Learning from multiple frameworks for aquifer vulnerability mapping and multiple modelling practices in groundwater vulnerability mapping studies

Learning from multiple frameworks (MF) in vulnerability mapping of aquifers and from multiple models (MM) is a novel research case tested in this paper by inclusive multiple modelling (IMM) practices. Each framework relates to multiple consensually selected data layers with an appropriate scoring system, which reflects intrinsic variances in the data layers and MF is particularly appropriate to shallow and patchy study areas. The IMM strategy is implemented at three levels: At Level 1, three frameworks (e.g., DRASTIC, SINTACS and GODS) are selected to map the vulnerability of a study area; At Level 2: inclusivity is achieved by employing the modelled output from Level 1 models as inputs for two additional machine learning models (e..g, support vector machine and multilayer perceptron) at Level 2. At Level 3: the outputs from these two models are combined using another model (e.g., random forest). The findings provide evidence that the Level 3 model produces more ‘defensible’ performance metrics by extracting information from all the models at Levels 1 and 2 with a better potential for learning from each output. The modelling results at Level 1 are ‘fit-for-purpose’, those at Level 3 are defensible and those at 2 are in between. For the patchy and shallow study area, the vulnerability maps at the higher level of the strategy are found to be more defensible than those at lower levels.