首页|Data on Machine Learning Reported by Researchers at Hohai University (Breaking t he Mold of Simulation-optimization: Direct Forward Machine Learning Methods for Groundwater Contaminant Source Identification)
Data on Machine Learning Reported by Researchers at Hohai University (Breaking t he Mold of Simulation-optimization: Direct Forward Machine Learning Methods for Groundwater Contaminant Source Identification)
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-Fresh data on Machine Learning are pre sented in a new report. According to news reporting out of Nanjing, People's Rep ublic of China, by NewsRx editors, research stated, "Groundwater Contaminant Sou rce Identification (GCSI) is important for addressing environmental concerns. Cu rrently, it is widely achieved using the Simulation/Optimization (S/O) method." Financial supporters for this research include National Key Research & Development Program of China, National Natural Science Foundation of China (NSFC ). Our news journalists obtained a quote from the research from Hohai University, " However, the utilization of optimization techniques may cause high computation c osts and parameter equifinality issues. We introduce two innovative GCSI methods,Direct Forward Machine Learning (DFML) and One-Hot Machine Learning (OHML), ut ilizing the classical Artificial Neuro Network (ANN) model in the machine learni ng field. Both new methods eliminate the need for an optimization algorithm in G CSI, thus reducing the construction effort and improving efficiency. The first m ethod, DFML can directly estimate eight parameters, providing valuable insights into the contaminant location, release history, and aquifer properties. The seco nd method, OHML can estimate the spatial probability distribution of the contami nant location through one-hot encoding, addressing uncertainties in the contamin ant source location estimations realized by DFML. Evaluations demonstrate that b oth methods exhibit satisfying performances. DFML can estimate contaminant locat ion and aquifer properties with high accuracy; and estimate the release history information with moderate accuracy. The OHML correctly assigns the higher contam inant probabilities to regions containing true contaminant locations. The combin ation of DFML and OHML offers a comprehensive framework."
NanjingPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningHohai University
NETL
NSTL
