Estimation of forest cover change using Sentinel-2 multi-spectral imagery in Georgia (the Caucasus)

Mikeladze, Giorgi; Gavashelishvili, Alexander; Akobia, I.; Metreveli, V.

doi:10.3832/ifor3386-013

Cited by 5 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Los usuarios utilizan este índice para comparar y comprobar datos obtenidos en Inventarios Forestales Nacionales (71) como capa de entrada para utilizar algoritmos de aprendizaje automático, (23,(32)(33)(34)(35) con algoritmos de aprendizaje profundo, (30,36) así como con otros índices espectrales. (18,37) Finalmente, los usuarios exploran métodos efectivos que completen y actualicen información explícita y detallada de los bosques, (16,14,(38)(39)(40)(41)(42)) los combina con métodos conocidos (43,44) o generan clasificadores para un determinado tipo de bosque. (45) Exactitud temática en la cartografía forestal Uno de los aspectos más importante que se tiene en cuenta cuando se elaboran mapas forestales es la exactitud temática; considerada como la fiabilidad de la clasificación de la imagen empleada frente a coberturas de referencias, la cual se consigue de elaborar una matriz de doble entrada donde se contrasta los aciertos o conflictos de las categorías encontradas en la clasificación versus la realidad.…”

Section: Resultados Y Discusiónunclassified

Una revisión del uso de imágenes Sentinel-2 para el monitoreo de la cobertura boscosa a nivel global

Puerta Tuesta,

Iannacone Oliver,

Reategui Inga

2023

inycomp

View full text Add to dashboard Cite

El presente trabajo tuvo como objetivo realizar una revisión sistemática del uso de imágenes Sentinel-2 para el monitoreo de la cobertura boscosa a nivel global, para lo cual se empleó el protocolo propuesto por Prisma 2009. La búsqueda de los artículos científicos publicados entre el 2015 y 2021 se realizó en las bases de datos: Scopus y Science Direct, analizándose un total de 65 artículos en los que se detalla los diferentes tipos de clasificadores utilizados para procesar las imágenes S-2, la exactitud temática lograda en la cartografía, así como el aumento, mantenimiento o retroceso de los bosques y sus principales causas a nivel mundial. Como resultados se encontró que Random Forest (RF) es el clasificador más utilizado para el procesamiento digital de las imágenes S-2, el cual logra en la mayoría de los casos una exactitud temática superior al 85%. En los trabajos multitemporales, se ha encontrado que la cobertura boscosa en Sudamérica y África se ha visto disminuida por actividades como la agricultura y ganadería. Mientras que, en algunos países asiáticos la cobertura boscosa se ha incrementado como consecuencia de la implementación de programas de reforestación y manejo forestal comunitario. Por lo que lo resultados sugieren que las imágenes Sentinel-2 presentan un enorme potencial para llevar a cabo el seguimiento continuo y sistemático de la pérdida o ganancia de los bosques en todo el planeta.

show abstract

Section: Resultados Y Discusiónunclassified

Una revisión del uso de imágenes Sentinel-2 para el monitoreo de la cobertura boscosa a nivel global

Puerta Tuesta,

Iannacone Oliver,

Reategui Inga

2023

inycomp

View full text Add to dashboard Cite

show abstract

“…This can to some degree explain the smaller efficiency of MA estimators for 2014 at least in Norway because FCL data from 2010-2014 were used in this estimate. Alternatives to FCL may be LandTrendr (Kennedy et al 2018), which is also based on Landsat timeseries, or Sentinel-2 based algorithms (Mikeladze et al 2020). The latter may become of interest for GHGIs once a longer timeseries and large-scale products based on Sentinel-2 become available.…”

Section: Discussionmentioning

confidence: 99%

Improving living biomass C-stock loss estimates by combining optical satellite, airborne laser scanning, and NFI data

et al. 2021

View full text Add to dashboard Cite

Policy measures and management decisions aiming at enhancing the role of forests in mitigating climate-change require reliable estimates of C-stock dynamics in greenhouse gas inventories (GHGIs). The aim of this study was to assemble design-based estimators to provide estimates relevant for GHGIs using national forest inventory (NFI) data. We improve basic expansion (BE) estimates of living-biomass C-stock loss using field-data only, by leveraging with remotely-sensed auxiliary data in model-assisted (MA) estimates. Our case studies from Norway, Sweden, Denmark, and Latvia covered an area of >70 Mha. Landsat-based Forest Cover Loss (FCL) and one-time wall-to-wall airborne laser scanning (ALS) data served as auxiliary data. ALS provided information on the C-stock before a potential disturbance indicated by FCL. The use of FCL in MA estimators resulted in considerable efficiency gains which in most cases were further increased by using ALS in addition. A doubling of efficiency was possible for national estimates and even larger efficiencies were observed at the sub-national level. Average annual estimates were considerably more precise than pooled estimates using NFI data from all years at once. The combination of remotely-sensed with NFI field data yields reliable estimates which is not necessarily the case when using remotely-sensed data without reference observations.

show abstract

“…The free availability of remotely sensed data (e.g., Landsat, MODIS or Sentinel) has led to a great increase in the use of this type of data in the last decade for estimating several forest variables such as growing stock volume [4,17], biomass [18,19], forest cover [16,20] and forest changes [21]. The Sentinel-2A and Sentinel-2B satellites, launched by the Euro-pean Space Agency (ESA) through its Copernicus program in 2015 (S2A) and 2017 (S2B), have a temporal resolution of five days, and the imagery includes 13 spectral bands with a spatial resolution ranging from 10, 20 and 60 m/pixel depending on the band [22].…”

Section: Introductionmentioning

confidence: 99%

Estimating Forest Variables for Major Commercial Timber Plantations in Northern Spain Using Sentinel-2 and Ancillary Data

Novo-Fernández,

López-Sánchez,

Cámara-Obregón

et al. 2024

Forests

View full text Add to dashboard Cite

In this study, we used Spanish National Forest Inventory (SNFI) data, Sentinel-2 imagery and ancillary data to develop models that estimate forest variables for major commercial timber plantations in northern Spain. We carried out the analysis in two stages. In the first stage, we considered plots with and without sub-meter geolocation, three pre-processing levels for the Sentinel-2 images and two machine learning algorithms. In most cases, geometrically, radiometrically, atmospherically and topographically (L2A-ATC) corrected images and the random forest algorithm provided the best results, with topographic correction producing a greater gain in model accuracy as the average slope of the plots increased. Our results did not show any clear impact of the geolocation accuracy of SNFI plots on results, suggesting that the usual geolocation accuracy of SNFI plots is adequate for developing forest models with data obtained from passive sensors. In the second stage, we used all plots together with L2A-ATC-corrected images to select five different groups of predictor variables in a cumulative process to determine the influence of each group of variables in the final RF model predictions. Yield variables produced the best fits, with R2 ranging from 0.39 to 0.46 (RMSE% ranged from 44.6% to 61.9%). Although the Sentinel-2-based estimates obtained in this research are less precise than those previously obtained with Airborne Laser Scanning (ALS) data for the same species and region, they are unbiased (Bias% was always below 1%). Therefore, accurate estimates for one hectare are expected, as they are obtained by averaging the values of 100 pixels (model resolution of 10 m pixel−1) with an expected error compensation. Moreover, the use of these models will overcome the temporal resolution problem associated with the previous ALS-based models and will enable annual updates of forest timber resource estimates to be obtained.

show abstract

Estimation of forest cover change using Sentinel-2 multi-spectral imagery in Georgia (the Caucasus)

Cited by 5 publications

References 35 publications

Una revisión del uso de imágenes Sentinel-2 para el monitoreo de la cobertura boscosa a nivel global

Una revisión del uso de imágenes Sentinel-2 para el monitoreo de la cobertura boscosa a nivel global

Improving living biomass C-stock loss estimates by combining optical satellite, airborne laser scanning, and NFI data

Estimating Forest Variables for Major Commercial Timber Plantations in Northern Spain Using Sentinel-2 and Ancillary Data

Contact Info

Product

Resources

About