Your current location:HOME >sport >Researchers develop deep 正文
TIME:2024-05-09 00:23:43 Source: Internet compilationEdit:sport
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.
China's telecoms industry expands steadily in Q12024-05-09 00:02
Special teams carry Rangers to a Game 3 win and a 32024-05-08 23:39
Why you might have heard Paul Simon’s ‘The Sound of Silence’ at Spanish Mass2024-05-08 23:33
Queen Máxima of the Netherlands is a hit with the kids as she high2024-05-08 23:11
The North Korean official whose propaganda helped build the Kim dynasty dies at 942024-05-08 23:01
Queen Maxima of the Netherlands dons sophisticated blue suit to meet the Nigeran President2024-05-08 23:00
UN warns Sudan paramilitary forces are encircling a capital in western Darfur, urges against attack2024-05-08 22:56
Man killed while fleeing Indiana police had previously resisted law enforcement2024-05-08 22:18
Türkiye's Istanbul welcomes 1st Chinese tourist group after pandemic2024-05-08 22:15
Solar panel plant coming to eastern North Carolina with 900 jobs2024-05-08 22:15
Louisiana lawmakers reject adding exceptions of rape and incest to abortion ban2024-05-08 23:52
South Dakota governor, a potential Trump running mate, writes in new book about killing her dog2024-05-08 23:30
Marlins place opening day starter Jesús Luzardo on injured list with left elbow tightness2024-05-08 23:19
China urges EU to create non2024-05-08 22:26
Demi Moore stuns at 61! Charlie's Angels star flutters down red carpet in butterfly2024-05-08 22:26
Woman pleads guilty to being accessory in fatal freeway shooting of 62024-05-08 22:25
Shocking moment father and son brawl with middle2024-05-08 22:07
Leicester promoted back to English Premier League2024-05-08 21:58
Lok Sabha elections 2024: Why Modi and BJP face strong resistance in south India2024-05-08 21:39
Feeling lucky? Brainteaser challenges YOU to spot a four2024-05-08 21:37