The invention discloses an in-situ monitoring and
early warning system and method for
loess aeration zone
pollutant migration and transformation, and belongs to the technical field of environment monitoring and soil
groundwater pollution prevention and control. The method comprises the following steps: constructing a
loess aeration zone three-dimensional in-situ intelligent sensing network, and collecting multi-source
original data based on the network; performing adaptive preprocessing on the multi-source
original data to generate a standardized spatial-temporal
feature data set; and constructing an improved
deep learning space-time prediction model, and training the improved
deep learning space-time prediction model based on the standardized space-time
feature data set to realize the concentration change of the target
pollutant in a specified time period in the future. According to the method, in-situ real-time monitoring of
moisture, chemical and pollutants in a
loess aeration zone is realized through a stereoscopic
perception network, the space-time process of
pollutant migration is accurately described by using an improved
deep learning model, and the risk that the concentration of pollutants in an underground water interface exceeds the standard can be predicted tens of hours in advance; the fundamental conversion from
passive monitoring to active intelligent early warning is realized, and reliable
technical support is provided for
pollution prevention and control of the loess area.