Crop breeding in the Global South faces a ‘phenotyping bottleneck’ due to reliance on manual visual phenotyping, which is both error-prone and challenging to scale across multiple environments, inhibiting selection of germplasm adapted to farmer production environments. This limitation impedes rapid varietal turnover, crucial for maintaining high yields and food security under climate change. Low adoption of improved varieties results from a top-down system in which farmers have been more passive recipients than active participants in varietal development. A new suite of research at the Alliance of Bioversity and CIAT seeks to democratize crop breeding by leveraging mobile phenotyping technologies for high-quality, decentralized data collection. This approach aims to resolve the inherent limitations and inconsistencies in traditional visual phenotyping methods, allowing for more accurate and efficient crop assessment. In parallel, the research seeks to harness multimodal data on farmer preferences to better tailor variety development to meet specific production and consumption goals. Novel mobile phenotyping tools were developed and field-tested on breeder stations in Colombia and Tanzania, and data from these trials were analyzed for quality and accuracy, and compared with traditional manual estimates and absolute ground truth data. Concurrently, Human-Centered Design (HCD) methods were applied to ensure the technology suits its context of use, and serves the nuanced requirements of breeders. Computer vison (CV)-enabled mobile phenotyping achieved a significant reduction in scoring variation, attaining imagery-modeled trait accuracies with Pearson Correlation values between 0.88 and 0.95 with ground truth data, and reduced labor requirements with the ability to fully phenotype a breeder's plot (4 m × 3 m) in under a minute. With this technology, high-quality quantitative phenotyping data can be collected by anyone with a smartphone, expanding the potential to measure crop performance in decentralized on-farm environments and improving accuracy and speed of crop improvement on breeder stations. Inclusive innovations in mobile phenotyping technologies and AI-supported data collection enable rapid, accurate trait assessment and actively involve farmers in variety selection, aligning breeding programs with local needs and preferences. These advancements offer a timely solution for accelerating varietal turnover to mitigate climate change impacts, while ensuring developed varieties are both high-performing and culturally relevant.

Background: Iron (Fe) and zinc (Zn) deficiencies remain important nutritional challenges, particularly where common bean ( Phaseolus vulgaris L.) is an important dietary staple. Understanding the genetic basis of seed micronutrient accumulation can facilitate development of nutritionally improved cultivars. This study aimed to identify genomic regions and marker–trait associations associated with seed Fe and Zn concentrations in a genetically diverse collection of common bean germplasm from Burundi using genome-wide association analysis. Results: Significant phenotypic variation was observed for both micronutrients, with Fe showing greater dispersion than Zn. Broad-sense heritability ranged from 0.73 to 0.81 for Fe and 0.70–0.81 for Zn, while genotypic effects accounted for 85.24% and 84.61% of total variation, respectively. Fe and Zn exhibited moderate positive phenotypic (rp = 0.58) and genetic (rg = 0.55) correlations, indicating potential for simultaneous improvement. Principal component analysis revealed pronounced differentiation between Andean ( n = 62) and Mesoamerican ( n = 101) gene pools, with PC1 explaining 44.12% of molecular variation. Linkage disequilibrium remained extended, with predicted r² = 0.2717 at 250 kb. Genome-wide association analysis identified no SNPs reaching the Bonferroni threshold for either trait. For Fe, 20 SNPs were significant under the Benjamini–Hochberg false discovery rate, and 16 Fe-associated SNPs were retained for detailed interpretation and candidate-gene analysis. These loci were distributed across Pv01, Pv04, Pv06, and Pv07 and individually explained 12.61–16.28% of phenotypic variance. In contrast, no significant or suggestive marker–trait associations were detected for Zn. LD-informed candidate-gene analysis identified 145 unique putative candidate genes within ± 100-kb regions surrounding the 16 Fe-associated SNPs. These genes represented diverse functional categories, including metal/mineral homeostasis, signalling, transcriptional regulation, redox processes, protein processing, RNA-related processes, and photosynthesis/chloroplast functions. Conclusion: The findings demonstrate substantial genetic variation and complex genetic control of seed Fe and Zn accumulation in Burundi common bean germplasm. The identified Fe-associated SNPs and candidate genes provide useful genomic resources for Fe biofortification, whereas the absence of detectable Zn associations highlights the potential value of genomic selection and multi-locus approaches for Zn improvement. Independent validation and functional characterization will be necessary to confirm the stability and biological relevance of the identified Fe-associated regions.