Related Experiment Video
Updated: Aug 13, 2026
08:47
Computer Vision-Based Biomass Estimation for Invasive Plants
Published on: February 9, 2024
Aboveground biomass estimation and multiscale spatial pattern analysis in desert rangelands using UAV hyperspectral
Shengli Wang1, Haiqing Tian1, Chunxiang Zhuo1
1College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot, 010018, China.
Summary
Accurate aboveground biomass (AGB) estimation in desert rangelands improved by combining spectral, textural, and dispersion features. Machine learning models, particularly random forest, enhanced AGB prediction and revealed grazing impacts on spatial patterns.
Area of Science:
- Ecology
- Remote Sensing
- Geospatial Analysis
Background:
- Accurate aboveground biomass (AGB) estimation is crucial for desert rangeland productivity and grazing management.
- Current remote sensing models using unmanned aerial vehicle (UAV) data primarily rely on spectral information, inadequately capturing spatial distribution and scale-dependent responses of plant communities.
- A need exists for integrated approaches that combine diverse data sources for improved AGB assessment.
Purpose of the Study:
- To develop and compare machine learning models for AGB estimation in desert rangelands by integrating UAV hyperspectral imagery with field data.
- To investigate the influence of grazing intensity on AGB and its spatial distribution patterns across various spatial scales.
- To evaluate the effectiveness of combining spectral, textural, and local statistical dispersion features for enhanced AGB estimation.
Main Methods:
- Integration of UAV hyperspectral imagery with field quadrat data from four grazing intensity levels.
- Development and comparison of six machine learning models (including Random Forest) for AGB estimation.
- Analysis of spectral, textural, and local statistical dispersion features to assess their contribution to AGB estimation accuracy.
Main Results:
- The integration of multisource features significantly improved AGB estimation accuracy, with the Random Forest model achieving R²=0.914.
- Textural and local statistical dispersion features provided complementary information to spectral features.
- Increasing grazing intensity led to decreased AGB and a shift from homogeneous to heterogeneous and patchy spatial distributions.
- Spatial variability metrics effectively indicated grazing impacts, especially under moderate to heavy grazing, complementing mean biomass data.
Conclusions:
- Combining spectral, textural, and local statistical dispersion features offers a robust approach for accurate AGB estimation in desert rangelands.
- Spatial variability metrics are valuable for understanding grazing disturbance impacts on rangeland structure.
- The study provides a technical framework for AGB estimation and spatial pattern analysis in grazed desert ecosystems.
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.
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...