Related Experiment Video
Updated: Jun 16, 2026
11:37
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
Precise estimation of rice leaf macro and micro nutrients from multi-spectral images using neural architecture search
Diksha Arora1, Jhilik Bhattacharya2, Chinmaya Panigrahy2
1Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, 147004, India. darora_phd21@thapar.edu.
Scientific Reports
|June 14, 2026
Summary
This study introduces a novel deep learning method using drone multispectral images to estimate rice leaf nutrients, improving precision agriculture. The approach enhances nutrient management and crop yield prediction with high accuracy.
Area of Science:
- Agricultural Science
- Remote Sensing
- Artificial Intelligence
Background:
- Estimating rice leaf nutritional status is vital for effective nutrient management and yield optimization.
- Conventional laboratory methods for nutrient analysis are laborious and time-consuming.
- Developing rapid, non-destructive techniques is essential for precision agriculture.
Purpose of the Study:
- To develop and evaluate a novel deep learning framework for estimating rice leaf macro/micro nutrients using UAV-based multispectral imagery.
- To improve the efficiency and accuracy of nutrient status assessment in rice cultivation.
- To address challenges of limited training data in deep learning models for agricultural applications.
Main Methods:
- Utilized multispectral images captured by unmanned aerial vehicles (UAVs).
- Developed a deep learning framework integrating differentiable neural search (DNS) with polynomial function approximators and an adaptive activation mechanism.
- Evaluated model performance using Mean Absolute Error (MAE) and R-squared values across different treatments and growth stages.
Main Results:
- The proposed model achieved low MAE values (0.06-0.11 for SAS-I, 0.06-0.16 for SAS-II) for eleven leaf macro/micro nutrients.
- Uncertainty estimation was performed to further validate nutrient prediction reliability.
- The framework demonstrated superior accuracy and robustness compared to conventional deep learning and machine learning methods.
Conclusions:
- The novel NAS-based deep learning framework enables precise and reliable nutrient assessment in rice.
- This approach offers a significant advancement for precision agriculture, supporting efficient nutrient management.
- The model's ability to handle limited data and its robustness across field conditions make it a valuable tool for crop science.
Related Concept Videos
02:16Light Acquisition
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.
02:35Key Elements for Plant Nutrition
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 atmosphere, the...