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

Flame Photometry: Overview01:02

Flame Photometry: Overview

811
Flame photometry, also known as flame emission spectrometry, is a technique used for the qualitative and quantitative analysis of elements present in a sample using a flame as the source of excitation energy. The concept of flame photometry was realized in the early 1860s by Kirchhoff and Bunsen, who discovered that specific elements emit characteristic radiation when excited in flames. The first instrument developed for this purpose was used to measure sodium (Na) in plant ash using a Bunsen...
811

You might also read

Related Articles

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

Sort by
Same author

Video-Based 3D Reconstruction: A Review of Photogrammetry and Visual SLAM Approaches.

Journal of imaging·2026
Same author

Post-Fire Forest Pulse Recovery: Superiority of Generalized Additive Models (GAM) in Long-Term Landsat Time-Series Analysis.

Sensors (Basel, Switzerland)·2026
Same author

Rapid and automatic burned area detection using sentinel-2 time-series images in google earth engine cloud platform: a case study over the Andika and Behbahan Regions, Iran.

Environmental monitoring and assessment·2022
See all related articles

Related Experiment Video

Updated: Sep 16, 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

1.6K

Machine learning-based burned area detection using Sentinel-2 imagery and spectral indices.

Zohreh Roodsarabi1, Hadi Farhadi2, Hamid Ebadi2

  • 1School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran.

Environmental Monitoring and Assessment
|July 11, 2025
PubMed
Summary

Accurate wildfire burned area mapping using Sentinel-2 imagery and Machine Learning (ML) improved with spectral indices. Random Forest and Support Vector Machine methods enhanced detection accuracy for post-fire management and vegetation recovery.

Keywords:
Burned areaClassificationRandom forestRemote sensingSupport vector machine

More Related Videos

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.4K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.0K

Related Experiment Videos

Last Updated: Sep 16, 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

1.6K
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.4K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.0K

Area of Science:

  • Remote Sensing and Geospatial Analysis
  • Machine Learning Applications in Environmental Science
  • Wildfire Ecology and Management

Background:

  • Wildfires pose significant global threats, necessitating rapid and accurate burned area mapping for effective post-fire response.
  • Timely information on burned landscapes is critical for guiding vegetation recovery monitoring and land management strategies.
  • Satellite imagery, particularly Sentinel-2, offers a valuable resource for large-scale environmental monitoring.

Purpose of the Study:

  • To compare the accuracy of burned area detection using Random Forest (RF) and Support Vector Machine (SVM) Machine Learning (ML) algorithms.
  • To evaluate the efficacy of using original Sentinel-2 bands versus a combination of important bands and spectral indices for improved detection.
  • To assess the performance of these methods in two distinct wildfire-affected regions in Iran: Farashband and Andika.

Main Methods:

  • Implementation of RF and SVM algorithms on the Google Earth Engine platform using Sentinel-2 satellite imagery.
  • Two scenarios were tested: (1) using original Sentinel-2 bands, and (2) combining selected important bands with spectral indices (BAIS2, BADI, MIRBI, NDSWIR, NBR).
  • Accuracy assessment using Overall Accuracy (OA) and Kappa Coefficient (KC) metrics.

Main Results:

  • Both RF and SVM models showed improved burned area detection accuracy when spectral indices were incorporated.
  • In Farashband, SVM achieved the highest accuracy (OA 97.96%, KC 0.99) in the second scenario, outperforming RF (OA 97.04%, KC 0.96).
  • In Andika, SVM also demonstrated superior performance (OA 97.65%, KC 0.98) compared to RF (OA 95.61%, KC 0.94) in the combined scenario. SWIR bands were crucial for RF, while Blue and Red Edge-1 bands were vital for SVM.

Conclusions:

  • Combining Sentinel-2 bands with relevant spectral indices significantly enhances the accuracy of ML-based burned area detection.
  • The proposed approach provides a robust and accurate method for mapping wildfire impacts, supporting post-fire rehabilitation efforts.
  • This methodology offers a scalable solution for monitoring burned areas globally, aiding in ecological recovery and resource management.