A method of farmland division based on fuzzy c-means clustering
A technology of mean clustering and cluster analysis, applied in the field of farmland division, can solve the problems of few classifications, inconsistent FPI and NCE classifications, and low degree of differentiation of farmland nutrient differences, and achieve the effect of improving the degree of discrimination.
Active Publication Date: 2015-08-19
NANJING AGRICULTURAL UNIVERSITY
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The method of using FPI and NCE evaluation functions to determine the optimal number of classifications for fuzzy c-means clustering to divide farmland has defects: FPI and NCE do not have a high degree of discrimination of farmland nutrient differences, resulting in a small number of final classifications and often The number of classifications corresponding to the minimum value of FPI and NCE is inconsistent, which makes it impossible to determine the appropriate number of classifications
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment
[0049] 1) Enter the soil organic matter content, total nitrogen content, available potassium content, available phosphorus content and coordinate position information in Rugao City, Jiangsu Province into ArcGIS 9.2, and perform ordinary Kriging interpolation on the four nutrient indicators of the soil. The interpolation results are shown in figure 2 . Among them, (a) is the interpolation result map of organic matter content, (b) is the interpolation result map of total nitrogen content, (c) is the interpolation result map of available potassium content, and (d) is the interpolation result map of available phosphorus content. The interpolation results are output in the form of ASCII files, and the soil nutrient data at the same grid position in 4 ASCII files are organized into a sample, and a sample matrix with n rows and 4 columns is obtained, where n is the number of samples, and each column of the sample matrix represents a soil Nutrient data.
[0050] 2) The maximum numbe...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a farmland division method based on fuzzy c-means clustering. The farmland division method comprises the following steps of: carrying out spatial interpolation on sampling point farmland soil nutrient data so as to generate grid data, and organizing grid data of different nutrients into a sample matrix; and carrying out clustering analysis on the sample matrix in a given classification range by using the fuzzy c-means clustering, calculating the clustering effect index S of all clustering results in the classification range, and taking the clustering result corresponding to the minimal S value as the farmland division result. According to the farmland division method, a method for determining optimal farmland classification number is adopted for solving the defects of FPI (Fibrosis Probability Index) and NCE (Normal Curve Equivalent) evaluation functions, so that the discrimination on soil nutrient difference in the farmland division process is improved, therefore the requirements of the farmland precise management or crop growth information monitoring on the farmland division can be better met.
Description
technical field [0001] The invention relates to a method for dividing farmland, in particular to a method for dividing farmland by using soil nutrient information. Background technique [0002] Precise farming management monitors crop growth and farmland environmental information, and implements positioning, quantitative, and timing agricultural precision management according to the farmland community environment and crop growth differences. On the premise of ensuring crop yield and quality, the best economic and ecological conditions can be obtained. benefit. The difference in crop growth is mainly affected by the difference in soil nutrients in farmland, and soil nutrients are spatially correlated. Therefore, soil nutrient information is used to divide farmland, so that farmland areas with similar nutrients can be divided into one category, which can reduce the number of farmland monitoring points. The quantity has important practical significance for realizing the rapid ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F19/00
Inventor 曹卫星刘乃森倪军朱艳田永超姚霞
Owner NANJING AGRICULTURAL UNIVERSITY