Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Light Acquisition02:16

Light 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

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Measurement of the forward-backward charge asymmetry and extraction of sin2thetaWeff in pp-->Z/gamma* + X-->e+e- +X events produced at sqrt[s] = 1.96 TeV.

Physical review letters·2008
Same author

Measurement of the electron charge asymmetry in pp[over ]-->W+X-->enu+X events at sqrt[s]=1.96 TeV.

Physical review letters·2008
Same author

Search for anomalous Wtb couplings in single top quark production.

Physical review letters·2008
Same author

Search for neutral Higgs bosons in multi-b-jet events in pp[over] collisions at sqrt[s]=1.96 TeV.

Physical review letters·2008
Same author

Observation of the doubly strange b baryon Omegab-.

Physical review letters·2008
Same author

Observation of ZZ production in p-p collisions at sqrt s=1.96 TeV.

Physical review letters·2008

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K

Inversion models of aboveground grassland biomass in Xinjiang based on multisource data.

R P Zhang1,2, J H Zhou1,2, J Guo3

  • 1College of Ecology and Environment, Xinjiang University, Urumqi, China.

Frontiers in Plant Science
|March 30, 2023
PubMed
Summary

Accurately estimating grassland biomass in drylands is challenging. The Random Forest model, utilizing key variables like SAVI and precipitation, proved most effective for grassland biomass inversion in Xinjiang.

Keywords:
Xinjiangbiomassgrasslandmachine learningprincipal component analysisvegetation index

More Related Videos

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
04:35

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

3.4K
Sampling Soils in a Heterogeneous Research Plot
07:11

Sampling Soils in a Heterogeneous Research Plot

Published on: January 7, 2019

34.6K

Related Experiment Videos

Last Updated: Aug 4, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K
Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
04:35

Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

Published on: July 3, 2020

3.4K
Sampling Soils in a Heterogeneous Research Plot
07:11

Sampling Soils in a Heterogeneous Research Plot

Published on: January 7, 2019

34.6K

Area of Science:

  • Ecology
  • Remote Sensing
  • Environmental Science

Background:

  • Grassland biomass monitoring is crucial for assessing ecosystem health and carbon cycling.
  • Satellite remote sensing of dryland grassland biomass presents significant challenges.
  • Existing models often lack clarity on predictive power across different grassland types and optimal variable selection.

Purpose of the Study:

  • To evaluate the accuracy of various statistical and machine learning models for grassland biomass inversion.
  • To identify the most influential variables for modeling biomass in different grassland types (desert grassland, steppe, meadow).
  • To determine the best-performing model for grassland biomass estimation in Xinjiang.

Main Methods:

  • Utilized 1201 ground-truth data points (2014-2021) including Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation indices, geographic, topographic, meteorological, and biophysical data.
  • Applied Principal Component Analysis (PCA) for key variable selection.
  • Assessed the accuracy of multiple linear regression, exponential regression, power function, Support Vector Machine (SVM), Random Forest (RF), and neural network models.

Main Results:

  • Single vegetation indices showed low biomass inversion accuracy; optimal indices included Soil-Adjusted Vegetation Index (SAVI), Normalized Difference Vegetation Index (NDVI), and Optimized Soil-Adjusted Vegetation Index (OSAVI).
  • Above-ground biomass (AGB) is influenced by multiple factors; models using single environmental variables had high errors.
  • Key variables for biomass modeling varied by grassland type: SAVI, aspect, slope, and precipitation for desert grasslands; NDVI, SWI2, longitude, temperature, and precipitation for steppe; OSAVI, PPR, longitude, precipitation, and temperature for meadows.
  • Non-parametric models outperformed statistical regression for meadow biomass.
  • The Random Forest (RF) model achieved the highest accuracy for overall grassland biomass inversion in Xinjiang (R² = 0.656), followed by meadow (R² = 0.610) and desert grassland (R² = 0.441).

Conclusions:

  • The Random Forest model demonstrates superior performance for grassland biomass inversion in diverse dryland environments.
  • Variable selection is critical and differs significantly across desert grassland, steppe, and meadow ecosystems.
  • Accurate grassland biomass monitoring in drylands requires integrating multiple data sources and advanced machine learning techniques.