A method for formulating improvement strategies based on saline-alkali land analysis

Abstract

The present invention provides a method for formulating an improvement strategy based on saline-alkali land analysis, and relates to the field of saline-alkali land improvement assessment. The present invention corrects the standard curve of successfully improved saline-alkali land according to the difference in improvement influencing factors between the saline-alkali land to be assessed and the successfully improved saline-alkali land, uses the corrected standard curve as the target curve, makes a difference between the saline-alkali land data of the saline-alkali land to be assessed and the target curve, obtains the difference curve up to the current time, predicts the improvement effect according to the difference curve, and only establishes a BP neural network when the difference curve exceeds the preset curve range to predict the change of saline-alkali land data, and adjusts the improvement strategy according to the prediction result, which simplifies the improvement strategy adjustment process and makes the adjustment of the improvement strategy more accurate.

Description

Technical Field

[0001] The present invention relates to the field of formulation of saline-alkali land improvement strategies, and in particular to a method for formulating an improvement strategy based on saline-alkali land analysis. Background Art

[0002] Saline-alkali land is highly harmful to crops due to its high salt content and high alkaline content, which is not conducive to the growth of crops. At present, the global saline-alkali land area is nearly 1 billion hectares, and the saline-alkali land area is increasing year by year. Soil salinization leads to the solidification and compaction of the shallow soil, which is not conducive to the growth of crops, making it impossible to effectively develop and utilize the land, and occupying a large amount of existing land resources.

[0003] At present, the formulation of saline-alkali land improvement strategies usually only considers factors such as soil salinity, and does not refer to the data changes during the improvement process of successfully improved saline-alkali land. It is impossible to accurately predict the improvement effect and cannot adjust the formulated improvement strategy in time, resulting in slow or failed saline-alkali land improvement. Summary of the invention

[0004] The purpose of the present invention is to propose a method for formulating an improvement strategy based on saline-alkali land analysis, aiming to solve the problem of deviation in the adjustment of existing improvement strategies and provide accurate guidance for formulating saline-alkali land improvement strategies.

[0005] The present invention provides a method for formulating an improvement strategy based on saline-alkali land analysis, comprising the following steps:

[0006] Establish a standard curve based on the saline-alkali land data of successfully improved saline-alkali land;

[0007] The standard curve is corrected according to the difference in the improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land, and the corrected standard curve is used as the target curve;

[0008] Make a difference between the saline-alkali land data of the saline-alkali land to be evaluated and the target curve to obtain a difference curve up to the current time;

[0009] If the difference curve is within the preset curve range, it is predicted that the saline-alkali land to be evaluated can be successfully improved and the improvement strategy does not need to be adjusted;

[0010] If the difference curve exceeds the preset curve range, a BP neural network is established, and data are selected from the improvement influencing factors of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, as well as the saline-alkali land data of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, to form a training set and a test set, and the BP neural network is trained and tested to obtain a BP neural network after the test;

[0011] Data are selected from the improvement influencing factors of successfully improved saline-alkali land and saline-alkali land to be evaluated, as well as the saline-alkali land data of successfully improved saline-alkali land and saline-alkali land to be evaluated, and the saline-alkali land data changes of the saline-alkali land to be evaluated are predicted based on the tested BP neural network, and the improvement strategy is adjusted according to the predicted results of the saline-alkali land data changes.

[0012] Preferably, the improvement influencing factors include initial soil salinity, climatic conditions, groundwater level, soil moisture and soil thickness.

[0013] Preferably, the climate conditions include temperature, humidity, sunshine intensity, percentage of sunny days, precipitation and wind speed.

[0014] Preferably, correcting the standard curve according to the difference in improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land specifically includes: comparing the improvement influencing factors of the saline-alkali land to be evaluated and the improvement influencing factors of the successfully improved saline-alkali land with preset improvement influencing factor thresholds, and correcting the standard curve according to the comparison results.

[0015] Preferably, the standard curve is corrected according to the difference factor δ between the improvement influencing factors of the saline-alkali land to be evaluated and the successfully improved saline-alkali land. The difference factor δ is calculated using the following formula, and the difference factor δ is multiplied by the standard curve to obtain the corrected standard curve:

[0016]

[0017] in,

[0018] X is the impact factor of saline-alkali land improvement to be evaluated;

[0019] B is the preset improved impact factor threshold;

[0020] Y is the influencing factor for successful improvement of saline-alkali land.

[0021] Preferably, the method further includes obtaining an electronic map of the saline-alkali land to be evaluated, dividing the saline-alkali land to be evaluated into regions, and respectively obtaining saline-alkali land data of each region.

[0022] Preferably, multiple detection points are set in each area. When the variance of the saline-alkali land data to be evaluated obtained by multiple detection points in the same area exceeds a preset range, the area continues to be divided until the deviation of the saline-alkali land data to be evaluated obtained in each area is within the preset range, and the area division is terminated.

[0023] Preferably, the saline-alkali land data includes saline-alkali land soil data and saline-alkali land vegetation data.

[0024] Preferably, each detection point collects a group of saline-alkali land data of the saline-alkali land to be evaluated. After the regional division is completed, the saline-alkali land data in each area are averaged to obtain the saline-alkali land data of the area, and the saline-alkali land data of the area are compared with the target curve. According to the comparison result, it is determined whether to establish a BP neural network, and the BP neural network is used to predict the improvement effect of each area, and the improvement strategy of each area is adjusted according to the predicted improvement effect.

[0025] Preferably, it also includes, after the improvement strategy is adjusted, collecting saline-alkali land data of the saline-alkali land to be evaluated according to preset intervals. If the improvement trend of the saline-alkali land data is better than the target curve, it is predicted that the saline-alkali land to be improved can be successfully improved. Otherwise, continue to use the collected saline-alkali land data and the saline-alkali land data of successfully improved saline-alkali land to train with the established BP neural network, predict the improvement effect, and adjust the improvement strategy again according to the predicted effect until it is predicted that the saline-alkali land to be improved can be successfully improved.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] (1) The present invention corrects the standard curve of successfully improved saline-alkali land according to the difference in improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land, and uses the corrected standard curve as the target curve, so that the predicted improvement effect is more accurate and the improvement strategy can be adjusted in time;

[0028] (2) The present invention first makes a difference between the saline-alkali land data of the saline-alkali land to be evaluated and the target curve to obtain a difference curve up to the current time, and predicts the improvement effect based on the difference curve. Only when the difference curve exceeds the preset curve range, a BP neural network is established to predict the change of saline-alkali land data, and the improvement strategy is adjusted according to the prediction result, which not only simplifies the improvement strategy adjustment process, but also makes the adjustment of the improvement strategy more accurate.

[0029] (3) The present invention first divides the saline-alkali land to be evaluated into regions. When the variance of the saline-alkali land data of the saline-alkali land to be evaluated obtained by multiple detection points in the same region exceeds a preset range, the region is further subdivided, thereby achieving a more reasonable and accurate division of the saline-alkali land regions, thereby making the adjustment of the improvement strategies of each region more accurate;

[0030] (4) When the present invention corrects the standard curve, a preset improvement impact factor threshold is set. The difference factor is obtained according to the improvement impact factor of the successfully improved saline-alkali land, the improvement impact factor of the saline-alkali land to be evaluated and the improvement impact factor threshold. The standard curve is corrected using the difference factor to obtain the target curve, so that the improvement effect prediction of the saline-alkali land to be evaluated is more accurate and the improvement strategy adjustment is also more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0032] Figure 1 The present invention provides an improved strategy formulation method based on saline-alkali land analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] The present invention provides a method for formulating an improvement strategy based on saline-alkali land analysis, comprising the following steps:

[0035] Establish a standard curve based on the saline-alkali land data of successfully improved saline-alkali land;

[0036] The standard curve is corrected according to the difference in the improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land, and the corrected standard curve is used as the target curve;

[0037] Make a difference between the saline-alkali land data of the saline-alkali land to be evaluated and the target curve to obtain a difference curve up to the current time;

[0038] If the difference curve is within the preset curve range, it is predicted that the saline-alkali land to be evaluated can be successfully improved and the improvement strategy does not need to be adjusted;

[0039] If the difference curve exceeds the preset curve range, a BP neural network is established, and data are selected from the improvement influencing factors of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, as well as the saline-alkali land data of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, to form a training set and a test set, and the BP neural network is trained and tested to obtain a BP neural network after the test;

[0040] Data are selected from the improvement influencing factors of successfully improved saline-alkali land and saline-alkali land to be evaluated, as well as the saline-alkali land data of successfully improved saline-alkali land and saline-alkali land to be evaluated, and the saline-alkali land data changes of the saline-alkali land to be evaluated are predicted based on the tested BP neural network, and the improvement strategy is adjusted according to the predicted results of the saline-alkali land data changes.

[0041] According to a specific embodiment of the present invention, the improvement influencing factors include initial soil salinity, climatic conditions, groundwater level, soil moisture and soil thickness.

[0042] According to a specific embodiment of the present invention, the climate conditions include temperature, humidity, sunshine intensity, percentage of sunny days, precipitation and wind speed.

[0043] According to a specific embodiment of the present invention, correcting the standard curve according to the difference in improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land specifically includes: comparing the improvement influencing factors of the saline-alkali land to be evaluated and the improvement influencing factors of the successfully improved saline-alkali land with preset improvement influencing factor thresholds, and correcting the standard curve according to the comparison results.

[0044] According to a specific embodiment of the present invention, the standard curve is corrected according to the difference factor δ between the improvement influencing factors of the saline-alkali land to be evaluated and the successfully improved saline-alkali land. The difference factor δ is calculated using the following formula, and the difference factor δ is multiplied by the standard curve to obtain a corrected standard curve:

[0045]

[0046] in,

[0047] X is the impact factor of saline-alkali land improvement to be evaluated;

[0048] B is the preset improved impact factor threshold;

[0049] Y is the influencing factor for successful improvement of saline-alkali land.

[0050] According to a specific embodiment of the present invention, it also includes obtaining an electronic map of the saline-alkali land to be evaluated, dividing the saline-alkali land to be evaluated into regions, and respectively obtaining saline-alkali land data of each region.

[0051] According to a specific embodiment of the present invention, multiple detection points are set in each area. When the variance of the saline-alkali land data to be evaluated obtained by multiple detection points in the same area exceeds a preset range, the area continues to be divided until the deviation of the saline-alkali land data to be evaluated obtained in each area is within the preset range, and the area division is terminated.

[0052] According to a specific embodiment of the present invention, the saline-alkali land data includes saline-alkali land soil data and saline-alkali land vegetation data.

[0053] According to a specific implementation scheme of the present invention, each detection point collects a group of saline-alkali land data of the saline-alkali land to be evaluated. After the regional division is completed, the saline-alkali land data in each area are averaged to obtain the saline-alkali land data of the area, and the saline-alkali land data of the area are compared with the target curve. According to the comparison result, it is determined whether to establish a BP neural network, and the BP neural network is used to predict the improvement effect of each area, and the improvement strategy of each area is adjusted according to the predicted improvement effect.

[0054] According to a specific embodiment of the present invention, it also includes, after the improvement strategy is adjusted, collecting saline-alkali land data of the saline-alkali land to be evaluated according to preset intervals, if the improvement trend of the saline-alkali land data is better than the target curve, it is predicted that the saline-alkali land to be improved can be successfully improved, otherwise, continuing to use the collected saline-alkali land data and the saline-alkali land data of successfully improved saline-alkali land to use the established BP neural network for training, predicting the improvement effect, and adjusting the improvement strategy again according to the predicted effect, until it is predicted that the saline-alkali land to be improved can be successfully improved.

[0055] The above descriptions are only optional embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A method for formulating an improvement strategy based on saline-alkali land analysis, characterized in that: The steps include: Establish a standard curve based on the saline-alkali land data of successfully improved saline-alkali land; According to the difference factors of the improvement influencing factors between the saline-alkali land to be evaluated and the successfully improved saline-alkali land The standard curve is modified by comparing the impact factors of the saline-alkali land improvement to be evaluated and the impact factors of the successfully improved saline-alkali land with the preset improvement impact factor thresholds, and calculating the difference factor using the following formula: , and use the difference factor Multiply it with the standard curve to obtain a corrected standard curve, and use the corrected standard curve as the target curve; in, X is the impact factor of saline-alkali land improvement to be evaluated; B is the preset improved impact factor threshold; Y is the influencing factor for successful improvement of saline-alkali land; Make a difference between the saline-alkali land data of the saline-alkali land to be evaluated and the target curve to obtain a difference curve up to the current time; If the difference curve is within the preset curve range, it is predicted that the saline-alkali land to be evaluated can be successfully improved and the improvement strategy does not need to be adjusted; If the difference curve exceeds the preset curve range, a BP neural network is established, and data are selected from the improvement influencing factors of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, as well as the saline-alkali land data of the successfully improved saline-alkali land and the saline-alkali land to be evaluated, to form a training set and a test set, and the BP neural network is trained and tested to obtain a BP neural network after the test; Data are selected from the improvement influencing factors of successfully improved saline-alkali land and saline-alkali land to be evaluated, as well as the saline-alkali land data of successfully improved saline-alkali land and saline-alkali land to be evaluated, and the saline-alkali land data changes of the saline-alkali land to be evaluated are predicted based on the tested BP neural network, and the improvement strategy is adjusted according to the predicted results of the saline-alkali land data changes.

2. The method for formulating an improvement strategy based on saline-alkali land analysis according to claim 1, characterized in that: Factors affecting improvement include initial soil salinity, climatic conditions, groundwater level, soil moisture and soil thickness.

3. The method for formulating an improvement strategy based on saline-alkali land analysis according to claim 2, characterized in that: Climate conditions include temperature, humidity, sunshine intensity, percentage of sunny days, precipitation and wind speed.

4. The method for formulating an improvement strategy based on saline-alkali land analysis according to claim 1, characterized in that: It also includes obtaining an electronic map of the saline-alkali land to be evaluated, dividing the saline-alkali land to be evaluated into regions, and obtaining saline-alkali land data for each region respectively.

5. The method for formulating an improved strategy based on saline-alkali land analysis according to claim 4, characterized in that: Multiple detection points are set in each area. When the variance of the saline-alkali land data to be evaluated obtained by multiple detection points in the same area exceeds a preset range, the area will continue to be divided until the deviation of the saline-alkali land data to be evaluated obtained in each area is within the preset range, and the area division is terminated.

6. The method for formulating an improved strategy based on saline-alkali land analysis according to claim 4, characterized in that: The saline-alkali land data include saline-alkali land soil data and saline-alkali land vegetation data.

7. The method for formulating an improved strategy based on saline-alkali land analysis according to claim 6, characterized in that: Each detection point collects a group of saline-alkali land data of the saline-alkali land to be evaluated. After the regional division is completed, the saline-alkali land data in each area are averaged to obtain the saline-alkali land data of the area, and the saline-alkali land data of the area are compared with the target curve. According to the comparison results, it is determined whether to establish a BP neural network. The BP neural network is used to predict the improvement effect of each area, and the improvement strategy of each area is adjusted according to the predicted improvement effect.

8. The method for formulating an improvement strategy based on saline-alkali land analysis according to claim 1, characterized in that: It also includes, after the improvement strategy is adjusted, collecting saline-alkali land data of the saline-alkali land to be evaluated according to preset intervals, if the improvement trend of the saline-alkali land data is better than the target curve, it is predicted that the saline-alkali land to be improved can be successfully improved, otherwise, continuing to use the collected saline-alkali land data and the saline-alkali land data of successfully improved saline-alkali land to train the established BP neural network, predicting the improvement effect, and adjusting the improvement strategy again according to the predicted effect, until it is predicted that the saline-alkali land to be improved can be successfully improved.

Images