中国土壤学过去30年在一些关键领域的研究进展

Due to continuous decreases in arable land area and continuous population increases,Chinese soil scientists face great challenges in meeting food demands,mitigating adverse environmental impacts,and sustaining or enhancing soil productivity under intensive agriculture.With the aim of promoting the application of soil science knowledge,this paper reviews the achievements of Chinese scientists in soil resource use and management,soil fertility,global change mitigation and soil biology over the last 30 years.During this period,soil resource science has provided essential support for the use and exploitation of Chinese soil resources,and has itself developed through introduction of new theories such as Soil Taxonomy and new technologies such as remote sensing.Soil fertility science has contributed to the alleviation and elimination of impeding physical and chemical factors that constrain availability of essential nutrients and water in soils,the understanding of nutrient cycling in agroecosystems,and the increase in nutrient use efficiency for sustainable crop production.Chinese soil scientists have contributed to the understanding of the cropland’s role in global change,particularly to the understanding of methane and nitrous oxide emission from rice fields and the effect of elevated carbon dioxide and ozone on rice-wheat system.Soil biology research has progressed in biological N fixation,distribution of fauna in Chinese soils,and bioremediation of polluted soils.A new generation of soil scientists has arisen in the last three decades.The gaps between research and application in these soil science fields are also discussed.     

内盖夫荒漠中小型土壤节肢动物群落的时空变化

Desert ecosystems are characterized by sparse vegetation that affects both abiotic parameters and soil biota along the soil profile.This study was conducted in 2010–2011 in a loess plain in the northern Negev Desert highlands, Israel, to test two main hypotheses:1) the abundance and diversity of microarthropods would vary seasonally in the top 30-cm soil layer, but would be relatively stable at soil depths between 30 and 50 cm and 2) soil microarthropods would be more abundant in soils under shrubs with large litter accumulations than under shrubs with less litter or bare soil. Soil samples were collected each season from the 0–50 cm profile at10-cm intervals under the canopies of Hammada scoparia and Zygophyllum dumosum and from the bare interspaces between them.Soil moisture and soil organic carbon in the top 30-cm layers varied seasonally, but there was little variation in the soil layers deeper than 30 cm. Soil mites were most abundant in the top 30-cm soil layer in autumn and winter, with the highest number of families found in winter. There were no differences in soil microarthropod abundance attributable to the presence or absence of shrubs of either species. The microarthropod communities of the microhabitats studied consisted of Acari, Psocoptera, and Collembola. The Acari were mostly identified to the family level and were dominated by Oribatida(55%) and Prostigmata(41%) in all seasons and microhabitats, while the psocopterans were most abundant in summer. These results are opposite to those obtained in other studies in similar xeric environments. Moreover, our findings were not in line with our hypothesis that a better microhabitat played a major role in microarthropod community composition, diversity, and density.     

长期种植苜蓿对中国半干旱地区黄土钾含量和粘土矿物的影响

Alfalfa cropping has been considered an efficient method of increasing soil fertility.Usually nitrogen increase in root nodules is considered to be the major beneficial effect.A 21-year time series (five sampling periods) of alfalfa cultivation plots on a loess soil,initially containing illite and chlorite,in Lanzhou of northwestern China was selected to investigate the relationships among alfalfa cropping,soil potassium (K) content and soil clay minerals.The results indicated that soil K significantly accumulated after cropping,with a peak value at about 15 years,and decreased afterwards.The accumulated K was associated with the K increase in the well-crystallized illite,which was not extracted by the traditional laboratory K extraction methods in assessing bioavailability.The steep decline in soil K content after 15-year cropping was in accord with the observed fertility loss in the alfalfa soil.Plant biomass productivity peaked at near 9 years of culture,whereas soil K and clay minerals continued to increase until cropping for 15 years.This suggested that K increased in the topsoil came from the deep root zone.Thus alfalfa continued to store K in clays even after peak production occurred.Nitrogen did not follow these trends,showing a general decline compared with the native prairie soils that had not been cropped.Therefore,the traditional alfalfa cropping can increase K content in the topsoil.     

类似但成土因素不同的土壤：巴西始成土的趋同演变

Soils result from the interaction of five independent formation factors.If one factor varies,while the others remain constant,different soils can be produced.Herein,we demonstrated an opposing trend,wherein two soils were similar,despite considerable differences in all factors of soil formation.We sampled two Inceptisols (Oxic Dystrudepts) formed on different parent materials (gneiss vs.mica schist),climate (tropical altimontane vs.warmer,drier plateau),topography (1 650 m,45％ slope vs.1000 m,8％ slope),time (rejuvenated vs.old,stable surface),and vegetation (rainforest vs.Cerrado savanna).The two soils had similar chemical properties,whereas the soil on mica schist had finer particle size distribution,lower porosity,and lower saturated hydraulic conductivity.These properties were related to a coarser blocky microstructure compared to the soil on gneiss.Both soils presented active mineral weathering and pronounced pedoplasmation,demonstrated by clay contents ＞ 300 g kg-1,although only the Dystrudept on gneiss possessed coarse rock fragments.The C horizons of both soils presented fragmented clay coatings suggestive of argilluviation,likely relict,because they were not observed in the B horizons.The similarities in many properties of the two Dystrudepts,despite contrasting factors of soil formation,suggest converging evolution and that soil classification at the subgroup level was efficient in grouping similar formative processes in tropical conditions.Moreover,this work revealed that similar pedogenic processes acting on different factors of soil formation can result in similar soil properties,at least for Inceptisols where further soil development is hindered by topographic limitations.     

地中海生态系统中可溶性有机N研究

Dissolved organic nitrogen (DON) in soils has recently gained increasing interest because it may be both a direct N source for plants and the dominant available N form in nutrient-poor soils, however, its prevalence in Mediterranean ecosystems remains unclear. The aims of this study were to i) estimate soil DON in a wide set of Mediterranean ecosystems and compare this levels with those for other ecosystems; ii) describe temporal changes in DON and dissolved inorganic nitrogen (DIN) forms (NH4+ and NO3? ), and characterize spatial heterogeneity within plant communities; and iii) study the relative proportion of soil DON and DIN forms as a test of Schimel and Bennett’s hypothesis that the prevalence of different N forms follows a gradient of nutrient availability. The study was carried out in eleven plant communities chosen to represent a wide spectrum of Mediterranean vegetation types, ranging from early to late successional status. DON concentrations in the studied Mediterranean plant communities (0-18.2 mg N kg-1) were consistently lower than those found in the literature for other ecosystems. We found high temporal and spatial variability in soil DON for all plant communities. As predicted by the Schimel and Bennett model for nutrient-poor ecosystems, DON dominance over ammonium and nitrate was observed for most plant communities in winter and spring soil samples. However, mineral-N dominated over DON in summer and autumn. Thus, soil water content may have an important effect on DON versus mineral N dominance in Mediterranean ecosystems.     

利用有机质和pH值估算中国西北和东北退耕还林土壤容重

Regression models for predicting soil bulk density (BD) have usually been related to organic matter content,but it remains unknown whether soil acidity modifies this relationship,particularly for afforested/reforested soils.We measured soil BD along with organic matter content and pH in an afforested/reforested area in Northwest and Northeast China.Using these measurements,we parameterized and validated three BD models:the Adams equation,and exponential and radical models.Model validation showed that the Adams equation failed to predict the BD of the afforested/reforested soils,producing a large overestimation.Incorporation of soil pH into the Adams equation significantly improved its performance.The exponential and radical models parameterized by the measured data simulated soil BD quite well,particularly when soil pH was incorporated.However,incorporation of soil texture variables into these models did not improve model performance compared with the pH-modified models.This led to the conclusion that the Adams equation,exponential,and radical models with pH modification are applicable to afforested/reforested soils with various acidities.     

基于小白菜Cd吸收推算土壤Cd安全阈值

Cadmium(Cd), a common toxic heavy metal in soil, has relatively high bioavailability, which seriously threatens agricultural products. In this study, 8 different soils with contrasting soil properties were collected from different regions in China to investigate the Cd transfer coefficient from soil to Chinese cabbage(Brassica chinensis L.) and the threshold levels of Cd in soils for production of Chinese cabbage according to the food safety standard for Cd. Exogenous Cd(0–4 mg kg~(-1)) was added to the soils and equilibrated for 2 weeks before Chinese cabbage was grown under greenhouse conditions. The influence of soil properties on the relationship between soil and cabbage Cd concentrations was investigated. The results showed that Cd concentration in the edible part of Chinese cabbage increased linearly with soil Cd concentration in 5 soils, but showed a curvilinear pattern with a plateau at the highest dose of exogenous Cd in the other 3 soils. The Cd transfer coefficient from soil to plant varied significantly among the different soils and decreased with increasing soil p H from 4.7 to 7.5. However, further increase in soil pH to 8.0 resulted in a significant decrease in the Cd transfer coefficient. According to the measured Cd transfer coefficient and by reference to the National Food Safety Standards of China, the safety threshold of Cd concentration in soil was predicted to be between 0.12 and 1.7 mg kg~(-1) for the tested soils. The predicted threshold values were higher than the current soil quality standard for Cd in 5 soils, but lower than the standard in the other 3 soils. Regression analysis showed a significant positive relationship between the predicted soil Cd safety threshold value and soil p H in combination with soil organic matter or clay content.     

巴西东北部地区土地退化对土壤微生物量和活性的影响

Land degradation causes great changes in the soil biological properties.The process of degradation may decrease soil microbial biomass and consequently decrease soil microbial activity.The study was conducted out during 2009 and 2010 at the four sites of land under native vegetation(NV),moderately degraded land(LDL),highly degraded land(HDL) and land under restoration for four years(RL) to evaluate changes in soil microbial biomass and activity in lands with different degradation levels in comparison with both land under native vegetation and land under restoration in Northeast Brazil.Soil samples were collected at 0-10 cm depth.Soil organic carbon(SOC),soil microbial biomass C(MBC) and N(MBN),soil respiration(SR),and hydrolysis of fluorescein diacetate(FDA) and dehydrogenase(DHA) activities were analyzed.After two years of evaluation,soil MBC,MBN,FDA and DHA had higher values in the NV,followed by the RL.The decreases of soil microbial biomass and enzyme activities in the degraded lands were approximately 8-10 times as large as those found in the NV.However,after land restoration,the MBC and MBN increased approximately 5-fold and 2-fold,respectively,compared with the HDL.The results showed that land degradation produced a strong decrease in soil microbial biomass.However,land restoration may promote short-and long-term increases in soil microbial biomass.     

人工油松林中跳虫群落恢复状况

Large areas of forest plantations have been developed in China.It is important to evaluate the soil fauna in plantations and the conditions needed for their recovery in view of the large areas of plantations in China.Three Pinus tabulaeformis forests,a 26-year-old plantation (P26) and a 45-year-old plantation (P45),exposed to clear-cutting before plantation,and an 80-260-year-old natural forest (N260),were chosen to study the effects of different forest ages/types on Collembola community in the litter and soil layers during 2008 and 2009.Soil conditions in P26 and P45 were significantly deteriorated when compared to N260.A higher value of soil bulk density and lower values of soil organic matter,soil N,litter depth,soil pH,and soil water content were observed in P26 and P45.Totally,the same genera of Collembola tended to occur in the forests of all ages studied;however,the Collembola community structure was significantly impacted by the differences in forest age.Both in the litter and soil layers,the density and generic richness of the Collembola were the highest in N260 and the lowest in P26.Some collembolan groups were sensitive to soil conditions in particular forest ages.N260 was associated with relatively high abundance of Plutomurus collembolans and P45 with relatively high abundance of Pseudofolsomia collembolans.The canonical correspondence analysis showed that the community structure of Collembola was mainly affected by forest age in both litter and soil layer.The ordination analysis of non-metric multidimensional scaling also found that the Collembola community did not recover to the level of natural forests in 26-year regeneration after clear-cutting.Even in 45-year regeneration after clear-cutting,the Collembola community only showed a slight recovery to the level of natural forests.Our results clearly showed that both Collembola community and soil conditions did not recover in 26-and 45-year regeneration after clear-cutting in P.tabulaeformis plantations;however,they might have the potential to recover in the future because the same genera of Collembola were distributed in the plantations and natural forests.     

中国亚热带不同种植制度下的土壤侵蚀

In order to optimise land use systems, to prevent erosion-induced degradation and to restore the degraded red soils in subtropical China, five cropping systems and four agroforestry systems were conducted in red soils with a slope of 7° from 1993 to 1995. The results showed that erosion risk period occurred from April to June, and the annual runoff and the losses of soil and nutrients with sediment were alarming for two conventional farming systems, whereas they were negligible for the farming systems with ridge tillage. Enrichment ratios of the lost soils from erosion were more than 1.20 for all nutrients with much higher values for hydrolysable N and organic matter. Compared with the control, the alley cropping systems also distinctly decreased runoff by 30% or 50%. However, the coverage of soil surface varied with alley cropping systems for the competition of nutrients and soil water, which made a profound difference in runoff. The cropping systems of sweet potato intercropped with soybean, the alley cropping systems and the measures of mulching and ridge tillage were the alternatives for red soil reclamation so as to prevent erosion-induced degradation.     

Estimating the bulk density in 0– 20 cm of tilled soils in China’s Loess Plateau using support vector machine modeling

ABSTRACT

Pedotransfer functions (PTFs), as an indirect forecasting method, offer an alternative for labor-intensive bulk density (BD) measurements. In order to improve the forecasting accuracies, support vector machine (SVM) method was first used to develop PTFs for predicting BD. Cross-validation and grid-search methods were used to automatically determine the SVM parameters in the forecasting process. Soil texture and organic matter content were selected as input variables based on results of predecessors, coupled with gray correlation theory. And additional properties were added as inputs for improving PTF's accuracy and reliability. The performance of the PTF established by SVM method was compared with artificial neural network (ANN) method and published PTFs using two indexes: root-mean-square error (RMSE) and coefficient of determination(R²). Results showed that the average RMSE of published PTFs was 0.1053, and the R² was 0.4558. The RMSE of ANN–PTF was 0.0638, and the R² was 0.7235. The RMSE of SVM–PTF was 0.0558, and the R² was 0.7658. Apparently, the SVM–PTF had better performance, followed by ANN–PTF. Additionally, performances could be improved when accumulated receiving water was added as predictor variable. Therefore, the first application of SVM data mining techniques in the prediction of soil BD was successful, improved the accuracy of predictions, and enhanced the function of soil PTFs. The idea of developing PTFs using SVM method for predicting soil BD in the study area could provide a reference for other areas.     

Predicting Cationic Exchange Capacity in Calcareous Soils of East-Azerbaijan Province,Northwest Iran

The aim of this research is to study the efficiency of pedotransfer functions (PTFs) and artificial neural networks (ANNs) for cationic exchange capacity (CEC) prediction using readily available soil properties. Here, 417 soil samples were collected from the calcareous soils located in East-Azerbaijan province, northwest Iran and readily available soil properties, such as particle size distribution (PSD), organic matter (OM) and calcium carbonate equivalent (CCE), were measured. The entire 417 soil samples were divided into two groups, a training data set (83 soil samples) and test data set (334 soil samples). The performances of several published and derived PTFs and developed neural network algorithms using multilayer perceptron were compared, using a test data set. Results showed that, based on statistics of RMSE and R², PTFs and ANNs had a similar performance, and there was no significant difference in the accuracy of the model results. The result of the sensitivity analysis showed that the ANN models were very sensitive to the clay variable (due to the high variability of the clay). Finally, the models tested in this study could account for 85% of the variations in cationic exchange capacity (CEC) of soils in the studied area.

Abbreviations: ANN: arti?cial neural networks; MLP: multilayer perceptron; MLR: multiple linear regression; PTFs: Pedotransfer Functions; RBF: Radial Basis Function; MAE: mean absolute error; MSE: mean square error; CEC: cationic exchange capacity     

Development of ensemble pedotransfer functions for cation exchange capacity of soils of Qingdao in China

Soil cation exchange capacity (CEC), which is considered to be an indicator of buffering capacity, is an important soil attribute that influences soil fertility but is costly, time‐consuming and labour‐intensive to measure. Pedotransfer functions (PTFs) have routinely been used to predict soil CEC from easily measured soil properties, such as soil pH, texture and organic matter content. However, uncertainty in which one to select can be substantial as different PTFs do not necessarily produce the same result. In this study, a total of 100 soil samples were collected from surface horizons (0–20 cm) in different regions of Qingdao City, China. Three ensemble PTFs (ePTFs), including simple ensemble mean (SEM), individually bias‐removed ensemble mean (IBREM) and collective bias‐removed ensemble mean (CBREM), were developed to reduce the uncertainty in CEC prediction based on 12 published regression‐based PTFs. In addition, a local PTF (LPTF) for CEC was also developed using multiple stepwise regression and basic soil properties. The performances of the three ePTFs were compared with those of the published PTFs and LPTF. Results show that the differences between the performances of the published PTFs were substantial. When the systematic bias of each published PTF was removed separately, the prediction capability of the PTFs was increased. The performance of LPTF was significantly better than that of SEM, but slightly worse than IBREM. It is noted that CBREM had higher accuracy than all of the other methods. Overall, CBREM is a promising approach for estimating soil CEC in the study area.     

Estimation of bulk density of waterlogged soils from basic properties

Pedotransfer functions (PTFs) to predict bulk density (BD) from basic soil data are presented. Available data pertaining to seasonally impounded shrink–swell soils of Jabalpur district in the Madhya Pradesh state of India were used for the study. The data included horizon-wise information of 41 soil profiles in the study area covering nearly 5 million ha. Six independent variables, namely textural data (sand, silt and clay), field capacity (FC), permanent wilting point (PWP) and organic carbon content (OC) were used as input in hierarchical steps to establish dependencies, with bulk density as the dependent variable, using statistical regression and artificial neural networks. The PTFs derived using neural networks [average root mean square error (RMSE) 0.05] were relatively better than statistical regression PTFs (average RMSE > 0.1). The best-performing PTFs required input data on sand, silt content, FC and PWP, with lowest prediction errors (RMSE 0.01, maximum absolute error (MAE) 0.01) and highest values of index of agreement (d, 0.95) and R ² (0.65). Use of measures of structure, as well as information on pore structure, was found to be essential to derive acceptable PTFs. Inclusion of OC as an input variable showed relatively better fitting to the training data set, implying an underlying relationship between OC and BD, but the neural networks could not mimic the relationship when tested against subset.     

Alternative methods in the development of pedotransfer functions for soil hydraulic characteristics

Soil hydraulic properties are needed in the modeling of water flow and solute movement in the vadose zone. Pedotransfer functions (PTFs) have received the attention of many researchers for indirect determination of hydraulic properties from basic soil properties as an alternative to direct measurement. The objective of this study was to compare the performance of cascade forward network (CFN), multiple-linear regression (MLR), and seemingly unrelated regression (SUR) methods using prediction capabilities of point and parametric PTFs developed by these methods. The point PTFs estimated field capacity (FC), permanent wilting point (PWP), available water capacity (AWC), and saturated hydraulic conductivity (Ks) and the parametric PTFs estimated the van Genuchten retention parameters. A total of 180 soil samples was extracted from the UNSODA database and divided into two groups as 135 for the development and 45 for the validation of the PTFs. The model performances were evaluated with three statistical tools: the maximum error (ME), the model efficiency (EF), and the D index (D) using the observed and predicted values of a given parameter. Despite the fact that the differences among the three methods in prediction accuracies of the point and parametric PTFs were not statistically significant (p > 0.05) except θ_r and α (p < 0.05) based on the ANOVA test, overall MLR and SUR were somewhat better than CFN in prediction of the point PTFs, whereas CFN performed better than the other two methods in prediction of the parametric PTFs. The F.F values of FC and θ_r for CFN, MLR, and SUR methods were 0.705. 0.805, 0.795 and 0.356, −0.290, −0.290, respectively, which refer to the best and worst predictions. Properties (Ks, θ_r, α) having some difficulty in prediction were better predicted by CFN and SUR methods, where these methods predict all hydraulic properties from basic soil properties simultaneously rather than individually as in MLR. This suggests that multivariate analysis using such functional relationships between hydraulic properties and basic soil properties can be utilized in developing more accurate point and parametric PTFs with less time and effort.     

Pedotransfer functions for predicting bulk density of coastal soils in East China

Soil bulk density(BD) is an important physical property and an essential factor for weight-to-volume conversion. However, BD is often missing from soil databases because its direct measurement is labor-intensive, time-consuming, and sometimes impractical, particularly on a large scale. Therefore, pedotransfer functions(PTFs) have been developed over several decades to predict BD. Here, six previously revised PTFs(including five basic functions and stepwise multiple linear regression(SMLR)) and t...     

Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity

Modeling water flow and solute transport in vadose zone requires knowledge of soil hydraulic properties, which are water retention and hydraulic conductivity curves. As an alternative to direct measurement, indirect determination of these functions from basic soil properties using pedotransfer functions (PTFs) has attracted the attention of researchers in a variety of fields such as soil scientists, hydrologists, and agricultural and environmental engineers. In this study, PTFs for point and parametric (van Genuchten's parameters) estimation of soil hydraulic parameters from basic soil properties such as particle-size distribution, bulk density, and three different pore sizes were developed and validated using artificial neural network (ANN) and multiple-linear regression methods and the predictive capabilities of the two methods was compared using some evaluation criteria. Total of 195 soil samples was divided into two groups as 130 for the development and 65 for the validation of PTFs. Although the differences between the two methods were not statistically significant (p > 0.05), regression predicted point and parametric variables of soil hydraulic parameters better than ANN. Both methods had lower accuracy in parametric predictions than in point predictions. Accuracy of the predictions was evaluated by the coefficient of determination (R²) and the root mean square error (RMSE) between the measured and predicted parameter values. The R² and RMSE varied from 0.637 to 0.979 and from 0.013 to 0.938 for regression, and varied from 0.444 to 0.952 and from 0.020 to 3.511 for ANN, respectively. Even though regression performs insignificantly better than ANN in this case, ANN produces promising results and its advantages can be utilized by developing or using new algorithms in future studies.     

Selection of a Suitable Soft Computing Model for Estimation of Soil Cation Exchange Capacity

ABSTRACT

Measuring of soil cation exchange capacity (CEC) is difficult and time-consuming. Therefore, it is essential to develop an indirect approach such as pedotransfer functions (PTFs) to predict this property from more readily available soil data. The aim of this study was to compare multiple linear and nonlinear regression, adaptive neurofuzzy inference system, and an artificial neural network (ANN) model to develop PTFs for predicting soil CEC. One hundred and seventy-one soil samples were used into two subsets for training and testing of the models. The model's prediction capability was evaluated by statistical indicators that include RMSE, R², MBE, and RI. Results showed that the ANN model had the most reliable prediction when compared with other models. This study provides a strong basis for predicting soil CEC and identifying the most determinant properties influencing soil CEC in the north regions of Iran. Analytical framework results could be applied to other parts of the world with similar challenges.

Abbreviations: ANFIS: Adaptive Neuro-Fuzzy Inference System; ANN: Artificial Neural Network; CEC: Cation Exchange Capacity; CV: Coefficient of Variation; FFBP: Feed-Forward Back-Propagation; FIS: Fuzzy Inference System; MBE: Mean Bias Error; MF: Membership Function; MLR: Multiple Linear Regressions; MNLR: Multiple Non-Linear Regressions; MLP: Multi-layer Perceptron; OC: Organic Carbon; PTFs: Pedotransfer Functions; R²: Determination Coefficient; RI: Relative Improvement; RMSE: Root Mean Square Error; SD: Standard Deviation     

Enhancing pedotransfer functions with environmental data for estimating bulk density and effective cation exchange capacity in a data‐sparse situation

Soil bulk density (BD) and effective cation exchange capacity (ECEC) are among the most important soil properties required for crop growth and environmental management. This study aimed to explore the combination of soil and environmental data in developing pedotransfer functions (PTFs) for BD and ECEC. Multiple linear regression (MLR) and random forest model (RFM) were employed in developing PTFs using three different data sets: soil data (PTF‐1), environmental data (PTF‐2) and the combination of soil and environmental data (PTF‐3). In developing the PTFs, three depth increments were also considered: all depth, topsoil (<0.40 m) and subsoil (>0.40 m). Results showed that PTF‐3 (R²; 0.29–0.69) outperformed both PTF‐1 (R²; 0.11–0.18) and PTF‐2 (R²; 0.22–0.59) in BD estimation. However, for ECEC estimation, PTF‐3 (R²; 0.61–0.86) performed comparably as PTF‐1 (R²; 0.58–0.76) with both PTFs out‐performing PTF‐2 (R²; 0.30–0.71). Also, grouping of data into different soil depth increments improves the estimation of BD with PTFs (especially PTF‐2 and PTF‐3) performing better at subsoils than topsoils. Generally, the most important predictors of BD are sand, silt, elevation, rainfall, temperature for estimation at topsoil while EVI, elevation, temperature and clay are the most important BD predictors in the subsoil. Also, clay, sand, pH, rainfall and SOC are the most important predictors of ECEC in the topsoil while pH, sand, clay, temperature and rainfall are the most important predictors of ECEC in the subsoil. Findings are important for overcoming the challenges of building national soil databases for large‐scale modelling in most data‐sparse countries, especially in the sub‐Saharan Africa (SSA).     

Model Development to Predict CEC Using the Intelligence Data Mining Approaches

ABSTRACT

Using easily measurable soil properties and pedotransfer functions (PTFs) is a time-saving, non-destructive and cost-saving way in the prediction of the cation exchange capacity (CEC). The purpose of this study was to compare and evaluate the regression tree (RT), multiple linear regression (MLR) and Mamdani fuzzy inference system (MFIS) in estimating CEC. For this work, 100 soil samples from unsaturated soil hydraulic database (UNSODA) data-set were used. %Organic matter (OM), bulk density (BD), the geometric mean particle diameter (dg) and fractal dimension of particle size (D) were applied as the input predictive variables. First, the type of relationship between easily measurable soil properties and CEC was investigated and, then used for the development of PTFs and fuzzy membership functions. The results showed that MLR method was developed only based on %OM (r = 0.68, p < .01) and D (r = 0.68, p < .01). While in the RT method, all of the predictive variables were appeared in the tree-like based on their correlation coefficient with CEC. The D and %OM also were considered as input variables in developing fuzzy membership functions. Results also revealed that RT method had a higher performance than MLR and MFIS in the estimation of CEC with the highest coefficient of determination (R² = 0.77), smallest root-mean-square error (RMSE = 5.14 meq/100_gsoil), normalized root-mean-square error (NRMSE = 0.25 meq/100_gsoil) and mean error (ME = ?1.80 meq/100_gsoil). In addition, the MFIS had a higher efficiency than the MLR in the CEC estimation.