Related Experiment Video
Updated: Feb 24, 2026
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
2.1K
UAV multispectral sensing and data-driven modeling for precision onion yield prediction.
Sagar M Wayal1, Shardul Parab2, Anusha Raj1
1ICAR-Directorate of Onion and Garlic Research, Pune, India.
Frontiers in Plant Science
|February 23, 2026
Summary
Unmanned aerial vehicle (UAV) multispectral imagery combined with machine learning accurately predicts onion yield. Random Forest models showed the best performance for optimizing precision agriculture and crop management.
Area of Science:
- Agricultural Science
- Remote Sensing
- Machine Learning
Background:
- Precision agriculture benefits from integrating Unmanned Aerial Vehicle (UAV)-assisted remote sensing with the Internet of Things (IoT) and Internet of Everything (IoE).
- Capturing spatiotemporal variability in crop growth is crucial for optimizing agricultural practices.
- UAV-based multispectral imagery offers a powerful tool for monitoring crop health and predicting yield.
Purpose of the Study:
- To predict the bulb yield of rainy-season onion crops using UAV-based multispectral imagery.
- To evaluate the performance of various machine learning algorithms for onion yield prediction.
- To assess the utility of vegetation indices derived from multispectral data for yield modeling.
Main Methods:
- Acquisition of canopy reflectance mosaics from UAVs at key growth stages.
- Extraction of vegetation indices (VIs) including NDVI, NDRE, SAVI, LAI, NORM2, and GNDVI.
- Development and assessment of yield prediction models using five machine learning algorithms (linear regression, random forest, support vector machine, gradient boosting, elastic net regression) with 10-fold cross-validation.
Main Results:
- Random Forest consistently outperformed other models, achieving high accuracy at the bulb development stage (validation R² = 0.755).
- Support Vector Machine also demonstrated strong predictive capability (validation R² = 0.716).
- Interannual variability in model performance was observed, with models trained on 2024 data showing better results than those from 2023.
Conclusions:
- UAV-derived multispectral sensing combined with machine learning is an effective and scalable approach for reliable onion yield prediction.
- This methodology provides timely decision support for managing rainy-season onion crops under diverse agronomic conditions.
- The study highlights the potential of advanced remote sensing and AI techniques in modern agriculture.
Related Concept Videos
02:16Light Acquisition
9.7K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.7K
02:35Key Elements for Plant Nutrition
24.5K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
24.5K