Fully integrative species delimitation with machine learning and diverse data types in delimSOM 2.0

Species delimitation increasingly relies on multiple sources of evidence, but most frameworks are still limited to genetics and morphology or analyze data types separately and compare results qualitatively. We present delimSOM 2.0, an R package that leverages unsupervised machine learning through multilayer self-organizing maps. Any kind of input data, including genomic, phenotypic, ecological, and spatial, is analyzed jointly, retaining each data type as a separate layer and balancing their contributions through layer-specific weighting. Our package provides functions for preprocessing, replicate training, multivariate clustering, hyperparameter optimization, model-quality assessment, and variable- and layer-importance analyses. We evaluated our approach using two simulation sets and eight empirical studies spanning diverse taxa and data types. Overall, performance was strongest with larger sample sizes (>10 individuals per lineage) and modest numbers of lineages (K < 5), but unlike most species delimitation methods, it can reliably infer K = 1. Across two-population demographic simulations of genetic data, our method performed similarly to the well-established DAPC across gene-flow and sampling regimes, was more conservative than STRUCTURE and sNMF in inferring K = 2 and showed mixed support for K = 1 and K = 2 at intermediate differentiation levels and with gene flow. Crucially, our method is robust to missing data and variation in hyperparameters. Empirical examples showed that genetic data were typically most influential, but phenotypic, ecological, and spatial layers often contributed substantial complementary information. By combining diverse data types into a single unsupervised analysis, delimSOM 2.0 enables fully integrative species delimitation, reduces over-splitting, and advances efforts toward more objective and standardized taxonomy and speciation biology.