首页|Ondokuz Mayis University Reports Findings in Machine Learning (Improving the sim ulations of the hydrological model in the karst catchment by integrating the con ceptual model with machine learning models)
Ondokuz Mayis University Reports Findings in Machine Learning (Improving the sim ulations of the hydrological model in the karst catchment by integrating the con ceptual model with machine learning models)
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 Machine Learning is th e subject of a report. According to news reporting originating from Samsun, Turk ey, by NewsRx correspondents, research stated, "Hydrological modelling can be co mplex in nonhomogeneous catchments with diverse geological, climatic, and topogr aphic conditions. In this study, an integrated conceptual model including the sn ow module with machine learning modelling approaches was implemented for daily r ainfall-runoff modelling in mostly karst Ljubljanica catchment, Slovenia, which has heterogeneous characteristics and is potentially exposed to extreme events t hat make the modelling process more challenging and crucial." Our news editors obtained a quote from the research from Ondokuz Mayis Universit y, "In this regard, the conceptual model CemaNeige Genie Rural a 6 parametres Jo urnalier (CemaNeige GR6J) was combined with machine learning models, namely wave let-based support vector regression (WSVR) and wavelet-based multivariate adapti ve regression spline (WMARS) to enhance modelling performance. In this study, th e performance of the models was comprehensively investigated, considering their ability to forecast daily extreme runoff. Although CemaNeige GR6J yielded a very good performance, it overestimated low flows. The WSVR and WMARS models yielded poorer performance than the conceptual and hybrid models. The hybrid model appr oach improved the performance of the machine learning models and the conceptual model by revealing the linkage between variables and runoff in the conceptual mo del, which provided more accurate results for extreme flows. Accordingly, the hy brid models improved the forecasting performance of the maximum flows up to 40 % and 61 %, and minimum flows up to 73 % and 72 % compared to the CemaNeige GR6J and stand-alone machine learning models."
SamsunTurkeyEurasiaCyborgsEmergi ng TechnologiesMachine Learning
NETL
NSTL
