• Research Article

    Early detection of Fusarium wilt in Pepper using multispectral images based on UAV
    Gang-In Je, Chan-Seok Ryu, Jong-Chan Jeong, Chang-Hyeok Park, Ye-Seong Kang
    Pepper (Capsicum annuum L.) is an essential seasoning vegetable in Korean food. However, pepper cultivation is constrained by various viruses. Especially, … + READ MORE
    Pepper (Capsicum annuum L.) is an essential seasoning vegetable in Korean food. However, pepper cultivation is constrained by various viruses. Especially, Fusarium wilt is an economic problem threatening pepper production in many countries. The peppers were transplanted on May 2, and the multispectral images were taken on June 28, July 27, and August 26. There were 30 sampling points to measure the vegetation of pepper, but Fusarium wilt infection was confirmed in 15 samples on July 27 and 11 samples on August 25. Therefore, the possibility of Fusarium wilt detection on July 27 and August 25 was confirmed using the multispectral image taken on June 28 and July 27. It was possible to build models for detecting infected peppers using machine learning (KNN; K-Nearest Neighbors, SVM; Support Vector Machine, LR; Logistic Regression) and applying backward elimination to remove the 9 VIs ranked via correlation analysis with the ratio of train and test as 8:2, 7:3, and 6:4. In the case of the disease detection on July 27 using the image of June 28, the KNN model with 8 Vis was selected as the best model with a 7:3 ratio. However, the LR model with NDRE was chosen as the best model for disease detection on July 27 and August 25 using the images of June 28 and July 27 with a 8:2 ratio. The performance of the model which excluded the non-infected samples on August 25 was the best with DVI, TCARI, and RVI as 0.783, 0.733, 0.917, and 0.815 for the calibration and 0.909, 0.833, 1.000, and 0.909 for the validation in order of accuracy, precision, recall, and F1 score. Moreover, there was no error that the infected pepper was confirmed as the non-infected pepper in the convolution matrix. This study aims to develop models for early detection of Pepper Fusarium wilt by calculating vegetation indices based on reflectance values extracted from UAV-based multispectral images and applying them to machine learning classification algorithms. The model developed in this study is expected to contribute to improving the productivity of peppers by preventing the spread of disease through the early detection of pepper wilt. - COLLAPSE
    31 December 2024
  • Research Article

    Development of a feedforward-based path tracking algorithm with steering bias compensation for an auto-guided tractor
    Yeon-Tae Kim, Yong-Hyun Kim, Hak-Jin Kim
    As the commercialization of self-driving agricultural machinery advances, domestic farmers are increasingly purchasing auto-guidance steering kits for agricultural operations. However, due to … + READ MORE
    As the commercialization of self-driving agricultural machinery advances, domestic farmers are increasingly purchasing auto-guidance steering kits for agricultural operations. However, due to the characteristics of the hydrostatic steering system in tractors, oil leakage can lead to steering bias during operation. While a wheel angle sensor can mitigate this issue, they incur additional costs. Moreover, using a wheel angle sensor to correct steering bias may introduce a delay, particularly when disturbances occur during agricultural tasks. This study developed a compensation algorithm for an auto-guidance system that operates without a wheel angle sensor, ensuring both accuracy and stability in path tracking. The proposed compensation algorithm predicts steering bias based on motor encoder from the tractor’s electric power steering system, eliminating the need for a steering angle sensor. It employed a feedforward method to compensate for steering bias in real time, enabling rapid response to disturbances and addressing the inherent limitation of the hydrostatic steering system. To control path tracking, the stanley algorithm was fused with a PID controller. Field experiments were conducted with various tractor models equipped with an automatic steering system. The results demonstrated that the path tracking system, incorporating the proposed compensation algorithm, closely followed straight reference paths. The system achieved a root mean square error of lateral deviation as low as 2 cm and heading errors of less than 1.1 degrees, confirming its effectiveness and precision. - COLLAPSE
    31 December 2024
  • Research Article

    Mechanization in conservation agriculture and options for sustainable intensification by smallholder farmers in Kenya: A review
    Nzuki Lewis, Tusan Park
    This paper examines the uptake of Conservation Agriculture (CA) in semi-arid areas of Kenya, underscoring the disparities in adoption rates between large-scale … + READ MORE
    This paper examines the uptake of Conservation Agriculture (CA) in semi-arid areas of Kenya, underscoring the disparities in adoption rates between large-scale farms and smallholder agricultural operations. It stresses the significance of fostering cooperation among different stakeholders, including extension services, researchers, non-governmental organizations (NGOs) and policymakers, to facilitate the incorporation of mechanization in semi-arid regions. This collaborative endeavor is aimed at equipping farmers with the requisite knowledge, resources and tools to effectively embrace and put into practice CA methods, ultimately leading to increased agricultural productivity and improved food security in challenging environments. - COLLAPSE
    31 December 2024
  • Review Article

    Recent advancement in direct delivery of active ingredients into plants: A shift from traditional approach to targeted precision: A review
    Vinayak Hegde, Mahesh P. Bhat, Dajeong Shin, Kyeong-Hwan Lee
    The agricultural sector heavily relied on active ingredients (AI) such as fungicides, insecticides, herbicides, growth hormones, and micro/macronutrients to enhance crop productivity. … + READ MORE
    The agricultural sector heavily relied on active ingredients (AI) such as fungicides, insecticides, herbicides, growth hormones, and micro/macronutrients to enhance crop productivity. Traditional AI application methods, such as foliar sprays and soil treatments, face significant challenges that impact efficiency and environmental safety. These methods often lead to uneven distribution, poor translocation due to environmental factors, and loss of AIs through runoff. Additionally, they can contribute to environmental pollution and harm non-target organisms, including beneficial insects and soil microbes. In contrast, novel approaches in direct delivery, particularly microneedles (MNs) and trunk injectors (TIs) have emerged to address these challenges. These platforms allow precise application of AIs by penetrating the outer protective layer of the plant and directly targeting vascular tissues, thereby enhancing the efficacy and environmental safety of AI applications. However, these systems exhibit limitations like tissue damage, clogging, or breaking of needles during the application which can affect efficiency. This review explores the development, mechanisms, and applications of MNs and TIs in AI delivery. Further, it compares them with traditional methods while evaluating their potential to mitigate resistance development in plants subjected to biological and environmental challenges. This review highlights the transformative potential of MN and TI platforms in precision and sustainability in AI applications. By enabling direct, and site-specific application of AIs, these technologies can help reduce runoff, high AI usage, exposure of non-target organisms, and environmental contamination. - COLLAPSE
    31 December 2024
  • Review Article

    Exploring microplastics as a macro problem for agricultural lands and terrestrial ecosystems: A review focuses on the research insights and challenges
    Md. Injamum-Ul Hoque, Md Mahfuzur Rahman, Ashim Kumar Das, Mohammod Ali, S.M. Ahsan, Aniruddha Sarker
    Microplastics (MPs) are persistent pollutants that pose significant environmental challenges globally. The primary reservoir of MPs is soil, which is a thin … + READ MORE
    Microplastics (MPs) are persistent pollutants that pose significant environmental challenges globally. The primary reservoir of MPs is soil, which is a thin stratum formed by rock weathering. However, our understanding of MPs' environmental and ecological impacts remains incomplete. The movement, transport, distribution, and ultimate fate of MPs in soil ecosystems, as well as their uptake by plants, are influenced by their physicochemical properties, soil characteristics, agricultural practices, and the heterogeneity of the soil biosphere. MPs have been identified as vectors for various environmental contaminants, and the mechanisms of their adsorption that affect soil properties have been explored. This review also describes how MP-induced stress impairs plant growth and physiological function by altering soil productivity. To scientifically assess MP contamination, methods for isolating and examining soil MPs have been outlined, contrasting the merits and limitations of different techniques and highlighting the potential challenges. Promising technologies for MP removal and degradation have been identified, including physicochemical and biological methods along with their mechanisms and determining factors. Among biological approaches, phytoremediation has emerged as a leading sustainable method, gaining prominence owing to the limitations of conventional techniques, and is briefly discussed here as a future prospect. Drawing on recent research and relevant case studies, a range of practical solutions is suggested. Furthermore, the necessity for cross-sector and cross-jurisdictional collaboration to effectively address this pressing environmental issue is emphasized. The insights from this study contribute to a broader understanding of microplastics and offer valuable information for policymakers, researchers, and stakeholders. - COLLAPSE
    31 December 2024