Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests

The commitment by over 100 governments covering over 90% of the world’s forests at the COP26 in Glasgow to end deforestation by 2030 requires more effective forest monitoring systems. The near real-time (NRT) change detection of forest cover loss enables forest landowners, government agencies and local communities to monitor natural and anthropogenic disturbances in a much timelier fashion than the thematic maps that are released every year. NRT deforestation alerts enable the establishment of more up-to-date forest inventories and rapid responses to unlicensed logging. The Copernicus Sentinel-2 satellites provide operational Earth observation (EO) data from multi-spectral optical/near-infrared wavelengths every five days at a global scale and at 10 m resolution. The amount of acquired data requires cloud computing or high-performance computing for ongoing monitoring systems and an automated system for processing, analyzing and delivering the information promptly. Here, we present a Sentinel-2-based NRT change detection system, assess its performance over two study sites, Manantlán in Mexico and Cartagena del Chairá in Colombia, and evaluate the forest changes that occurred in 2018. An independent validation with very high-resolution PlanetScope (~3 m) and RapidEye (~5 m) data suggests that the proposed NRT change detection system can accurately detect forest cover loss (> 87%), other vegetation loss (> 76%) and other vegetation gain (> 71%). Furthermore, the proposed NRT change detection system is designed to be attuned using in situ data. Therefore, it is scalable to larger regions, entire countries and even continents.

Saved in:
Bibliographic Details
Main Authors: Pacheco Pascagaza, Ana María autora, Gou, Yaqing autor/a, Louis, Valentin autor, Robert, John F. autor, Rodríguez Veiga, Pedro autor, Bispo, Polyanna da Conceição autor/a, Espírito Santo, Fernando D. B. autor, Robb, Ciaran autor/a, Upton, Caroline autora, Galindo, Gustavo autor, Cabrera, Edersson autor, Pachón Cendales, Indira Paola autora, Castillo Santiago, Miguel Ángel Doctor autor 8371, Carrillo Negrete, Oswaldo autor, Meneses, Carmen autora, Iñiguez, Marco autor, Balzter, Heiko autor/a
Format: Texto biblioteca
Language:eng
Subjects:Deforestación, Bosques tropicales, Monitoreo forestal, Cambio climático, Paisajes fragmentados,
Online Access:https://doi.org/10.3390/rs14030707
Tags: Add Tag
No Tags, Be the first to tag this record!
id KOHA-OAI-ECOSUR:62763
record_format koha
institution ECOSUR
collection Koha
country México
countrycode MX
component Bibliográfico
access En linea
En linea
databasecode cat-ecosur
tag biblioteca
region America del Norte
libraryname Sistema de Información Bibliotecario de ECOSUR (SIBE)
language eng
topic Deforestación
Bosques tropicales
Monitoreo forestal
Cambio climático
Paisajes fragmentados
Deforestación
Bosques tropicales
Monitoreo forestal
Cambio climático
Paisajes fragmentados
spellingShingle Deforestación
Bosques tropicales
Monitoreo forestal
Cambio climático
Paisajes fragmentados
Deforestación
Bosques tropicales
Monitoreo forestal
Cambio climático
Paisajes fragmentados
Pacheco Pascagaza, Ana María autora
Gou, Yaqing autor/a
Louis, Valentin autor
Robert, John F. autor
Rodríguez Veiga, Pedro autor
Bispo, Polyanna da Conceição autor/a
Espírito Santo, Fernando D. B. autor
Robb, Ciaran autor/a
Upton, Caroline autora
Galindo, Gustavo autor
Cabrera, Edersson autor
Pachón Cendales, Indira Paola autora
Castillo Santiago, Miguel Ángel Doctor autor 8371
Carrillo Negrete, Oswaldo autor
Meneses, Carmen autora
Iñiguez, Marco autor
Balzter, Heiko autor/a
Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
description The commitment by over 100 governments covering over 90% of the world’s forests at the COP26 in Glasgow to end deforestation by 2030 requires more effective forest monitoring systems. The near real-time (NRT) change detection of forest cover loss enables forest landowners, government agencies and local communities to monitor natural and anthropogenic disturbances in a much timelier fashion than the thematic maps that are released every year. NRT deforestation alerts enable the establishment of more up-to-date forest inventories and rapid responses to unlicensed logging. The Copernicus Sentinel-2 satellites provide operational Earth observation (EO) data from multi-spectral optical/near-infrared wavelengths every five days at a global scale and at 10 m resolution. The amount of acquired data requires cloud computing or high-performance computing for ongoing monitoring systems and an automated system for processing, analyzing and delivering the information promptly. Here, we present a Sentinel-2-based NRT change detection system, assess its performance over two study sites, Manantlán in Mexico and Cartagena del Chairá in Colombia, and evaluate the forest changes that occurred in 2018. An independent validation with very high-resolution PlanetScope (~3 m) and RapidEye (~5 m) data suggests that the proposed NRT change detection system can accurately detect forest cover loss (> 87%), other vegetation loss (> 76%) and other vegetation gain (> 71%). Furthermore, the proposed NRT change detection system is designed to be attuned using in situ data. Therefore, it is scalable to larger regions, entire countries and even continents.
format Texto
topic_facet Deforestación
Bosques tropicales
Monitoreo forestal
Cambio climático
Paisajes fragmentados
author Pacheco Pascagaza, Ana María autora
Gou, Yaqing autor/a
Louis, Valentin autor
Robert, John F. autor
Rodríguez Veiga, Pedro autor
Bispo, Polyanna da Conceição autor/a
Espírito Santo, Fernando D. B. autor
Robb, Ciaran autor/a
Upton, Caroline autora
Galindo, Gustavo autor
Cabrera, Edersson autor
Pachón Cendales, Indira Paola autora
Castillo Santiago, Miguel Ángel Doctor autor 8371
Carrillo Negrete, Oswaldo autor
Meneses, Carmen autora
Iñiguez, Marco autor
Balzter, Heiko autor/a
author_facet Pacheco Pascagaza, Ana María autora
Gou, Yaqing autor/a
Louis, Valentin autor
Robert, John F. autor
Rodríguez Veiga, Pedro autor
Bispo, Polyanna da Conceição autor/a
Espírito Santo, Fernando D. B. autor
Robb, Ciaran autor/a
Upton, Caroline autora
Galindo, Gustavo autor
Cabrera, Edersson autor
Pachón Cendales, Indira Paola autora
Castillo Santiago, Miguel Ángel Doctor autor 8371
Carrillo Negrete, Oswaldo autor
Meneses, Carmen autora
Iñiguez, Marco autor
Balzter, Heiko autor/a
author_sort Pacheco Pascagaza, Ana María autora
title Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
title_short Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
title_full Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
title_fullStr Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
title_full_unstemmed Near real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests
title_sort near real-time change detection system using sentinel-2 and machine learning a test for mexican and colombian forests
url https://doi.org/10.3390/rs14030707
work_keys_str_mv AT pachecopascagazaanamariaautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT gouyaqingautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT louisvalentinautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT robertjohnfautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT rodriguezveigapedroautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT bispopolyannadaconceicaoautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT espiritosantofernandodbautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT robbciaranautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT uptoncarolineautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT galindogustavoautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT cabreraederssonautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT pachoncendalesindirapaolaautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT castillosantiagomiguelangeldoctorautor8371 nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT carrillonegreteoswaldoautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT menesescarmenautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT iniguezmarcoautor nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
AT balzterheikoautora nearrealtimechangedetectionsystemusingsentinel2andmachinelearningatestformexicanandcolombianforests
_version_ 1794792369700208640
spelling KOHA-OAI-ECOSUR:627632024-03-12T12:54:08ZNear real-time change detection system using sentinel-2 and machine learning a test for Mexican and Colombian forests Pacheco Pascagaza, Ana María autora Gou, Yaqing autor/a Louis, Valentin autor Robert, John F. autor Rodríguez Veiga, Pedro autor Bispo, Polyanna da Conceição autor/a Espírito Santo, Fernando D. B. autor Robb, Ciaran autor/a Upton, Caroline autora Galindo, Gustavo autor Cabrera, Edersson autor Pachón Cendales, Indira Paola autora Castillo Santiago, Miguel Ángel Doctor autor 8371 Carrillo Negrete, Oswaldo autor Meneses, Carmen autora Iñiguez, Marco autor Balzter, Heiko autor/a textengThe commitment by over 100 governments covering over 90% of the world’s forests at the COP26 in Glasgow to end deforestation by 2030 requires more effective forest monitoring systems. The near real-time (NRT) change detection of forest cover loss enables forest landowners, government agencies and local communities to monitor natural and anthropogenic disturbances in a much timelier fashion than the thematic maps that are released every year. NRT deforestation alerts enable the establishment of more up-to-date forest inventories and rapid responses to unlicensed logging. The Copernicus Sentinel-2 satellites provide operational Earth observation (EO) data from multi-spectral optical/near-infrared wavelengths every five days at a global scale and at 10 m resolution. The amount of acquired data requires cloud computing or high-performance computing for ongoing monitoring systems and an automated system for processing, analyzing and delivering the information promptly. Here, we present a Sentinel-2-based NRT change detection system, assess its performance over two study sites, Manantlán in Mexico and Cartagena del Chairá in Colombia, and evaluate the forest changes that occurred in 2018. An independent validation with very high-resolution PlanetScope (~3 m) and RapidEye (~5 m) data suggests that the proposed NRT change detection system can accurately detect forest cover loss (> 87%), other vegetation loss (> 76%) and other vegetation gain (> 71%). Furthermore, the proposed NRT change detection system is designed to be attuned using in situ data. Therefore, it is scalable to larger regions, entire countries and even continents.The commitment by over 100 governments covering over 90% of the world’s forests at the COP26 in Glasgow to end deforestation by 2030 requires more effective forest monitoring systems. The near real-time (NRT) change detection of forest cover loss enables forest landowners, government agencies and local communities to monitor natural and anthropogenic disturbances in a much timelier fashion than the thematic maps that are released every year. NRT deforestation alerts enable the establishment of more up-to-date forest inventories and rapid responses to unlicensed logging. The Copernicus Sentinel-2 satellites provide operational Earth observation (EO) data from multi-spectral optical/near-infrared wavelengths every five days at a global scale and at 10 m resolution. The amount of acquired data requires cloud computing or high-performance computing for ongoing monitoring systems and an automated system for processing, analyzing and delivering the information promptly. Here, we present a Sentinel-2-based NRT change detection system, assess its performance over two study sites, Manantlán in Mexico and Cartagena del Chairá in Colombia, and evaluate the forest changes that occurred in 2018. An independent validation with very high-resolution PlanetScope (~3 m) and RapidEye (~5 m) data suggests that the proposed NRT change detection system can accurately detect forest cover loss (> 87%), other vegetation loss (> 76%) and other vegetation gain (> 71%). Furthermore, the proposed NRT change detection system is designed to be attuned using in situ data. Therefore, it is scalable to larger regions, entire countries and even continents.DeforestaciónBosques tropicalesMonitoreo forestalCambio climáticoPaisajes fragmentadosRemote Sensinghttps://doi.org/10.3390/rs14030707Acceso en línea sin restricciones