Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau

Dai, Fuqiang; Zhou, Qihai; Lv, Zhiqiang; Wang, Xuemei; Liu, Gangcai

doi:10.1016/j.ecolind.2014.04.003

Cited by 203 publications

(105 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the case of MLR and ANN methods, residual kriging contributed to better accuracy of the basal area estimates. These results are consistent with the results of Dai et al (2014), who reported that the combination of the residual kriging with artificial neural networks provides an improvement in the estimate accuracy of the variables of interest. The combination of MLR with residual kriging also provided improvements in estimates in the studies of Viana et al (2012), Castillo-Santiago et al (2013), and GaleanaPizaña et al (2014.…”

Section: Discussionsupporting

confidence: 82%

Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

Reis

Carvalho

Mello

et al. 2018

N.Z. j. of For. Sci.

View full text Add to dashboard Cite

Background: In fast-growing forests such as Eucalyptus plantations, the correct determination of stand productivity is essential to aid decision making processes and ensure the efficiency of the wood supply chain. In the past decade, advances in remote sensing and computational methods have yielded new tools, techniques, and technologies that have led to improvements in forest management and forest productivity assessments. Our aim was to estimate and map the basal area and volume of Eucalyptus stands through the integration of forest inventory, remote sensing, parametric, and nonparametric methods of spatial prediction. Methods: This study was conducted in 20 5-year-old clonal stands (362 ha) of Eucalyptus urophylla S.T.Blake x Eucalyptus camaldulensis Dehnh. The stands are located in the northwest region of Minas Gerais state, Brazil. Basal area and volume data were obtained from forest inventory operations carried out in the field. Spectral data were collected from a Landsat 5 TM satellite image, composed of spectral bands and vegetation indices. Multiple linear regression (MLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN) methods were used for basal area and volume estimation. Using ordinary kriging, we spatialised the residuals generated by the spatial prediction methods for the correction of trends in the estimates and more detailing of the spatial behaviour of basal area and volume. Results: The ND54 index was the spectral variable that had the best correlation values with basal area (r = − 0.91) and volume (r = − 0.52) and was also the variable that most contributed to basal area and volume estimates by the MLR and RF methods. The RF algorithm presented smaller basal area and volume errors when compared to other machine learning algorithms and MLR. The addition of residual kriging in spatial prediction methods did not necessarily result in relative improvements in the estimations of these methods. Conclusions: Random forest was the best method of spatial prediction and mapping of basal area and volume in the study area. The combination of spatial prediction methods with residual kriging did not result in relative improvement of spatial prediction accuracy of basal area and volume in all methods assessed in this study, and there is not always a spatial dependency structure in the residuals of a spatial prediction method. The approaches used in this study provide a framework for integrating field and multispectral data, highlighting methods that greatly improve spatial prediction of basal area and volume estimation in Eucalyptus stands. This has potential to support fast growth plantation monitoring, offering options for a robust analysis of high-dimensional data.

show abstract

Section: Discussionsupporting

confidence: 82%

Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

Reis

Carvalho

Mello

et al. 2018

N.Z. j. of For. Sci.

View full text Add to dashboard Cite

show abstract

“…The estimated results of the SOM content by ELMOK were much closer to the measured values, which were demonstrated an acceptable range for monitoring site-specific SOM and its quality evaluation in comparison with [8,13,14]. Generally, a higher resolution and higher precision of SOM can capture its changes more acutely in a regional spatial range, while it is difficult to reflect the continuous dynamic changes because only one year of data is used.…”

Section: Sustainable Monitoring Of Digital Mapping For Sommentioning

confidence: 66%

“…Not only did it need to re-modeled and re-trained as the model lacked robustness and stability, but it also avoided over-fitting because the sample variations disrupted the one-to-one relationships between the pixel value of the auxiliary variables and the samples of SOM. In other words, the first subset produced was random, yet the validation set was independent in the subsequent process of modeling analysis [14,31]. Table 1 summarizes the descriptive statistics of SOM and the auxiliary variables at all sites in the study area.…”

Section: Accuracy Evaluation Of Prediction Performancementioning

confidence: 99%

“…The high-efficiency quantitative model is an indispensable technique for predicting the spatial variability of soil properties, which is based on the application of multi-source auxiliary variables [14]. The explanatory ability of spatial variability between soil properties and auxiliary variables can be efficiently described using traditional geostatistical methods such as simple kriging (SK), ordinary kriging (OK), universal kriging (UK), and cokriging (CK) [15][16][17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Prediction of Soil Organic Matter Using a Hybrid Geostatistical Model of an Extreme Learning Machine and Ordinary Kriging

Song

Lian-an

et al. 2017

Sustainability

View full text Add to dashboard Cite

An accurate estimation of soil organic matter (SOM) content for spatial non-point prediction is an important driving force for the agricultural carbon cycle and sustainable productivity. This study proposed a hybrid geostatistical method of extreme learning machine-ordinary kriging (ELMOK), to predict the spatial variability of the SOM content. To assess the feasibility of ELMOK, a case study was conducted in a regional scale study area in Shaanxi Province, China. A total of 472 topsoil (0-20 cm) samples were collected. A total of 14 auxiliary variables (predictors) were obtained from remote sensing data and environmental factors. The proposed method was compared with the ability of traditional geostatistical methods such as simple kriging (SK) and ordinary kriging (OK), in addition to hybrid geostatistical methods such as regression-ordinary kriging (ROK) and artificial neural network-ordinary kriging (ANNOK). The results showed that the extreme learning machines (ELM) model used principal components (PCs) as input variables, and performed better than both multiple linear regression (MLR) and artificial neural network (ANN) models. Compared with geostatistical and hybrid geostatistical prediction methods of SOM spatial distribution, the ELMOK model had the highest coefficient of determination (R 2 = 0.671) and ratio of performance to deviation (RPD = 2.05), as well as the lowest root mean square error (RMSE = 1.402 g kg −1 ). In conclusion, the application of remote sensing imagery and environmental factors has a deeper driven significance of a non-linear and multi-dimensional hierarchy relationship for explaining the spatial variability of SOM, tracing local carbon sink and high quality SOM maps. More importantly, it is possibly concluded that the sustainable monitoring of SOM is a significant process through the pixel-based revisit sampling, an analysis of the mapping results of SOM, and methodological integration, which is the primary step in spatial variations and time series. The proposed ELMOK methodology is a promising and effective approach which can play a vital role in predicting the spatial variability of SOM at a regional scale.

show abstract

“…To determine the output value for each location, the Kriging tool fits a mathematical function to a specified number of points, or all points within a specified radius. The Kriging process involves the following steps: a) exploratory statistical analysis of the data, b) variogram modeling, c) creating the surface, and d) exploring a variance surface which is optional (29,30). The estimator in the Kriging method is defined as follows (Equation 1):…”

Section: Statistical Analysis and Spatial Mappingmentioning

confidence: 99%

Atmospheric Heavy Metals Biomonitoring Using a Local Pinus eldarica Tree

et al. 2016

View full text Add to dashboard Cite

Background: Trees are one of the most commonly used bio-indicators and have been widely applied for heavy metals (HMs) monitoring in the ambient air because of their simple and efficient sampling and examination. Objectives: The main objective of this study was to evaluate local pine trees for their potential as a bio-indicator of HMs in urban areas. Besides, the distribution pattern of HMs in the study area, meteorological and land use factors affecting this pattern, and HMs source identification were investigated. Methods: Forty-eight sampling locations were selected in the Yazd city, capital of Yazd province in Iran, and concentrations of five HMs-iron (Fe), copper (Cu), zinc (Zn), lead (Pb), and cadmium (Cd)-were measured in the leaves of the most abundantly local pine trees, Pinus eldarica, using the atomic absorption spectroscopy method. The obtained data were analyzed for source identification using Spearman's rank correlation coefficient and principal component analysis (PCA). The ordinary Kriging method was used to obtain a spatial map of HMs distribution in the study area. Results: Iron had the highest concentration (345.0053 mg/kg) in leaves when compared with other HMs. The concentration of Zn, Cu, Pb and Cd were 26.1384, 5.5905, 2.9963 and 0.7383 mg/kg, respectively. Spatial mapping indicated that industrial districts and areas with heavy traffic had the highest HMs pollution. Wind direction was recognized to be the most important factor in HMs transportation. Anthropogenic sources were known as the main responsible factor for HMs emission. Conclusions: Pine trees can be used as a worthy bio-indicator for HMs pollution monitoring in the ambient air in areas with extensive vegetation of pine trees.

show abstract

Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau

Cited by 203 publications

References 56 publications

Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

Spatial Prediction of Soil Organic Matter Using a Hybrid Geostatistical Model of an Extreme Learning Machine and Ordinary Kriging

Atmospheric Heavy Metals Biomonitoring Using a Local Pinus eldarica Tree

Contact Info

Product

Resources

About