Agricultural Tasks Research Articles

Can Distributed Ledgers Help to Overcome the Need of Labeled Data for Agricultural Machine Learning Tasks?

Can Distributed Ledgers Help to Overcome the Need of Labeled Data for Agricultural Machine Learning Tasks?

Retracted: Optimization of Agricultural Machinery Task Scheduling Algorithm Based on Multiobjective Optimization

Retracted: Optimization of Agricultural Machinery Task Scheduling Algorithm Based on Multiobjective Optimization

Assessing genetic diversity and population structure of Iranian melons (Cucumis melo) collection using primer pair markers in association with resistance to Fusarium wilt.

We evaluated genetic diversity and population structure of Iranian melons (Cucumis melo L.) using combinations of 35 primer pairs: 15 Simple-Sequence-Repeats (SSR); 10 Inter-Simple-Sequence-Repeats (ISSR); and 10 Sequence-related amplified polymorphism (SRAP) markers in association with resistance to melon Fusarium wilt, caused by Fusarium oxysporum f. sp. melonis (FOM). Genetic similarity was determined by simple matching coefficient (SSM) and dendrogram by clustering-analysis with unweighted pair groups using arithmetic averages (UPGMA). By combining ISSR-SSR-SRAP markers, a high degree of variation among the melons was detected. The mean polymorphism information content (PIC), marker index (MI), effective-number of alleles (I), expected heterozygosity (H), and Nei's gene diversity parameters were 0.392, 0.979, 1.350, 0.551 and 0.225, respectively. According to MI, PIC, I, H, and Nei indices evaluation, ISSR6, ISSR9, SRAP3, SRAP5, SSR3 and SSR6 had the best performance in genetic diversity of the related melons population. The 35 primers yielded a total of 264 bands, of which 142 showed polymorphism. Clustering of genotypes based on resistance to Fusarium wilt, and comparison with grouping on SSR, SRAP and ISSR marker revealed a significant compliance between disease severity and molecular marker dendrograms. Thus, increasing the number of molecular markers for genetic diversity provides a powerful tool for future agricultural and conservation tasks.

Modeling and forecasting tasks of agriculture based on machine learning

Continuous advances in computer technology have provided good support for the expansion of agricultural research using machine learning. This article considered the current problem of yield forecasting using methods and algorithms of machine learning to support management decision-making in the agricultural sector. For a set of data collected from five districts of the Issyk-Kul region, such as weather conditions, soil characteristics and pre-processing of the sowing area, a study of the yield of various crops using advanced machine learning algorithms, such as the support vector method, k-nearest neighbors, variants of gradient boosting and random forest, etc., is demonstrated. To assess the accuracy of the models, a comparative analysis with the results of multiple regression was carried out. It is shown that powerful regression machine learning algorithms like k-nearest neighbors (KNN), random forest (RF), support vector method (SVR) and gradient boosting (GBR) give tangible results in prediction compared to other machine learning methods (MAPE=10%). The calculation results showed the effectiveness of using algorithms with ensemble methods to solve the problems of yield forecasting, and that environmental factors (weather conditions) have a greater impact on yield than soil genotype.

Продуктивность севооборота в зависимости от систем применения удобрений в длительном опыте

The problem of increasing soil fertility is one of the main tasks of agriculture in the Udmurt Republic and the Non-Chernozem region. The most acceptable way of solving this problem is biologisation, which provides for a decrease in the amount of chemicals and an increase in the amount of biologicalagents. If there is a lack of fertiliser, the use of green manure or straw alone will not solve the problem. On acidic soils, a complex action on the soil is needed, starting with liming and the use of optimal doses of mineral fertiliser, which help to increase land productivity and crop rotation in a short period of time. Since 1971, the Udmurt Research Institute of Agriculture has been studying different fertilizer systems in 8-field crop rotations (1 – fallow; 2 – winter rye; 3 – potato, corn; 4 – spring wheat; 5 – clover; 6 – clover; 7 – winter rye; 8 – barley). Factor A are backgrounds: 0 – “zero” [10]; I2 – lime per one hydrolytic acidity (4.9 t/ha CaCO3) in the first rotation + two hydrolytic acidities (7.5 t/ha) in the second rotation; Н5С – manure 40 (first rotation) + 60 t/ha (2d‑5th rotations) + green manure (6th rotation); L2M5GM – lime + manure + green manure similarly. Factor B are options. Options without fertiliser and NPK are considered. Lime reduced soil acidity to a neutral level, slightly increased in the 4th rotation. The content of P2O5, K2O, and humus reached the highest level in the 5th rotation on manured backgrounds, resulting in 3.23 and 3.31 tce/ha in six rotations (18.3 and 22.0% more than without fertiliser). In lime and manure systems, mineral fertiliser increased crop rotation productivity by 32.4–35.7% on average over the entire period. Optimal doses for 3.0–4.0 t grain units/ha were 40–50 kg NPK/ha. Reducing the doses from 40–60 to 10–30 kg/ha of NPK in the last two rotations led to a decrease in crop rotation productivity (2.74–2.84) by 0.41–0.49 t grain units /ha. The lime-organomineral fertiliser system in the 3d, 4th and 5th rotations with “the addition of micronutrient fertiliser (zinc for winter rye, cobalt for potatoes, copper for spring wheat and barley, boron and molybdenum for clover)” [9] provided the highest crop rotation productivity – 4.67; 4.25; 3.32 t grain units/ha, with the highest increases – 2.05; 1.12; 1.05 t grain units/ha or 78.2; 35.8; 46.2%, respectively, in rotations. Manure can only be replaced periodically with a pea-oat mixture.

A novel design for carrying out automated agricultural tasks using an agriculturally developed robot

This paper gives the design and development of a precision farming robot. Since a long time ago, agriculture has been a significant part of the Indian economy. 18% of India's gross domestic product is produced by the agriculture sector (GDP). A better answer for precision agriculture is provided by robotics and the internet of things. Selective harvesting is necessary when picking fruits or vegetables like tomatoes and apples. In traditional farming, each fruit is hand-picked by a worker, requiring a huge amount of labour to carry out selective farming. We suggest a robot that helps farmers with a variety of labor-intensive chores, such as selective crop harvesting and qualitative segregation, while also simultaneously providing data on crop health, soil nutritional status, and crop shelf-life detection. An android application is used to analyse, process, and send the obtained data to the farmer. Later, the weight, colour, and health of the particular crop are checked to grade its quality. The fruit is subsequently moved into the designated container after being graded. Spoiled or overripe fruits and vegetables would be plucked and dropped so as not to interfere with the plant's growth. A harvesting arm on the proposed robot would reach the fruit or vegetable and pick it from the plant or tree. The fruit would then be transferred to the appropriate container. With the aid of the app, the user would be able to give the device a certain task based on his requirements. Crop health monitoring, segregation, and selective harvesting all require image processing using a camera. Additionally, using image processing, illnesses are found. The image segmentation and pre-processing are being done by us. The guided, supervised, and advanced machine learning technique k-nearest neighbours (KNN) is used to build solutions for both classification and regression issues. This gives the farmer useful information that is essential for choosing the correct insecticides, herbicides, and fertilisers for higher yield. Every nation's primary issue and developing topic is agriculture automation. The need for food is rising rapidly as the world's population is growing at an extremely rapid rate. Farmers must apply toxic pesticides more frequently since their traditional methods are insufficient to meet the growing demand. This damages the soil. This has a significant impact on agricultural practises, and as a result, the land remains unproductive and desolate. You can employ a variety of automation techniques, including IOT, wireless communications, machine learning, artificial intelligence, and deep learning. The work given here is a mini-project that is taken up as a part of the curriculum completed by lectronics and communication engineering students in the second year of the electronics & communication engineering department at Dayananda Sagar College of Engineering in Bangalore.

IoT BASED DESIGN AND DEVELOPMENT OF SOLAR ASSISTED PESTICIDE SPRINKLER

Pesticide spraying is an important agricultural task that preserves crops from pests, diseases, and insect infestation and controls weeds. This conventional sprayer causes user fatigue because of its huge and bulky construction. We make this design and fabrication of a model that is a solar sprinkler, this will ergonomically eliminate the back attachment of the sprayer, reducing the user's fatigue level. Solar panels generate electricity by converting sunlight into electrical energy. This energy is used to power the entire system and the energy is stored in a battery which can be used to power the devices when sunlight is not available. The fuel-powered spray pump's engine will be eliminated resulting in reduced vibrations and noise. Our technique is going to be less harmful to the environment as we eliminate the fuel that is used. The NODE MCU contains an ESP8266 Wi-Fi module connected to the l298n motor driver module which controls all motors via an application created using the Internet of Things (IoT) application called blynk. The Blynk application is used to control and monitor the entire assembly.

Standardizing and Centralizing Datasets for Efficient Training of Agricultural Deep Learning Models.

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural datasets. This lack of agriculture-specific fine-tuning potentially increases training time and resource use, and decreases model performance, leading to an overall decrease in data efficiency. To overcome this limitation, we collect a wide range of existing public datasets for 3 distinct tasks, standardize them, and construct standard training and evaluation pipelines, providing us with a set of benchmarks and pretrained models. We then conduct a number of experiments using methods that are commonly used in deep learning tasks but unexplored in their domain-specific applications for agriculture. Our experiments guide us in developing a number of approaches to improve data efficiency when training agricultural deep learning models, without large-scale modifications to existing pipelines. Our results demonstrate that even slight training modifications, such as using agricultural pretrained model weights, or adopting specific spatial augmentations into data processing pipelines, can considerably boost model performance and result in shorter convergence time, saving training resources. Furthermore, we find that even models trained on low-quality annotations can produce comparable levels of performance to their high-quality equivalents, suggesting that datasets with poor annotations can still be used for training, expanding the pool of currently available datasets. Our methods are broadly applicable throughout agricultural deep learning and present high potential for substantial data efficiency improvements.

Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images.

Accurate segmentation and detection of rice seedlings is essential for precision agriculture and high-yield cultivation. However, current methods suffer from high computational complexity and poor robustness to different rice varieties and densities. This article proposes 2 lightweight neural network architectures, LW-Segnet and LW-Unet, for high-precision rice seedling segmentation. The networks adopt an encoder-decoder structure with hybrid lightweight convolutions and spatial pyramid dilated convolutions, achieving accurate segmentation while reducing model parameters. Multispectral imagery acquired by unmanned aerial vehicle (UAV) was used to train and test the models covering 3 rice varieties and different planting densities. Experimental results demonstrate that the proposed LW-Segnet and LW-Unet models achieve higher F1-scores and intersection over union values for seedling detection and row segmentation across varieties, indicating improved segmentation accuracy. Furthermore, the models exhibit stable performance when handling different varieties and densities, showing strong robustness. In terms of efficiency, the networks have lower graphics processing unit memory usage, complexity, and parameters but faster inference speeds, reflecting higher computational efficiency. In particular, the fast speed of LW-Unet indicates potential for real-time applications. The study presents lightweight yet effective neural network architectures for agricultural tasks. By handling multiple rice varieties and densities with high accuracy, efficiency, and robustness, the models show promise for use in edge devices and UAVs to assist precision farming and crop management. The findings provide valuable insights into designing lightweight deep learning models to tackle complex agricultural problems.

Warm Soil, Westerly Wind, and Wet Feet: Feeling and Measuring Ecological Time in the Roman World

Although climate change, pollution, and environmental degradation are contemporary problems, these are also challenges with deep historic roots in antiquity. 2,000years ago, during the Roman Climate Optimum, a period of unusually warm, wet, and stable temperatures in the Mediterranean from roughly 200 BCE to 150 CE, the Romans altered the natural environment so greatly that they produced a level of pollution that was unparalleled until the Industrial Revolution. It is precisely in this contradictory time of unusually productive growth and destruction that we discover a blossoming of textual and visual ecological calendars illustrating how the Romans experienced the changing Mediterranean seasons. Roman agricultural treatises instruct us on specific agricultural tasks based on celestial movement, the arrival of particular winds, and on corporeal sensations, such as the warmth of the soil. Literary texts from the period portray kinship and shared corporeality between farmers and plants, with parent farmers listening to and assisting plant-children in achieving their desires. The concept of measuring time by means of the human body and its sensations is most explicit in the agricultural mosaics of the Late Roman period, which depict enslaved workers laboring, sweating, stomping, plowing, and performing seasonal tasks. While much of the conceptualization of indigenous ecological calendars is framed within the context of modern states, juxtaposing ancient predecessors and contemporary practices offers a new perspective on this topic.

A reliable and low-cost deep learning model integrating convolutional neural network and transformer structure for fine-grained classification of chicken Eimeria species

Chicken coccidiosis is a disease caused by Eimeria spp. and costs the broiler industry more than 14 billion dollars per year globally. Different chicken Eimeria species vary significantly in pathogenicity and virulence, so the classification of different chicken Eimeria species is of great significance for the epidemiological survey and related prevention and control. The microscopic morphological examination for their classification was widely used in clinical applications, but it is a time-consuming task and needs expertise. To increase the classification efficiency and accuracy, a novel model integrating transformer and convolutional neural network (CNN), named Residual-Transformer-Fine-Grained (ResTFG), was proposed and evaluated for fine-grained classification of microscopic images of seven chicken Eimeria species. The results showed that ResTFG achieved the best performance with high accuracy and low cost compared with traditional models. Specifically, the parameters, inference speed and overall accuracy of ResTFG are 1.95M, 256 FPS and 96.9%, respectively, which are 10.9 times lighter, 1.5 times faster and 2.7% higher in accuracy than the benchmark model. In addition, ResTFG showed better performance on the classification of the more virulent species. The results of ablation experiments showed that CNN or Transformer alone had model accuracies of only 89.8% and 87.0%, which proved that the improved performance of ResTFG was benefit from the complementary effect of CNN's local feature extraction and transformer's global receptive field. This study invented a reliable, low-cost, and promising deep learning model for the automatic fine-grain classification of chicken Eimeria species, which could potentially be embedded in microscopic devices to improve the work efficiency of researchers and extended to other parasite ova, and applied to other agricultural tasks as a backbone.

Development of technical appearance of human-machine interface for group control of unmanned robots when performing agricultural tasks

Abstract One of the promising areas of using robotic systems (RS) is group control of robots. The means of ensuring the operator's interaction with autonomous RS for monitoring and remote control - the human-machine interface (HMI) of the robotic systems, are discussed in the paper. The foreign and domestic publications describing existing approaches and priority directions to the construction of HMIs for various types of robotic systems - ground and air, as well as modern commercial solutions in this area are analyzed in the paper. The performed analysis allows us to conclude that the most popular and convenient type of human-machine interface for the types of robotic systems under consideration today is a digital application with a graphical interface. To implement complex scenarios of human-machine interaction, combinations of several methods are used, such as: a digital application with a graphical interface, virtual reality tools, gesture recognition, voice commands. The technical appearance of the man-machine interface of group unmanned robots based on the results of the analysis was developed. It ensures the prompt formulation of the applied problem to be solved and the subsequent control of its execution by the operator. The proposed solution is intuitive and flexible, which provides the user with a higher speed of information processing. Key words Group robotics, human-machine interface (HMI), group control of robots, HMI architecture, robotic system.

Technical vision system of qadcopter for precision farming

Precision farming is a modern direction of agricultural development, which opens new opportunities to increase the productivity of each land by taking into account its specific features. Its implementation requires an assessment of the spatial heterogeneity of soils and agricultural vegetation. This ensures the timely application of adequate agricultural measures in those places that need it.
 In this work, ways of solving the problems of precision farming are analyzed. The expediency of using a quadcopter with a technical vision system to obtain high-resolution images of the studied land plot is shown.
 Specialized systems of technical vision for the tasks of precision agriculture are currently not mass-produced. Therefore, a block diagram of the quadcopter's technical vision system was developed, which made it possible to determine the necessary technical characteristics and select the appropriate industrial equipment.
 Necessary software and algorithms were developed for the technical vision system. The proposed algorithm is based on the use of high-quality images from the technical vision system of the quadcopter, low-resolution satellite images and the results of agrochemical analyzes. When processing data, individual images taken with a quadcopter camera are combined into a single orthofotoplan. Then NDVI indicators from satellite images and results of agrochemical analyzes are added to it. The identified zones of plant fertility make it possible to build a differentiated fertilizer application map and a map of the agro-operations task plan for precision farming equipment.
 To verify the results, studies were conducted on a test site with an area of 57.4 hectares, which was located in the Chaplin district of Kherson region. With the help of the selected equipment and the developed algorithms, images of the area were obtained, an orthofotoplan with plant germination zones was formed, and a map of fertilizer application for precision farming equipment was developed. Field studies fully confirmed the correctness of the calculations and the performance of the proposed algorithms.

Comparison of Performance in Mechanised Agricultural Tasks Between Precision and Conventional Agriculture on Farms in Tolima (Colombia)?

Purpose: Agricultural work in Colombia, particularly in small and medium-sized farms, is lagging behind in terms of technology; advances such as precision agriculture (PA) are unknown. This project managed to promote the implementation of PA technologies in the primary tasks of land adaptation, by comparing efficiency indices when conventional practices were used against the use of new technologies. Theoretical framework: The company CasaToro SA, with its John Deere® agricultural line, allowed the implementation of StarFire TM6000®, 4240® Monitors, Auto Track 200®, and JDLink® technologies, and the use of T3RRA CUTTA® software, in tractors of its brand in different farms in Tolima, Colombia. Method/design/approach: Measurements of time and area worked in situ were taken and the data obtained were statistically compared using Analysis of Variance (ANOVA). Results and conclusion: Finding significant differences in tasks such as contour line drawing, which reported a decrease of up to 30% in the time needed in h ha–1, and in primary tillage with discs with increases of up to 13% of the tilled area in ha h–1. Research implications: In conclusion, in Tolima, which has extensive areas of agricultural production, the implementation of PA can improve yields and reduce production costs. Originality/value: To demonstrate the benefits of PA.

Data analytics for crop management: a big data view

Recent advances in Information and Communication Technologies have a significant impact on all sectors of the economy worldwide. Digital Agriculture appeared as a consequence of the democratisation of digital devices and advances in artificial intelligence and data science. Digital agriculture created new processes for making farming more productive and efficient while respecting the environment. Recent and sophisticated digital devices and data science allowed the collection and analysis of vast amounts of agricultural datasets to help farmers, agronomists, and professionals understand better farming tasks and make better decisions. In this paper, we present a systematic review of the application of data mining techniques to digital agriculture. We introduce the crop yield management process and its components while limiting this study to crop yield and monitoring. After identifying the main categories of data mining techniques for crop yield monitoring, we discuss a panoply of existing works on the use of data analytics. This is followed by a general analysis and discussion on the impact of big data on agriculture.

STUDY OF PATHOGENICITY OF FIELD STRAINS OF XANTHOMONAS CAMPESTRIS BACTERIA

Gram-negative bacterium Xanthomonas campestris, which is the causative agent of bacterial diseases of many cultivated plants, annually leads to significant economic losses in many sarans of the world. The development of modern methods of combating this phytopathogen is an urgent task for agriculture. One of the promising methods is the use of bacteriophages, the selection of which requires working directly with bacteria that have pathogenic properties in relation to natural host plants. This paper presents the results of studying the pathogenicity of the existing collection of microorganisms in relation to various varieties of cabbage. 38 strains of Xanthomonas campestris bacteria were used as the object of the study. The pathogenicity of the selected crops was studied by methods of studying hypersensitivity on tobacco plants and by infiltration into natural host plants. Studies have shown that the bacteria had varying degrees of activity in relation to cabbage varieties F1, Agamer 611 and Siberian 60. At the same time, 21 of the 38 strains studied showed their pathogenic properties on plants of all three varieties. In most cases, characteristic V-shaped lesions were found on the leaves of plants, which eventually led to the withering of the entire leaf. In some cases, necrosis was observed at the sites of inoculation of the studied strain of bacteria. Analysis of the time of manifestation of symptoms of bacteriosis showed that strains previously isolated from affected plants visually showed their pathogenic properties 5-6 days earlier than strains isolated from seed material. The obtained results will be used in the future to select bacteriophages with the greatest spectrum of action against bacteria with pathogenic properties.

Modeling of Fuzzy Cognitive Maps with a Metaheuristics-Based Rainfall Prediction System

Rainfall prediction remains a hot research topic in smart city environments. Precise rainfall prediction in smart cities becomes essential for planning security measures before construction and transportation activities, flight operations, water reservoir systems, and agricultural tasks. Precise rainfall forecasting now becomes more complex than before because of extreme climatic changes. Machine learning (ML) approaches can forecast rainfall by deriving hidden patterns from historic meteorological datasets. Selecting a suitable classification method for forecasting has become a tough job. This article introduces the Fuzzy Cognitive Maps with a Metaheuristics-based Rainfall Prediction System (FCMM-RPS) technique. The intention of the FCMM-RPS technique is to predict rainfall automatically and efficiently. To accomplish this, the presented FCMM-RPS technique primarily pre-processes the rainfall data to make it compatible. In addition, the presented FCMM-RPS technique predicts rainfall using the FCM model. To enhance the rainfall prediction outcomes of the FCM model, the parameter optimization process is performed using a modified butterfly optimization algorithm (MBOA). The performance assessment of the FCMM-RPS technique is tested on a rainfall dataset. A widespread comparison study highlights the improvements of the FCMM-RPS technique in the rainfall forecasting process compared to existing techniques with a maximum accuracy of 94.22%.

Sensor-Driven Human-Robot Synergy: A Systems Engineering Approach

Knowledge-based synergistic automation is a potential intermediate option between the opposite extremes of manual and fully automated robotic labor in agriculture. Disruptive information and communication technologies (ICT) and sophisticated solutions for human-robot interaction (HRI) endow a skilled farmer with enhanced capabilities to perform agricultural tasks more efficiently and productively. This research aspires to apply systems engineering principles to assess the design of a conceptual human-robot synergistic platform enabled by a sensor-driven ICT sub-system. In particular, this paper firstly presents an overview of a use case, including a human-robot synergistic platform comprising a drone, a mobile platform, and wearable equipment. The technology framework constitutes a paradigm of human-centric worker-robot logistics synergy for high-value crops, which is applicable in operational environments of outdoor in-field harvesting and handling operations. Except for the physical sub-system, the ICT sub-system of the robotic framework consists of an extended sensor network for enabling data acquisition to extract the context (e.g., worker's status, environment awareness) and plan and schedule the robotic agents of the framework. Secondly, this research explicitly presents the underpinning Design Structure Matrix (DSM) that systematically captures the interrelations between the sensors in the platform and data/information signals for enabling synergistic operations. The employed Systems Engineering approach provides a comprehensible analysis of the baseline structure existing in the examined human-robot synergy platform. In particular, the applied DSM allows for understanding and synthesizing a sensor sub-system's architecture and enriching its efficacy by informing targeted interventions and reconfiguring the developed robotic solution modules depending on the required farming tasks at an orchard. Human-centric solutions for the agrarian sector demand careful study of the features that the particular agri-field possesses; thus, the insight DSM provides to system designers can turn out to be useful in the investigation of other similar data-driven applications.

Farmers' attitudes towards agricultural plastics – Management and disposal, awareness and perceptions of the environmental impacts

The amount of plastic waste resulting from agricultural practices is increasing and this trend is expected to continue. Although plastics are essential for certain farming tasks, their impact on the environment is becoming a major issue of concern. Mismanaged larger plastics can disintegrate into microplastics and make their way into soils, surface and groundwater sources. Microplastics are extremely persistent and have the potential to facilitate the transfer of contaminants through the environment, potentially affecting terrestrial and aquatic wildlife. A descriptive survey was conducted on a sample of farmers (n = 430) in Ireland to assess their attitudes on agricultural plastic waste management and their awareness and perceptions of the impacts of microplastics and plastics on the environment. This study found that most farmers (88.2%) are concerned about the amount of plastic waste generated by farming activities. Agricultural plastic disposal methods vary and recycling rates mostly depend on the type of plastic, the cost of recycling and access to facilities. Most farmers view agricultural plastics negatively due to their impact on the environment but also because of the monetary and logistical burdens associated with them. Farmers were relatively aware of microplastics (57.5%), but overall more farmers felt they knew more about plastic pollution than microplastic pollution and these issues in aquatic systems. This was also evident when it came to their perception of the risks plastics pose on the environment with more farmers believing that aquatic environments are at greater risk than the terrestrial environments. Future research efforts must focus on plastic and microplastic pollutions in soils to inform policy-makers and to create greater public awareness. In addition to this, several developments are needed in a collective effort by governments, policy-makers and other stakeholders to reduce plastic and microplastic problems in agriculture.

Prevalence of occupational injury among vegetable cultivators of West Bengal, India

Manual agricultural task is an accident prone task in the harsh working environment, with occupation related health problem and injuries. They are exposed to extensive usage of primitive tools, bearing awkward working postures, handling of chemicals during long working hours. This study thus aims at studying the prevalence of occupational injury of vegetable cultivators in North 24 Parganas, West Bengal. A cross-sectional study on 181 male vegetable cultivators using traditional and/or modern agricultural techniques was conducted using predesigned survey questionnaire and direct observation of the mode of work. It was observed that 68% of mechanized workers and 86% of traditional workers suffered from cut accident (p<0.05). Traditional workers are more prone to occupational injuries like cut, fracture, sprain injury, etc. rather than mechanized cultivators, hinting at reduced work performance. Ergonomic interventions viz., natural working posture, work-rest schedule and optimization of body movements are required to reduce the prevalent accident frequency.