The study used extensive gravimetric load‑cell and ambient sensor data collected over seven years from hundreds of greenhouse-grown crops to train machine‑learning models for predicting daily whole‑plant transpiration. Random Forest and XGBoost achieved the highest accuracy (R² up to 0.89), with ambient temperature identified as the dominant driver. These results highlight the promise of ML‑based tools for precise agricultural water management.

The study used high-resolution chemical imaging to map cell-type specific metabolic changes in plant roots inoculated with a nine-strain endophyte consortium under drought, revealing that endophytes differentially alter root metabolomes across spatial domains. Machine learning identified metabolites and exudates predictive of drought and endophyte treatment, and correlation analyses showed dynamic endophyte–metabolite relationships under stress.

The study introduces ENTRAP-seq, a high‑throughput in‑planta assay that couples protein‑coding libraries with a nuclear magnetic sorting‑based reporter to multiplexively assess transcriptional regulatory activity of thousands of protein variants. Using this platform and machine‑learning analysis, the authors screened 1,495 plant viral proteins, uncovering numerous novel regulatory domains, and applied machine‑guided, semi‑rational design to modify the activity of a plant transcription factor.

The study used phylogeny‑based analyses of 36 legume genomes and a newly created multiparent advanced generation intercross (MAGIC) population of common bean to predict and characterize genome‑wide deleterious mutations. Machine‑learning integration of conservation and protein features identified thousands of potentially deleterious sites, whose variation correlated negatively with flowering time, maturity, and yield, highlighting the impact of genetic load on breeding performance.

The authors introduce S²-PepAnalyst, a web-based tool that leverages plant-specific datasets and advanced machine learning to predict small signaling peptides (SSPs) with 99.5% accuracy and minimal false negatives. By integrating protein language models, geometric‑topological analysis, and reinforcement learning, the tool surpasses existing predictors such as SignalP 6.0 in classifying peptide families like CLE and RALF.

The study evaluated 11 intermediate phenotypes linked to stalk lodging resistance in a diverse panel of 566 maize (Zea mays L.) inbred lines across four environments, preserving individual stalk identity to capture plant-level variation. This high-density phenotypic dataset enabled statistical genomics, predictive modeling, and machine learning to uncover genetic factors underlying lodging resistance, offering insights applicable to other grass species.

The study utilizes explainable artificial intelligence (XAI) combined with machine learning to assess how inter‑annual weather variability influences oilseed sunflower yields across the United States from 1976 to 2022. Key climate predictors, especially summer maximum temperature and total precipitation, were identified, and predictive models were projected under various Shared Socioeconomic Pathways to 2080, revealing region‑specific yield declines.

The study examined transposable element (TE) silencing in the duckweed Spirodela polyrhiza, which exhibits unusually low DNA methylation, scarce 24‑nt siRNAs, and missing RdDM components. While degenerated TEs lack DNA methylation and H3K9me2, they retain heterochromatin marks H3K9me1 and H3K27me1, whereas the few intact TEs show high DNA methylation and H3K9me2, indicating a shift in RdDM focus toward potentially active TEs and suggesting heterochromatin can be maintained independently of DNA methylation in flowering plants.