GIS Applications and Machine Learning Approaches in Civil Engineering

The positions of earth observations or features, along with the properties that go with them and the spatial relationships that exist between them, are displayed using GIS (Geographic Information Systems) data. GIS statistical analysis ranges greatly and includes modeling and projections, these are typically highly computational and sophisticated, particularly whenever huge datasets must be handled. Due to its considerable quickness, precision, automation, and consistency, approaches like machine learning (ML) have been proposed as an imminent revolution in the evaluation of GIS data as computing technologies develop. The flexibility in transferring data from a particular database to a different one is possibly the most significant advantage when utilizing combined GIS and ML. The present study provides an overview of the ML models and their applications in infrastructure/urban development, health, flood prediction, groundwater detection and contamination, erosion modeling and prediction, landslide susceptibility prediction (LSP), LULCC modeling, managing forests and their resources, and biodiversity conservation using GIS tools. In addition to this, the study highlights several limitations associated with deploying different ML models in conjunction with GIS.