Identifying high-yielding and drought-tolerant chickpea genotypes helps ensure food production stability in regions prone to water scarcity and climate variability. Kohonen’s self-organizing maps (SOMs) as a type of artificial neural network was applied to assess genetic variation among 50 chickpea genotypes. Predictor Importance analysis indicated that pod weight, protein percentage, hundred-seed weight and chlorophyll content had the strongest influence on seed yield, followed by plant fresh weight, plant height, plant dry weight, and number of unfilled pods. Thus, pod weight, protein percentage, hundred-seed weight, and chlorophyll content can be targeted for breeding resilient chickpea varieties suited for changing climatic conditions. By targeting genotypes with high seed yield and biomass, farmers can increase production on limited land, reducing the need for land expansion and deforestation. Integration of precision breeding and site-specific genotype selection can minimize input waste (fertilizers, pesticides) while maintaining high yields. The identification of pod weight, protein percentage, hundred-seed weight, and chlorophyll content as critical yield determinants highlight their potential for selection in breeding programs aimed at improving chickpea performance in semi-arid environments. This study’s findings bridge scientific innovation and practical agricultural solutions, offering a data-driven approach to climate adaptation and resource-efficient farming. By integrating machine learning in genotype selection, policymakers, researchers, and farmers can develop locally adapted, globally relevant strategies for chickpea production in resource-constrained environments.
