Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on artificial in telligence have been published. According to news originating from Karlsruhe, Ge rmany, by NewsRx correspondents, research stated, “Seasons are known to have a m ajor influence on groundwater recharge and therefore groundwater levels; however , underlying relationships are complex and partly unknown.” Our news journalists obtained a quote from the research from Fraunhofer Institut e of Optronics: “The goal of this study is to investigate the influence of the s easons on groundwater levels (GWLs), especially during low-water periods. For th is purpose, we train artificial neural networks on data from 24 locations spread throughout Germany. We exclusively focus on precipitation and temperature as in put data and apply layer-wise relevance propagation to understand the relationsh ips learned by the models to simulate GWLs. We find that the learned relationshi ps are plausible and thus consistent with our understanding of the major physica l processes. Our results show that for the investigated locations, the models le arn that summer is the key season for periods of low GWLs in fall, with a connec tion to the preceding winter usually only being subordinate. Specifically, dry s ummers exhibit a strong influence on low-water periods and generate a water defi cit that (preceding) wet winters cannot compensate for.”
NETL
NSTL