Related Experiment Video
Updated: May 12, 2026
08:47
Computer Vision-Based Biomass Estimation for Invasive Plants
Published on: February 9, 2024
Improving the estimation accuracy of rice leaf protein nitrogen using data augmentation, explainable machine
Yiping Peng1,2,3, Yuting Tu1,2,3, Yanggui Xu1,2,3
1Institute of Agricultural Resources and Environment, Guangdong Academy of Agricultural Sciences, Guangzhou, China.
Frontiers in Plant Science
|May 11, 2026
Summary
Estimating rice leaf nitrogen content using hyperspectral imagery is improved by data augmentation with Wasserstein-generative adversarial networks (WGAN). This enhances machine learning model accuracy for precision fertilization and nitrogen use efficiency.
Area of Science:
- Agricultural Science
- Remote Sensing
- Data Science
Background:
- Accurate estimation of rice leaf protein nitrogen (LPN) content is vital for crop nutrition and precision fertilization.
- Unmanned aerial vehicle (UAV)-based hyperspectral imagery offers a promising approach for LPN estimation.
- Traditional machine learning models require extensive data, face challenges in generalizability, and lack interpretability.
Purpose of the Study:
- To address data scarcity and interpretability issues in LPN estimation using hyperspectral data.
- To enhance the performance of machine learning models for LPN estimation through data augmentation.
- To identify key spectral features contributing to LPN estimation.
Main Methods:
- Utilized Wasserstein-generative adversarial network (WGAN) for hyperspectral data augmentation.
- Developed LPN estimation models using statistical regression (MLR, PLSR) and machine learning (SVM, KNN).
- Employed Shapley Additive exPlanations (SHAP) for feature importance analysis.
Main Results:
- The K-nearest neighbor (KNN) model achieved optimal estimation performance.
- Data augmentation with WGAN improved model accuracy, increasing the R² value by 10.39%.
- SHAP analysis identified B775.6, DCNI, and MTCI as critical variables for LPN estimation.
Conclusions:
- WGAN-based data augmentation significantly enhances LPN estimation accuracy.
- The KNN model, augmented with WGAN, provides a robust solution for LPN estimation.
- Key spectral indices and wavelengths identified can guide future research and applications in precision agriculture.
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...
01:29Application of Linearization and Approximation
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...