Abstract
The Ant Miner algorithm was compared with the bivariate frequency ratio (FR) and boosted regression trees (BRT) algorithms in terms of its capacity to assess groundwater potential. A geospatial dataset was prepared that contains two components: a flowing well inventory map and eleven factors relevant to groundwater conditions. Average nearest neighbor technique was used to investigate the spatial pattern of flowing wells and to find the appropriate distance between flowing and nonflowing points in the study area. A wrapper approach known as random forest classifier and a filtering approach known as information gain ratio were used to identify the most relevant groundwater factors. The developed models were validated via the area under the operating characteristic curve. Results revealed that the Ant Miner model performed better in terms of both success (0.944) and prediction (0.92) rates compared to FR and BRT. Furthermore, the Ant Miner algorithm derived five simple, easily interpreted rules for predicting groundwater potential that can be used by hydrogeologists for identifying potential groundwater well locations with minimal effort and cost.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.