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.

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 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.

The study benchmarked several sampling approaches for simultaneous profiling of root exudates and rhizosphere microbiota in soil-grown barley, revealing consistent exudate chemistry across methods but variation in root morphology and nitrogen exudation. High‑throughput amplicon sequencing and quantitative PCR showed protocol‑specific impacts on microbial composition, yet most rhizosphere-enriched microbes were captured by all approaches. The authors conclude that different protocols provide comparable integrated data, though methodological differences must be aligned with experimental objectives.

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 investigates how maternal environmental conditions, specifically temperature and light intensity, influence seed longevity in eight Arabidopsis thaliana natural accessions. Seeds developed under higher temperature (27 °C) and high light showed increased longevity, with transcriptome analysis of the Bor-4 accession revealing dynamic changes in stored mRNAs, including upregulation of antioxidant defenses and raffinose family oligosaccharides. These findings highlight the genotype‑dependent modulation of seed traits by the maternal environment.

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 investigates the evolutionary shift from archegonial to embryo‑sac reproduction by analyzing transcriptomes of Ginkgo reproductive organs and related species. It reveals that the angiosperm pollen‑tube guidance module MYB98‑CRP‑ECS is active in mature Ginkgo archegonia and that, while egg cell transcription is conserved, changes in the fate of other female gametophyte cells drove the transition, providing a molecular framework for this major reproductive evolution.