首页|Data from University of California Provide New Insights into Machine Learning (R eservoir-based flood forecasting and warning: deep learning versus machine learn ing)
Data from University of California Provide New Insights into Machine Learning (R eservoir-based flood forecasting and warning: deep learning versus machine learn ing)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-Investigators discuss new findings in artificial intelligence. According to news originatingfrom the University of Ca lifornia by NewsRx correspondents, research stated, "In response to increasingf lood risks driven by the climate crisis, urban areas require advanced forecastin g and informed decisionmakingto support sustainable development. This study se eks to improve the reliability of reservoir-basedflood forecasting and ensure a dequate lead time for effective response measures."The news correspondents obtained a quote from the research from University of Ca lifornia: "Themain objectives are to predict hourly downstream flood discharge at a reference point, compare dischargepredictions from a single reservoir with a four-hour lead time against those from three reservoirs with aseven-hour lea d time, and evaluate the accuracy of data-driven approaches. The study takes pla ce inthe Han River Basin, located in Seoul, South Korea. Approaches include two non-deep learning (NDL)(random forest (RF), support vector regression (SVR)) a nd two deep learning (DL) (long short-termmemory (LSTM), gated recurrent unit ( GRU)). Scenario 1 incorporates data from three reservoirs, whileScenario 2 focu ses solely on Paldang reservoir. Results show that RF performed 4.03% (in R 2) better than SVR, while GRU performed 4.69% (in R 2) bette r than LSTM in Scenario 1. In Scenario 2, none ofthe models showed any outstand ing performance."
University of CaliforniaCyborgsEmerg ing TechnologiesMachine Learning
NETL
NSTL
