Agronomy

Accurate counting of spikes in crested wheatgrass, an important forage resource, is essential for breeding and yield evaluation. However, traditional manual counting is inefficient, and instance-level supervised methods face challenges such as high annotation costs and counting errors caused by overlapping targets in complex field scenes. To address these issues, this study proposes the Multi-Granularity Gating Image-Level Supervision Count Network (MGG-ISCNet), a lightweight image-level supervised counting network. The network integrates multi-granularity features adaptively and employs a lightweight regression head with two 1D convolution layers and global average pooling for efficient feature compression, greatly reducing parameter complexity. Requiring only image-level count labels without positional annotations, the proposed approach substantially lowers labeling costs. On a self-constructed crested wheatgrass dataset, the MGG-ISCNet achieved an MAE of 2.73, RMSE of 3.86, and R² of 0.81. Furthermore, transfer experiments on the wheat spike dataset GWHD2020 demonstrated strong generalization. The proposed method achieved the best accuracy among both instance-level and image-level supervised approaches, with MAE = 3.63, RMSE = 4.73, and R² = 0.95, while featuring significantly fewer parameters (61.08 M) compared to the existing image-level method. Overall, this work provides an efficient and lightweight solution for spike counting in crested wheatgrass and other cereal crops, offering valuable support for breeding and forage production.

Cercophora species, typically known as saprobes or coprophiles, have occasionally been isolated from healthy roots and have recently been recognized as endophytes. Their dark-pigmented structures suggest adaptation traits similar to dark septate endophytes, although their symbiotic potential remains unclear. This study isolated and characterized Cercophora sp. NPKC241 from mung bean roots grown under artificial drought in soils with different fertilization histories, using PCR-based DNA sequencing and morphological observation. Its effects on legume growth were subsequently evaluated through pot inoculation experiments under drought. These experiments focused on mung bean, a species known to exhibit significant reductions in chlorophyll content and yield under drought conditions. Among 29 isolates, Cercophora sp. consistently promoted legume growth. In mung bean, it increased shoot and root mass, chlorophyll content, and root elongation under both optimal and water-limited conditions. Under drought, inoculated plants showed approximately threefold higher chlorophyll levels, two- to threefold greater biomass, and roots approximately 5 cm longer than the control, indicating mitigation of drought-induced physiological decline. These findings suggest that Cercophora sp. can act as a beneficial root-associated fungus, enhancing legume performance under drought. Future studies will further explore this interaction by underlying physiological mechanisms and the field-level application potential.

Microplastics (MPs) and perfluorooctanoic acid (PFOA) are ubiquitously present in agroecosystems, which can cause varying degrees of environmental damage. This study reports the investigation of the effect of MPs on PFOA adsorption by soil. A comprehensive analysis was performed on the adsorption–desorption dynamics of PFOA by MPs and soil under different conditions. The surface morphology of MPs and their interaction with PFOA were characterized. Irregularly shaped MPs facilitated accurate simulation of real-world conditions, influencing the adsorption quantity of PFOA in soil. Additionally, the peak intensity of various preadsorption and post-adsorption MP functional groups was altered, indicating that MPs augmented PFOA adsorption. The kinetics of PFOA adsorption followed the quasi-second-order reaction, and the isotherm data aligned well with the Freundlich model. This study reveals the mechanism by which the co-sorption of PFOA and MPs in agroecosystems affects their respective environmental behaviors, providing basic research data for the control of pollutants in agroecosystem soil.