Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data

Chen, Lin; Wang, Yeqiao; Ren, Chunying; Zhang, Bai; Wang, Zongming

doi:10.3390/rs11040414

Cited by 82 publications

(74 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RF is a decision tree algorithm and an effective machine learning model for predicting a forest of variables. Based on its powerful modeling capabilities, the RF regression has been widely used in scientific research [94][95][96][97][98][99]. The principle of the RF algorithm is to use the bootstrap method to randomly extract multiple samples to generate a group of regression trees (ntree) from the original sample population.…”

Section: Statistical Models For Estimating the Fsvmentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The forest stock volume (FSV) is one of the key indicators in forestry resource assessments on local, regional, and national scales. To date, scaling up in situ plot-scale measurements across landscapes is still a great challenge in the estimation of FSVs. In this study, Sentinel-2 imagery, the Google Earth Engine (GEE) cloud computing platform, three base station joint differential positioning technology (TBSJDPT), and three algorithms were used to build an FSV model for forests located in Hunan Province, southern China. The GEE cloud computing platform was used to extract the imagery variables from the Sentinel-2 imagery pixels. The TBSJDPT was put forward and used to provide high-precision positions of the sample plot data. The random forests (RF), support vector regression (SVR), and multiple linear regression (MLR) algorithms were used to estimate the FSV. For each pixel, 24 variables were extracted from the Sentinel-2 images taken in 2017 and 2018. The RF model performed the best in both the training phase (i.e., R 2 = 0.91, RMSE = 35.13 m 3 ha −1 , n = 321) and in the test phase (i.e., R 2 = 0.58, RMSE = 65.03 m 3 ha −1 , and n = 138). This model was followed by the SVR model (R 2 = 0.54, RMSE = 65.60 m 3 ha −1 , n = 321 in training; R 2 = 0.54, RMSE = 66.00 m 3 ha −1 , n = 138 in testing), which was slightly better than the MLR model (R 2 = 0.38, RMSE = 75.74 m 3 ha −1 , and n = 321 in training; R 2 = 0.49, RMSE = 70.22 m 3 ha −1 , and n = 138 in testing) in both the training phase and test phase. The best predictive band was Red-Edge 1 (B5), which performed well both in the machine learning methods and in the MLR method. The Blue band (B2), Green band (B3), Red band (B4), SWIR2 band (B12), and vegetation indices (TCW, NDVI_B5, and TCB) were used in the machine learning models, and only one vegetation index (MSI) was used in the MLR model. We mapped the FSV distribution in Hunan Province (3.50 × 10 8 m 3 ) based on the RF model; it reached a total accuracy of 63.87% compared with the official forest report in 2017 (5.48 × 10 8 m 3 ). The results from this study will help develop and improve satellite-based methods to estimate FSVs on local, regional and national scales.The forest stock volume (FSV, m 3 ha −1 ) is the sum of the stem volumes of all the living trees per unit area, and is one of key forest variables for forest resources management and assessments on local, region and country scales [1]. FSVs have a strong relationship with the aboveground biomass (AGB) and carbon stocks [2]. To understand the spatial distribution of carbon in forests and to derive predictions for monitoring carbon stock trends, the FSV must be quantified [3]. Traditionally, the FSV is estimated by sampling several plots, which involves substantial manpower, materials, and financial resources [4]. With the development of remote sensing technology, particularly the Landsat series since 1972, satellite imagery has played an important role in forest inventory. Various studies have been performed to estimate the forest variables ...

show abstract

Section: Statistical Models For Estimating the Fsvmentioning

confidence: 99%

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The ALOS Global Digital Surface Model (AW3D30) used in this study was a global dataset generated from L band SAR images collected using the ALOS from 2006 to 2011 ( Figure 1e). The data were download from the Japan Aerospace Exploration Agency to extract topographic indices from previous researches by Spatial Analyst of ArcGIS software (version 10.0, ESRI, RedLands, CA, USA) [60,61]. All remote sensing variables were re-projected into UTM Zone 52 WGS84, and then resampled to the 30 m pixel size by ArcGIS.…”

Section: Satellite Data Pre-processing and Derived Variablesmentioning

confidence: 99%

Multi-Sensor Prediction of Stand Volume by a Hybrid Model of Support Vector Machine for Regression Kriging

Chen

Ren

Zhang

et al. 2020

Forests

Self Cite

View full text Add to dashboard Cite

Quantifying stand volume through open-access satellite remote sensing data supports proper management of forest stand. Because of limitations on single sensor and support vector machine for regression (SVR) as well as benefits from hybrid models, this study innovatively builds a hybrid model as support vector machine for regression kriging (SVRK) to map stand volume of the Changbai Mountains mixed forests covering 171,450 ha area based on a small training dataset (n = 928). This SVRK model integrated SVR and its residuals interpolated by ordinary kriging. To determine the importance of multi-sensor predictors from ALOS and Sentinel series, the increase in root mean square error (RMSE) of SVR was calculated by removing the variable after the standardization. The SVRK model achieved accuracy with mean error, RMSE and correlation coefficient in -2.67%, 25.30% and 0.76, respectively, based on an independent dataset (n = 464). The SVRK improved the accuracy of 9% than SVR based on RMSE values. Topographic indices from L band InSAR, backscatters of L band SAR, and texture features of VV channel from C band SAR, as well as vegetation indices of the optical sensor were contributive to explain spatial variations of stand volume. This study concluded that SVRK was a promising approach for mapping stand volume in the heterogeneous temperate forests with limited samples.

show abstract

“…By producing the forest up to a user-defined number of trees, RF creates trees with large variance and small bias [98,99]. The abovementioned two user-defined parameters, i.e., numFeatures and numIterations, were selected by the smallest root mean square error (RMSE) in WEKA software (version 3.8, The University of Waikato, Hamilton, New Zealand), and the attribute importance was also estimated [100]. The new unlabeled data were input to evaluate and vote, and the finial prediction was the average of the membership (Figure 2a).…”

Section: Spatial Modeling Of Stand Volume and Forest Age By Random Fomentioning

confidence: 99%

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

et al. 2019

Self Cite

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

Optimal Combination of Predictors and Algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data

Cited by 82 publications

References 84 publications

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Estimating Forest Stock Volume in Hunan Province, China, by Integrating In Situ Plot Data, Sentinel-2 Images, and Linear and Machine Learning Regression Models

Multi-Sensor Prediction of Stand Volume by a Hybrid Model of Support Vector Machine for Regression Kriging

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

Contact Info

Product

Resources

About