Hasil untuk "Agricultural industries"

Zhiqiang Li, Kun Luo, Liang Tao et al.

Electric fertilizer applicators significantly improve the uniformity, stability, and efficiency of summer maize fertilization. However, the complex soil environment in farmlands introduces uncertainties such as parameter variations, load disturbances, frictional resistance, and positioning errors, which degrade the control accuracy and robustness of the driving motor. To address these challenges, this study proposes a disturbance observer (DO)-based adaptive sliding mode control (ASMC) method. First, a control model for the soil-straw coupling system of the electric fertilizer applicator (EFA) was established, accounting for parameter variations and external load disturbances, thereby simplifying controller design. Second, a convergence rate mechanism was introduced to accelerate convergence time, ensuring the system reaches the sliding surface within a finite time, with the convergence rate being adjustable through parameter design. Additionally, a disturbance observer was designed to estimate both mismatched and matched disturbances, enabling feedforward compensation to improve tracking accuracy and reduce system chattering. Experimental results demonstrate that the proposed method achieves high control accuracy and robustness, ensuring rapid and stable state regulation for the EFA. This work provides new ideas for the design of smart agricultural machinery controllers and effectively promotes the control upgrade of agricultural electromechanical systems.

Yumeng Yang, Qi Liu, Xiaodong Gao et al.

In the past decades, extreme precipitation and drought have increased in both intensity and frequency in global drylands, threatening the sustainability of agricultural systems. To address this challenge, this study refined the process-oriented STEMMUS (simultaneous transfer of energy, mass, and momentum in unsaturated soil) model by introducing a dynamic leaf area index (LAI) development sub-module, and defined scenarios incorporating variations in precipitation amount, precipitation intensity, and temperature. These scenarios elucidate the response patterns of shallow and deep soil moisture and apple orchard evapotranspiration to climatic fluctuations. Key findings reveal that, at the interannual scale, increased growing-season precipitation significantly enhanced soil water storage in both shallow (0–200 cm) and deep (200–450 cm) layers. High-intensity precipitation partially increased soil water storage, particularly under reduced precipitation scenarios, though its contribution to deep soil remained limited. Compared to ambient temperature conditions, 2°C warming resulted in maximum reductions of 30.6 mm and 29.7 mm in shallow and deep soil water storage, respectively. Growing-season cumulative canopy transpiration (T), soil evaporation (E), and T/ET all increased significantly with greater precipitation. Conversely, high-intensity precipitation and 2°C warming reduced cumulative transpiration by 9.7–16.4 % and 7.2–18.3 %, respectively, while T/ET decreased by 4.0–9.4 % and 8.9–15.5 %. Notably, 2°C warming markedly amplified cumulative soil evaporation by 11.5–15.7 %, whereas high-intensity precipitation had no significant effect on soil evaporation. These findings provide a theoretical foundation for developing sustainable water management and climate adaptation strategies in dryland agroecosystems.

Xiaoyan XIE, Yunxi ZHANG, Ying WANG et al.

In this study, white kidney bean protein was utilized as a primary material to produce antioxidant peptides through a combined approach involving Bacillus subtilis fermentation and neutral protease treatment. The optimal processing conditions for peptide production were determined using single-factor experiments and response surface methodology, and the amino acid composition and the molecular weight distribution of the peptides were analyzed. Ultrafiltration was employed to isolate specific peptide fractions, and their antioxidant properties were assessed. The most promising antioxidant peptides were identified through liquid chromatography-tandem mass spectrometry (LC-MS/MS). Further investigation into the peptide's potential antioxidative properties was conducted through virtual screening, molecular docking, and molecular dynamics simulation. Results indicated that the ideal conditions for peptide formation were a fermentation temperature of 37.0 ℃, a fermentation period of 48.0 h, and an inoculum level of 5.0%. Under these conditions, the DPPH radical scavenging ability reached 76.12%±0.36%, and the peptide yield was 17.59%±0.16%. In WKBPs, the content of hydrophobic, basic, and acidic amino acids was relatively high, at 21.932%, 11.331%, and 20.583% respectively. The molecular weight distribution was predominantly below 3 kDa, and ultrafiltration showed that peptides with molecular weights under 3 kDa exhibited substantial antioxidant activity, as indicated by their DPPH, ABTS+, and hydroxyl radical scavenging rates, with IC50 values of 0.307, 0.310, and 0.361 mg/mL, respectively. The total antioxidant capacity was measured at 0.66±0.0018 mmol Fe2+/g at a concentration of 1 mg/mL. Among the 6364 peptide sequences analyzed, three active pentapeptides (FGWGP, FGHPEW and FGPYF) were identified, each forming a stable complex with Keap1 protein through hydrogen bonds and hydrophobic interactions. Molecular dynamics simulations indicated that these peptides could bind tightly to Keap1, forming stable conformations. This study provides both a technical guide and a theoretical foundation for further exploration and development of white kidney bean proteins and antioxidant peptide-based products.

Zhang Wenbo, Zhang Ziyang, Xi Chengyu et al.

Accurate identification of wheat varieties at the seedling stage is crucial for maintaining seed purity and optimizing field management. However, the subtle phenotypic variations among seedlings present a significant challenge for visual recognition. To address this, we propose SeedlingNet, a novel deep learning model specifically designed for fine-grained wheat seedling variety classification. The core innovations of SeedlingNet include: The Kolmogorov-Arnold-based Convolutional Attention (KCA) mechanism, which dynamically enhances feature representation by replacing static activation functions with learnable, adaptive ones; A multi-scale feature fusion architecture that integrates hierarchical features to capture both global and local characteristics. We established a comprehensive image dataset of 13,600 images representing 17 wheat varieties at the early growth stage. Experimental results demonstrate that SeedlingNet achieves a remarkable classification accuracy of 99.26 %, outperforming traditional machine learning methods and mainstream deep learning models. Ablation studies confirm the significant impact of the KCA module and the multi-scale fusion structure on the model's performance. This research provides an effective, non-destructive tool for early-stage variety identification, with strong potential for precision agriculture applications.The dataset is licensed in Zhang, Wenbo (2025), ''Seedings'', Mendeley Data, V1, doi: 10.17632/f8ykx4sz6w. 1.

Sebastian G. Nosenzo, Rafael Kelman

Agricultural residues represent a vast, underutilized resource for renewable energy. This study combines empirical analysis from 179 countries with a case study of a pelletization facility to evaluate the global potential of agricultural pelletization for fossil fuel replacement. The findings estimate a technical availability of 1.44 billion tons of crop residues suitable for pellet production, translating to a 4.5% potential displacement of global fossil fuel energy use, equating to 22 million TJ and equivalent to 917 million tons of coal annually. The economically optimized scenario projects annual savings of $163 billion and a reduction of 1.35 billion tons of CO2 equivalent in emissions. Utilizing the custom-developed CLASP-P and RECOP models, the study further demonstrates that agricultural pellets can achieve competitive pricing against conventional fossil fuels in many markets. Despite logistical and policy challenges, agricultural pelletization emerges as a scalable, market-driven pathway to support global decarbonization goals while fostering rural economic development. These results reinforce the need for targeted investment, technological advancement, and supportive policy to unlock the full potential of agricultural pellets in the renewable energy mix.

Qingmei Li, Yang Zhang, Zurong Mai et al.

Large Multimodal Models (LMMs) has demonstrated capabilities across various domains, but comprehensive benchmarks for agricultural remote sensing (RS) remain scarce. Existing benchmarks designed for agricultural RS scenarios exhibit notable limitations, primarily in terms of insufficient scene diversity in the dataset and oversimplified task design. To bridge this gap, we introduce AgroMind, a comprehensive agricultural remote sensing benchmark covering four task dimensions: spatial perception, object understanding, scene understanding, and scene reasoning, with a total of 13 task types, ranging from crop identification and health monitoring to environmental analysis. We curate a high-quality evaluation set by integrating eight public datasets and one private farmland plot dataset, containing 27,247 QA pairs and 19,615 images. The pipeline begins with multi-source data pre-processing, including collection, format standardization, and annotation refinement. We then generate a diverse set of agriculturally relevant questions through the systematic definition of tasks. Finally, we employ LMMs for inference, generating responses, and performing detailed examinations. We evaluated 20 open-source LMMs and 4 closed-source models on AgroMind. Experiments reveal significant performance gaps, particularly in spatial reasoning and fine-grained recognition, it is notable that human performance lags behind several leading LMMs. By establishing a standardized evaluation framework for agricultural RS, AgroMind reveals the limitations of LMMs in domain knowledge and highlights critical challenges for future work. Data and code can be accessed at https://rssysu.github.io/AgroMind/.

Abdelghani Belgaid, Oumnia Ennaji

Data scarcity in African agriculture hampers machine learning (ML) model performance, limiting innovations in precision agriculture. The Synthetic Agriculture Data for Africa (SAGDA) library, a Python-based open-source toolkit, addresses this gap by generating, augmenting, and validating synthetic agricultural datasets. We present SAGDA's design and development practices, highlighting its core functions: generate, model, augment, validate, visualize, optimize, and simulate, as well as their roles in applications of ML for agriculture. Two use cases are detailed: yield prediction enhanced via data augmentation, and multi-objective NPK (nitrogen, phosphorus, potassium) fertilizer recommendation. We conclude with future plans for expanding SAGDA's capabilities, underscoring the vital role of open-source, data-driven practices for African agriculture.

Md Ahmed Al Muzaddid, Jordan A. James, William J. Beksi

Multiple-object tracking (MOT) in agricultural environments presents major challenges due to repetitive patterns, similar object appearances, sudden illumination changes, and frequent occlusions. Contemporary trackers in this domain rely on the motion of objects rather than appearance for association. Nevertheless, they struggle to maintain object identities when targets undergo frequent and strong occlusions. The high similarity of object appearances makes integrating appearance-based association nontrivial for agricultural scenarios. To solve this problem we propose CropTrack, a novel MOT framework based on the combination of appearance and motion information. CropTrack integrates a reranking-enhanced appearance association, a one-to-many association with appearance-based conflict resolution strategy, and an exponential moving average prototype feature bank to improve appearance-based association. Evaluated on publicly available agricultural MOT datasets, CropTrack demonstrates consistent identity preservation, outperforming traditional motion-based tracking methods. Compared to the state of the art, CropTrack achieves significant gains in identification F1 and association accuracy scores with a lower number of identity switches.

Mihir Gupta, Abhay Mangla, Ross Greer et al.

Precision agriculture relies heavily on accurate image analysis for crop disease identification and treatment recommendation, yet existing vision-language models (VLMs) often underperform in specialized agricultural domains. This work presents a domain-aware framework for agricultural image processing that combines prompt-based expert evaluation with self-consistency mechanisms to enhance VLM reliability in precision agriculture applications. We introduce two key innovations: (1) a prompt-based evaluation protocol that configures a language model as an expert plant pathologist for scalable assessment of image analysis outputs, and (2) a cosine-consistency self-voting mechanism that generates multiple candidate responses from agricultural images and selects the most semantically coherent diagnosis using domain-adapted embeddings. Applied to maize leaf disease identification from field images using a fine-tuned PaliGemma model, our approach improves diagnostic accuracy from 82.2\% to 87.8\%, symptom analysis from 38.9\% to 52.2\%, and treatment recommendation from 27.8\% to 43.3\% compared to standard greedy decoding. The system remains compact enough for deployment on mobile devices, supporting real-time agricultural decision-making in resource-constrained environments. These results demonstrate significant potential for AI-driven precision agriculture tools that can operate reliably in diverse field conditions.

Chee Mei Ling, Thangarajah Akilan, Aparna Ravinda Phalke

Agricultural image semantic segmentation is a pivotal component of modern agriculture, facilitating accurate visual data analysis to improve crop management, optimize resource utilization, and boost overall productivity. This study proposes an efficient image segmentation method for precision agriculture, focusing on accurately delineating farmland anomalies to support informed decision-making and proactive interventions. A novel Dual Atrous Separable Convolution (DAS Conv) module is integrated within the DeepLabV3-based segmentation framework. The DAS Conv module is meticulously designed to achieve an optimal balance between dilation rates and padding size, thereby enhancing model performance without compromising efficiency. The study also incorporates a strategic skip connection from an optimal stage in the encoder to the decoder to bolster the model's capacity to capture fine-grained spatial features. Despite its lower computational complexity, the proposed model outperforms its baseline and achieves performance comparable to highly complex transformer-based state-of-the-art (SOTA) models on the Agriculture Vision benchmark dataset. It achieves more than 66% improvement in efficiency when considering the trade-off between model complexity and performance, compared to the SOTA model. This study highlights an efficient and effective solution for improving semantic segmentation in remote sensing applications, offering a computationally lightweight model capable of high-quality performance in agricultural imagery.

Hung Hon Cheng, Josie Hughes

CAFEs (Collaborative Agricultural Floating End-effectors) is a new robot design and control approach to automating large-scale agricultural tasks. Based upon a cable driven robot architecture, by sharing the same roller-driven cable set with modular robotic arms, a fast-switching clamping mechanism allows each CAFE to clamp onto or release from the moving cables, enabling both independent and synchronized movement across the workspace. The methods developed to enable this system include the mechanical design, precise position control and a dynamic model for the spring-mass liked system, ensuring accurate and stable movement of the robotic arms. The system's scalability is further explored by studying the tension and sag in the cables to maintain performance as more robotic arms are deployed. Experimental and simulation results demonstrate the system's effectiveness in tasks including pick-and-place showing its potential to contribute to agricultural automation.

Saail Narvekar, Soofiyan Atar, Vishal Gupta et al.

The growing demand for innovation in agriculture is essential for food security worldwide and more implicit in developing countries. With growing demand comes a reduction in rapid development time. Data collection and analysis are essential in agriculture. However, considering a given crop, its cycle comes once a year, and researchers must wait a few months before collecting more data for the given crop. To overcome this hurdle, researchers are venturing into digital twins for agriculture. Toward this effort, we present an agricultural framework(agriFrame). Here, we introduce a simulated greenhouse environment for testing and controlling a robot and remotely controlling/implementing the algorithms in the real-world greenhouse setup. This work showcases the importance/interdependence of network setup, remotely controllable rover, and messaging protocol. The sophisticated yet simple-to-use agriFrame has been optimized for the simulator on minimal laptop/desktop specifications.

Lina Zhang, Bin Zhao, Fan Yang et al.

Visual livestock measurement techniques offer non-contact operation, high efficiency, and reduced animal stress. However, traditional 2D imaging lacks depth data, while 3D reconstruction faces computational and environmental constraints, limiting real-world applicability. This study presents a novel RGB-D fusion method for efficient sheep morphometric analysis. Using Kinect V2 sensors, top-down and lateral RGB-D data were captured from Dorper sheep. An optimized YOLOv8pose_slimneck framework was used to detect keypoints of body dimension in color images, with depth values derived from aligned RGB-D pairs. Six body dimensions—body length, height, rump height, chest depth, chest width, and rump width—were calculated. On-farm experiment demonstrated that the automated body dimension measurements achieved <5 % error, and subsequent liveweight prediction based on these visual measurements yielded a mean error of 5.3 %. This approach demonstrates strong practical feasibility for implementing precision sheep farming.

George Papadopoulos, Maria-Zoi Papantonatou, Havva Uyar et al.

This review paper delved into the economic and environmental benefits of Digital Agricultural Technological Solutions (DATSs) in livestock farming systems. Synthesising data from 52 peer-reviewed papers it presents the outcomes of a systematic literature review on livestock farming DATSs, conducted with the use of the PRISMA methodology. The analysis highlighted the contribution of DATSs across three main livestock farming DATSs categories: Automated Milking Systems (AMS), Feed and Live Weight Measurement technologies, and Health Monitoring Systems. The results showed that AMS has the potential to boost cow productivity by up to 15 % while also reducing energy consumption by 35 %. Feed and Live Weight Measurement technologies contribute notably to sustainability and cost savings, with feed waste reductions of 75 % and feeding savings of 33 %. Health Monitoring Systems are especially effective in improving herd health and productivity through early detection of clinical issues, which directly enhances animal welfare and farm efficiency. Environmentally, AMS and health monitoring tools play a vital role in reducing greenhouse gas emissions, with AMS lowering global warming potential by up to 5.83 %. Overall, the findings of this review highlight the potentials of livestock DATSs towards economic viability and environmental sustainability, suggesting that the wider adoption could offer substantial benefits for the livestock farming sector. Up to now, DATSs have shown great potential in dairy cattle by improving milk yield, quality, and animal health, with advancements such as AMS increasing productivity and health monitoring systems enhancing early disease detection. In contrast, their application in sheep, goats, and pigs is still in its early stages, mainly limited to basic health monitoring and feeding technologies, despite the economic importance of these species, especially in the Mediterranean area, where most of the studies are conducted.

Beketova K.N., Kurmash A.Sh., Rysmakhanova G.Zh.

After Russia’s war against Ukraine, the U.S. and Western Europe imposed heavy sanctions on Russia, affecting multiple industries. Since most of Kazakhstan’s exports to Europe pass through Russia, the country faces indirect economic challenges. These sanctions create additional difficulties for Kazakh exporters.This study examines the status of key industries and export changes by analyzing Kazakhstan’s recent economy. A SWOT analysis using KazData covers major export products, including oil, natural gas, metals, wood, and agricultural raw materials.Findings reveal that sanctions on Russia have disrupted Kazakhstan’s exports, causing market instability and artificial commodity shortages. The analysis offers insights for economists and scholars studying the broader economic consequences of these sanctions.

Deng Pan, Menghao Xia, Chuanzhen Li et al.

Abstract Background Pesticide resistance is a serious problem that threatens crop industries. Major resistance towards pyridaben, an acaricidal inhibitor of mitochondrial electron transport complex I (METI-Is), has been reported in tetranychids following its extensive use worldwide. Understanding mechanisms of pyridaben resistance is crucial for sustainable resistance management. Results The inheritance of pyridaben resistance was incompletely recessive and controlled by multiple genes in P. citri, which was determined by reciprocal crosses and backcross experiments. Bulked segregant analysis was performed to identify gene loci underlying pyridaben resistance. Subsequently, the two PSST-subunit mutations H107R and the previously undiscovered V103I mutation were positively correlated with pyridaben resistance in different populations or strains by single mite genotyping. The bioassay further showed that H107R contributed to moderate resistance, while V103I in combination with H107R was responsible for a very high level of resistance in homozygous P. citri strains. These contributions to pyridaben resistance were also verified in transgenic Drosophila through the introduction of the wildtype, single- or double-mutated P. citri PSST subunit. In addition, life-table analysis and behavioral measures were conducted to assess the fitness cost associated with resistance development. Accompanied by reduced ATP levels and complex I activity, a fitness cost was observed as reduced fecundity and lower mobility due to PSST mutations. Conclusions Our findings provide direct evidence that PSST mutations conferred the evolution of pyridaben resistance but simultaneously led to a fitness cost due to functional defects in complex I. These data provide theoretical insights into sustainable resistance management in agricultural production.

Gong Cheng, Zhanling Wu, Xiaonan Guo et al.

Bashang Plateau in China serves as an ecological barrier against wind-driven sand invasion and is a vital water conservation area in the Beijing-Tianjin-Hebei region. Since the 1990s, the expansion of the vegetable industry has increased irrigation demand and actual groundwater extraction, threatening regional water security and ecological stability. This study aims to quantify crop-specific water consumption and explore sustainable planting structures that reduce agricultural water use while maintaining economic and ecological viability. We analyzed the temporal dynamics of dominant crop planting areas (corn, beans, naked oats, oilseeds, coarse cereals, sugar crop, potatoes, and vegetables), and the spatial-temporal characteristics of regional precipitation, temperature, and soil moisture distribution from 2000 to 2020. Crop-specific evapotranspiration (ET) was measured through field experiments (2021–2022), and the nondominated sorting genetic algorithm II (NSGA-II) was employed to generate sustainable planting structures under 10 %, 20 %, and 30 % regional water-saving targets. Over two decades, planting structure shifted toward water-intensive crops, peaking during 2013–2016 before declining due to water scarcity and market dynamics. The 10 % water reduction scenario (S1) proved feasible by reducing the planting area of potatoes and vegetables and increasing coarse cereals (particularly in Shangyi and Kangbao, with lower precipitation), maintaining economic benefits and ecosystem service value. However, 20 % and 30 % reduction (S2, S3) caused economic losses of 6 % and 12.7 %, respectively, due to coarse cereals could not fully offset losses from reduced potato and vegetable production. Balancing groundwater sustainability with agricultural productivity requires optimizing planting structures, supported by improved irrigation technologies and policy incentives. The findings emphasize the need for a balanced crop restructuring strategy, prioritizing high-value crops while limiting water-intensive crops to ensure a sustainable agricultural system in this ecologically sensitive region.

E. Mathiowitz

Kasara Sai Pratyush Reddy, Y. Roopa, N KovvadaRajeevL et al.

Agriculture balances both food requirement for mankind and supplies indispensable raw materials for many industries, and it is the most significant and fundamental occupation in India. The advancement in inventive farming techniques is gradually enhancing the crop yield making it more profitable and reduce irrigation wastages. The proposed model is a smart irrigation system which predicts the water requirement for a crop, using machine learning algorithm. Moisture, temperature and humidity are the three most essential parameters to determine the quantity of water required in any agriculture field. This system comprises of temperature, humidity and moisture sensor, deployed in an agricultural field, sends data through a microprocessor, developing an IoT device with cloud. Decision tree algorithm, an efficient machine learning algorithm is applied on the data sensed from the field in to predict results efficiently. The results obtained through decision tree algorithm is sent through a mail alert to the farmers, which helps in decision making regarding water supply in advance.

Chung Hee Kim, Abhisesh Silwal, George Kantor

Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system for autonomous pepper harvesting designed to operate in these unprotected, complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the feasibility and effectiveness of leveraging imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings.