Lima bean (Phaseolus lunatus L.) is the second most important socioeconomic species of the genus, consisting of a food alternative as green or mature beans. It is an income option for family farmers and the lack of superior varieties makes its recommendation difficult, considering the peculiar lima bean variability. Thus, aimed to select landraces of lima beans based on desirable agronomic traits, enabling their use in breeding programs and later recommendations to family farmers. Evaluation trials were carried out with 14 landraces of lima beans in the municipalities of São Domingos do Maranhão - MA, Teresina - PI, Bom Jesus - PI, and Tianguá - CE. The agronomic traits were evaluated: number of days until flowering, number of days until pod maturation, pod length, pod width, pod thickness, number of seeds per pod, 100-seed weight, and grain yield. The data were initially subjected to univariate analysis of variance to determine the genetic variability in different environments and, subsequently, to multivariate and cluster analyses. The evaluated landraces showed genetic divergence, not being grouped according to geographic origin, demonstrating the existence of similarity between germplasms of rural communities in neighboring states. The varieties Boca de Moça, Raio de Sol, and Fava Branca CE are the earliest; Boca de Moça, Rajada, and Raio de Sol presented the longest pods and largest seeds; and Boca de Moça, Rajada, and Mulatinha are the most productive. Therefore, it qualifies them for recommendation to family farmers and/or incorporation in lima bean breeding programs.

Morpho-agronomic characterization studies aiming at the discrimination and classification of lima bean accessions in relation to the centers of domestication and biological status have been of great importance for conserving the biodiversity of this species. For this purpose, researchers have widely used the multivariate analysis called discriminant analysis, which is not always capable of producing satisfactory results. Computational intelligence-based classifiers are additional tools for understanding complex classification problems. In this study, the objective was to test the use of the decision tree in the classification of lima bean according to the centers of domestication and biological status (cultivated and wild), based on eight phenotypic traits of the seed. Sixty accessions of lima bean from the Phaseolus Germplasm Bank of Universidade Federal do Piauí (BGP / UFPI) were evaluated, and classification was performed using two approaches: conventional statistics with discriminant analysis of principal components (DAPC) and computational intelligence through decision tree (DT). The results showed that the use of DT was efficient to identify patterns in the classification of lima bean accessions, due to its comprehensibility. Seed weight was one of the main descriptors used to explain the origin and diversity of the species. The results found will be useful for studies that involve the conservation of genetic resources, mainly for the maintenance of germplasm banks and in breeding programs. In addition, it is recommended to integrate machine learning algorithms in studies aimed at classifying lima bean.