首页|New Findings from University of Peradeniya in the Area of Machine Learning Publi shed (A new frontier in streamflow modeling in ungauged basins with sparse data: A modified generative adversarial network with explainable AI)
New Findings from University of Peradeniya in the Area of Machine Learning Publi shed (A new frontier in streamflow modeling in ungauged basins with sparse data: A modified generative adversarial network with explainable AI)
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 Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news reporting from Peradeniya, S ri Lanka, by NewsRx journalists, research stated, "Streamflow forecasting is cru cial for effective water resource planning and early warning systems, especially in regions with complex hydrological behaviors and uncertainties. While machine learning (ML) has gained popularity for streamflow prediction, many studies hav e overlooked the predictability of future events considering anthropogenic, stat ic physiographic, and dynamic climate variables." Our news reporters obtained a quote from the research from University of Peraden iya: "This study, for the first time, used a modified generative adversarial net work (GAN) based model to predict streamflow. The adversarial training concept m odifies and enhances the existing data to embed featureful information enough to capture extreme events rather than generating synthetic data instances. The mod el was trained using (sparse data) a combination of anthropogenic, static physio graphic, and dynamic climate variables obtained from an ungauged basin to predic t monthly streamflow. The GAN-based model was interpreted for the first time usi ng local interpretable model-agnostic explanations (LIME), explaining the decisi onmaking process of the GAN-based model. The GAN-based model achieved R2 from 0 .933 to 0.942 in training and 0.93-0.94 in testing. Also, the extreme events in the testing period have been reasonably well captured. The LIME explanations gen erally adhere to the physical explanations provided by related work." According to the news editors, the research concluded: "This approach looks prom ising as it worked well with sparse data from an ungauged basin. The authors sug gest this approach for future research work that focuses on machine learning-bas ed streamflow predictions."
University of PeradeniyaPeradeniyaSr i LankaAsiaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
