首页|University of Agriculture and Forestry Reports Findings in Machine Learning (Int egrating machine learning models with crossvalidation and bootstrapping for eva luating groundwater quality in Kanchanaburi Province, Thailand)
University of Agriculture and Forestry Reports Findings in Machine Learning (Int egrating machine learning models with crossvalidation and bootstrapping for eva luating groundwater quality in Kanchanaburi Province, Thailand)
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 in Hue City, Viet nam, by NewsRx journalists, research stated, “Exploring the potential of new mod els for mapping groundwater quality presents a major challenge in water resource management, particularly in Kanchanaburi Province, Thailand, where groundwater faces contamination risks. This study aimed to explore the applicability of rand om forest (RF) and artificial neural networks (ANN) models to predict groundwate r quality.” The news reporters obtained a quote from the research from the University of Agr iculture and Forestry, “Particularly, these two models were integrated into cros s-validation (CV) and bootstrapping (B) techniques to build predictive models, i ncluding RF-CV, RF-B, ANN-CV, and ANN-B. Entropy groundwater quality index (EWQI ) was converted to normalized EWQI which was then classified into five levels fr om very poor to very good. A total of twelve physicochemical parameters from 180 groundwater wells, including potassium, sodium, calcium, magnesium, chloride, s ulfate, bicarbonate, nitrate, pH, electrical conductivity, total dissolved solid s, and total hardness, were investigated to decipher groundwater quality in the eastern part of Kanchanaburi Province, Thailand. Our results indicated that grou ndwater quality in the study area was primarily polluted by calcium, magnesium, and bicarbonate and that the RF-CV model (RMSE = 0.06, R = 0.87, MAE = 0.04) out performed the RF-B (RMSE = 0.07, R = 0.80, MAE = 0.04), ANN-CV (RMSE = 0.09, R = 0.70, MAE = 0.06), and ANN-B (RMSE = 0.10, R = 0.67, MAE = 0.06). Our findings highlight the superiority of the RF models over the ANN models based on the CV a nd B techniques. In addition, the role of groundwater parameters to the normaliz ed EWQI in various machine learning models was found.”
Hue CityVietnamAsiaCyborgsEmergi ng TechnologiesMachine LearningThailand
NETL
NSTL
