UAV remote sensing for yield prediction in staple crops: a review

Area of Science:

• Agricultural Science
• Remote Sensing
• Data Science

Background:

• Accurate crop yield prediction is vital for global food security and precision agriculture.
• Unmanned Aerial Vehicles (UAVs) offer advanced capabilities for crop monitoring and yield estimation.

Purpose of the Study:

• To conduct a structured integrative review of UAV-based crop yield prediction studies.
• To synthesize evidence on data, ground truth, models, and decision-making frameworks.

Main Methods:

• PRISMA-guided literature search and synthesis of 70 peer-reviewed studies (2018-2025).
• Analysis of UAV platforms, sensors, feature engineering, and model architectures.
• Evaluation of yield-label acquisition methods and prediction scales (microplot, field, regional).

Main Results:

• UAV yield prediction reliability hinges on image acquisition, multi-source fusion, model architecture, scale-consistent labels, and validation strategies.
• Key challenges include scale mismatch, error propagation, limited transferability, weak interpretability, and deployment difficulties.
• Reliability depends on optimal image acquisition, multi-source feature fusion, and scale-consistent yield labels.

Conclusions:

• Future research must focus on scale-explicit datasets, quality-controlled ground truth, data fusion (UAV-satellite-ground), spatiotemporal deep learning, and edge-cloud systems.
• Developing robust, interpretable, and deployable UAV-based yield prediction systems is achievable.
• Addressing scale mismatch and improving data fusion are critical for advancing UAV-based yield prediction.