Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments

Zhao, Quantang; Yu, Shikai; Zhao, Fei; Tian, Linghong; Zhong, Zhao

doi:10.1016/j.foreco.2018.12.019

Cited by 105 publications

(54 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RFs were more consistent in responding to small perturbations in the data, and the randomness in the RFs reduces overfitting during model training [71]. This result was consistent with some other studies that showed that RF and SVR have great potential for forest biomass estimation with remote-sensing techniques [41,44,46,47]. Additionally, the main advantage of the RF algorithm was to identify important predictor variables and model the relationship between them and the AGC.…”

Section: Model Performance Of the Mlassupporting

confidence: 85%

“…The MLAs, which demonstrated great potential to estimate forest parameters, especially AGB and AGC, can overcome the multicollinearity problem and they do not make assumptions about the nature of the data distribution [44]. The comparison of the MLAs showed that RFs had better performance in AGC estimation than SVR and ANN in this study ( Table 4).…”

Section: Model Performance Of the Mlasmentioning

confidence: 67%

“…However, linear regression methods are based on the assumption of linear relationships between biomass and predictors or independent variables, and thus, they may not provide satisfactory results due to the complex relationships between remote-sensing variables and biomass [41][42][43]. In this case, nonparametric and machine-learning algorithms (MLAs), such as artificial neural network (ANN), support vector regression (SVR), and random forest (RF), can deal with nonlinear relationships, learn from limited training data, and successfully solve classification problems that are difficult to distinguish; such approaches have been widely employed in forest biomass estimation [41,42,[44][45][46][47]. Nevertheless, there is no single MLA that performs best for every study object and area [41,[44][45][46][47], and a comparison of MLAs is highly desired, which will help us select the most appropriate model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Remote Estimation of Mangrove Aboveground Carbon Stock at the Species Level Using a Low-Cost Unmanned Aerial Vehicle System

Zan

Yang

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

There is ongoing interest in developing remote sensing technology to map and monitor the spatial distribution and carbon stock of mangrove forests. Previous research has demonstrated that the relationship between remote sensing derived parameters and aboveground carbon (AGC) stock varies for different species types. However, the coarse spatial resolution of satellite images has restricted the estimated AGC accuracy, especially at the individual species level. Recently, the availability of unmanned aerial vehicles (UAVs) has provided an operationally efficient approach to map the distribution of species and accurately estimate AGC stock at a fine scale in mangrove areas. In this study, we estimated mangrove AGC in the core area of northern Shenzhen Bay, South China, using four kinds of variables, including species type, canopy height metrics, vegetation indices, and texture features, derived from a low-cost UAV system. Three machine-learning algorithm models, including Random Forest (RF), Support Vector Regression (SVR), and Artificial Neural Network (ANN), were compared in this study, where a 10-fold cross-validation was used to evaluate each model’s effectiveness. The results showed that a model that used all four type of variables, which were based on the RF algorithm, provided better AGC estimates (R2 = 0.81, relative RMSE (rRMSE) = 0.20, relative MAE (rMAE) = 0.14). The average predicted AGC from this model was 93.0 ± 24.3 Mg C ha−1, and the total estimated AGC was 7903.2 Mg for the mangrove forests. The species-based model had better performance than the considered canopy-height-based model for AGC estimation, and mangrove species was the most important variable among all the considered input variables; the mean height (Hmean) the second most important variable. Additionally, the RF algorithms showed better performance in terms of mangrove AGC estimation than the SVR and ANN algorithms. Overall, a low-cost UAV system with a digital camera has the potential to enable satisfactory predictions of AGC in areas of homogenous mangrove forests.

show abstract

Section: Model Performance Of the Mlassupporting

confidence: 85%

Section: Model Performance Of the Mlasmentioning

confidence: 67%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remote Estimation of Mangrove Aboveground Carbon Stock at the Species Level Using a Low-Cost Unmanned Aerial Vehicle System

Zan

Yang

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Random forest (RF) is a machine learning algorithm based on decision trees that has been used extensively for forest AGB mapping using remote sensing data in the last two decades. RF provides higher accuracy than comparative machine learning methods and conventional statistical regressions because RF is less sensitive to noise in the training samples (Hoover et al 2018;Powell et al 2010;Zhao et al 2019). However, a major shortcoming of RF is that it ignores the spatial autocorrelation of the data when mapping the feature distribution (Chen et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests

Shen

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Aboveground biomass (AGB) is a fundamental indicator of forest ecosystem productivity and health and hence plays an essential role in evaluating forest carbon reserves and supporting the development of targeted forest management plans. Methods: Here, we proposed a random forest/co-kriging framework that integrates the strengths of machine learning and geostatistical approaches to improve the mapping accuracies of AGB in northern Guangdong province of China. We used Landsat time-series observations, Advanced Land Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) data, and National Forest Inventory (NFI) plot measurements, to generate the forest AGB maps at three time points (1992, 2002, and 2010) showing the spatio-temporal dynamics of AGB in the subtropical forests in Guangdong, China. Results: The proposed model provided excellent performance for mapping AGB using spectral, textural, and topographical variables, and the radar backscatter coefficients. The root mean square error of the plot-level AGB validation was between 15.62 and 53.78 (t/ha), the mean absolute error ranged from 6.54 to 32.32 t/ha, and the relative improvement over the random forest algorithm was between 3.8% and 17.7%. The highest coefficient of determination (0.81) and the lowest mean absolute error (6.54 t/ha) were observed in the 1992 AGB map. The spectral saturation effect was minimized by adding the PALSAR data to the modeling variable set in 2010. By adding elevation as a covariable, the co-kriging outperformed the ordinary kriging method for the prediction of the AGB residuals, because co-kriging resulted in better interpolation results in the valleys and plains of the study area. Conclusions: Validation of the three AGB maps with an independent dataset indicated that the random forest/co-kriging performed best for AGB prediction, followed by random forest coupled with ordinary kriging (random forest/ordinary kriging), and the random forest model. The proposed random forest/co-kriging framework provides an accurate and reliable method for AGB mapping in subtropical forest regions with complex topography. The resulting AGB maps are suitable for the targeted development of forest management actions to promote carbon sequestration and sustainable forest management in the context of climate change.

show abstract

“…This study provides a methodology on forest condition assessment at regional scales, as well as the up-to-date information for the forest ecosystem in the CMNNR. usually contains indicators of community structure and productivity [6][7][8]. The sub-compartment measurements of the National Forest Inventory in China contain the information about structure, including canopy closure, stand density and forest age, and function, including stand volume and soil condition [9,10].The explicit mapping of spatial variations of forest structure and function parameters has been an essential effort in ecological analysis [11][12][13][14].…”

mentioning

confidence: 99%

Mapping Spatial Variations of Structure and Function Parameters for Forest Condition Assessment of the Changbai Mountain National Nature Reserve

et al. 2019

View full text Add to dashboard Cite

Forest condition is the baseline information for ecological evaluation and management. The National Forest Inventory of China contains structural parameters, such as canopy closure, stand density and forest age, and functional parameters, such as stand volume and soil fertility. Conventionally forest conditions are assessed through parameters collected from field observations, which could be costly and spatially limited. It is crucial to develop modeling approaches in mapping forest assessment parameters from satellite remote sensing. This study mapped structure and function parameters for forest condition assessment in the Changbai Mountain National Nature Reserve (CMNNR). The mapping algorithms, including statistical regression, random forests, and random forest kriging, were employed with predictors from Advanced Land Observing Satellite (ALOS)-2, Sentinel-1, Sentinel-2 satellite sensors, digital surface model of ALOS, and 1803 field sampled forest plots. Combined predicted parameters and weights from principal component analysis, forest conditions were assessed. The models explained spatial dynamics and characteristics of forest parameters based on an independent validation with all r values above 0.75. The root mean square error (RMSE) values of canopy closure, stand density, stand volume, forest age and soil fertility were 4.6%, 33.8%, 29.4%, 20.5%, and 14.3%, respectively. The mean assessment score suggested that forest conditions in the CMNNR are mainly resulted from spatial variations of function parameters such as stand volume and soil fertility. This study provides a methodology on forest condition assessment at regional scales, as well as the up-to-date information for the forest ecosystem in the CMNNR. usually contains indicators of community structure and productivity [6][7][8]. The sub-compartment measurements of the National Forest Inventory in China contain the information about structure, including canopy closure, stand density and forest age, and function, including stand volume and soil condition [9,10].The explicit mapping of spatial variations of forest structure and function parameters has been an essential effort in ecological analysis [11][12][13][14]. Remote sensing modeling combined sample plot data has become a well adopted method to generate spatially explicit estimates of forest parameters [15,16]. The selection of predictor variables from various sensors and algorithms can affect the results considerably [17,18]. Variables from optical sensors are commonly applied to predict horizontal forest structure such as canopy closure and density [19,20]. This is due to the close relationship between horizontal forest structure and aggregate spectral signatures, i.e., reflectance or vegetation indices, with global coverage, repetitiveness, and cost-effectiveness [21,22]. However, synthetic aperture radar (SAR) and light detection and ranging (LiDAR) sensors are capable of penetrating cloud and canopies and are suitable for mapping vertical forest parameters such as tree height and stand volum...

show abstract

Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments

Cited by 105 publications

References 45 publications

Remote Estimation of Mangrove Aboveground Carbon Stock at the Species Level Using a Low-Cost Unmanned Aerial Vehicle System

Remote Estimation of Mangrove Aboveground Carbon Stock at the Species Level Using a Low-Cost Unmanned Aerial Vehicle System

Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests

Mapping Spatial Variations of Structure and Function Parameters for Forest Condition Assessment of the Changbai Mountain National Nature Reserve

Contact Info

Product

Resources

About