Mashori et al. (2026) Remote Sensing through UAVs for Precision Agriculture: Applications, Technical Foundations, Current Barriers, and Future Opportunities

Identification

• Journal: Smart Agricultural Technology
• Year: 2026
• Date: 2026-04-01
• Authors: Abdul Sattar Mashori, Fuzhong Li, Muhammad Aman, Wuping Zhang, Shujie Jia, Aamir Ali, Nida Jabeen, Wangli Hao, Yuqiao Yan
• DOI: 10.1016/j.atech.2026.102074

Research Groups

• College of Agricultural Engineering, Shanxi Agricultural University, Taigu, Jinzhong 030801, China
• Faculty of Software Technologies, Shanxi Agricultural University, Taigu Jinzhong 030801, China
• College of Agriculture, Shanxi Agricultural University, Taigu Jinzhong 030801, China
• School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Short Summary

This paper systematically reviews the evolving applications of Unmanned Aerial Vehicles (UAVs) in precision agriculture, detailing their technical foundations, current barriers, and future opportunities in enhancing operational efficiency and sustainability. It concludes that UAVs, integrated with advanced remote sensing and AI/ML, are pivotal for data-driven farming, despite challenges like limited endurance and regulatory hurdles.

Objective

• To systematically examine the evolving applications of UAVs within agricultural domains, emphasizing their growing role in enhancing operational efficiency and supporting sustainable farming practices.
• To consolidate recent technological developments, application use cases, and prevailing limitations to provide a comprehensive reference for researchers, agronomists, and policymakers.

Study Configuration

• Spatial Scale: Plot-scale to regional-scale agricultural areas, covering hundreds of hectares per sortie, with site-specific and field-level monitoring.
• Temporal Scale: Real-time, time-sensitive, continuous monitoring, and temporal crop assessments, with a literature review spanning 2010 to 2025.

Methodology and Data

• Models used: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), Gradient Boosting, Linear/Ridge/Lasso Regression, Naïve Bayes, Convolutional Neural Networks (CNNs) (e.g., ResNet, EfficientNet, U-Net, DeepLabv3+, Mask R-CNN, YOLO, Faster R-CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Transformer-Based Models, Multimodal Fusion Models, MobileNet, ShuffleNet, Tiny-YOLO, Denoising autoencoders, Generative Adversarial Networks (GANs), YOLOv8-DDS, Rose Mamba YOLO, Succulent YOLO.
• Data sources: UAV-acquired imagery (RGB, multispectral, hyperspectral, thermal), Light Detection and Ranging (LiDAR) point clouds, environmental sensor data (air temperature, relative humidity, atmospheric pressure, wind speed, solar radiation, CO₂ concentration), fluorescence data, radar data (Synthetic Aperture Radar (SAR), Ground Penetrating Radar (GPR)), gas and chemical sensor data, proximity and ultrasonic sensor data, Global Positioning System (GPS)/Global Navigation Satellite System (GNSS) data. Ground truth data from soil moisture probes, leaf water potential, field ratings, lab pathology tests, manual annotation, quadrat sampling, harvest records, plot yield data, manual trait measurements, evapotranspiration (ET) models, application logs, and field inspection. Literature review from IEEE Xplore, MDPI, Wiley, Frontiers, Springer, and Elsevier.

Main Results

• UAVs, equipped with diverse remote sensing technologies (RGB, multispectral, hyperspectral, thermal, LiDAR, environmental, fluorescence, radar, gas/chemical, proximity/ultrasonic, GPS/GNSS), enable high-resolution, real-time monitoring and data acquisition for precision agriculture.
• Key applications include plant growth monitoring, crop health and disease detection, weed mapping, yield estimation, precision spraying/fertilization, planting/seeding, precision water application, and livestock monitoring.
• Advanced data processing pipelines, integrating photogrammetry, radiometric/geometric correction, and AI/ML (classical ML, deep learning, image restoration, lightweight models), transform raw data into actionable agronomic insights.
• Despite significant advantages, widespread UAV adoption faces technical (limited flight endurance, payload capacity, weather sensitivity), regulatory (airspace restrictions, licensing), economic (high capital expenditure/operational expenditure), and data-related (volume, processing expertise, privacy) limitations.
• Future opportunities lie in autonomous swarm-based operations, hybrid Vertical Take Off and Landing (VTOL) platforms, multi-sensor fusion, and edge computing to overcome current barriers and enhance system robustness.

Contributions

• A comprehensive, unified, and end-to-end technical framework systematically integrating all key components of UAV-based precision agriculture, from data acquisition to analysis and decision support.
• A detailed and systematic taxonomy of UAV platforms and associated sensor modalities, clearly categorizing their types, characteristics, and roles within precision agriculture applications.
• A well-structured and systematic mapping between UAV-based agricultural applications, the sensors employed, and the corresponding data analytics techniques, enabling clearer understanding of their interdependencies and practical integration.

Funding

• Science and Technology Major Project of Shanxi Province, China (202202140601021).

Citation

@article{Mashori2026Remote,
  author = {Mashori, Abdul Sattar and Li, Fuzhong and Aman, Muhammad and Zhang, Wuping and Jia, Shujie and Ali, Aamir and Jabeen, Nida and Hao, Wangli and Yan, Yuqiao},
  title = {Remote Sensing through UAVs for Precision Agriculture: Applications, Technical Foundations, Current Barriers, and Future Opportunities},
  journal = {Smart Agricultural Technology},
  year = {2026},
  doi = {10.1016/j.atech.2026.102074},
  url = {https://doi.org/10.1016/j.atech.2026.102074}
}