Abstract
With the increase of climate change and the risk of human activities, seawater intrusion has become an essential threat to human health and sustainable economic development in coastal areas. Therefore, identifying the critical features of seawater intrusion is significantly important, but the existing research on it is insufficient. Moreover, most of the work cannot reflect the direct impact of different shared socioeconomic paths on groundwater salinity in the future. To solve this problem, this study first established a numerical model of variable density flow for the Dagu River Basin based on SEAWAT to analyze the main aquifers' current flow field and concentration field distribution. Then two machine learning methods, random forest and mutual information methods, are introduced to identify critical features of seawater intrusion for the first time. Finally, taking the characteristics affected by climate are used as variables for selecting GCMs, the seawater intrusion in the study area is predicted by six GCMs under shared socioeconomic paths (ssp1-2.6 and ssp5-8.5) from 2020.12.30 to 2030.12.30. The findings indicate that regional precipitation and groundwater extraction exert significant influence on seawater intrusion, with the hydraulic conductivity of the primary aquifer also demonstrating crucial importance. Moreover, it is observed that the potential impact of different shared socioeconomic paths on future variations of seawater intrusion is negligible. This study verifies the effectiveness of machine learning in seawater intrusion analysis to a certain extent and has specific reference significance for the optimal management of water resources in coastal areas and the effective mitigation of seawater intrusion.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call