首页|Report Summarizes Machine Learning Study Findings from University of Saskatchewa n (What Controls Hydrology? an Assessment Across the Contiguous United States Th rough an Interpretable Machine Learning Approach)
Report Summarizes Machine Learning Study Findings from University of Saskatchewa n (What Controls Hydrology? an Assessment Across the Contiguous United States Th rough an Interpretable Machine Learning Approach)
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 – Research findings on Machine Learning are discussed in a new report. According to news reporting out of Saskatoon, Can ada, by NewsRx editors, research stated, “Machine learning (ML) is increasingly perceived as a futuristic, superior data-driven approach to scientific discovery . It has already demonstrated remarkable performance in forecasting and predicti on, yet its role in enhancing our understanding of hydrological processes remain s underexplored.” Our news journalists obtained a quote from the research from the University of S askatchewan, “Traditional hydrological interpretations have relied heavily on mo del-dependent interpretation methods, focusing on the predictive accuracy of ML model predictions. Since hydrological models are built on a collection of assump tions and simplifications, model-dependent approaches might suffer from limited model realism, adequacy, accuracy, and equifinality issues. To address this gap, this study provides an ML approach that works in a model-independent context, w orking directly on hydroclimatic data collected through monitoring systems. We a pply our model-independent interpretation approach to a carefully designed set o f hydrologic data collected across the contiguous United States to address the f ollowing questions: (1) What are the primary controls of runoff-generation mecha nisms, and how can such controls be attributed to catchment properties? (2) How and under what circumstances can the history of climate variables, such as preci pitation, be a surrogate for present-time state variables, such as soil moisture and snowpack? We show that the ML approach aids in distinguishing catchments ch aracterized by strong overland flow, interflow, or baseflow components and those primarily driven by rainfall, snowmelt, or a mix thereof.”
SaskatoonCanadaNorth and Central Ame ricaCyborgsEmerging TechnologiesMachine LearningUniversity of Saskatchew an
NETL
NSTL
