CN103529189B - A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable - Google Patents
A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable Download PDFInfo
- Publication number
- CN103529189B CN103529189B CN201310268497.0A CN201310268497A CN103529189B CN 103529189 B CN103529189 B CN 103529189B CN 201310268497 A CN201310268497 A CN 201310268497A CN 103529189 B CN103529189 B CN 103529189B
- Authority
- CN
- China
- Prior art keywords
- soil
- organic matter
- value
- point
- distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
4), contrast method 3), research method 2), auxiliary data source and process 1), Data Source the invention discloses a kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable, it is characterized in that: step is as follows::::.Owing to have employed technique scheme, compared with prior art, the present invention uses artificial nerve network model, on the basis of merging the quantitative and qualitative analysis auxiliary environment variablees such as soil types, terrain factor and vegetation index, carry out the space distribution prediction of soil organic matter content, to being region high precision soil Property Spaces forecast of distribution supplying method reference.
Description
Technical field
The present invention relates to a kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable.
Background technology
The soil organism is the important indicator of soil characteristic, is also the mineral nutrition of plant and organotrophic source, in regional soil fertility, agricultural production and environmental protection etc., all has important function and significance.Due to the impact of the multiple factors of soil formation and ecological process, soil organic matter content spatially presents non-uniform Distribution.Usually based on the sampling point soil organic matter content information that sampling obtains, the actual demand meeting opposite region soil content of organic matter distribution characteristics in regional agriculture production and environmental protection is difficult to.Therefore, accurately obtaining the space distribution information of soil organic matter content, is accurately grasp regional soil fertility state, the soil nutrient test of science and the actual needs of regional environment protection.
The Spatial Distribution Pattern of soil property is formed under the acting in conjunction of various ground surface environment factor.Introduce the soil property space distribution Forecasting Methodology of relevant earth's surface envirment factor as auxiliary variable, considering the impact of correlative environmental factors on soil property space distribution in varying degrees, the method that its precision of prediction more only carries out spatial interpolation based on sampling point data is significantly improved.In all kinds of auxiliary variable, Quantitative Factors is easy to operation relatively as factors such as meteorology, terrain feature parameters, is widely used in the prediction of soil property space distribution.Qualitative factor such as Land-Use, soil types and Organic matter type etc. also have significant impact to soil property spatial variability, and such factor even can weaken the effect of Quantitative Factors to soil property spatial variability.Therefore, in Forecasting Methodology, introduce quantitative and qualitative analysis auxiliary variable is improve one of the inevitable requirement and the most effective approach of soil property space distribution precision of prediction further simultaneously.But in the prediction of soil property space distribution, the use of qualitative factor is obviously on the low side.
In the Forecasting Methodology introducing environmental variance, the methods such as multivariate regression model, Cokriging and Regression-kriging method are widely used in the relation of portraying between soil property and envirment factor, and then the space distribution of prediction soil property.But be a kind of extremely complicated nonlinear relationship between soil property and environmental factor, accurately the complex relationship of expressing between soil property and environmental factor is the key improving precision of prediction.Artificial nerve network model can disclose the Nonlinear Mapping relation in complication system between polynary environmental variance and target variable more exactly, be successfully applied to the nonlinear relationship described between the soil and environment factor, in the space distribution forecasting research of soil property, receive increasing concern.
Summary of the invention
The technical problem to be solved in the present invention overcomes above-mentioned defect, there is provided a kind of and use artificial nerve network model, on the basis of merging the quantitative and qualitative analysis auxiliary environment variablees such as soil types, terrain factor and vegetation index, carry out the soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable of the space distribution prediction of soil organic matter content.
For solving the problem, the technical solution adopted in the present invention is:
Based on a soil organism space distribution Forecasting Methodology for quantitative and qualitative analysis auxiliary variable, it is characterized in that: step is as follows:
1), Data Source: with the study area topomap chosen, present landuse map and soil types distribution plan for supplementary, the basis taking into account representative and homogeneity principle considers the laying that the information such as landform, soil types carries out soil sampling point, adopts at each soil sampling point place the method for multiple spot mixing to gather top layer pedotheque; Each sampled point all records its geographic coordinate and sea level elevation with GPS, records the environmental information at sampling point place in detail simultaneously; Laboratory milled 1mm sieve after natural air drying taken back by the sample collected, and adopts potassium bichromate titrimetric method to measure each soil sample content of organic matter;
2), auxiliary data source and process:
In research, Quantitative Factors mainly have selected terrain factor and vegetation index; Terrain factor is auxiliary environment variable the most frequently used in the prediction of soil property space distribution, comprises elevation (H), the gradient (S), planar curvature (Ct), profile curvature (Cp) and Topographic Wetness Index (TI); In ArcGIS9.3, generate the data elevation model of 30m resolution based on study area 1:5 ten thousand topomap, utilize the spatial analysis of ArcGIS9.3 and raster symbol-base function to obtain the gradient of study area 30m resolution, planar curvature, profile curvature and Topographic Wetness Index distribution plan further;
The vegetation index obtained based on remote sensing image can the growth conditions of reflecting regional surface vegetation and vegetation coverage information preferably, is the another auxiliary variable being usually used in the prediction of soil property space distribution; Adopt the enhancement mode meta file in MODIS remotely-sensed data product as the quantitative Vegetation factors of forecasting research district soil organic matter content space distribution in study area;
3), research method:
What research method adopted is the radial basis function neural network method merging quantitative and qualitative analysis auxiliary variable;
Relation between the measured value of each sampled point soil organism and environmental factor is expressed as:
Z(x
i,k,y
j,k)＝m(k)+r(x
i,k,y
j,k)(1)
r(x
i,k,y
j,k)＝f(t(x
i,y
j),v(x
i,y
j),...)(2)
In formula: Z (x
i,k, y
j,k) represent that the soil sample belonging to kth kind soil types is at (x
i, y
j) content of organic matter value at place, (x
i, y
j) be sample point coordinate, its ranks number are respectively i and j; M (k) is kth kind soil types content of organic matter mean value; R (x
i,k, y
j,k) be sampled point (x
i, y
j) deduct the residual error after soil types content of organic matter mean value belonging to this point.T (x
i, y
j) be point (x
i, y
j) terrain parameter value, v (x
i, y
j) be point (x
i, y
j) vegetation index value.Namely suppose that the soil types of the variation of the soil organism on specified point position first residing for this point determines, the local environmental factors such as the landform Vegetation condition of its residual values then residing for this point are determined; Mean value m (k) and residual error r (x
i,k, y
j,k) separate.
Relation between each point position residual values and local environmental factor adopts RBF kernel function model tormulation; This model is a kind of three layers of feed-forward type neural network model with single hidden layer, and Forecasting Methodology process is as follows:
(1), according to sampled point soil organic matter content value, the mean value of each soil types soil organic matter content and residual values corresponding to each soil sampling point in statistical research district respectively;
(2), according to each soil types content of organic matter mean value calculated and study area soil types distribution plan, making and research district each soil types organic matter value content mean value distribution plan;
(3), input using the landform of each soil sampling point and vegetation characteristics parameters value as network, export using the soil organism residual values after the normalization of corresponding point position as network, build neural network model, in MATLAB, simulation obtains the residual distribution figure of the study area soil organism;
(4), finally each for study area soil types organic value mean value distribution plan is added and namely obtain study area soil organic matter content spatial distribution map by the residual distribution figure that Neural Network model predictive obtains;
4), contrast method:
Select the method method in contrast that normal stabilizing pile, Regression-kriging method and neural network model are combined with Ordinary Kriging Interpolation; The regression forecasting that first Regression-kriging method adopts multiple stepwise regression to carry out between the soil organism and envirment factor, with common Ke Lifa, interpolation is carried out to regression forecasting result residual error again, finally regression forecasting result and normal stabilizing pile are added the estimated value of residual error, namely obtain the spatial distribution map of the study area soil organism; The method that neural network model is combined with Ordinary Kriging Interpolation is then complete with the regression model in neural network model alternative regression Kriging method to predict the space distribution of the study area soil organism.
Owing to have employed technique scheme, compared with prior art, the present invention with the Santai County of hills area, the Sichuan Basin for study area, use artificial nerve network model, on the basis of merging the quantitative and qualitative analysis auxiliary environment variablees such as soil types, terrain factor and vegetation index, carry out the space distribution prediction of soil organic matter content, to being region high precision soil Property Spaces forecast of distribution supplying method reference.
Accompanying drawing explanation
Fig. 1 is the histogram of study area soil organic matter content and Logarithm conversion value thereof;
Fig. 2 is the predict the outcome figure of different Forecasting Methodology to soil organic matter content space distribution.
Embodiment
Embodiment:
Based on a soil organism space distribution Forecasting Methodology for quantitative and qualitative analysis auxiliary variable, step is as follows:
1), Data Source: with the study area topomap chosen, present landuse map and soil types distribution plan for supplementary, the basis taking into account representative and homogeneity principle considers the laying that the information such as landform, soil types carries out soil sampling point, adopts at each soil sampling point place the method for multiple spot mixing to gather top layer pedotheque.The whole district gathers soil sample 2346 sampled points altogether, and each sampled point all records its geographic coordinate and sea level elevation with GPS, simultaneously in detail the environmental information at record sampling point place as soil types, cultivate the information such as crop and farmland crop rotation method.Laboratory milled 1mm sieve after natural air drying taken back by the sample collected, and adopts potassium bichromate titrimetric method to measure each soil sample content of organic matter.
2), auxiliary data source and process:
In research, Quantitative Factors mainly have selected terrain factor and vegetation index; Terrain factor is auxiliary environment variable the most frequently used in the prediction of soil property space distribution, comprises elevation (H), the gradient (S), planar curvature (Ct), profile curvature (Cp) and Topographic Wetness Index (TI); In ArcGIS9.3, generate the data elevation model of 30m resolution based on study area 1:5 ten thousand topomap, utilize the spatial analysis of ArcGIS9.3 and raster symbol-base function to obtain the gradient of study area 30m resolution, planar curvature, profile curvature and Topographic Wetness Index distribution plan further.
The vegetation index obtained based on remote sensing image can the growth conditions of reflecting regional surface vegetation and vegetation coverage information preferably, is the another auxiliary variable being usually used in the prediction of soil property space distribution; Adopt the enhancement mode meta file in MODIS remotely-sensed data product as the quantitative Vegetation factors of forecasting research district soil organic matter content space distribution in study area.Consider the accumulation characteristic of the soil organism, the EVI data of the 250m resolution of annual July and August 16d synthesis in 2001 to 2006 years have been selected in the present invention, average and be resampled to 30m resolution after downloaded EVI data being carried out to quality check and process, namely use average vegetation index when biomass was maximum in 2001 to 2006 years as one of quantitative auxiliary variable.For convenience of calculating, all Quantitative Factors are all normalized.
Research shows, hills area soil types is large on the impact of soil organic matter content space distribution compared with land use pattern, and in therefore studying, Selecting research district soil types is as the qualitative auxiliary variable of this research.Study area soil types distribution plan derives from the second time overall survey of soil.After to the scanning of study area soil type map, utilize ArcGIS9.3 to carry out vector quantization, obtain study area digital soil Map of Distributions of Types.
3), research method:
What research method adopted is the radial basis function neural network method merging quantitative and qualitative analysis auxiliary variable;
Relation between the measured value of each sampled point soil organism and environmental factor is expressed as:
Z(x
i,k,y
j,k)＝m(k)+r(x
i,k,y
j,k)(1)
r(x
i,k,y
j,k)＝f(t(x
i,y
j),v(x
i,y
j),...)(2)
In formula: Z (x
i,k, y
j,k) represent that the soil sample belonging to kth kind soil types is at (x
i, y
j) content of organic matter value at place, (x
i, y
j) be sample point coordinate, its ranks number are respectively i and j; M (k) is kth kind soil types content of organic matter mean value; R (x
i,k, y
j,k) be sampled point (x
i, y
j) deduct the residual error after soil types content of organic matter mean value belonging to this point.T (x
i, y
j) be point (x
i, y
j) terrain parameter value, v (x
i, y
j) be point (x
i, y
j) vegetation index value.Namely suppose that the soil types of the variation of the soil organism on specified point position first residing for this point determines, the local environmental factors such as the landform Vegetation condition of its residual values then residing for this point are determined; Mean value m (k) and residual error r (x
i,k, y
j,k) separate.
Relation between each point position residual values and local environmental factor adopts RBF kernel function model tormulation; This model is a kind of three layers of feed-forward type neural network model with single hidden layer, and Forecasting Methodology process is as follows:
(1), according to sampled point soil organic matter content value, the mean value of each soil types soil organic matter content and residual values corresponding to each soil sampling point in statistical research district respectively;
(2), according to each soil types content of organic matter mean value calculated and study area soil types distribution plan, making and research district each soil types organic matter value content mean value distribution plan;
(3), input using the landform of each soil sampling point and vegetation characteristics parameters value as network, export using the soil organism residual values after the normalization of corresponding point position as network, build neural network model, in MATLAB, simulation obtains the residual distribution figure of the study area soil organism;
(4), finally each for study area soil types organic value mean value distribution plan is added and namely obtain study area soil organic matter content spatial distribution map by the residual distribution figure that Neural Network model predictive obtains;
4), contrast method:
Select the method method in contrast that normal stabilizing pile, Regression-kriging method and neural network model are combined with Ordinary Kriging Interpolation; The regression forecasting that first Regression-kriging method adopts multiple stepwise regression to carry out between the soil organism and envirment factor, with common Ke Lifa, interpolation is carried out to regression forecasting result residual error again, finally regression forecasting result and normal stabilizing pile are added the estimated value of residual error, namely obtain the spatial distribution map of the study area soil organism; The method that neural network model is combined with Ordinary Kriging Interpolation is then complete with the regression model in neural network model alternative regression Kriging method to predict the space distribution of the study area soil organism.
Adopt each method of individual authentication sampling point set pair to predict the outcome for the above-mentioned soil organism space distribution Forecasting Methodology predicted exactitude evaluation method based on quantitative and qualitative analysis auxiliary variable to evaluate, namely at random 20% (469) are extracted as check post from 2346 soil sampling points, all the other 80% (1877) are as modeling point, with mean absolute error (MAE), root-mean-square error (RMSE) and average relative error (MRE), the predicted value of check post and actual observed value are analyzed, draw precision evaluation result.
The above-mentioned soil organism space distribution Forecasting Methodology results and analysis based on quantitative and qualitative analysis auxiliary variable:
1, descriptive statistical analysis.
Show according to the statistical study of modeling point, as shown in table 1, the mean value of study area soil organism massfraction is 17.97g/kg; The coefficient of variation is between 10 ~ 100%, is moderate variability.Soil type soil organic matter content differs greatly, and rice soil quality of organic matter score average reaches 22.49g/kg, far above other 3 soil typess; Next is moisture soil and purple soil, and mean value is respectively 15.87 and 14.09g.kg-1; Yellow soil is minimum, and mean value is 13.66g.kg-1.From degree of variation, rice soil and purple soil content of organic matter degree of variation a little more than another 2 great soil groups, but all belong to moderate variation.
From the distributional pattern of data, raw data is obvious partial velocities, by its degree of bias value after Logarithm conversion and kurtosis value and distribution frequency figure obviously closer to normal distribution, as shown in table 1, Fig. 1.Therefore, the numerical value after Logarithm conversion is for the calculating of various Forecasting Methodology in studying.
Table 1 study area soil type content of organic matter descriptive statistic feature
2, the relationship analysis of the soil organism and environmental variance.
Variance analysis is utilized to test to study area soil type content of organic matter difference, result shows, as shown in table 2, there is extremely significant difference (P<0.001) in 4 kinds, the study area soil types content of organic matter, namely the space distribution of Spatial Distribution Pattern on study area soil organic matter content of soil types has important impact.
The variance analysis of the content of organic matter between table 2 soil type
Correlation analysis result between soil organic matter content and 6 Quantitative Factors shows, study area soil organic matter content is obviously subject to the impact of landform and vegetation factor, as shown in table 3.Wherein, there is extremely significant negative correlativing relation in sea level elevation and the gradient and soil organism massfraction, related coefficient is respectively-0.06 (P=0.0067<0.01) and-0.22 (P=4.17E-21<0.01), this illustrates that on the some position that physical features is higher, the gradient is larger, soil organic matter content is lower.Topographic Wetness Index and the related coefficient between vegetation index and soil organism massfraction are respectively 0.24 and 0.17, all reach extremely significant positive correlation (P=6.87E-27 and 5.67E-13), this shows that on the position that physical features is more low-lying, vegetation cover degree is larger, soil organic matter content is higher.In addition, topographic profile curvature and soil organic matter content also have correlativity (related coefficient 0.06, P=0.02) to a certain degree.
Table 3 soil type organic content and the relative coefficient (n=1877) between each soil types average residual error and envirment factor
The residual error obtained after great soil group mean value belonging to each sampling point content of organic matter being removed and each Quantitative Factors carry out correlation analysis, result shows, as shown in table 3, the related coefficient of average residual error and the gradient is-0.09, reaches extremely significant negative correlativing relation (P=9.35E-05); Be respectively 0.10 and 0.13 with the related coefficient of Topographic Wetness Index and vegetation index, all show as extremely significant positive correlation (P=9.43E-06 and 2.81E-08).This shows, after removing each soil types mean value, the difference of study area soil organic matter content is main relevant with the difference of surface slope, Topographic Wetness Index and plant cover situation.
3, Semi-variance analysis
Modeling point soil organic matter content value, the residual values of multiple stepwise regression prediction and the residual error of neural network prediction result are carried out Logarithm conversion, makes it closer to normal distribution, complete the Semi-variance analysis to above-mentioned 3 data item on this basis.Result shows, as table 4,3 data item all meet spherical model, and the coefficient of determination of model is all more than 0.85, and the fitting degree of namely selected theoretical semivariance model is higher, can reflect the spatial structure characteristic of each index preferably.From the parameter of model, the nugget effect value of 3 data item is between 0.742 ~ 0.765, and range is between 6.00 ~ 7.00km, and this shows, the space correlation degree of the study area soil organism is more weak, and the scope of spatial autocorrelation is little; Semivariance model parameter and the former variable change of regression equation and Neural Network model predictive residual error are less, substantially remain the spatial structure characteristic of former variable.
The semivariance model parameter of the table 4 study area soil organism and recurrence and neural network prediction residual values
LnSOM: the Logarithm conversion value of the soil organism; The Logarithm conversion value of lnMLRresiduals soil organism regression residuals; LnRBFNNresiduals: the Logarithm conversion value of soil organism neural network prediction residual error.
4, soil organic matter content space distribution predicts the outcome
Fig. 2 is the study area soil organic matter content spatial distribution map that different Forecasting Methodology obtains.From the figure that predicts the outcome, study area soil organic matter content distribution trend is also not obvious, and this is relevant with the landform of study area fragmentation.The distinct methods difference that predicts the outcome is obvious.Normal stabilizing pile (OK) predicts the outcome comparatively level and smooth, and Spring layer and low value district are obvious block distribution (Fig. 2 c).Regression-kriging method (RK) predicts the outcome similar with the method that neural network model combines with normal stabilizing pile (RBFNN+OK), can embody detailed information (Fig. 2 b and d) of soil organic matter content with topography variation to a certain extent; But all there are 2 pieces of high level regions significantly in block distribution in northeast, study area and east.The neural net method merging quantitative and qualitative analysis auxiliary variable predicts the outcome and does not obviously become the high level areal distribution of block in figure, and as in Fig. 2 a figure, white portion is waters, Spring layer mainly appears in the coombe of hypsography low-lying.
In Sichuan Basin, in the coombe that physical features is more low-lying, main distribute soil type is rice soil, and statistics has shown that its content of organic matter is apparently higher than other soil types, as shown in table 1.Correlation analysis shows that landform low-lying place soil organic matter content is higher, as shown in table 3.The statistic analysis result of other correlative study shows, under the mima type microrelief of Sichuan Basin, content of organic matter difference is: waist > brae, pin > mound, mound; Under this mima type microrelief, the distribution characteristics of soil organic matter content determines into the actual conditions that the Spring layer of block distribution and low value district all do not meet the study area of breaking topography.Therefore, the neural net method merging quantitative and qualitative analysis auxiliary variable is more consistent with study area actual conditions to predicting the outcome of study area soil organism Spatial Distribution Pattern.
2.5 predicted exactitude evaluation
Table 5 is error statistics results that different Forecasting Methodology predicts the outcome to 469 checking sampling points.As can be seen from error analysis, neural net method (ST+RBFNN) predicated error merging quantitative and qualitative analysis auxiliary variable is significantly less than other 3 kinds of methods.Wherein, ST+RBFNN reduces 30.78%, 27.43% and 25.70% respectively to the method that the mean absolute error that 469 checking sampling points predict the outcome is combined with Ordinary Kriging Interpolation compared with normal stabilizing pile, Regression-kriging method and neural network; Average relative error reduces 35.27%, 31.86% and 30.06% respectively, and root-mean-square error reduces 22.15%, 19.35 and 17.94% respectively, and error-reduction amplitude is obvious.
From soil type, the neural net method merging quantitative and qualitative analysis auxiliary variable is maximum to purple soil check post precision of prediction increase rate, and every error between 25.93 ~ 49.27%, on average reduces by 38.24% compared with the reduction amplitude of other 3 kinds of methods; Next is yellow soil, and the reduction amplitude of every error, between 17.92 ~ 46.19%, on average reduces by 30.04%; Be moisture soil again, the reduction amplitude of every error, between 12.50 ~ 25.70%, on average reduces by 19.42%; And the amplitude that reduces minimum be rice soil, the reduction amplitude of every error, between 0.59 ~ 18.55%, on average reduces by 10.08%.This mainly can disclose the development characteristics of front 3 kinds of soil typess comparatively speaking better due to selected orographic factor, and region each landform factor difference of rice soil distribution is relatively little.
The different Forecasting Methodology predicated error of table 5 is analyzed
Note: OK: normal stabilizing pile; RK: Regression-kriging method; RBFNN+OK: the method that radial basis function neural network combines with Ordinary Kriging Interpolation; ST+RBFNN: the neural net method merging qualitative, quantitative auxiliary variable; MAE: mean absolute error; MRE: average relative error; RMSE: root-mean-square error.
According to embodiments of the invention, can draw the following conclusions:
(1) soil organism massfraction in study area is between 4.20 ~ 47.60g.kg-1, average out to 17.97g.kg-1; Value for coefficient of variation 36.89% is moderate variability.In soil type, the rice soil content of organic matter is maximum, and its average mass fraction is 22.49g.kg-1; Next is moisture soil and purple soil, and mean value is respectively 15.87 and 14.09g.kg-1; Yellow soil is minimum, and mean value is 13.66g.kg-1.The results of analysis of variance shows, between soil type, the content difference of the soil organism reaches the pole level of signifiance (F=411.75, P<0.001), namely the space distribution of soil types factor on this regional soil content of organic matter has significant impact.
(2) correlation analysis shows, there is extremely significant negative correlativing relation (P<0.01) in soil organic matter content and study area sea level elevation, the gradient, there is extremely significant positive correlation (P<0.01) with Topographic Wetness Index and vegetation index, also have certain correlativity (P<0.05) with profile curvature.After removal soil types factor, the gradient, landform humidity and Vegetation factors are the Main Factors causing study area Spatial Variability of Soil Organic.
(3) Semi-variance analysis shows, the block gold number of the study area soil organism and the ratio of base station value are between 0.742 ~ 0.765, and spatial auto-correlation is more weak; Range is between 6.00 ~ 7.00km, and the scope of spatial autocorrelation is little.
(4) the method precision that the neural network model merging soil types factor and landform vegetation factor combines with Ordinary Kriging Interpolation compared with normal stabilizing pile, Regression-kriging method and neural network is significantly improved; The method reduces 30.78%, 27.43% and 25.70% to the mean absolute error that 469 check posts predict the outcome respectively compared with other 3 kinds of methods; Average relative error reduces 35.27%, 31.86% and 30.06% respectively, and root-mean-square error reduces 22.15%, 19.35 and 17.94% respectively, and error-reduction amplitude is obvious.The spatial variability research that the method can be complex environment regional soil character provides Research Thinking.
The present invention is not limited to above-mentioned preferred implementation, and anyone should learn the structure change made under enlightenment of the present invention, and every have identical or akin technical scheme with the present invention, all belongs to protection scope of the present invention.
Claims (1)
1., based on a soil organism space distribution Forecasting Methodology for quantitative and qualitative analysis auxiliary variable, it is characterized in that: step is as follows:
1), Data Source: with the study area topomap chosen, present landuse map and soil types distribution plan for supplementary, take into account representative with the basis of homogeneity principle on consider landform, laying that these information of soil types carry out soil sampling point, adopt the method for multiple spot mixing to gather top layer pedotheque at each soil sampling point place; Each sampled point all records its geographic coordinate and sea level elevation with GPS, records the environmental information at sampling point place in detail simultaneously; Laboratory milled 1mm sieve after natural air drying taken back by the sample collected, and adopts potassium bichromate titrimetric method to measure each soil sample content of organic matter;
2), auxiliary data source and process:
In research, Quantitative Factors mainly have selected terrain parameter and vegetation index; Terrain parameter is auxiliary environment variable the most frequently used in the prediction of soil property space distribution, comprises elevation, the gradient, planar curvature, profile curvature and Topographic Wetness Index; In ArcGIS9.3, generate the data elevation model of 30m resolution based on study area 1:5 ten thousand topomap, utilize the spatial analysis of ArcGIS9.3 and raster symbol-base function to obtain the gradient of study area 30m resolution, planar curvature, profile curvature and Topographic Wetness Index distribution plan further;
The vegetation index obtained based on remote sensing image can the growth conditions of reflecting regional surface vegetation and vegetation coverage information preferably, is the another auxiliary variable being usually used in the prediction of soil property space distribution; Adopt the enhancement mode meta file in MODIS remotely-sensed data product as the quantitative Vegetation factors of forecasting research district soil organic matter content space distribution in study area;
3), research method:
What research method adopted is the radial basis function neural network method merging quantitative and qualitative analysis auxiliary variable;
Relation between the measured value of each sampled point soil organism and environmental factor is expressed as:
Z(x
i,k,y
j,k)＝m(k)+r(x
i,k,y
j,k)(1)
r(x
i,k,y
j,k)＝f(t(x
i,y
j),v(x
i,y
j))(2)
In formula: Z (x
i,k, y
j,k) represent that the soil sample belonging to kth kind soil types is at (x
i, y
j) content of organic matter value at place, (x
i, y
j) be sample point coordinate, its ranks number are respectively i and j; M (k) is kth kind soil types content of organic matter mean value; R (x
i,k, y
j,k) be sampled point (x
i, y
j) content of organic matter deducts the residual error after soil types content of organic matter mean value belonging to this point; T (x
i, y
j) be point (x
i, y
j) terrain parameter value, v (x
i, y
j) be point (x
i, y
j) vegetation index value; Namely suppose that the soil types of the variation of the soil organism on specified point position first residing for this point determines, its residual values these local environmental factors of landform Vegetation condition then residing for this point are determined; Mean value m (k) and residual error r (x
i,k, y
j,k) separate;
Relation between each point position residual values and local environmental factor adopts RBF kernel function model tormulation; This model is a kind of three layers of feed-forward type neural network model with single hidden layer, and Forecasting Methodology process is as follows:
(1), according to sampled point soil organic matter content value, the mean value of each soil types soil organic matter content and residual values corresponding to each soil sampling point in statistical research district respectively;
(2), according to each soil types content of organic matter mean value calculated and study area soil types distribution plan, making and research district each soil types organic matter value content mean value distribution plan;
(3), input using the terrain parameter value of each soil sampling point and vegetation index value as network, export using the soil organism residual values after the normalization of corresponding point position as network, build neural network model, in MATLAB, simulation obtains the residual distribution figure of the study area soil organism;
(4), finally each for study area soil types organic value mean value distribution plan is added and namely obtain study area soil organic matter content spatial distribution map by the residual distribution figure that Neural Network model predictive obtains;
4), contrast method:
The method selecting neural network model to be combined with Ordinary Kriging Interpolation, normal stabilizing pile and Regression-kriging method method in contrast; The regression forecasting that first Regression-kriging method adopts multiple stepwise regression to carry out between the soil organism and envirment factor, with common Ke Lifa, interpolation is carried out to regression forecasting result residual error again, finally regression forecasting result and normal stabilizing pile are added the estimated value of residual error, namely obtain the spatial distribution map of the study area soil organism; The method that neural network model is combined with Ordinary Kriging Interpolation is then complete with the regression model in neural network model alternative regression Kriging method to predict the space distribution of the study area soil organism;
5), predicted exactitude evaluation method
Adopt each method of individual authentication sampling point set pair to predict the outcome to evaluate, namely at random 20% is extracted as check post from 2346 soil sampling points, all the other are 80% as modeling point, with mean absolute error, root-mean-square error and average relative error, the predicted value of check post and actual observed value are analyzed, draw precision evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310268497.0A CN103529189B (en) | 2013-06-28 | 2013-06-28 | A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310268497.0A CN103529189B (en) | 2013-06-28 | 2013-06-28 | A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103529189A CN103529189A (en) | 2014-01-22 |
| CN103529189B true CN103529189B (en) | 2016-01-06 |
Family
ID=49931368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310268497.0A Expired - Fee Related CN103529189B (en) | 2013-06-28 | 2013-06-28 | A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103529189B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109001127A (en) * | 2018-06-01 | 2018-12-14 | 华南农业大学 | A kind of heavy metal content in soil space predicting method |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239446B (en) * | 2014-09-01 | 2017-06-30 | 北京农业信息技术研究中心 | A kind of method that sampled point layout is carried out using auxiliary variable data |
| CN104408258B (en) * | 2014-12-01 | 2017-12-15 | 四川农业大学 | The large scale soil organic matter spatial distribution analogy method of integrated environment factor |
| CN104933699B (en) * | 2015-04-22 | 2017-06-30 | 吉林大学 | The method that surface vegetation phenology information is automatically extracted based on Gaussian function fitting variance |
| CN105243435B (en) * | 2015-09-15 | 2018-10-26 | 中国科学院南京土壤研究所 | A kind of soil moisture content prediction technique based on deep learning cellular Automation Model |
| CN105528523B (en) * | 2015-12-18 | 2018-09-21 | 中国科学院遥感与数字地球研究所 | A kind of thickness of soil inversion method based on remotely-sensed data |
| CN106198434A (en) * | 2016-07-26 | 2016-12-07 | 新疆农垦科学院 | A kind of remote-sensing monitoring method of the North SinKiang desert grey soil content of organic matter |
| CN107860889A (en) * | 2017-09-22 | 2018-03-30 | 华南农业大学 | The Forecasting Methodology and equipment of the soil organism |
| CN107657633A (en) * | 2017-09-28 | 2018-02-02 | 哈尔滨工业大学 | A kind of soil improving straw mulching rate measuring method based on BP neural network and sensor data acquisition |
| CN109374860A (en) * | 2018-11-13 | 2019-02-22 | 西北大学 | A kind of soil nutrient prediction and integrated evaluating method based on machine learning algorithm |
| CN111413484A (en) * | 2020-03-02 | 2020-07-14 | 南京信息职业技术学院 | Analysis method for spatial correlation between soil chromium content and land utilization type |
| CN112816658A (en) * | 2021-01-05 | 2021-05-18 | 四川大学 | Large-area-scale surface soil nutrient space characteristic monitoring method based on low-altitude remote sensing |
| CN113379188B (en) * | 2021-05-06 | 2022-10-25 | 贵州省烟草公司贵阳市公司 | Tobacco crop rotation planting method and system based on Internet of things |
| CN114814167B (en) * | 2022-04-08 | 2023-02-03 | 中科吉安生态环境研究院 | Soil heavy metal content inversion method fusing multi-source environment variables and spectral information |
| CN115932154A (en) * | 2022-09-21 | 2023-04-07 | 中国科学院东北地理与农业生态研究所 | Soil organic carbon remote sensing mapping method considering soil type |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01311248A (en) * | 1988-06-09 | 1989-12-15 | Soiru & Lock Eng Kk | Method of extracting homogeneous sample soil body |
| JPH11316221A (en) * | 1998-04-30 | 1999-11-16 | Yanmar Agricult Equip Co Ltd | Soil nutrient distribution analyzing method |
| CN101788553A (en) * | 2010-03-02 | 2010-07-28 | 中国农业大学 | Multiscale analysis method for vegetation indexes of refuse dump and soil nutrient space |
| CN102680413A (en) * | 2012-05-25 | 2012-09-19 | 浙江大学 | Device and method for hyperspectral rapid detection on content of field soil organic matters by using panoramic annular belt |
-
2013
- 2013-06-28 CN CN201310268497.0A patent/CN103529189B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01311248A (en) * | 1988-06-09 | 1989-12-15 | Soiru & Lock Eng Kk | Method of extracting homogeneous sample soil body |
| JPH11316221A (en) * | 1998-04-30 | 1999-11-16 | Yanmar Agricult Equip Co Ltd | Soil nutrient distribution analyzing method |
| CN101788553A (en) * | 2010-03-02 | 2010-07-28 | 中国农业大学 | Multiscale analysis method for vegetation indexes of refuse dump and soil nutrient space |
| CN102680413A (en) * | 2012-05-25 | 2012-09-19 | 浙江大学 | Device and method for hyperspectral rapid detection on content of field soil organic matters by using panoramic annular belt |
Non-Patent Citations (2)
| Title |
|---|
| 丘陵区土壤有机质空间分布预测的神经网络方法;李启权等;《农业环境科学学报》;20121231;第31卷(第12期);第2451－2458页 * |
| 基于神经网络模型和地统计学方法的土壤养分空间分布预测;李启权等;《应用生态学报》;20130228;第24卷(第2期);第459－466页 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109001127A (en) * | 2018-06-01 | 2018-12-14 | 华南农业大学 | A kind of heavy metal content in soil space predicting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103529189A (en) | 2014-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103529189B (en) | A kind of soil organism space distribution Forecasting Methodology based on quantitative and qualitative analysis auxiliary variable | |
| Chen et al. | Estimating soil moisture over winter wheat fields during growing season using machine-learning methods | |
| CN109142679B (en) | Forest soil nutrient space prediction method based on artificial neural network kriging interpolation | |
| Jin et al. | Spatio-temporal distribution of NDVI and its influencing factors in China | |
| Hussain et al. | Satellite-based evaluation of temporal change in cultivated land in Southern Punjab (Multan region) through dynamics of vegetation and land surface temperature | |
| CN106372277B (en) | Method for optimizing variation function model in forest land index space-time estimation | |
| Shi-Biao et al. | GIS-based and data-driven bivariate landslide-susceptibility mapping in the Three Gorges area, China | |
| Zhang et al. | Quantifying methane emissions from rice paddies in Northeast China by integrating remote sensing mapping with a biogeochemical model | |
| Uniyal et al. | Quantification of carbon sequestration by urban forest using Landsat 8 OLI and machine learning algorithms in Jodhpur, India | |
| Li et al. | Remote sensing prediction and characteristic analysis of cultivated land salinization in different seasons and multiple soil layers in the coastal area | |
| CN113011372B (en) | Automatic monitoring and identifying method for saline-alkali soil | |
| Bishop et al. | Digital soil-terrain modeling: the predictive potential and uncertainty | |
| Dan et al. | Delineating the rice crop activities in Northeast China through regional parametric synthesis using satellite remote sensing time-series data from 2000 to 2015 | |
| CN107194054B (en) | A kind of kriging analysis model building method for taking SOCD special heterogeneity into account | |
| Liu et al. | Effects of farmland landscape pattern on spatial distribution of soil organic carbon in Lower Liaohe Plain of northeastern China | |
| Lu et al. | Examining soil organic carbon distribution and dynamic change in a hickory plantation region with Landsat and ancillary data | |
| CN105528523A (en) | Soil thickness inversion method based on remote sensing data | |
| Sun et al. | Regional-scale drought monitor using synthesized index based on remote sensing in northeast China | |
| Jiang et al. | Monitoring the coastal environment using remote sensing and GIS techniques | |
| Cui et al. | Estimating maize yield in the black soil region of Northeast China using land surface data assimilation: integrating a crop model and remote sensing | |
| Luo et al. | Mapping the soil organic matter content in a typical black-soil area using optical data, radar data and environmental covariates | |
| Oskouei et al. | Mapping climate zones of Iran using hybrid interpolation methods | |
| Zhuo et al. | Aboveground biomass retrieval of wetland vegetation at the species level using UAV hyperspectral imagery and machine learning | |
| Wang et al. | Exploring the feasibility of winter wheat freeze injury by integrating grey system model with RS and GIS | |
| Antonarakis et al. | Regional carbon predictions in a temperate forest using satellite lidar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160106 Termination date: 20170628 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |