Modeling of Aboveground Biomass with Landsat 8 OLI and Machine Learning in Temperate Forests

López-Serrano, Pablito Marcelo; Domínguez, José Luis Cárdenas; Corral-Rivas, José Javier; Jiménez, Enrique; López-Sánchez, Carlos A.; Vega-Nieva, Daniel José

doi:10.3390/f11010011

Cited by 62 publications

(38 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most of them are from visible and NIR bands, such as the ratio vegetation index (RVI), NDVI, soil-adjusted vegetation index (SAVI), modified soil-adjusted vegetation index (MSAVI), and optimized soil-adjusted vegetation index (OSAVI). The SWIR spectral band is one of the most important variables in predicting AGB [64][65][66], and spectral indices containing SWIR have stronger relationships with AGB [67,68] under complex forest structures. Thus, some spectral indices derived from SWIR were also calculated.…”

Section: Modis Potential Variable Predictors Of Acdmentioning

confidence: 99%

Modeling Forest Aboveground Carbon Density in the Brazilian Amazon with Integration of MODIS and Airborne LiDAR Data

Jiang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Timely updates of carbon stock distribution are needed to better understand the impacts of deforestation and degradation on forest carbon stock dynamics. This research aimed to explore an approach for estimating aboveground carbon density (ACD) in the Brazilian Amazon through integration of MODIS (moderate resolution imaging spectroradiometer) and a limited number of light detection and ranging (Lidar) data samples using linear regression (LR) and random forest (RF) algorithms, respectively. Airborne LiDAR data at 23 sites across the Brazilian Amazon were collected and used to calculate ACD. The ACD estimation model, which was developed by Longo et al. in the same study area, was used to map ACD distribution in the 23 sites. The LR and RF methods were used to develop ACD models, in which the samples extracted from LiDAR-estimated ACD were used as dependent variables and MODIS-derived variables were used as independent variables. The evaluation of modeling results indicated that ACD can be successfully estimated with a coefficient of determination of 0.67 and root mean square error of 4.18 kg C/m2 using RF based on spectral indices. The mixed pixel problem in MODIS data is a major factor in ACD overestimation, while cloud contamination and data saturation are major factors in ACD underestimation. These uncertainties in ACD estimation using MODIS data make it difficult to examine annual ACD dynamics of degradation and growth, however this method can be used to examine the deforestation-induced ACD loss.

show abstract

Section: Modis Potential Variable Predictors Of Acdmentioning

confidence: 99%

Modeling Forest Aboveground Carbon Density in the Brazilian Amazon with Integration of MODIS and Airborne LiDAR Data

Jiang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the past, many studies have been carried out using both linear and non-linear modeling approaches [57][58][59]. In many cases, it was found that when the prediction models become too complex, they operate with statistically insignificant predictor variables [60][61][62]. In such cases, selecting suitable variables is of prime importance to reduce the number of model parameters and thus to increase the generalization of a model.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Forest Aboveground Biomass Using Multitemporal Multispectral Remote Sensing Data

2021

View full text Add to dashboard Cite

Forest aboveground biomass (AGB) is a prime forest parameter that requires global level estimates to study the global carbon cycle. Light detection and ranging (LiDAR) is the state-of-the-art technology for AGB prediction but it is expensive, and its coverage is restricted to small areas. On the contrary, spaceborne Earth observation data are effective and economical information sources to estimate and monitor AGB at a large scale. In this paper, we present a study on the use of different spaceborne multispectral remote sensing data for the prediction of forest AGB. The objective is to evaluate the effects of temporal, spectral, and spatial capacities of multispectral satellite data for AGB prediction. The study was performed on multispectral data acquired by Sentinel-2, RapidEye, and Dove satellites which are characterized by different spatial resolutions, temporal availability, and number of spectral bands. A systematic process of least absolute shrinkage and selection operator (lasso) variable selection generalized linear modeling, leave-one-out cross-validation, and analysis was accomplished on each satellite dataset for AGB prediction. Results point out that the multitemporal data based AGB models were more effective in prediction than the single-time models. In addition, red-edge and short wave infrared (SWIR) channel dependent variables showed significant improvement in the modeling results and contributed to more than 50% of the selected variables. Results also suggest that high spatial resolution plays a smaller role than spectral and temporal information in the prediction of AGB. The overall analysis emphasizes a good potential of spaceborne multispectral data for developing sophisticated methods for AGB prediction especially with specific spectral channels and temporal information.

show abstract

“…De acuerdo con Herold et al (2011) existe un particular interés en el manejo forestal del uso de sensores remotos para la estimación de atributos forestales, ya que favorecen la obtención de datos consistente, actualizada y espacialmente explícita en áreas de difícil acceso y con amplia cobertura. Al respecto, la estimación de parámetros forestales a partir de la combinación del uso de sensores remotos y de sitios de campo georreferenciados (sitios permanentes) se han convertido en técnicas útiles y confiables para estimar variables como el volumen forestal, el área basal y la biomasa forestal aérea (Hernández-Ramos et al, 2020;López-Serrano et al, 2020).…”

Section: Introductionunclassified

“…Con base en esas tecnologías, dicha actividad se realiza de manera indirecta con el uso de técnicas estadísticas robustas bajo el supuesto de una alta correlación entre datos satelitales y datos del inventario tradicional (Aguirre-Salado et al, 2011;Song, 2013;Wulder et al, 2014;Acosta et al, 2017;López-Serrano et al, 2020).…”

Section: Introductionunclassified

“…Dicha variación en los resultados del RCME y R 2 Adj en la estimación y monitoreo de la vegetación con sensores remotos podrían atribuirse a la resolución espacial de las imágenes, a las condiciones ambientales prevalecientes durante su toma, e incluso al tipo de vegetación en cada estudio de caso (López-Serrano et al, 2016;Torres-Rojas et al,2016;Hawryło et al, 2018;Pham et al, 2019;Hernández-Ramos et al, 2020;López-Serrano et al, 2020).…”

unclassified

See 1 more Smart Citation

Estimación de parámetros forestales mediante datos de Sentinel 2A en Pueblo Nuevo, Durango

López-Serrano

Vega-Nieva

Aldaba

et al. 2021

RMCF

Self Cite

View full text Add to dashboard Cite

Los bosques templados requieren de un monitoreo periódico con el fin de lograr un manejo sustentable. Los sensores remotos permiten hacer estimaciones de manera indirecta bajo el supuesto de que existe una correlación estadística entre datos satelitales y parámetros forestales. El objetivo del presente trabajo fue estimar el área basal (G), el volumen forestal (Vta) y la biomasa forestal aérea (W) mediante datos espectrales del satélite Sentinel 2A en la Comunidad de San Bernardino de Milpillas Chico, Pueblo Nuevo, Durango. Se realizó un análisis de correlación entre información dasométrica procedente de 22 Sitios Permanentes de Investigación Forestal y de Suelos (SPIFyS) e información espectral de alta resolución del sensor Sentinel 2A. Posteriormente, se generó un modelo de regresión múltiple para cada parámetro forestal. El coeficiente de correlación (r) más alto se observó en el NDVI con valores de 0.77, 0.68 y 0.76 para los parámetros forestales de Vta, G y W, respectivamente. Los modelos desarrollados explicaron 59 % de la varianza total observada en el Vta (RCME=57.60 m3 ha-1), 58 % en W (RCME=39.29 Mg ha-1), y 51 % en G (RCME=4.40 m2 ha-1). El NDVI fue la principal variable predictiva en los tres modelos. Los datos de Sentinel 2A con resolución de 10 m en combinación con información dasométrica derivada de SPIFyS mostraron una buena capacidad para el mapeo de parámetros forestales en bosques templados.

show abstract

Modeling of Aboveground Biomass with Landsat 8 OLI and Machine Learning in Temperate Forests

Cited by 62 publications

References 86 publications

Modeling Forest Aboveground Carbon Density in the Brazilian Amazon with Integration of MODIS and Airborne LiDAR Data

Modeling Forest Aboveground Carbon Density in the Brazilian Amazon with Integration of MODIS and Airborne LiDAR Data

Prediction of Forest Aboveground Biomass Using Multitemporal Multispectral Remote Sensing Data

Estimación de parámetros forestales mediante datos de Sentinel 2A en Pueblo Nuevo, Durango

Contact Info

Product

Resources

About