scholarly journals Evaluation of FORMOSAT-2 and PlanetScope Imagery for Aboveground Oil Palm Biomass Estimation in a Mature Plantation in the Congo Basin

2020 ◽  
Vol 12 (18) ◽  
pp. 2926
Author(s):  
Pierre Migolet ◽  
Kalifa Goïta
Keyword(s):  
Remote Sensing ◽  
Oil Palm ◽  
Aboveground Biomass ◽  
Fourier Transforms ◽  
Canopy Structure ◽  
Principal Component ◽  
Congo Basin ◽  
Biomass Estimation ◽  
Mean Square Errors

The present study developed methods using remote sensing for estimation of total dry aboveground biomass (AGB) of oil palm in the Congo Basin. To achieve this, stem diameters at breast height (DBH, 1.3 m) and stem heights were measured in an oil palm plantation located in Gabon (Congo Basin, Central Africa). These measurements were used to determine AGB in situ. The remote sensing approach that was used to estimate AGB was textural ordination (FOTO) based upon Fourier transforms that were applied, respectively, to PlanetScope and FORMOSAT-2 satellite images taken from the area. The FOTO method is based on the combined use of two-dimensional (2D) Fast Fourier Transform (FFT) and Principal Component Analysis (PCA). In the context of the present study, it was used to characterize the variation in canopy structure and to estimate the aboveground biomass of mature oil palms. Two types of equations linking FOTO indices to in situ biomass were developed: multiple linear regressions (MLR); and multivariate adaptive spline regressions (MARS). All best models developed yielded significant results, regardless of whether they were derived from PlanetScope or from FORMOSAT-2 images. Coefficients of determination (R2) varied between 0.80 and 0.92 (p ≤ 0.0005); and relative root mean-square-errors (%RMSE) were less than 10.12% in all cases. The best model was obtained using MARS approach with FOTO indices from FORMOSAT-2 (%RMSE = 6.09%).

scholarly journals Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

Forests ◽  
2019 ◽  
Vol 10 (12) ◽  
pp. 1073 ◽  
Author(s):  
Li ◽  
Li ◽  
Li ◽  
Liu
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Variable Selection ◽  
Aboveground Biomass ◽  
Forest Type ◽  
Learning Algorithms ◽  
Forest Biomass ◽  
Machine Learning Algorithms ◽  
Biomass Estimation ◽  
Landsat 8

Forest biomass is a major store of carbon and plays a crucial role in the regional and global carbon cycle. Accurate forest biomass assessment is important for monitoring and mapping the status of and changes in forests. However, while remote sensing-based forest biomass estimation in general is well developed and extensively used, improving the accuracy of biomass estimation remains challenging. In this paper, we used China’s National Forest Continuous Inventory data and Landsat 8 Operational Land Imager data in combination with three algorithms, either the linear regression (LR), random forest (RF), or extreme gradient boosting (XGBoost), to establish biomass estimation models based on forest type. In the modeling process, two methods of variable selection, e.g., stepwise regression and variable importance-base method, were used to select optimal variable subsets for LR and machine learning algorithms (e.g., RF and XGBoost), respectively. Comfortingly, the accuracy of models was significantly improved, and thus the following conclusions were drawn: (1) Variable selection is very important for improving the performance of models, especially for machine learning algorithms, and the influence of variable selection on XGBoost is significantly greater than that of RF. (2) Machine learning algorithms have advantages in aboveground biomass (AGB) estimation, and the XGBoost and RF models significantly improved the estimation accuracy compared with the LR models. Despite that the problems of overestimation and underestimation were not fully eliminated, the XGBoost algorithm worked well and reduced these problems to a certain extent. (3) The approach of AGB modeling based on forest type is a very advantageous method for improving the performance at the lower and higher values of AGB. Some conclusions in this paper were probably different as the study area changed. The methods used in this paper provide an optional and useful approach for improving the accuracy of AGB estimation based on remote sensing data, and the estimation of AGB was a reference basis for monitoring the forest ecosystem of the study area.

A survey of remote sensing-based aboveground biomass estimation methods in forest ecosystems

2014 ◽  
Vol 9 (1) ◽  
pp. 63-105 ◽  
Author(s):  
Dengsheng Lu ◽  
Qi Chen ◽  
Guangxing Wang ◽  
Lijuan Liu ◽  
Guiying Li ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Aboveground Biomass ◽  
Forest Ecosystems ◽  
Estimation Methods ◽  
Biomass Estimation

scholarly journals Modeling Evapotranspiration during SMACEX: Comparing Two Approaches for Local- and Regional-Scale Prediction

2005 ◽  
Vol 6 (6) ◽  
pp. 910-922 ◽  
Author(s):  
H. Su ◽  
M. F. McCabe ◽  
E. F. Wood ◽  
Z. Su ◽  
J. H. Prueger
Keyword(s):  
Remote Sensing ◽  
Surface Energy ◽  
Regional Scale ◽  
Remote Sensing Data ◽  
Surface Fluxes ◽  
Heat Fluxes ◽  
High Quality ◽  
Sensing Data ◽  
Mean Square Errors

Abstract The Surface Energy Balance System (SEBS) model was developed to estimate land surface fluxes using remotely sensed data and available meteorology. In this study, a dual assessment of SEBS is performed using two independent, high-quality datasets that are collected during the Soil Moisture–Atmosphere Coupling Experiment (SMACEX). The purpose of this comparison is twofold. First, using high-quality local-scale data, model-predicted surface fluxes can be evaluated against in situ observations to determine the accuracy limit at the field scale using SEBS. To accomplish this, SEBS is forced with meteorological data derived from towers distributed throughout the Walnut Creek catchment. Flux measurements from 10 eddy covariance systems positioned on these towers are used to evaluate SEBS over both corn and soybean surfaces. These data allow for an assessment of modeled fluxes during a period of rapid vegetation growth and varied hydrometeorology. Results indicate that SEBS can predict evapotranspiration with accuracies approaching 10%–15% of that of the in situ measurements, effectively capturing the temporal development of surface flux patterns for both corn and soybean, even when the evaporative fraction ranges between 0.50 and 0.90. Second, utilizing high-resolution remote sensing data and operational meteorology, a catchment-scale examination of model performance is undertaken. To extend the field-based assessment of SEBS, information derived from the Landsat Enhanced Thematic Mapper (ETM) and data from the North American Land Data Assimilation System (NLDAS) were combined to determine regional surface energy fluxes for a clear day during the field experiment. Results from this analysis indicate that prediction accuracy was strongly related to crop type, with corn predictions showing improved estimates compared to those of soybean. Although root-mean-square errors were affected by the limited number of samples and one poorly performing soybean site, differences between the mean values of observations and SEBS Landsat-based predictions at the tower sites were approximately 5%. Overall, results from this analysis indicate much potential toward routine prediction of surface heat fluxes using remote sensing data and operational meteorology.

Sign in / Sign up

Export Citation Format

Share Document