论文部分内容阅读
Restrictions of groundwater management are often derived from the insufficient or missing groundwater database.A suitable and complete groundwater database will allow sound engineering plans for sustainable water usage,including the drilling of wells,rates of water withdrawal,and eventually artificial recharge of the aquifer.The spatial-temporal variations of groundwater monitoring data are fluently influenced by the presence of manual factors,monitor equipment malfunctioning,natural phenomena,etc.Thus,it is necessary for researchers to check and infill the groundwater database before running the numerical groundwater model.In this paper,an artificial neural network(ANN)-based model is formulated using the hydrological and meteorological data to infill the inadequate data in the groundwater database.Prediction results present that ANN method could be a desirable choice for estimating the missing groundwater data.
Restrictions of groundwater management are often derived from the insufficient or missing groundwater database. A suitable and complete groundwater database will allow sound engineering plans for sustainable water usage, including the drilling of wells, rates of water withdrawal, and eventually artificial recharge of the aquifer. The spatial-temporal variations of groundwater monitoring data are fluently influenced by the presence of manual factors, monitor equipment malfunctioning, natural phenomena, etc. Thus, it is necessary for researchers to check and infill the groundwater database before running the numerical groundwater model. this paper, an artificial neural network (ANN) -based model is formulated using the hydrological and meteorological data to infill the inadequate data in the groundwater database. Prediction results present that ANN method could be desirable for estimating the missing groundwater data.