lesbos has been given a drastic overhaul2024-05-08 15:30
Chinese satellite detects over 100 solar white2024-05-08 15:14
Gujarat crashes to 89 all out against Delhi, loses IPL game by 6 wickets at home2024-05-08 15:09