Automated Input Variable Selection for Analog Methods Using Genetic Algorithms

Analog methods (AMs) have long been used for precipitation prediction and climate studies. However, they rely on manual selections of parameters, such as predictor variables and analogy criteria. Previous work showed the potential of genetic algorithms (GAs) to optimize most of the AM parameters. This research goes one step further and investigates the potential of GAs for automating the selection of the input variables and the analogy criteria (distance metric between two data fields) in AMs. Our study focuses on the prediction of daily precipitation in central Europe, specifically Switzerland, as a representative case. Comparative analysis against established methods demonstrates the superiority of GA-optimized AMs in terms of predictive accuracy. The selected input variables exhibit strong associations with key meteorological processes that influence the generation of precipitation. Further, we identify a new analogy criterion inspired by the Teweles-Wobus criterion, which consistently performs better than other Euclidean distances and could be used in classic AMs. In contrast to conventional stepwise selection approaches, GA-optimized AMs display a preference for a flatter structure characterized by a single level of analogy and an increased number of variables. Overall, our study demonstrates the successful application of GAs in automating input variable selection for AMs, with potential implications for application in diverse locations and data exploration to predict alternative predictands. In a broader context, GAs could be used to perform input variable selection in other data-driven methods, opening perspectives for a broad range of applications. Analog methods (AMs) predict precipitation by searching for similar past meteorological situations. However, setting up these methods requires manual selection of meteorological variables and how to compare them. Genetic algorithms (GAs) can already optimize some of AM parameters, and our study goes further to explore whether GAs can automatically select the variables and comparison metrics. Our results indicate that AMs improved by GAs outperform other AMs in predicting rainfall. The chosen variables strongly relate to important weather processes influencing rainfall. We also identified a new criterion for measuring the similarity of meteorological situations, which outperforms others used in traditional methods. Unlike conventional stepwise approaches, GAs prefer a simpler structure with a single level of analogy. In summary, our study demonstrates that GAs simplify the process of choosing variables for AMs, with potential applications in various locations and data exploration for local weather prediction. Additionally, such approaches can be extended to select relevant variables in other data-driven methods. Genetic algorithms were successful in selecting relevant input variables for the prediction of precipitation by analog methods The analogy criteria were automatically selected, resulting in the discovery of a new promising criterion The optimization resulted in a structure combining different predictors into a single level of analogy, while outperforming stepwise methods