Related Experiment Video
Updated: Jul 12, 2025
11:37
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
16.2K
Modeling the spatial-spectral characteristics of plants for nutrient status identification using hyperspectral data
Frank Gyan Okyere1,2, Daniel Cudjoe1,2, Pouria Sadeghi-Tehran1
1Sustainable Soils and Crops, Rothamsted Research, Harpenden, United Kingdom.
Frontiers in Plant Science
|November 1, 2023
Summary
A new hybrid deep learning model accurately identifies nitrogen and phosphorus levels in quinoa and cowpea using hyperspectral imaging. This precision agriculture tool aids sustainable fertilizer management by analyzing combined spectral and spatial plant data.
Area of Science:
- Agricultural Science
- Remote Sensing
- Plant Physiology
Background:
- Sustainable fertilizer management is crucial for economic and environmental health in precision agriculture.
- Hyperspectral imaging offers a remote sensing approach to monitor plant nutrient status by analyzing physiological changes.
- Conventional hyperspectral processing often analyzes spectral or spatial information separately, limiting comprehensive analysis.
Purpose of the Study:
- To develop a hybrid Convolutional Neural Network (CNN) model for simultaneous extraction of spatial and spectral information from hyperspectral data.
- To accurately identify the nutrient status of quinoa and cowpea plants at various growth stages.
- To evaluate the impact of different pre-processing techniques on hyperspectral-based nutrient phenotyping.
Main Methods:
- A nutrient experiment with varying nitrogen and phosphorus levels was conducted under glasshouse conditions.
- A hybrid CNN model, integrating 3D CNN for spectral-spatial information and 2D CNN for spatial details, was proposed.
- Data pre-processing techniques (second-order derivative, standard normal variate, linear discriminant analysis) were applied, and model performance was compared against existing methods.
Main Results:
- The proposed hybrid CNN model achieved over 94% classification accuracy in identifying nitrogen and phosphorus status.
- The model demonstrated superior performance compared to standalone 3D CNN, 2D CNN, and HybridSN models.
- Effective wavebands were identified and utilized to further enhance model accuracy across different growth stages.
Conclusions:
- The developed hybrid CNN model effectively integrates spectral and spatial information for accurate plant nutrient status identification.
- This approach shows significant potential for advancing precision agriculture through enhanced hyperspectral data analysis.
- The findings support the use of advanced deep learning techniques for sustainable crop management and improved fertilizer use efficiency.
Related Concept Videos
02:35Key Elements for Plant Nutrition
18.8K
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...
18.8K
02:16Light Acquisition
8.5K
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.
8.5K