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.

Four barley genotypes were examined under simultaneous Fusarium culmorum infection and drought, revealing genotype-dependent Fusarium Head Blight severity and largely additive transcriptomic responses dominated by drought. Co‑expression and hormone profiling linked ABA and auxin to stress‑specific gene modules, and a multiple linear regression model accurately predicted combined‑stress gene expression from single‑stress data, suggesting modular regulation.

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.

PlantCV v4 is an open-source Python framework that simplifies image-based plant phenotyping by providing extensive tutorials and streamlined installation, enabling users with limited coding skills to automate trait extraction. The release adds support for fluorescence, thermal, and hyperspectral imaging and introduces a new subpackage for morphological measurements such as leaf angle, which is validated against manual data collection methods.

The study combined high-throughput image-based phenotyping with genome-wide association studies to uncover the genetic architecture of tolerance to the spittlebug Aeneolamia varia in 339 interspecific Urochloa hybrids. Six robust QTL were identified for plant damage traits, explaining up to 21.5% of variance, and candidate genes linked to hormone signaling, oxidative stress, and cell‑wall modification were highlighted, providing markers for breeding.

The study examined nitrogen use strategies in the model alga Chlamydomonas reinhardtii by comparing growth on ammonium, nitrate, and urea, finding similar molar nitrogen utilization efficiency under saturating conditions. Rapid nitrogen uptake and storage were demonstrated through pulse experiments, and source‑specific transcriptome analysis revealed distinct regulation of assimilation pathways and transporters, supporting a model of flexible nitrogen acquisition and storage.

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.