The authors applied semi‑supervised deep‑learning to super‑resolution images of modern and fossil grass pollen, training convolutional neural networks to extract abstract morphological features. These features were used to quantify past grass community diversity and C3:C4 ratios in a 25,000‑year lake‑sediment record, revealing a marked diversity loss during the last glacial and a gradual decline of C4 grasses in the Holocene.

The authors introduce AdaPoinTr, a geometry-aware transformer that predicts the alpha‑shape of coniferous tree crowns from incomplete terrestrial or mobile laser‑scanning point clouds, focusing on crown reconstruction rather than full tree completion. Trained on synthetically generated partial crowns, the model consistently improves crown shape similarity and reduces height estimation bias across three diverse forest datasets, providing a cost‑effective solution for enhanced 3D forest structural monitoring.

The study characterizes a radiation‑induced root‑suppressed (Rs) mutant in tomato that displays dwarfism and pleiotropic defects in leaves, flowers, and fruits. Metabolite profiling and rescue with H2S donors implicate disrupted sulfur metabolism, and whole‑genome sequencing identifies promoter mutations in two root‑meristem‑specific sulfotransferase genes as likely contributors to the root phenotype.

The study identifies members of the REMORIN protein family as inhibitors of plasma membrane H⁺‑ATPases, leading to extracellular pH alkalinization that modulates cell surface processes such as steroid hormone signaling and coordinates root developmental transitions in Arabidopsis thaliana. This inhibition represents an ancient mechanism predating root evolution, suggesting that extracellular pH patterning has shaped plant morphogenesis.

The authors compiled and standardized published data on Rubisco dark inhibition for 157 flowering plant species, categorizing them into four inhibition levels and analyzing phylogenetic trends. Their meta‑analysis reveals a complex, uneven distribution of inhibition across taxa, suggesting underlying chloroplast microenvironment drivers and providing a new resource for future photosynthesis improvement efforts.

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 examined drought tolerance across nine provenances of the conifer Pinus nigra using high‑throughput phenotyping combined with metabolomic and transcriptomic analyses under controlled soil‑drying conditions. Drought tolerance, measured by the decline in Fv/Fm, varied among provenances but was not linked to a climatic gradient and was independent of growth, with tolerant provenances showing distinct flavonoid and diterpene profiles and provenance‑specific gene expression patterns. Integrating phenotypic and molecular data revealed metabolic signatures underlying drought adaptation in this non‑model conifer.

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 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.