The study assessed how well common deep learning models (ResNet, EfficientNet, Inception, MobileNet) generalize across different tomato pest and disease image datasets. While models performed well on the dataset they were trained on, they suffered substantial accuracy drops when applied to other datasets, indicating that architectural changes alone cannot overcome dataset variability. The results highlight the necessity for more diverse, representative training data to improve real-world deployment of PPD diagnostic tools.

The study demonstrates that hyperspectral imaging can non‑destructively differentiate active nitrogen‑fixing root nodules from non‑fixing nodules and root tissue based on distinct spectral signatures. By integrating deep‑learning models, the authors created an automated nodule counting pipeline that works across multiple legume species and growth conditions, eliminating labor‑intensive manual counting and reliably detecting nodules within dense root systems.

The study introduces the Botanical Spectrum Analyzer (BSA), a GUI that incorporates a modified U‑Net deep neural network for accurate segmentation of plant images from RGB and hyperspectral (VNIR and SWIR) data. BSA was tested on wheat, barley, and Arabidopsis datasets, achieving >99% accuracy and F1‑scores above 98%, and markedly outperformed commercial tools on root segmentation tasks.

The study developed a high-throughput phenotyping platform to assess root infestation by Orobanche cumana in a diverse sunflower association mapping population and applied a dual GWAS using SNPs and k-mers to uncover resistance loci. It validated known QTLs with higher resolution, identified novel candidate genes such as leucine‑rich repeat receptor kinases, and highlighted introgressed segments from wild Helianthus species that contribute to broomrape resistance.

The study reports the creation and validation of a high‑density Axiom SNP array for Solanum tuberosum, based on 10X Genomics sequencing of 108 diverse clones and integration of existing Illumina markers. The array demonstrated high reproducibility and, after filtering, provided 206,616 informative markers for population structure analysis, GWAS of polyphenol oxidase activity, and genomic prediction with accuracies up to 0.86.

A genome-wide association study of 166 Iberian Arabidopsis accessions identified loci, including ABA3 and GA2ox2, that modulate the inhibitory effect of the auxin precursor indole-3-acetamide (IAM) on primary root elongation. Integrating sequence analysis, transcriptomics, 3D protein modeling, and mutant physiology revealed that IAM promotes ABA biosynthesis and signaling, uncovering a novel node of hormone crosstalk.

The study used multi‑season phenotyping for iron, zinc, and protein content together with whole‑genome re‑sequencing of a groundnut mini‑core collection to conduct a genome‑wide association study, identifying numerous marker‑trait associations and candidate genes linked to nutrient homeostasis. SNP‑based KASP markers were designed for nine loci, of which three showed polymorphism and are ready for deployment in genomics‑assisted breeding for nutrient‑rich groundnut varieties.

The study integrates genome, transcriptome, and chromatin accessibility data from 380 soybean accessions to dissect the genetic and regulatory basis of symbiotic nitrogen fixation (SNF). Using GWAS, TWAS, eQTL mapping, and ATAC-seq, the authors identify key loci, co‑expression modules, and regulatory elements, and validate the circadian clock gene GmLHY1b as a negative regulator of nodulation via CRISPR and CUT&Tag. These resources illuminate SNF networks and provide a foundation for soybean improvement.

The study introduces a deep‑learning based image analysis pipeline that scores blackleg disease severity from stem cross‑section images of canola species, achieving greater consistency than median expert raters while preserving comparable heritability of susceptibility traits. This standardized scoring method aims to improve selection of resistant varieties in breeding programs.

The study presents a deep‑learning pipeline that uses state‑of‑the‑art convolutional neural networks to automatically estimate the establishment of perennial groundcovers in agricultural research plots from smartphone images. By employing region‑of‑interest markers and deploying the models on AWS SageMaker with a lightweight Django web interface, the approach provides fast, objective, and reproducible assessments that can be adopted by researchers and growers across the Midwest.