As an important step in image processing, image segmentation can be used to determine the accuracy of object counts, and area and contour data. In addition, image segmentation is indispensable in seed testing research. Due to the uneven grey level of the original image, traditional watershed algorithms generate many incorrect edges, resulting in oversegmentation and undersegmentation, which affects the accuracy of obtaining seed phenotype information. The DMR-watershed algorithm, an improved watershed algorithm based on distance map reconstruction, is proposed in this paper. According to the grey distribution characteristics of the image, the grey reduction amplitude h was selected to generate the mask image with the same grey distribution trend as that of the original image. The original greyscale map was reconstructed with corresponding thresholds selected according to the false minima of different regions that are to be segmented, which generates an accurate distance map that eliminates the wrong edges. An adzuki bean (Vigna angularis L.) image was selected as the experimental material and the residual rate of the segmentation counting results of each algorithm was investigated in two cases of two-particle adhesion and multiparticle adhesion. The results of the proposed algorithm were compared with those of the traditional watershed algorithm, edge detection algorithm and concave point analysis algorithm which are commonly used for seed segmentation. In the case of two-particle adhesion, the residual rates of the watershed algorithm and edge detection algorithm were 0.233 and 0.275, respectively, while the residual rate of the concave point analysis algorithm was 0 which proved to be suitable for two-particle adhesion. In the case of multiparticle adhesion, the concave point analysis algorithm was not applicable because it would destroy the seed image. The residual rates of the watershed algorithm and edge detection algorithm were 0.063 and 0.188, respectively, while the residual rate of the proposed algorithm in the two-particle adhesion cases was 0 and the counting accuracy reached 100%, which proved the effectiveness of the proposed algorithm. The algorithm in this paper significantly improves the accuracy of image segmentation of adherent seeds, and provides a new reference for image segmentation processing in seed testing.

Saline-alkali land is an important reserve cultivated land resource, and increasing soybean yield in it is significant for food security. As soybean is sensitive to saline-alkali stress, planting it in such soil often causes problems like blocked root development and yield decline. In this study, field experiments were carried out in coastal saline-alkali land in Huanghua City, Hebei Province. Jidou 12 with strong saline-alkali tolerance was selected, and four treatments (CK:conventional fertilization;T1:conventional fertilization + 75L/hm²Bacillus subtilis 8–32 agent; T2:conventional fertilization + 75L/hm²Bradyrhizobium liaoningense CCBAU05525;T3:conventional fertilization + 75L/hm²Bacillus subtilis 8–32 agent and 75L/hm²Bradyrhizobium liaoningense CCBAU05525). Through data analysis, the effects of co-inoculation of Bacillus subtilis and Rhizobium on soybean yield, soil properties, enzyme activity and bacterial community composition were studied. The results showed that T3 significantly increased soybean yield to 3182.67 kg/hm², with yield, grains per pod and 100-grain weight increasing by 18.03%, 18.6% and 2.7% respectively compared with CK. The pH, electrical conductivity and total water-soluble salt content of rhizosphere soil decreased by 2.8%, 11.0% and 5.4%, while water and organic matter content increased by 5.6% and 11.6%. The activities of alkaline phosphatase, sucrase, urease and catalase increased by 14.9%, 22.4%, 15.1% and 5.2%. Co-inoculation increased the relative abundance of Sphingomonas. There was no significant difference in the Ace and Chao indices, indicating no significant difference in OTU number. The Shannon index of T1 was lower, meaning lower bacterial community species diversity. Co-inoculation improved plant stress resistance by enhancing the rhizosphere soil environment, regulating the microbial community structure and soil salinity, promoting soybean yield formation. It provides a theoretical basis for scientific fertilization and soil improvement in saline-alkali soybean planting.

As extreme rainfall events become more frequent, leading to increased waterlogging hazards, it is crucial to explore various drainage methods that can alleviate the adverse effects of waterlogging on crop growth, thus addressing challenges related to global food security. Field experiments were carried out to evaluate the impacts of different drainage technologies on waterlogging mitigation, rice growth, dry matter accumulation, and yield. The experimental setup included varying straw blind ditch spacings (2, 3, 4, and 5 m) and subsurface pipe drainage spacings (6, 9, and 12 m), with surface drainage serving as the control (CK). The findings revealed that, in comparison to pipe drainage treatments, blind ditch treatments enhanced subsurface drainage volume by 15.1%. Regarding groundwater levels and soil moisture, the soil moisture in the 0–90 cm soil layer and groundwater levels under the blind ditch treatments were 11.3% and 6.1% lower than those under the CK as well as 22.0% and 23.9% lower than the pipe drainage treatments, respectively. Subsurface drainage treatments led to significant improvements in rice yield, with blind ditch and pipe drainage treatments increasing the yield by 8.0% and 6.0% compared to the CK. Rice yields initially increased before decreasing as burial spacing reduced. The S3 treatment resulted in yield increases of 14.4%, 8.6%, and 10.7% over the S2, S4, and S5 treatments, respectively. The G9 treatment produced 3.6% and 10.4% higher yields compared to the G6 and G12 treatments. The highest rice yield, 7.501 Mg·ha⁻¹, was achieved with a blind ditch spacing of 3 m. Compared to the S4 and S5 treatments, the yield per hectare for the S3 treatment was higher by 0.592 Mg and 0.726 Mg, while the input cost was higher by CNY 3038 and 4560, respectively. Path analysis indicated that root biomass made the largest direct contribution (0.517) to the increase in rice yield. Subsurface drainage contributed to the regulation of soil moisture, reducing leaf biomass while increasing stem biomass, which enabled the blind ditch treatments to produce optimal rice yield. These results provide a scientific basis for agricultural drainage in waterlogged areas.

Wheat (Triticum aestivum L.) is one of the significant food crops in the world, and the number of wheat ears serves as a critical indicator of wheat yield. Accurate quantification of wheat ear counts is crucial for effective scientific management of wheat fields. To address the challenges of missed detections, false detections, and diminished detection accuracy arising from the dense distribution, small size, and high overlap of wheat ears in Unmanned Aerial Vehicle (UAV) imagery, we propose a lightweight model, PSDS-YOLOv8 (P2-SPD-DySample-SCAM-YOLOv8), on the basis of the improved YOLOv8 framework, for the accurate detection of wheat ears in UAV images. First, the high resolution micro-scale detection layer (P2) is introduced to enhance the model’s ability to recognize and localize small targets, while the large-scale detection layer (P5) is eliminated to minimize computational redundancy. Then, the Spatial Pyramid Dilated Convolution (SPD-Conv) module is employed to improve the ability of the network to learn features, thereby enhancing the representation of weak features of small targets and preventing information loss caused by low image resolution or small target sizes. Additionally, a lightweight dynamic upsampler, Dynamic Sample (DySample), is introduced to decrease computational complexity of the upsampling process by dynamically adjusting interpolation positions. Finally, the lightweight module Spatial Context-Aware Module (SCAM) is utilized to accurately map the connection between small targets and global features, enhancing the discrimination of small targets from the background. Experimental results demonstrate that the improved PSDS-YOLOv8 model achieves Mean Average Precision(mAP) 50 and mAP50:95 scores of 96.5% and 55.2%, which increases by 2.8% and 4.4%, while the number of parameters is reduced by 40.6% in comparison with the baseline YOLOv8 model. Compared to YOLOv5, YOLOv7, YOLOv9, YOLOv10, YOLOv11, Faster RCNN, SSD, and RetinaNet, the improved model demonstrates superior accuracy and fewer parameters, exhibiting the best overall performance. The methodology proposed in this study enhances model accuracy while concurrently reducing resource consumption and effectively addressing the issues of missed and false detections of wheat ears, thereby providing technical support and theoretical guidance for intelligent counting of wheat ears in UAV imagery.

To discuss the water consumption patterns of winter wheat (Triticum aestivum L.) and the difference in yield traits among varieties under different irrigation systems, three field water treatments were established (jointing water, W1, CK; jointing water + flowering water, W2; and rising water + booting water + filling water, W3). Two winter wheat varieties (Hengmai4399 and Hengguan35) were selected in 2020–2021, and three (Hengmai4399, Hengguan35, and Hengmai28) were selected in 2021–2022 to investigate the impact of the irrigation amount on water consumption and its interaction with the varieties on yield traits of winter wheat. The results showed that there was a positive and significant correlation between soil water consumption and soil moisture reserve presowing; the correlation was the strongest in the 150–200 cm layer. The response of the yield of the three varieties to irrigation was Hengmai4399 > Hengmai28 > Hengguan35, and the drought resistance was Hengguan35 > Hengmai28 > Hengmai4399. When the soil water storage presowing was insufficient, Hengmai4399 combined with the W3 treatment achieved the highest yield and water use efficiency; when the soil water storage presowing was sufficient, Hengmai28 combined with the W2 treatment achieved a high-level yield and the highest WUE.