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

Applications of GIS: Disaster Management and Emergency Response01:29

Applications of GIS: Disaster Management and Emergency Response

88
Geographic Information System (GIS) technology is essential for risk identification, action prioritization, and resource optimization in critical situations like flooding and earthquakes. By integrating spatial and demographic data, GIS provides a comprehensive framework for emergency response.GIS integrates data layers, like rainfall intensity, topography, elevation profiles, and river levels, to model high-risk flood zones. These layers assess areas susceptible to flooding based on their...
88
Survival Tree01:19

Survival Tree

87
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
87
Selected Data About Geographic Locations01:25

Selected Data About Geographic Locations

27
Geographic Information Systems (GIS) rely on two core types of data: spatial data and attribute data.Spatial DataSpatial data defines the physical location of features within a coordinate system, typically expressed in terms of latitude and longitude. It provides precise positioning for elements like roads, rivers, or buildings.Attribute DataAttribute data complements spatial data by adding descriptive information about these features. For example, a road's spatial data includes its start and...
27

You might also read

Related Articles

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

Sort by
Same author

Remote sensing and monitoring of water resources: A comparative study of different indices and thresholding methods.

The Science of the total environment·2024
Same author

Geographic information system-assisted site quality assessment for hazelnut cultivation using multi-criteria decision analysis in the Black Sea region, Turkey.

Environmental science and pollution research international·2022
Same author

Effectiveness of autoencoder for lake area extraction from high-resolution RGB imagery: an experimental study.

Environmental science and pollution research international·2021
Same author

A GIS-based multi-criteria model for offshore wind energy power plants site selection in both sides of the Aegean Sea.

Environmental monitoring and assessment·2020
Same author

A novel unsupervised change detection approach based on reconstruction independent component analysis and ABC-Kmeans clustering for environmental monitoring.

Environmental monitoring and assessment·2019

Related Experiment Video

Updated: Jul 8, 2025

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

13.3K

Deep learning-based burned forest areas mapping via Sentinel-2 imagery: a comparative study.

Ümit Haluk Atasever1, Emre Tercan2

  • 1Department of Geomatics Engineering, Faculty of Engineering, Erciyes University, 38039, Kayseri, Turkey.

Environmental Science and Pollution Research International
|December 19, 2023
PubMed
Summary

Deep learning-based Stacked Autoencoders accurately map burned forest areas from Sentinel-2 satellite images. This unsupervised method outperformed supervised algorithms in quantitative and qualitative analyses for ecosystem research.

Keywords:
Burned area mappingDeep learningRemote sensingSentinel-2Stacked Autoencoders

More Related Videos

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

1.4K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.2K

Related Experiment Videos

Last Updated: Jul 8, 2025

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

13.3K
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

1.4K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.2K

Area of Science:

  • Ecology and Environmental Science
  • Remote Sensing
  • Computer Science

Background:

  • Accurate mapping of burned forest areas is crucial for understanding ecosystem dynamics post-wildfire.
  • Satellite imagery and image classification algorithms are key tools for effective and economical forest fire assessment.
  • Evaluating diverse classification algorithms for burned area extraction is an active research area.

Purpose of the Study:

  • To assess the capability of Stacked Autoencoders (SAE), an unsupervised deep learning method, for mapping burned forest areas using Sentinel-2 satellite data.
  • To compare the performance of SAE against various supervised learning algorithms for burned area delineation.
  • To provide an objective evaluation using contrasting forest zones and comprehensive accuracy metrics.

Main Methods:

  • Utilized Sentinel-2 satellite images for burned forest area mapping.
  • Applied Stacked Autoencoders (SAE) as an unsupervised learning method.
  • Compared SAE with supervised algorithms: k-Nearest Neighbors (k-NN), Subspaced k-NN, Support Vector Machines, Random Forest, Bagged Decision Tree, Naive Bayes, and Linear Discriminant Analysis.
  • Performed accuracy assessment using manually digitized burned areas and metrics like Overall Accuracy, MSE, Correlation Coefficient, SSIM, PSNR, UQI, and KAPPA.

Main Results:

  • Stacked Autoencoders demonstrated superior performance in mapping burned forest areas compared to all evaluated supervised learning algorithms.
  • Both quantitative and qualitative analyses confirmed the higher accuracy of the SAE method.
  • Boxplots indicated consistent results produced by the Stacked Autoencoders method across different test zones.

Conclusions:

  • The Stacked Autoencoders method is highly effective and accurate for burned forest area mapping using Sentinel-2 satellite imagery.
  • Unsupervised deep learning approaches, like SAE, offer a promising alternative to traditional supervised methods for ecological assessments.
  • This study highlights the potential of advanced machine learning techniques for improving wildfire impact analysis and ecosystem management.