Aiming at precise evaluation of the performance of soybean seed metering devices, a photoelectric sensor-based real-time monitoring system was designed. The proposed system mainly included a photoelectric sensor module for seeding signal collecting, Hall sensors speeding module, microcontroller unit (MCU), light and sound alarm module, human–machine interface (HMI), and other parts. The indexes of miss, multiples, flow rate, and application rate were estimated on the basis of seeder speed, seed metering disk rotation rate, photoelectric sensor signals, and clock signals. These real-time statistics of the seeding process were recorded by seeding management system. The laboratory results showed that the detection errors of seeding quantity of both big- and small-diameter soybeans were less than 2.0%. Miss and multiples index estimated by this system were 0.4% and 0.5% than that of seeding image monitoring platform (SIMP), respectively. In field tests, miss and multiples index can be used to evaluate the performance of seed metering device, and big-diameter seeds can be detected more precisely than small ones by these photoelectric sensors. This system can provide support for evaluation of working performance of seed metering devices and have a positive effect on seeding monitoring technology.

The rapid and accurate detection of weeds is the prerequisite and foundation for precision weeding, automation, and intelligent field operations. Due to the wide variety of weeds in the field and their significant morphological differences, most existing detection methods can only recognize major crops and weeds, with a pressing need to enhance accuracy. This study introduces a novel weed detection approach that integrates the GFPN (Green Feature Pyramid Network), Slide Loss, and multi-SEAM (Spatial and Enhancement Attention Modules) to enhance accuracy and improve efficiency. This approach recognizes crop seedlings utilizing an improved YOLO v8 algorithm, followed by the reverse detection of weeds through graphics processing technology. The experimental results demonstrated that the improved YOLO v8 model achieved remarkable performance, with an accuracy of 92.9%, a recall rate of 87.0%, and an F1 score of 90%. The detection speed was approximately 22.47 ms per image. And when shooting from a height ranging from 80 cm to 100 cm in the field test, the crop detection effect was the best. This reverse weed detection method addresses the challenges posed by weed diversity and complexities in image recognition modeling, thereby contributing to the enhancement of automated and intelligent weeding efficiency and quality. It also provides valuable technical support for precision weeding in farmland operations.

Variable-rate technology (VRT) has been paid more attentions by farmers in an attempt to match inputs to local growing conditions efficiently. Farmers in every country are highly encouraged to adopt this practice rather than uniform-rate application (URA). However, the standard methods and design used to quantify application accuracy for VRT remain lacking. Therefore, a variable-rate liquid fertilization control system was designed to meet accurate fertilization demand. The designed control system could enable the real-time proportion and mixture of three kinds of liquid fertilizers, namely, N, P and K, in accordance with decision support subsystem. The task controller reads related information and sends such data to the control system, which is responsible for fertilization operation. The controller could realize liquid fertilizer adjusting through the electromagnetic flow control valves. A high-precision flow meter could measure the fertilization amount, which is sent as feedback to the controller to form a closed-loop control system based on the improved proportional-integral-derivative (PID) control algorithm that could enhance the stability and accuracy of precision variable-rate liquid fertilization control systems. Comparisons between the actual and planned application rates indicated good performance for both static and field experimental trials. Mathematical models and transfer functions for some functional modules were then constructed by classical theories to derive a system characteristic equation. To verify the static and dynamic performances, the control system was simulated using the Simulink module on Matlab. Results showed that the variable-rate fertilization was in accordance with the planned data and that the signal trace effect was good. The error was less than 5% for fertilization amount and fertilizer proportion, respectively, and the control response time was 6 s. Keywords: fertilization control system, variable-rate technology, precision fertilization, closed-loop control system, improved PID control algorithm, Simulink DOI: 10.25165/j.ijabe.20181101.2583 Citation: Zhang J C, Hou S Y, Wang R T, Ji W Y, Zheng P, Wei S. Design of variable-rate liquid fertilization control system and its stability analysis. Int J Agric & Biol Eng, 2018; 11(1): 109–114.

With the global energy structure transitioning toward low-carbon and sustainable development, improving the stability and predictability of renewable energy generation has become a key challenge for achieving carbon neutrality goals. However, photovoltaic power output exhibits significant variability and uncertainty, and accurate power forecasting is of great significance for optimizing grid dispatch, improving renewable energy integration capacity, and reducing system reserve requirements. Therefore, this paper proposes a multi-stage prediction model that integrates Ensemble Empirical Mode Decomposition (EEMD), Improved Whale Optimization Algorithm-based Variational Mode Decomposition (IWOA-VMD), and an Improved Sparrow Search Algorithm (ISSA)-optimized Bidirectional Gated Recurrent Unit (BiGRU) network. Specifically, EEMD is first used to decompose the photovoltaic power sequence to extract Intrinsic Mode Functions (IMFs); then, the residual IMF is further decomposed using IWOA-optimized VMD to enhance low-frequency modeling capability; next, ISSA adaptively optimizes the hidden layer dimensions and learning rate of the BiGRU; Finally, each component is predicted individually, and the overall power sequence is reconstructed. Experimental results based on publicly available real photovoltaic data demonstrate that the proposed model outperforms BiGRU and several hybrid models in terms of MAE and RMSE. The research findings contribute to improving the accuracy of photovoltaic power forecasting, thereby providing technical support for the low-carbon transition and sustainable development of energy systems.

The massive quantities of genetic data generated by high-throughput sequencing pose challenges to data storage, transmission and analyses. These problems are effectively solved through data compression, in which the size of data storage is reduced and the speed of data transmission is improved. Several options are available for compressing and storing genetic data. However, most of these options either do not provide sufficient compression rates or require a considerable length of time for decompression and loading. Here, we propose TRCMGene, a lossless genetic data compression method that uses a referential compression scheme. The novel concept of two-step compression method, which builds an index structure using K-means and k-nearest neighbours, is introduced to TRCMGene. Evaluation with several real datasets revealed that the compression factor of TRCMGene ranges from 9 to 21. TRCMGene presents a good balance between compression factor and reading time. On average, the reading time of compressed data is 60% of that of uncompressed data. Thus, TRCMGene not only saves disc space but also saves file access time and speeds up data loading. These effects collectively improve genetic data storage and transmission in the current hardware environment and render system upgrades unnecessary. TRCMGene, user manual and demos could be accessed freely from https://github.com/tangyou79/TRCM. The data mentioned in this manuscript could be downloaded from: https://github.com/tangyou79/TRCM/wiki.

: To improve the efficiency of rhizobial inoculation operations and address the current situation of rhizobial inoculation being labor-intensive, a spraying and control system for variable rate application (VRA) of liquid rhizobia was developed. The system can accurately regulate the spraying rate of liquid rhizobia according to the desired rate of rhizobia by incremental Proportional Integral Derivative (PID) closed-loop control algorithm, making it particularly suitable for precise spraying with small amounts. In the laboratory experiment of precise flow control, variation coefficient of spraying nozzle from 0.10 MP to 0.20 MP pressure were no more than 1.2%. A clear linear relationship was observed between the spraying rate and pressure. The maximum response time was 1.93 seconds, while the average response time was 1.62 seconds when controlling the spraying system for small amounts. Field trial was conducted in Heilongjiang Agricultural Xianghe Farm of China. Average seeds number and 100-seed weight of soybean plant with rhizobia inoculation treatment were better than control group, and average yield of spraying liquid rhizobia agent with full base fertilizer increased by 232.5 kg/hm2, representing a significant 7.4% improvement over the control group. The results of these trails clearly showed the positive effect of the spraying and control system for liquid rhizobial inoculation, which has superior to existing inoculation manners, and provides an important technical support for the widespread adoption of rhizobia technology.