CN-121981606-A - Land improvement suitability evaluation and farmland quality improvement method based on big data

CN121981606ACN 121981606 ACN121981606 ACN 121981606ACN-121981606-A

Abstract

The invention relates to the technical field of agricultural data analysis, in particular to a land improvement suitability evaluation and cultivation land quality improvement method based on big data, which comprises the following steps: the method comprises the steps of obtaining and superposing land utilization, soil and elevation data to construct a multisource land attribute evaluation data set, calculating the distance from a map spot to a water source, reconstructing weights through Gaussian attenuation to form a space distance weighting feature matrix, extracting gradient and irrigation guarantee rate, cutting the conflict threshold value overrun part, carrying out linear weighting calculation on comprehensive scores after normalization, dividing a treatment priority area, matching quality lifting measures to form a plough quality lifting engineering layout, forming a map spot level evaluation basis through multisource attribute space superposition, introducing water source distance attenuation calculation to enable weights to change along with reachability, strengthening irrigation difference response, carrying out conflict constraint correction on gradient and irrigation guarantee, inhibiting adverse combination influence, forming stable sequencing through uniform scale weighting, and carrying out identification and quality lifting measure directional configuration on the support treatment priority area.

Inventors

FENG DA
ZENG RONG
ZHANG YI
XU SHUANG
LI TINGTING
ZHANG ZHIJIAN
LIU YI
TANG WEIYI

Assignees

湖南省测绘科技研究所

Dates

Publication Date: 20260505
Application Date: 20260126

Claims (10)

1. The land improvement suitability evaluation and cultivation quality improvement method based on big data is characterized by comprising the following steps of: S1, acquiring land utilization pattern spot data, soil physicochemical detection data and digital elevation model data, performing spatial superposition on the land utilization pattern spot data and the soil physicochemical detection data, mapping the digital elevation model data to a superimposed pattern spot unit, and constructing a multi-source land attribute evaluation data set; S2, calling the multisource land attribute evaluation data set, calculating Euclidean distance from the central point of the pattern spot unit to a water source area, inputting the Euclidean distance to a Gaussian attenuation model for carrying out space influence intensity calculation, carrying out multiplication proportion reconstruction on attribute weights of the pattern spot unit according to the space influence intensity, and outputting a space distance weighting feature matrix; S3, extracting a terrain gradient attribute value and an irrigation guarantee rate attribute value from the space distance weighted feature matrix, and performing weight reduction operation on the terrain gradient attribute value and the irrigation guarantee rate attribute value which exceed a preset terrain irrigation conflict judgment threshold value at the same time to generate a conflict constraint correction evaluation matrix; And S4, performing range normalization processing on the conflict constraint correction evaluation matrix, performing linear weighted summation based on the weight after reduction, obtaining the index value of the sub-item, calculating the comprehensive score value, and constructing a comprehensive evaluation matrix for the suitability of the cultivated land.
2. The big data-based land reclamation suitability evaluation and tilling and upgrading method as recited in claim 1, wherein the multi-source land attribute evaluation dataset includes a land utilization type, a soil physicochemical property, terrain elevation data, and a spatial distribution pattern, the spatial distance weighting feature matrix includes a center point euclidean distance, a distance weight coefficient, and a distance attenuation coefficient, the conflict constraint correction evaluation matrix includes a conflict identifier, a weight correction coefficient, and an evaluation correction coefficient, and the tilling suitability comprehensive evaluation matrix includes a comprehensive score, a sub-term index, and a weight summary result.
3. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 1, wherein the specific steps of S1 are as follows: S101, acquiring land utilization pattern spot data and soil physicochemical detection data, executing coordinate reference verification and reference conversion, executing space connection according to the relation between detection points and pattern spot boundaries, and executing index field aggregation and structure arrangement on a matched record to generate a soil attribute superposition pattern spot unit set; s102, based on the soil attribute superposition pattern spot unit set, acquiring digital elevation model data, executing grid scale consistency check, searching an elevation grid set according to a pattern spot space range, executing mean value statistical calculation on grid values, and writing pattern spot fields to obtain an elevation attribute mapping pattern spot unit set; S103, calling the elevation attribute map spot unit set, performing field integrity judgment and type check on land utilization codes, soil physicochemical indexes and elevation attributes, uniformly identifying missing fields, performing merging and index recombination on a multi-source attribute structure, and generating a multi-source land attribute evaluation data set.
4. The land reclamation suitability evaluation and the cultivated land upgrading method based on big data as recited in claim 3, wherein the specific steps of S2 are as follows: s201, calling the multi-source land attribute evaluation data set, analyzing the boundary coordinates of the pattern spot units and calculating the center point coordinates of the pattern spots, acquiring the space coordinates of the water source and unifying a coordinate reference system, and executing distance quantization processing according to the space position relation between the center point and the water source coordinates to generate a pattern spot-to-water source Euclidean distance sequence; S202, reading the distance index item by item based on the Euclidean distance sequence from the pattern spot to the water source, substituting the distance index into a Gaussian attenuation model structure, executing attenuation function mapping on the distance variable, outputting a continuous numerical result, and generating a space influence intensity coefficient set by keeping the one-to-one correspondence between the distance index and the numerical result; The Gaussian attenuation model comprehensively judges influence intensity through a distance value and a preset distance scale parameter, the influence intensity has an exponential weakening trend along with the increase of the distance, the distance scale parameter controls the attenuation speed and the influence range of the model, and the parameter value can be adjusted to reflect different space influence degrees according to actual conditions; s203, according to the space influence intensity coefficient set, a multi-source land attribute evaluation data set is called, a map spot attribute weight field is extracted, item-by-item combination operation is carried out on the weight field and the intensity coefficient according to the map spot index, the map spot index is mapped to a row dimension, an attribute item is mapped to a column dimension, and a space distance weighting feature matrix is generated.
5. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 4, wherein the specific steps of S3 are as follows: s301, based on the space distance weighted feature matrix, positioning a terrain gradient attribute field and an irrigation guarantee rate attribute field corresponding to the bitmap index, and performing synchronous extraction and position verification on attribute values according to an index sequence to generate a terrain gradient irrigation attribute combination sequence; S302, reading the topographic gradient attribute value and the irrigation guarantee rate attribute value item by item according to the topographic gradient irrigation attribute combination sequence, respectively comparing with preset topographic irrigation conflict judgment threshold value execution conditions, executing identification collection on the combined indexes meeting the conditions at the same time, and obtaining a topographic irrigation conflict index set; S303, calling attribute weight values of corresponding index positions for the terrain irrigation conflict index set, performing proportion reduction and replacement on weights at the marked index positions, and performing vector recombination on all weight results according to the pattern index sequence to generate a conflict constraint correction evaluation matrix.
6. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 5, wherein the preset terrain irrigation conflict determination threshold includes a terrain gradient threshold interval and an irrigation assurance rate threshold interval, and is determined based on a statistical analysis result of a terrain irrigation data set, a lower limit of the terrain gradient threshold interval is 95% fraction of a minimum terrain gradient value in the data set, an upper limit is 95% fraction of a maximum terrain gradient value, and an upper limit of the irrigation assurance rate threshold interval is a maximum value of the data set minus a standard deviation of the irrigation assurance rate.
7. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 5, wherein the specific steps of S4 are as follows: s401, performing range normalization processing on the conflict constraint correction evaluation matrix, searching for value distribution corresponding to the evaluation factor index, extracting all values of the same type factors, determining upper and lower limits of the interval, and performing proportional mapping operation on single values and interval difference values to generate a normalized evaluation index vector set; s402, based on the normalized evaluation index vector set, invoking the weight value after reduction in the conflict constraint correction evaluation matrix, performing product calculation on the normalized index value and the corresponding weight according to the same index position, and performing linear aggregation operation on the product result according to indexes to obtain a subitem evaluation index value sequence; s403, according to the subitem evaluation index value sequence, performing accumulation operation on subitem index values at the same index position to form single index corresponding comprehensive score values, and performing matrixing arrangement according to the pattern spot index sequence to establish a comprehensive evaluation matrix for cultivation suitability.
8. The big data based land reclamation suitability evaluation and tilling and upgrading method as recited in claim 1, further comprising the step of S5: s5, analyzing the comprehensive evaluation matrix of the cultivated land remediation suitability, dividing a priority remediation area according to the comprehensive score value, matching cultivated land quality improvement measures aiming at the restrictive obstacle factors in the subitem index value, and outputting a cultivated land quality improvement engineering layout; the tilling quality-improving engineering layout includes a lifting scheme, a improvement measure, and an implementation path.
9. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 8, wherein the specific steps of S5 are as follows: s501, analyzing the comprehensive evaluation matrix of the cultivated land remediation suitability, reading a comprehensive score value corresponding to the map spot index, comparing and judging a section according to the score value and a grading reference section, determining a grade label to which the score belongs, and encoding and collecting according to the map spot index sequence to generate a remediation priority grade partition sequence; S502, based on the remediation priority level partition sequence, calling the index value of the corresponding index item evaluation, performing item-by-item value comparison on the index value and the restriction judgment threshold value, marking index positions which do not meet the threshold value condition, and performing set arrangement on the index positions to obtain a restriction obstacle factor index set; S503, according to the restrictive obstacle factor index set, calling index corresponding subitem index values and an engineering measure parameter mapping table, executing consistency judgment on index attributes and measure adaptation conditions, carrying out combined coding on the index indexes and the measure types which are judged to be established, and establishing a plough quality improvement engineering layout.
10. The big data based land reclamation suitability evaluation and cultivation improvement method as recited in claim 9, wherein the grading reference interval divides the comprehensive grading value into at least three and at most five continuous closed value intervals according to a preset proportion, the upper and lower limit values of each value interval have fixed value spans, and the comprehensive grading value in the interval corresponds to a unique grade label; The limiting judgment threshold value is a single upper limit value or a single lower limit value preset for each item of evaluation index, the upper limit value or the lower limit value is determined by the technical requirements of the indexes, and when item-by-item value comparison is executed, if the value of a certain index does not reach the preset upper limit value or the preset lower limit value, the judgment index does not meet the standard, and the limiting factor is marked.

Description

Land improvement suitability evaluation and farmland quality improvement method based on big data Technical Field The invention relates to the technical field of agricultural data analysis, in particular to a land improvement suitability evaluation and cultivation quality improvement method based on big data. Background The technical field of agricultural data analysis refers to a related technical set for collecting, sorting, analyzing and utilizing multi-source data formed in agricultural production activities, the core matters of the technical set include processing and analyzing natural environment data of land resource data crop production data and management and planning data, and basic support is provided for agricultural planning land utilization management and management of cultivated land by carrying out systematic carding and comprehensive analysis on information such as current situation of water resource utilization of soil type landform climate conditions, cultivation utilization conditions and the like. The traditional land reclamation suitability evaluation and cultivation quality improvement method is characterized in that in the land reclamation and cultivation quality management process, specific indexes such as road accessibility of soil layer thickness gradient irrigation conditions and the like are selected according to existing land investigation results and statistical data, evaluation indexes are subjected to grading assignment through manually set evaluation standards, a land reclamation suitability judgment result is formed in an index weighting and summarizing mode, and land reclamation and quality improvement arrangement is carried out by combining specific measures such as farmland water conservancy matching and land force fertilizer management on the basis. The existing land remediation suitability evaluation is developed by means of static investigation data and experience rules, index weights are kept fixed in an evaluation period, space position differences are only indirectly reflected by attribute values, continuous influences of water source distances on irrigation guarantee are difficult to embody, mutual constraints between terrain slopes and irrigation conditions lack of an explicit constraint mechanism, adverse factors are easy to average in a weighted summarization process, the actual remediation risk is not recognized sufficiently as an evaluation result, partition ordering and measure configuration are biased to macroscopic judgment, and fine and quality improvement decisions are difficult to support. Disclosure of Invention In order to solve the technical problems that the existing land reclamation suitability evaluation is developed by depending on static investigation data and experience rules, index weights are kept fixed in an evaluation period, space position differences are only indirectly reflected by attribute values, continuous influences of water source distances on irrigation guarantee are difficult to embody, mutual constraints between terrain slopes and irrigation conditions lack an explicit constraint mechanism, adverse factors are easy to average in a weighted summarization process, so that an evaluation result is insufficient in recognition of actual reclamation risks, partition ordering and measure configuration are biased to macroscopic judgment, and fine and quality improvement decisions are difficult to support, the embodiment of the invention provides a land reclamation suitability evaluation and cultivated land quality improvement method based on big data. In order to achieve the above purpose, the invention adopts a land improvement suitability evaluation and cultivation quality improvement method based on big data, which comprises the following steps: S1, acquiring land utilization pattern spot data, soil physicochemical detection data and digital elevation model data, performing spatial superposition on the land utilization pattern spot data and the soil physicochemical detection data, mapping the digital elevation model data to a superimposed pattern spot unit, and constructing a multi-source land attribute evaluation data set; S2, calling the multisource land attribute evaluation data set, calculating Euclidean distance from the central point of the pattern spot unit to a water source area, inputting the Euclidean distance into a Gaussian attenuation model for space influence intensity calculation, carrying out multiplication proportion reconstruction on attribute weights of the pattern spot unit according to the space influence intensity, and outputting a space distance weighting feature matrix; S3, extracting a terrain gradient attribute value and an irrigation guarantee rate attribute value from the space distance weighted feature matrix, and performing weight reduction operation on the terrain gradient attribute value and the irrigation guarantee rate attribute value which exceed a preset terrain irrigation conflict judgment thresho