IoT-based system of prevention and control for crop diseases and insect pests

Spectroscopic detection of cotton Verticillium wilt by spectral feature selection and machine learning methods

Introduction

Verticillium wilt is a severe soil-borne disease that affects cotton growth and yield. Traditional monitoring methods, which rely on manual investigation, are inefficient and impractical for large-scale applications. This study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt.

Methods

We conducted comprehensive hyperspectral measurements using handheld devices (350-2500 nm) to analyze cotton leaves in a controlled greenhouse environment and employed Unmanned Aerial Vehicle (UAV) hyperspectral imaging (400-995 nm) to capture canopy-level data in field conditions. The hyperspectral data were pre-processed to extract wavelet coefficients and spectral indices (SIs), enabling the derivation of disease-specific spectral features (DSSFs) through advanced feature selection techniques. Using these DSSFs, we developed detection models to assess both the incidence and severity of leaf damage by Verticillium wilt at the leaf scale and the incidence at the canopy scale. Initial analysis identified critical spectral reflectance bands, wavelet coefficients, and SIs that exhibited dynamic responses as the disease progressed.

Results

Model validation demonstrated that the incidence detection models at the leaf scale achieved a peak classification accuracy of 85.83%, which is about 10% higher than traditional methods without feature selection. The severity detection models showed improved precision as disease severity of damage increased, with accuracy ranging from 46.82% to 93.10%. At the canopy scale, UAV-based hyperspectral data achieved a remarkable classification accuracy of 93.0% for disease incidence detection.

Discussion

This study highlights the significant impact of feature selection on enhancing the performance of hyperspectral-based remote sensing models for cotton wilt monitoring. It also explores the transferability of sensitive spectral features across different scales, laying the groundwork for future large-scale early warning systems and monitoring cotton Verticillium wilt.

Integration of smart sensors and IOT in precision agriculture: trends, challenges and future prospectives

Traditional farming methods, effective for generations, struggle to meet rising global food demands due to limitations in productivity, efficiency, and sustainability amid climate change and resource scarcity. Precision agriculture presents a viable solution by optimizing resource use, enhancing efficiency, and fostering sustainable practices through data-driven decision-making supported by advanced sensors and Internet of Things (IoT) technologies. This review examines various smart sensors used in precision agriculture, including soil sensors for moisture, pH, and plant stress sensors etc. These sensors deliver real-time data that enables informed decision-making, facilitating targeted interventions like optimized irrigation, fertilization, and pest management. Additionally, the review highlights the transformative role of IoT in precision agriculture. The integration of sensor networks with IoT platforms allows for remote monitoring, data analysis via artificial intelligence (AI) and machine learning (ML), and automated control systems, enabling predictive analytics to address challenges such as disease outbreaks and yield forecasting. However, while precision agriculture offers significant benefits, it faces challenges including high initial investment costs, complexities in data management, needs for technical expertise, data security and privacy concerns, and issues with connectivity in remote agricultural areas. Addressing these technological and economic challenges is essential for maximizing the potential of precision agriculture in enhancing global food security and sustainability. Therefore, in this review we explore the latest trends, challenges, and opportunities associated with IoT enabled smart sensors in precision agriculture.

Exploitation of volatile organic compounds for rice field insect-pest management: current status and future prospects

Insect pests are major biotic factors that cause significant damage to rice crops, posing a major challenge to global rice production. Synthetic pesticides are the most effective and reliable technique for pest management. However, their high cost, non-biodegradability, and adverse effects on human and environmental health have driven the search for more sustainable, eco-friendly, and economically viable alternatives. Recently, Volatile Organic Compounds (VOCs), both plant-derived or synthetically made, have emerged as a promising tool for insect pest management in diverse agricultural practices. Rice plants continuously release VOCs that facilitate tritrophic interactions among the plants, their herbivores, and the natural enemies of these herbivores, highlighting their ecological importance. VOCs are being explored as semiochemicals in pest management strategies in various crops, including rice. Although applications of VOCs remain in the laboratory stage, they hold great promise for future field implementation. This review highlights the role of rice VOCs in herbivore-natural enemy interactions and explores the factors regulating their release. It provides a comprehensive analysis of recent advancements, ongoing challenges, and prospects in using VOCs for rice pest management. Additionally, the review emphasizes the integration of VOCs with precision agriculture and genetic engineering approaches along with advanced monitoring technologies, to develop sustainable and effective pest management practices in rice agroecosystems.

Individual action, sharing scarce resources, sharing information? A study on how to effectively manage forest pests and diseases based on carbon trading

In recent years, forest pests and diseases have had a significant impact on forest ecosystems. To incentivize corporations to manage forest pests and diseases, the government provides certain carbon compensations to enterprises involved in this management. In the process of controlling forest pests and diseases, the modes of collaboration between the government and corporations are primarily categorized into three modes: independent action, scarce resource sharing, and information sharing. To determine the applicability of each relational mode, this paper constructs three differential game models and compares and analyzes the equilibrium results obtained from these modes. The research indicates that if the cost of government-managed forest pest and disease control is high and the benefits of such control are low, then the scarce resource sharing mode can offer the government the maximum benefit; conversely, the information sharing mode can provide the government with the greatest benefit. If the cost and benefits of corporate-managed forest pest and disease control are low, then the information sharing mode can offer corporations the maximum benefit; otherwise, the scarce resource sharing mode can provide corporations with the greatest benefit.

Portable solutions for plant pathogen diagnostics: development, usage, and future potential

The increasing prevalence of plant pathogens presents a critical challenge to global food security and agricultural sustainability. While accurate, traditional diagnostic methods are often time-consuming, resource-intensive, and unsuitable for real-time field applications. The emergence of portable diagnostic tools represents a paradigm shift in plant disease management, offering rapid, on-site detection of pathogens with high accuracy and minimal technical expertise. This review explores portable diagnostic technologies' development, deployment, and future potential, including handheld analyzers, smartphone-integrated systems, microfluidics, and lab-on-a-chip platforms. We examine the core technologies underlying these devices, such as biosensors, nucleic acid amplification techniques, and immunoassays, highlighting their applicability to detect bacterial, viral, and fungal pathogens in diverse agricultural settings. Furthermore, the integration of these devices with digital technologies, including the Internet of Things (IoT), artificial intelligence (AI), and machine learning (ML), is transforming disease surveillance and management. While portable diagnostics have clear advantages in speed, cost-effectiveness, and user accessibility, challenges related to sensitivity, durability, and regulatory standards remain. Innovations in nanotechnology, multiplex detection platforms, and personalized agriculture promise to further enhance the efficacy of portable diagnostics. By providing a comprehensive overview of current technologies and exploring future directions, this review underscores the critical role of portable diagnostics in advancing precision agriculture and mitigating the impact of plant pathogens on global food production.