Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River, China

Ge, J.; Meng, Baoping; Liang, Tiangang; Feng, Qisheng; Gao, Jinlong; Yang, Shuai; Huang, Xiaodong; Xie, Hongjie

doi:10.1016/j.rse.2018.09.019

Cited by 107 publications

(95 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, our analysis revealed that most of the reviewed studies focused on the investigation of single river basins only, in particular ∼94% of all articles (e.g., [15,38,39]). In ∼6% of all studies, more than one river basin was analyzed (e.g., [40][41][42]).…”

Section: Spatial Scale Of Reviewed Research Articlesmentioning

confidence: 99%

“…For example, Huang et al [118] evaluated land surface change induced by fire events using Landsat-based normalized difference vegetation index (NDVI), albedo, and land surface temperature. In addition, several studies quantified vegetation cover changes with specific focus on the source regions of the Mekong, Yangtze, and Yellow river basins (e.g., [39,120,121]). These studies used MODIS as well as SPOT-VGT data at low spatial resolution together with meteorological measurements.…”

Section: Biosphere: Vegetationmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Earth Observation-Based Analyses for Major River Basins

Uereyen

Kuenzer

2019

Remote Sensing

View full text Add to dashboard Cite

Regardless of political boundaries, river basins are a functional unit of the Earth’s land surface and provide an abundance of resources for the environment and humans. They supply livelihoods supported by the typical characteristics of large river basins, such as the provision of freshwater, irrigation water, and transport opportunities. At the same time, they are impacted i.e., by human-induced environmental changes, boundary conflicts, and upstream–downstream inequalities. In the framework of water resource management, monitoring of river basins is therefore of high importance, in particular for researchers, stake-holders and decision-makers. However, land surface and surface water properties of many major river basins remain largely unmonitored at basin scale. Several inventories exist, yet consistent spatial databases describing the status of major river basins at global scale are lacking. Here, Earth observation (EO) is a potential source of spatial information providing large-scale data on the status of land surface properties. This review provides a comprehensive overview of existing research articles analyzing major river basins primarily using EO. Furthermore, this review proposes to exploit EO data together with relevant open global-scale geodata to establish a database and to enable consistent spatial analyses and evaluate past and current states of major river basins.

show abstract

Section: Spatial Scale Of Reviewed Research Articlesmentioning

confidence: 99%

Section: Biosphere: Vegetationmentioning

confidence: 99%

A Review of Earth Observation-Based Analyses for Major River Basins

Uereyen

Kuenzer

2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…A number of carbon stock estimation methods have been developed to ues remote-sensing data [19,[21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40]. The most popular and commonly used approaches are empirical statistical methods [18,[21][22][23]26,31], which link various predictor variables derived from remotely sensed data to carbon stock values measured at the ground.…”

Section: Introductionmentioning

confidence: 99%

“…The most popular and commonly used approaches are empirical statistical methods [18,[21][22][23]26,31], which link various predictor variables derived from remotely sensed data to carbon stock values measured at the ground. Another widely used type of approach is machine-learning methods, such as artificial neural networks [18,31,35,36], support vector machines [37], and random forests [31,32,[38][39][40]. Unlike regression methods, these approaches can easily handle a large number of explanatory variables derived from remotely sensed and ancillary data that are linearly or nonlinearly related to biomass [41].…”

Section: Introductionmentioning

confidence: 99%

Estimating Grassland Carbon Stocks in Hulunber China, Using Landsat8 Oli Imagery and Regression Kriging †

Ding

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

Accurately estimating grassland carbon stocks is important in assessing grassland productivity and the global carbon balance. This study used the regression kriging (RK) method to estimate grassland carbon stocks in Northeast China based on Landsat8 operational land imager (OLI) images and five remote sensing variables. The normalized difference vegetation index (NDVI), the wide dynamic range vegetation index (WDRVI), the chlorophyll index (CI), Band6 and Band7 were used to build the RK models separately and to explore their capabilities for modeling spatial distributions of grassland carbon stocks. To explore the different model performances for typical grassland and meadow grassland, the models were validated separately using the typical steppe, meadow steppe or all-steppe ground measurements based on leave-one-out crossvalidation (LOOCV). When the results were validated against typical steppe samples, the Band6 model showed the best performance (coefficient of determination (R2) = 0.46, mean average error (MAE) = 8.47%, and root mean square error (RMSE) = 10.34 gC/m2) via the linear regression (LR) method, while for the RK method, the NDVI model showed the best performance (R2 = 0.63, MAE = 7.04 gC/m2, and RMSE = 8.51 gC/m2), which were much higher than the values of the best LR model. When the results were validated against the meadow steppe samples, the CI model achieved the best estimation accuracy, and the accuracy of the RK method (R2 = 0.72, MAE = 8.09 gC/m2, and RMSE = 9.89 gC/m2) was higher than that of the LR method (R2 = 0.70, MAE = 8.99 gC/m2, and RMSE = 10.69 gC/m2). Upon combining the results of the most accurate models of the typical steppe and meadow steppe, the RK method reaches the highest model accuracy of R2 = 0.69, MAE = 7.40 gC/m2, and RMSE = 9.01 gC/m2, while the LR method reaches the highest model accuracy of R2 = 0.53, MAE = 9.20 gC/m2, and RMSE = 11.10 gC/m2. The results showed an improved performance of the RK method compared to the LR method, and the improvement in the accuracy of the model is mainly attributed to the enhancement of the estimation accuracy of the typical steppe. In the study region, the carbon stocks showed an increasing trend from west to east, the total amount of grassland carbon stock was 79.77 × 104 Mg C, and the mean carbon stock density was 47.44 gC/m2. The density decreased in the order of temperate meadow steppe, lowland meadow steppe, temperate typical steppe, and sandy steppe. The methodology proposed in this study is particularly beneficial for carbon stock estimates at the regional scale, especially for countries such as China with many grassland types.

show abstract

“…In the broad spectrum of machine learning models, Support Vector Machine (SVM) is one of the most widely used models. In geosciences, SVMs have been used to interpolate scarce measurements to regional [2][3][4], continental [5,6] and global scales [7,8]. SVM was introduced in the early 1990s [9] for classification and later extended to function regression [10].…”

Section: Introductionmentioning

confidence: 99%

Generalization of Parameter Selection of SVM and LS-SVM for Regression

Zeng

Tan

Matsunaga

et al. 2019

MAKE

View full text Add to dashboard Cite

A Support Vector Machine (SVM) for regression is a popular machine learning model that aims to solve nonlinear function approximation problems wherein explicit model equations are difficult to formulate. The performance of an SVM depends largely on the selection of its parameters. Choosing between an SVM that solves an optimization problem with inequality constrains and one that solves the least square of errors (LS-SVM) adds to the complexity. Various methods have been proposed for tuning parameters, but no article puts the SVM and LS-SVM side by side to discuss the issue using a large dataset from the real world, which could be problematic for existing parameter tuning methods. We investigated both the SVM and LS-SVM with an artificial dataset and a dataset of more than 200,000 points used for the reconstruction of the global surface ocean CO2 concentration. The results reveal that: (1) the two models are most sensitive to the parameter of the kernel function, which lies in a narrow range for scaled input data; (2) the optimal values of other parameters do not change much for different datasets; and (3) the LS-SVM performs better than the SVM in general. The LS-SVM is recommended, as it has less parameters to be tuned and yields a smaller bias. Nevertheless, the SVM has advantages of consuming less computer resources and taking less time to train. The results suggest initial parameter guesses for using the models.

show abstract

Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River, China

Cited by 107 publications

References 84 publications

A Review of Earth Observation-Based Analyses for Major River Basins

A Review of Earth Observation-Based Analyses for Major River Basins

Estimating Grassland Carbon Stocks in Hulunber China, Using Landsat8 Oli Imagery and Regression Kriging †

Generalization of Parameter Selection of SVM and LS-SVM for Regression

Contact Info

Product

Resources

About