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 integrated 16 Arabidopsis thaliana whole‑genome bisulfite sequencing datasets from 13 stress experiments using a unified bioinformatic pipeline to map common and stress‑specific DNA methylation changes. Differentially methylated regions varied by stress type and methylation context, with CG DMRs enriched in gene bodies and CHG/CHH DMRs in transposable elements, some of which overlapped loci prone to stable epimutations. Gene ontology and TE enrichment analyses highlighted shared stress pathways and suggest environmental stress can generate heritable epigenetic variation.

High-quality PacBio HiFi draft genome assemblies were generated for three Bouteloua species (B. curtipendula, B. gracilis, B. eriopoda) with >98.5% BUSCO completeness. Gene prediction with Helixer produced inflated gene counts likely reflecting polyploidy and fragmented predictions, and panEDTA identified 25–40% transposable-element content dominated by LTR retrotransposons. These assemblies provide foundational references for comparative genomics within PACMAD grasses.

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.

Regenerative agriculture using a grass-clover ley increased wheat yields and macroaggregate stability despite reduced root biomass, but did not enhance soil carbon sequestration as measured by 14C retention. Drought further decreased photosynthate allocation to roots, especially in ley soils, while genotype effects on yield were minimal.

The study examined how soil phosphorus and nitrogen availability influence wheat root-associated arbuscular mycorrhizal fungal (AMF) communities and the expression of mycorrhizal nutrient transporters. Field sampling across two years combined with controlled pot experiments showed that P and N jointly affect AMF colonisation, community composition (with Funneliformis dominance under high P), and regulation of phosphate, ammonium, and nitrate transporters. Integrating metabarcoding and RT‑qPCR provides a framework to assess AMF contributions to crop nutrition.

The study compared aphid resistance and Barley Yellow Dwarf Virus (BYDV) transmission among three wheat varieties (G1, RGT Wolverine, RGT Illustrious). G1 emits the repellent 2‑tridecanone, restricts aphid phloem access, and shows reduced BYDV transmission, whereas RGT Wolverine limits systemic viral infection despite high transmission efficiency. The authors suggest breeding the two resistance mechanisms together for improved protection.

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 adapted high‑throughput transposable‑element sequencing and introduced the deNOVOEnrich pipeline to map somatic TE insertions in Arabidopsis thaliana, uncovering ~200,000 new events across wild‑type and epigenetic mutant lines. Somatic integration is non‑random and TE‑specific, with families like ONSEN, EVADE, and AtCOPIA21 preferentially targeting chromosomal arms, genic regions, and chromatin marked by H2A.Z, H3K27me3, and H3K4me1, especially near environmentally‑responsive genes such as resistance loci and biosynthetic clusters.

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.