Search Results (3,040)

Orchard production involves intensive labor requirements, limited operational periods, and highly dynamic and complex working environments. Consequently, the development of intelligent orchard robots has become a important approach to enhancing production efficiency and reducing reliance on manual operations. This review focuses on the demands of autonomous robotic systems operating in challenging orchard scenarios and provides a comprehensive overview of key technologies, including environmental perception and semantic cognition, autonomous navigation and environmental modeling, intelligent task execution, and collaborative robotic systems. Recent advances in fruit and blossom detection, branch and canopy structure perception, multi-modal sensor fusion for localization, semantic mapping, robotic harvesting control, variable-rate spraying, precision pollination, and autonomous intra-row weed management are systematically discussed. Furthermore, emerging technologies such as multi-robot coordination, robot–UAV cooperation, large language models (LLMs), and vision-language models (VLMs) for enhancing decision-making capabilities in agricultural robotics are reviewed. Finally, the existing challenges of orchard robots in terms of perception reliability, long-term autonomous navigation, operational robustness, system-level integration, and standardized performance evaluation are analyzed, followed by discussions on potential future research directions. Full article

Acetamiprid (ACE) and fipronil (FIP) are extensively applied broad-spectrum insecticides. They are recalcitrant to degradation and accumulate along food chains, creating prominent residual hazards to food security and ecological environments. Herein, a high-stability competitive electrochemical immunosensor was established for quantitative detection of ACE and FIP. Cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS) characterized the layer-by-layer assembly of sensing interfaces, verifying the validity of competitive immune recognition. Under optimal conditions, the sensor exhibited linear ranges of 0.49–125.0 ng/mL for ACE and 0.49–62.5 ng/mL for FIP, with all determination coefficients (R² > 0.99). The limits of detection (LODs) reached 0.33 ng/mL and 0.25 ng/mL, respectively. Spike-recovery detection on six fruit and vegetable matrices yielded recoveries of 84.63–100.80% with RSDs less than 7.8%, which confirmed excellent consistency between the immunosensor and standard LC-MS. This sensing platform combines fast response, high sensitivity, and superior stability, delivering a novel technical approach for rapid on-site screening of trace ACE and FIP residues in agricultural and environmental samples, and offering technical support for food safety supervision and pesticide risk assessment. Full article

Vertical farming (VF) offers a smart way to grow crops in stacked layers inside controlled indoor environments. By doing so, it uses far less land and water than traditional open-field agriculture, making it a promising solution for cities with limited space and resources. In recent years, artificial intelligence (AI), machine learning (ML), and Internet of Things (IoT) technologies have begun to transform vertical farming. These tools are moving the industry away from rigid, rule-based systems toward more flexible, data-driven operations that can adapt in real time. This paper presents a systematic review of 208 peer-reviewed studies from 2015 to 2025. It explores how AI, ML, and IoT are applied across the VF ecosystem, focusing on key areas such as computer vision for disease detection, crop growth and yield prediction, smart climate control, and precision nutrient and irrigation management. This review examines the performance of different algorithms, including Convolutional Neural Networks (CNNs), Random Forest, XGBoost, and LSTMs across hydroponic, aeroponic, and aquaponic systems. The review also covers IoT setups with multi-sensor networks, edge-cloud computing, and automated control systems. Commercial farms have shown real gains in resource efficiency and shorter supply chains. However, challenges remain: high energy use (especially from LED lighting, which makes up 40–60% of costs), expensive setup, scattered datasets, and limited real-world testing. Many high-accuracy claims (>95%) come from lab conditions and need better validation in actual farms. Overall, AI-powered vertical farming has strong potential to support resilient urban food systems. Future work should focus on lightweight edge AI models, improved data standards, explainable AI, and robust life cycle assessments to ensure the benefits outweigh the environmental and economic costs. Full article

Accurate mapping of crop residue cover (CRC) is important for sustainable agricultural management because residue supports soil health, erosion control, and carbon sequestration. Traditional ground-based CRC methods are labor-intensive and spatially limited, increasing interest in UAV-based remote sensing. UAVs can carry RGB, multispectral, and hyperspectral sensors, which capture different spectral information for distinguishing crop residue from soil. This study compared four high-spatial-resolution (2.5 cm) UAV imagery types—RGB, multispectral, visible–near-infrared (VNIR) hyperspectral, and shortwave infrared (SWIR) hyperspectral—for fine-scale CRC classification. A fully connected neural network (FCNN) was developed to classify residue and soil pixels. Performance was evaluated using two complementary approaches: pixel-level accuracy assessment based on manually delineated image samples and plot-level validation against residue percentages derived from ground photos. Results showed that high pixel-level classification accuracy values were achieved across all imagery types, with overall accuracies above 94%. However, plot-level validation revealed that sensor performance depended on the evaluation metric considered. Multispectral imagery produced the highest R² with ground photo-derived reference CRC values (R² = 0.672). These results indicate that greater spectral dimensionality did not necessarily improve plot-level CRC estimation under the tested field conditions. More importantly, the findings show that high pixel-level classification accuracy does not necessarily translate into stronger plot-level CRC estimation, highlighting the importance of using complementary validation approaches when evaluating UAV-based CRC estimation. Full article

Agriculture is increasingly challenged by water scarcity, climate change, and rising energy demands, requiring more efficient and sustainable irrigation solutions. Conventional irrigation systems often lack the capability to adapt their operation to changing soil conditions and renewable energy availability, resulting in inefficient water and energy use. This study proposes a digital twin-based framework for energy management and irrigation optimization in photovoltaic (PV)-powered smart agriculture systems using Internet of Things (IoT) soil monitoring. The proposed system integrates a physical irrigation infrastructure, an IoT monitoring network, a fuzzy logic control layer, and a digital twin environment that periodically synchronizes the virtual model with IoT measurements to support the system representation and decision-making. The digital twin models soil moisture, temperature, nutrient levels, PV energy generation, battery state of charge, and irrigation water consumption. The virtual representation was periodically aligned with the physical system using measurements transmitted through the long-range (LoRa)-based network. An energy-aware irrigation scheduling strategy was developed to optimize irrigation timing based on soil conditions, battery status, and solar energy availability. The framework was evaluated using field data collected in a real apple orchard through an ESP32-based IoT platform and a standalone PV-powered irrigation system; quantitative experimental validation was performed for the soil twin. The results demonstrate high soil twin synchronization accuracy, with an overall RMSE of 1.47 percentage points and R² of 0.981, based on experimental field measurements. The energy twin and irrigation twin were evaluated using experimentally acquired sensor data together with model-based performance assessment, demonstrating the potential of the proposed digital twin framework for integrated water–energy management in smart agriculture. Full article

Agricultural machinery is rapidly developing toward electrification, intelligence, and autonomy, and the electric drive chassis has become a key technology for improving power transmission performance, operational efficiency, and energy utilization. This paper presents a review of research on electric drive chassis for agricultural machinery, focusing on four major aspects: electric drive systems, anti-slip and stability control of electric drive chassis, autonomous navigation system control technologies, and energy management strategies. The electric drive system is reviewed from the perspectives of drive motor technologies and drive architectures. Chassis control technologies are mainly discussed in terms of longitudinal anti-slip control and lateral stability control under complex terrain conditions. Autonomous navigation systems are summarized with respect to multi-source environmental perception, path planning, and path tracking control. Energy management strategies are classified into rule-based, optimization-based, and learning-based approaches according to their control principles, and the characteristics and applicable scenarios of each approach are analyzed. On this basis, the collaborative relationships among drive architecture, chassis control, autonomous navigation, and energy management are further discussed. Finally, future research directions are proposed, including highly integrated electric drive systems, vehicle-level collaborative control, multi-source sensor fusion, hybrid model-driven and data-driven control, global energy optimization, and multi-machine cooperative operation. This review provides a reference for the design and development of intelligent electric drive chassis for agricultural machinery. Full article

This scoping review synthesizes 35 studies on sensor technologies and artificial intelligence for fruit detection, classification, and quality assessment, contrasting Latin American and international research traditions. The analysis suggests notable differences in technological approaches between the included Latin American and international studies: Latin American research tends to emphasize in developing accessible, practical solutions using classical computer vision and low-cost hardware, while international studies more frequently employ through deep learning architectures, multi-modal sensing, and complete robotic automation systems. Across the included studies, relatively limited attention was given to AI-assisted decision support for agricultural practitioners, insufficient consideration of inclusivity, and the scarce integration of environmental sustainability into intelligent sensing system design. The review identifies that only 8 of 35 studies originate from Latin America, suggesting an uneven geographical distribution of the available evidence. The included studies generally reported high accuracy values, yet these findings must be interpreted with caution given the reliance on curated datasets that may not represent real-world variability. The reviewed evidence suggests that future research may benefit not from one approach dominating the other, but from a thoughtful integration of complementary strategies, including knowledge transfer, edge computing democratization, and human-centered design. Overall, this review suggests that the ultimate goal extends beyond accuracy metrics to the transformation of agricultural practices that enhance food security, economic development, and environmental sustainability across the global agricultural landscape. It is important to note that this work does not propose or validate a new fruit detection algorithm but rather synthesizes and critically evaluates existing scientific evidence regarding sensor technologies and artificial intelligence applied to fruit detection and quality assessment. Full article

Binocular stereo vision is a low-cost and scalable 3D perception technology that shows strong potential in agricultural phenotyping and smart agriculture. By estimating depth from multi-view RGB images, it enables non-contact, high-precision sensing of crop structure, canopy morphology, growth dynamics, and livestock traits, providing essential support for digital and intelligent agricultural production. With recent advances in deep learning-based stereo matching, multimodal sensor fusion, and 3D reconstruction, its robustness and accuracy in complex field environments have been significantly improved. This paper systematically reviews recent progress in agricultural applications of binocular stereo vision, covering system architectures, traditional and deep learning-based stereo matching methods, point cloud reconstruction techniques, and emerging supervision strategies such as 3D Gaussian splatting. It further summarizes key applications, including high-throughput phenotyping, fruit localization and robotic harvesting, weed detection and precision spraying, autonomous navigation, and livestock body condition assessment, highlighting its role in multi-task agricultural perception systems. Finally, the paper discusses major challenges, including low-texture matching difficulty, occlusions in complex environments, cross-domain generalization, real-time lightweight deployment, and limited dataset availability. Future directions are outlined in foundation model-based visual perception, self- and weakly supervised learning, multimodal fusion, and edge-efficient model design, aiming to support large-scale deployment in smart agriculture. Full article

Wearable sensors provide significant potential for continuous animal monitoring. However, the practical implementation of such technologies on livestock farms for animal monitoring raises significant challenges related to power efficiency, robustness, and reliability. In this research paper, we propose the design, implementation, and field testing of a low-energy, low-cost, multi-sensor wearable collar specifically designed for continuous monitoring of ruminants using LoRa. The proposed collar is based on a modular hardware platform that incorporates inertial sensing, temperature sensing, and wireless communication, with special attention to sensor choice, location on the body, casing, and mounting mechanism. Reduced weight, environmental protection, and long-term wearability without affecting animal behavior are the primary focus in the hardware design. Power optimization management strategies, including sleep mode and duty cycling functionality, are implemented to maximize autonomy and battery lifetime and are evaluated under realistic operating scenarios. Field deployment was conducted in a ruminant farm, where the wearable devices operated flawlessly for a long time period. Characteristic sensor data are collected, including accelerometer readings induced by animal movement, variability in received signal strength (RSSI), and animal temperature. The system demonstrates stable operation, satisfactory data completeness and consistency on multi-day basis. The knowledge acquired brings into focus the practical challenges and design issues associated with the use of wearable sensors in livestock and offers insights into designing efficient sensor collars for precision livestock farming. Full article

As smart agriculture gradually shifts from single-yield monitoring toward the coordinated optimization of input efficiency, resource conservation, and farm profitability, the use of multi-source agricultural data to support precise water, fertilizer, and pesticide inputs has become an important issue. To address the inconsistent sampling frequencies, heterogeneous semantic scales, and difficulty in directly modeling input–profit relationships among field images, meteorological environments, soil states, and agricultural management records, a Multimodal Agricultural Input–Output Optimization Network, termed MAION, is proposed. In this framework, a unified plot–time-window agricultural state representation is constructed through a cross-modal spatiotemporal alignment module. The potential effects of different input behaviors on yield, cost, and net profit are estimated through an input–output causal profit modeling module, and profit-driven reinforcement learning is further used to generate input strategies oriented toward long-term net profit maximization. Since the task belongs to yield, cost, and profit regression prediction and continuous agricultural decision optimization rather than classification or recognition, classification metrics such as accuracy, precision, and recall were not adopted. Instead, RMSE, MAE, $R^2$, Net Profit Improvement, Input–Output Ratio, Cumulative Reward, Policy Stability, and Regret were used for evaluation. Experimental results show that MAION achieves the best performance in yield, cost, and net profit prediction, with RMSE values of $0.587$, $0.531$, and $0.648$, respectively, and corresponding $R^2$ values of $0.914$, $0.891$, and $0.883$. These results are markedly superior to those of Random Forest, XGBoost, LSTM, GRU, Transformer, Multimodal Transformer, and reinforcement learning baseline models. In the economic decision-making experiment, MAION achieves a Net Profit Improvement of $17.68\%$, an Input–Output Ratio of $1.71$, a Cost Efficiency Gain of $15.46\%$, and a Cumulative Reward of $301.27$, while obtaining the lowest policy fluctuation and regret. The results indicate that the proposed framework can provide effective data-driven decision support for precision input, cost control, and profit optimization in smart agriculture. Full article

The Internet of Plants (IoP) represents the convergence of Artificial Intelligence (AI), Big Data analytics, and the Internet of Things (IoT) within protected agricultural systems. This study presents an IoP platform designed to collect, process, and analyze real-time environmental data using specialized IoT sensors capable of monitoring critical variables, including carbon dioxide concentration (CO₂), pH, air temperature, and relative humidity in hydroponic production systems. The proposed framework integrates advanced machine-learning algorithms, including Random Forest Regressor and Long Short-Term Memory (LSTM) neural networks, to process large volumes of environmental data and support crop management. In addition, the platform incorporates Vapor Pressure Deficit (VPD) and Growing Degree Days (GDD) analyses to provide crop-specific recommendations and support informed decision-making. This platform establishes a benchmark for smart agriculture in Mexico’s Laja–Bajío region, facilitating informed decision-making and maximizing the sustainability of food systems. Experimental validation was conducted under both controlled and semi-controlled environments using Swiss chard (Beta vulgaris subsp. cicla L.) and lettuce (Lactuca sativa L.) cultivated in hydroponic systems. These environments represented contrasting climatic conditions, allowing evaluation of platform stability and forecasting performance under varying thermal regimes. The Random Forest Regressor model, trained using growth chamber data consisting of 19,836 valid observations, reproduced the deterministic VPD relationship with a coefficient of determination (R²) of 0.90 and a root mean square error (RMSE) of 0.08 kPa, confirming internal consistency and identifying temperature as the dominant contributing variable rather than predicting an independent outcome. The dynamic alarm system, integrated with crop phenological stages, demonstrated greater effectiveness than conventional static-threshold approaches by generating alerts according to crop developmental requirements. Furthermore, the web-based visualization platform enabled users to interpret environmental conditions through intuitive graphical representations, facilitating decision-making without requiring specialized technical expertise. The results demonstrate the feasibility of the IoP platform as a comprehensive environmental management tool for protected agricultural systems. The proposed framework provides a scalable solution for precision agriculture applications in the Laja–Bajío region of Mexico and in other regions with similar production systems. Full article

This paper presents the design and preliminary field validation of a portable, low-cost Internet of Things (IoT) station for georeferenced soil nutrient profiling in agricultural environments. The proposed system integrates a digital RS-485 NPK soil sensor, an ESP32 microcontroller, and a SIM7000G GSM/GPS module to enable on-site acquisition and real-time transmission of nitrogen (N), phosphorus (P), and potassium (K) measurements using the MQTT protocol. Data are serialized in JSON format and transmitted to a ThingsBoard cloud platform for remote storage and visualization. The portable architecture supports manual spatial sampling across multiple locations without reliance on fixed infrastructure, making it suitable for small- and medium-scale agricultural contexts with limited connectivity. Preliminary testing in a controlled lemon plantation demonstrated stable GSM connectivity, successful geotagging, and consistent cloud-based visualization, with an average acquisition–transmission cycle of 30–45 s per measurement. Spatial heat maps generated from collected data illustrate the system’s capability for indicative nutrient mapping. Although laboratory-grade validation is ongoing, the results confirm the technical feasibility of integrating low-cost sensing, cellular communication, and georeferenced data acquisition into a compact IoT unit. The system establishes a foundation for future calibration, large-scale field validation, and decision-support applications in precision agriculture. Full article

High-resolution satellite imagery has substantially improved the monitoring of vegetation dynamics; however, the influence of spatial resolution and pixel aggregation on NDVI time series consistency remains insufficiently quantified, particularly across multiple native resolutions within a single sensor platform. This study evaluates how Sentinel-2 spatial resolutions (10 m, 20 m, and 60 m) and two pixel aggregation methods (pure-pixel and centroid) affect NDVI time series in 14,031 grassland plots across mainland Spain over the period 2018–2023. High-quality NDVI time series were selected using the Interpolation Efficiency Indicator (IEI), and discrepancies relative to a 10 m pure-pixel baseline were quantified through the Time Series Angle Distance (TSAD) and Root Mean Square Error (RMSE). A sensitivity check confirmed that the radiometric differences between Band 8 (10 m) and Band 8A (20/60 m) introduce negligible bias compared with genuine spatial-resolution effects. Formal non-parametric statistical testing—omnibus Kruskal–Wallis with epsilon-squared (${\epsilon }^2$) effect sizes and pairwise Cliff’s Delta comparisons—was applied to assess the magnitude and practical significance of the observed differences across plot area categories and Köppen climate groups (B, Cs, Cf). Results show that coarser resolutions (60 m) substantially reduce NDVI reliability, excluding more than half of the plots under the pure-pixel criterion and smoothing temporal variability, whereas 10 m and 20 m resolutions preserve most spectral and temporal information. The 20 m resolution introduces moderate but non-severe phenological distortion (median TSAD ≈ 0.05 rad, RMSE ≈ 0.026) with a 78% reduction in data volume and 72% reduction in processing time. The choice between pure-pixel and centroid sampling has negligible impact at 10–20 m but becomes relevant at 60 m, where pure-pixel selection reduces errors from spectral mixing at the cost of severe sample attrition. Parcel area strongly conditions the error metrics, with large effect sizes (${\epsilon }^2=0.273$) in the smallest plots, while Köppen climate classification decisively shapes TSAD (up to ${\epsilon }^2=0.447$), indicating that spatial degradation distorts phenological patterns differently across climate classes. These findings support a multi-scale monitoring strategy: 10 m for fragmented, heterogeneous grasslands (<3 ha), 20 m as a computationally efficient alternative for homogeneous areas (>10 ha), and outline potential implications for policy frameworks such as the Common Agricultural Policy (CAP). Full article

Recent advances in Earth observation and machine learning have significantly enhanced the capacity to monitor agricultural systems and terrestrial vegetation across spatial and temporal scales. This editorial synthesizes the contributions of eleven studies published in the Special Issue ‘Machine Learning for Applications in Agriculture and Vegetation Using Remote Sensing’. These contributions highlight emerging methodological trends, as well as persistent challenges in remote sensing for agriculture and vegetation measurement and monitoring, and reflect the growing dominance of deep learning in high-resolution mapping and segmentation. An increasing importance of multi-sensor data fusion, integrating multi- and hyperspectral satellites, UAV, and environmental data, is found. Deep learning is emerging as an effective approach for retrieving key biophysical parameters such as biomass, crop height, and yield. The collected studies also emphasize the critical role of sensor characteristics and scale, particularly the trade-offs between spectral, spatial, and temporal resolution in vegetation analysis. Despite notable progress, several limitations remain. Model transferability across regions and sensors is still constrained and multi-source data integration often lacks standardized frameworks. Empirical approaches still dominate the retrieval of biophysical variables, limiting robustness and physical interpretability. The contributions also reveal a persistent gap between high-resolution, small-scale analyses and their scalability to regional or global applications. Therefore, this editorial argues for a transition towards hybrid modeling approaches that combine physical knowledge with data-driven machine learning methods, the adoption of formal data assimilation frameworks for multi-source integration, and the development of scalable and uncertainty-aware workflows. The broader scientific context of the contributions is given by providing a critical perspective on the current state of the field and outlining the key research directions necessary to advance remote sensing in agriculture and ecosystem monitoring. Full article

Hilly orchards are characterized by undulating terrain, canopy occlusion, irregular tree-row structures, and marked variations in ground adhesion conditions, which challenge the autonomous navigation of agricultural machinery by degrading perception and localization, increasing reference path uncertainty, and reducing closed-loop robustness. Perception and localization errors can propagate progressively along the chain of “sensor observation–vehicle pose estimation/environmental-structure perception–reference path generation–path-tracking controller inputs–vehicle closed-loop response,” ultimately affecting path-tracking accuracy, control smoothness, and operational safety. This review examines perception and localization error propagation and robust path-tracking control for agricultural machinery in hilly orchards. The review first summarizes the navigation roles and error characteristics of key observation sources and then analyzes how perception, localization, and reference path generation provide state variables, reference variables, and safety constraints to controllers. It subsequently compares typical path-tracking methods under multi-source disturbances and actuator constraints and discusses key challenges and an integrated robust design direction coupling perception and localization, reference path generation, and path-tracking control. The proposed integrated framework represents a synthesis-derived design direction rather than a complete architecture that has already been experimentally validated in hilly orchard field environments. Full article