Unraveling the local and structured variation of soil nutrients using two-dimensional empirical model decomposition in Fen River Watershed, China

Zhu, Hongfen; Sun, Ruipeng; Bi, Rutian; Li, Tiangliang; Jing, Yaodong; Hu, Wei

doi:10.1080/03650340.2019.1681588

Cited by 6 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is the BIMF, and r(x,y) is the residue. The detailed description of 2DEMD can be found in other studies (Huang et al, 2017;Xu, Wang, & Xu, 2011;Zhu et al, 2019).…”

Section: Data Acquisitionmentioning

confidence: 99%

Revealing the 2D–scale, location–specific variations of soil properties in the coal mining area of Changhe watershed, China

Zhu

Sun

et al. 2020

Land Degrad Dev

Self Cite

View full text Add to dashboard Cite

Many researches have been conducted to understand the scale-location specific variations of soil properties in one-dimensional soil samples. However, these results did not enable us to properly understand the 2D (two-dimensional) distributions of soil characteristics, especially in the coal mining areas. Therefore, the objective of this study is to reveal the scale-location dependent variation of two-dimensional patterns for soil properties and to develop a soil organic matter (SOM) prediction based on those scale-location effects in the coal mining area. To this end, SOM, porosity, and silt were measured in the top (0-20 cm), middle (20-40 cm), and bottom (40-60 cm) layers of soil in Changhe watershed, China. The scale-specific spatial patterns of soil properties were extracted using two-dimensional empirical mode decomposition (2DEMD), and SOM was predicted using stepwise multiple linear regression (SMLR) and 2DEMD GS. It was found that the spatial distributions of SOM residue (>24 km) at middle layer and porosity residue at top and bottom layers could reveal the differentiation between coal mining and non-coal mining areas. The scale-effects on the relationships between SOM and its covariates was stronger than that of land uses, and the relationships of SOM with the covariates in different land use types were distinctive at top layer, and were similar at bottom layer. 2DEMD GS performed better than SMLR on SOM prediction for its involvement of scale and location effects. Therefore, the relationship between SOM and influencing factors is a function of scale, location, and land uses activities, and the scale-and location-dependent method should be considered for SOM prediction. K E Y W O R D S bidimensional intrinsic mode function (BIMF), coal mining area, land use type, soil organic matter (SOM), two-dimensional empirical mode decomposition (2DEMD) 1 | INTRODUCTION Soil is one of the most valuable nonrenewable resources (Lal, 2015) and serves as an nexus for the atmosphere, hydrosphere, biosphere, and lithosphere (Alcañiz, Outeiro, Francos, & Úbeda, 2018). Previous studies indicated that minesoils undergo rapid changes in chemical, physical, and biological properties as a result of mining activities and pedogenic weathering processes (Shrestha & Lal, 2007; Skousen, 1995), and their spatial variation differed greatly compared with those in the non

show abstract

“…is the BIMF, and r(x,y) is the residue. The detailed description of 2DEMD can be found in other studies (Huang et al, 2017;Xu, Wang, & Xu, 2011;Zhu et al, 2019).…”

Section: Data Acquisitionmentioning

confidence: 99%

Revealing the 2D–scale, location–specific variations of soil properties in the coal mining area of Changhe watershed, China

Zhu

Sun

et al. 2020

Land Degrad Dev

Self Cite

View full text Add to dashboard Cite

show abstract

“…The spatial distributions of BIMF1 varied greatly (Figure 3), and the worst predicting performance at BIMF1 (Table 5) demonstrated the stochastic variation at the small scale of BIMF1. In addition, a previous study [31] also proved the stochastic variation of soil nutrients at the small scale of BIMF1. Consequently, predicting models that excluded BIMF1 could improve their stability of predicting performance.…”

Section: Discussionmentioning

confidence: 76%

“…Two-dimensional empirical mode decomposition has been used to separate the overall variation of any spatial or temporal dataset into different scale components called bi-dimensional intrinsic mode function (BIMFs) [31]. Unlike EMD finding the overall extrema, 2D-EMD determines the local extrema (maxima and minima) of the spatial dataset.…”

Section: Two-dimensional Empirical Mode Decomposition (2d-emd)mentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Soil Nutrients Based on Topographic Factors and Remote Sensing Index in a Coal Mining Area, China

et al. 2020

Self Cite

View full text Add to dashboard Cite

1) Background: Coal mining operations caused severe land subsidence and altered the distributions of soil nutrients that influenced by multiple environmental factors at different scales. However, the prediction performances for soil nutrients based on their scale-specific relationships with influencing factors remains undefined in the coal mining area. The objective of this study was to establish prediction models of soil nutrients based on their scale-specific relationships with influencing factors in a coal mining area. (2) Methods: Soil samples were collected based on a 1 × 1 km regular grid, and contents of soil organic matter, soil available nitrogen, soil available phosphorus, and soil available potassium were measured. The scale components of soil nutrients and the influencing factors collected from remote sensing and topographic factors were decomposed by two-dimensional empirical mode decomposition (2D-EMD), and the predictions for soil nutrients were established using the methods of multiple linear stepwise regression or partial least squares regression based on original samples (MLSR Ori or PLSR Ori ), partial least squares regression based on bi-dimensional intrinsic mode function (PLSR BIMF ), and the combined method of 2D-EMD, PLSR, and MLSR (2D-EMD PM ).(3) Results: The correlation types and correlation coefficients between soil nutrients and influencing factors were scale-dependent. The variances of soil nutrients at smaller scale were stochastic and non-significantly correlated with influencing factors, while their variances at the larger scales were stable. The prediction performances in the coal mining area were better than those in the non-coal mining area, and 2D-EMD PM had the most stable performance. (4) Conclusions: The scale-dependent predictions can be used for soil nutrients in the coal mining areas.

show abstract

“…Agricultural production [ 35 , 36 , 37 ], soil structure [ 38 ], soil properties [ 39 ], soil sample data characteristics [ 40 ], along with the methods of data preprocessing [ 16 , 41 ], all affect the STN concentration prediction modeling and model performance. Due to the results we achieved in this paper, the STN prediction models with good performance and generalization come from the data set with greater size and more evenly distributed within a country.…”

Section: Resultsmentioning

confidence: 99%

Comparison of Soil Total Nitrogen Content Prediction Models Based on Vis-NIR Spectroscopy

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Visible-near-infrared spectrum (Vis-NIR) spectroscopy technology is one of the most important methods for non-destructive and rapid detection of soil total nitrogen (STN) content. In order to find a practical way to build STN content prediction model, three conventional machine learning methods and one deep learning approach are investigated and their predictive performances are compared and analyzed by using a public dataset called LUCAS Soil (19,019 samples). The three conventional machine learning methods include ordinary least square estimation (OLSE), random forest (RF), and extreme learning machine (ELM), while for the deep learning method, three different structures of convolutional neural network (CNN) incorporated Inception module are constructed and investigated. In order to clarify effectiveness of different pre-treatments on predicting STN content, the three conventional machine learning methods are combined with four pre-processing approaches (including baseline correction, smoothing, dimensional reduction, and feature selection) are investigated, compared, and analyzed. The results indicate that the baseline-corrected and smoothed ELM model reaches practical precision (coefficient of determination (R2) = 0.89, root mean square error of prediction (RMSEP) = 1.60 g/kg, and residual prediction deviation (RPD) = 2.34). While among three different structured CNN models, the one with more 1 × 1 convolutions preforms better (R2 = 0.93; RMSEP = 0.95 g/kg; and RPD = 3.85 in optimal case). In addition, in order to evaluate the influence of data set characteristics on the model, the LUCAS data set was divided into different data subsets according to dataset size, organic carbon (OC) content and countries, and the results show that the deep learning method is more effective and practical than conventional machine learning methods and, on the premise of enough data samples, it can be used to build a robust STN content prediction model with high accuracy for the same type of soil with similar agricultural treatment.

show abstract

Unraveling the local and structured variation of soil nutrients using two-dimensional empirical model decomposition in Fen River Watershed, China

Cited by 6 publications

References 31 publications

Revealing the 2D–scale, location–specific variations of soil properties in the coal mining area of Changhe watershed, China

Revealing the 2D–scale, location–specific variations of soil properties in the coal mining area of Changhe watershed, China

Prediction of Soil Nutrients Based on Topographic Factors and Remote Sensing Index in a Coal Mining Area, China

Comparison of Soil Total Nitrogen Content Prediction Models Based on Vis-NIR Spectroscopy

Contact Info

Product

Resources

About