Performance Analysis ofANNPrediction for Groundwater Level ConsideringRegional‐SpecificInfluence Components

Abstract

Groundwater level (GWL) varies periodically or non-periodically with various factors including precipitation, river stage (RS) change, sea level, and dewatering activities. In this study, the effect of influence components on the prediction of GWL using an artificial neural network (ANN) was investigated. Six regions with different hydrologic and geologic conditions were collected and adopted in the investigation using various input combinations. In urban areas with a high surface paved ratio, GWL was mainly affected by RS. In rural areas, the permeability of ground showed a significant impact on GWL. For such cases, the moving average (MA) was a suitable component as it could reflect both time lag and the effect of preceding precipitation. It was shown that site-specific influence component should be firstly identified and introduced into input for more enhanced and reliable prediction of GWL using ANN. The effect of learning data length (LDL) was less significant. In urban and rural areas, the introduction of RS and MA into ANN input significantly improved the prediction performance, respectively, which was consistent with the correlation analysis of GWL influence components.

Characterizing Soil Permeability based on Response of Groundwater Level to River Stage using Regional Database

“…In uence factors that control the uctuation of GWL are different depending on geotechnical, geological, and geographical conditions at given area, all vary according to regional characteristics. In rural areas, where ground surfaces are largely exposed, precipitation dominates GWL as rainfall directly in ltrates into ground causing a change in GWL (Kim and Lee, 2022b). In urban areas, the large portions of ground surfaces are covered with pavement, and rainfall runs off owing out through the sewer system into river, as described in Fig.…”

Prediction of groundwater levels by 2100 considering climate change based on precipitation and river stage

“…According to Kim and Lee 4,5 , the predominant in uencing component on GWL is different depending on geological and geographical conditions at target area. In urban areas, the large portions of ground surfaces are covered with pavement, and the direct in ltration of rainfall into ground is usually limited, leading that GWL is in uenced mainly by near-by river stage.…”