Method for evaluating drought tolerance of a sugarcane hybrid combination

Abstract

The application discloses a kind of drought resistance evaluation method of sugarcane hybrid combination, it is related to drought resistance evaluation technical field, according to the constraint of drought coefficient to the record frequency of each index, and after obtaining the character data of sugarcane seedling, the similarity of the character between different groups of sugarcane seedling is judged by similarity analysis and constructs difference coefficient, if difference coefficient exceeds expectation, use trained drought resistance evaluation model to carry out drought resistance evaluation to sugarcane seedling, after obtaining the drought resistance score of each sugarcane seedling, generate drought degree, according to drought degree in several sugarcane hybrid combinations Screening target combination;According to the difference degree in several drought resistance states, the target character is screened out, and the parent of sugarcane is recombined by pre-trained genetic algorithm, and several groups of sugarcane hybrid combinations are reacquired.In several sugarcane hybrid combinations, the target combination with better drought resistance effect is screened out, and the reliability of the evaluation result is higher.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of drought tolerance evaluation, in particular to a method for evaluating drought tolerance of sugarcane hybrid combinations. BACKGROUND

[0002] In sugarcane breeding, sexual hybridization technology occupies a core position. Through careful selection of parents and implementation of hybridization, researchers can fully utilize favorable variations based on the complex genetic basis of sugarcane to cultivate new varieties with high yield, high sugar, and excellent stress resistance. Among them, drought tolerance, as a key trait for sugarcane to cope with drought challenges, has made significant progress. Through molecular marker-assisted breeding and transgenic technology, scientists not only revealed the genetic genes and physiological mechanisms closely related to drought tolerance, but also successfully selected a series of new sugarcane varieties that can maintain excellent growth and yield in drought environments, providing strong impetus for the sustainable development of agricultural production.

[0003] In the Chinese invention patent with the application publication number CN116359436A, a method for evaluating the drought tolerance of garden plants is disclosed. The method includes the following steps: selecting garden plants with consistent growth; subjecting the garden plants to water stress treatment and then transferring them to normal maintenance after the water stress treatment ends; determining the drought tolerance indicators of the garden plants subjected to the water stress treatment to obtain drought tolerance indicator determination data; and evaluating the drought tolerance of the garden plants based on the drought tolerance indicator determination data. The drought tolerance indicators include morphological scores, leaf trait parameters, leaf photosynthetic gas exchange parameters, and chlorophyll fluorescence parameters. This method objectively, accurately, and reasonably evaluates the drought tolerance of plants.

[0004] In combination with the above application and the content in the prior art:

[0005] Considering that the rainfall in the sugarcane planting area is usually low and often in a drought state, the drought tolerance of sugarcane is particularly important. In order to improve the drought tolerance of sugarcane varieties, it is necessary to cross the sugarcane and select the best drought-tolerant variety from the obtained several sugarcane seedlings.

[0006] However, due to the multiple drought tolerance traits of sugarcane, there is a lack of unified standard for evaluating the drought tolerance of sugarcane, and there is a certain difficulty in selecting high drought-tolerant sugarcane seedlings. In the existing method for evaluating the drought tolerance of sugarcane hybrid combinations, several drought tolerance parameters of sugarcane seedlings are collected after the hybridization test is completed, and the drought tolerance parameters are used as the evaluation. This evaluation method is relatively direct and can screen out some sugarcane seedlings with better drought tolerance from the existing sugarcane seedlings, but it is difficult to screen out the key drought tolerance traits of the sugarcane seedlings based on the drought tolerance parameters, and it cannot effectively assist in improving the success rate of the hybridization test.

[0007] To this end, the application provides a drought resistance evaluation method of sugarcane hybrid combination. SUMMARY

[0008] (I) Technical problems solved

[0009] In view of the deficiencies in the prior art, the application provides a drought resistance evaluation method of sugarcane hybrid combination, which judges the similarity of the traits of sugarcane seedlings between different groups through similarity analysis and constructs a difference coefficient, uses a trained drought resistance evaluation model to evaluate the drought resistance of the sugarcane seedlings if the difference coefficient exceeds the expectation, generates a drought degree after obtaining the drought resistance scores of each sugarcane seedling, and screens out a target combination from a plurality of sugarcane hybrid combinations according to the drought degree. According to the difference degree, a target trait is screened out from a plurality of drought resistance states, and the parents of the sugarcane are recombined through a pre-trained genetic algorithm to reacquire a plurality of sugarcane hybrid combinations. A target combination with better drought resistance effect is screened out from a plurality of sugarcane hybrid combinations, and the evaluation result has high reliability, thereby solving the technical problems proposed in the background art.

[0010] (II) Technical solutions

[0011] To achieve the above object, the application is implemented by the following technical solutions: a drought resistance evaluation method of sugarcane hybrid combination, comprising: collecting drought data in a target area to generate a regional drought data set, constructing a drought coefficient Ghot from the regional drought data set, and issuing a test instruction to the outside if the drought coefficient Ghot exceeds a drought threshold value;

[0012] After recognizing the environment mode in the target area and selecting sugarcane seedlings, a corresponding sugarcane hybrid strategy is developed and executed, and a trained conditional automatic control model is used to automatically control the environmental conditions when the planting environment in the sugarcane cultivation area is abnormal;

[0013] The recording frequency of each index is constrained according to the drought coefficient Ghot, and after obtaining the trait data of the sugarcane seedlings, the similarity of the traits of the sugarcane seedlings between different groups is judged through similarity analysis and a difference coefficient Yto is constructed, and a drought resistance evaluation instruction is issued to the outside if the difference coefficient Yto exceeds the expectation;

[0014] A trained drought resistance evaluation model is used to evaluate the drought resistance of the sugarcane seedlings, and a drought degree Hop is generated after obtaining the drought resistance scores of each sugarcane seedling, and a target combination is screened out from a plurality of sugarcane hybrid combinations according to the drought degree Hop. The drought resistance score Hy is linearly normalized, and the corresponding data value is mapped to the interval [0, 1], and then the drought degree Hop is generated in the following manner:

[0015]

[0016] weight coefficient, 0≤a≤1, 0≤β≤1, and a+β=1; Hy i is the drought tolerance score of the i th sugarcane seedling, Hy a is the drought tolerance score average, i=1, 2, …k, k is the number of sugarcane seedlings;

[0017] The difference between the target seedling and the control variety is analyzed to obtain the drought tolerance trait, and the target trait is selected from several drought tolerance states according to the difference, and the parents of the sugarcane are recombined by using the pre-trained genetic algorithm to obtain several groups of sugarcane hybrid combinations.

[0018] Further, when the drought data in the target area does not meet the expectation, the current planting condition is determined as a drought scenario; when the target area is in a drought scenario, the drought time and drought value that generates the drought scenario are obtained, and a regional drought data set is generated; the drought coefficient Ghot is generated from the regional drought data set in the following way:

[0019]

[0020] weight coefficient, 0≤p i ≤1, p i is the weighted value of the i th drought value; k is the number of drought scenarios, Gh ij is the difference between the i th drought scenario and the j th drought scenario, Gh a is the average of the drought value difference.

[0021] Further, after receiving the test instruction, the planting environment data in the target area is collected, and the trained recurrent neural network is trained from the labeled sample data to obtain a trained planting mode recognition model;

[0022] The trained planting mode recognition model is used to identify the planting environment data in the target area to obtain the corresponding environment mode; the environment mode is used as input, and the pre-constructed sugarcane hybrid strategy library is matched to the corresponding sugarcane hybrid strategy for the target area.

[0023] Further, when the sugarcane hybrid strategy is executed, the meteorological condition data in the sugarcane cultivation area is monitored, and a planting condition data set is generated after being summarized; the condition abnormality degree Jtp is generated from the planting condition data set, and if the obtained abnormality degree Jtp exceeds the abnormality threshold, an automatic control instruction is sent to the outside;

[0024] After receiving the automatic control instruction, the reference value of the planting condition data is set for each planting stage according to the sugarcane hybrid strategy, and the current planting condition data is used as input to use the trained condition automatic control model to automatically control the environmental conditions.

[0025] Further, linearly normalize the temperature Rt, humidity Rh and precipitation amount Ry, and map the corresponding data values into the interval [0, 1], and generate the condition abnormality degree Jtp according to the following manner:

[0026]

[0027] wherein, Rt i is the temperature at the i th monitoring node, Rt b is the acceptable value of the temperature, Rh i is the humidity at the i th monitoring node, Rh b is the acceptable value of the humidity, Ry i is the precipitation amount at the i th monitoring node, Ry b is the acceptable value of the precipitation amount, weight coefficient, 0≤S1≤1, 0≤S2≤1, 0≤S3≤1.

[0028] Further, the sugarcane planting stage is divided into several sub-stages, and after obtaining the historical drought data of each sub-stage, the corresponding drought coefficient Ghot is generated, and the recording frequency of each index is constrained according to the drought coefficient Ghot, and the constraint manner is as follows:

[0029]

[0030] weight coefficient, 0≤α≤1, 0≤β≤1; n is the number of data recording nodes, Po ij is the time interval from the i th recording node to the j th recording node, Po a is the average value of the time interval;

[0031] Record the sugarcane planting data on the recording nodes that meet the constraint conditions, and generate the sugarcane planting trait data set after summarizing.

[0032] Further, after obtaining the trait data of the sugarcane seedlings in each group, the similarity analysis is performed on the trait data of different sugarcane seedlings, and the corresponding similarity data is obtained, and the difference coefficient Yto is constructed from a plurality of groups of similarity data, wherein,

[0033] Linearly normalize the similarity Xy and map the corresponding data values into the interval [0, 1], and according to the following manner:

[0034]

[0035] wherein, Xy i is the i th similarity data, Xy a is the average value of the similarity, n is the number of similarity data, and p is the weight coefficient, 0≤p≤1.

[0036] Further, the growth trait data of the sugarcane is collected; the growth trait data of the sugarcane is taken as input, the drought tolerance evaluation model after training is used for drought tolerance evaluation of the sugarcane seedling, and the corresponding drought tolerance score is output; after the drought tolerance score of each sugarcane seedling is obtained, the drought resistance Hop is generated, and each sugarcane seedling is sorted according to the drought resistance Hop.

[0037] The sugarcane hybrid combination corresponding to the sugarcane seedling with the highest drought resistance Hop is taken as the target combination, and the corresponding sugarcane seedling is taken as the target seedling; the drought tolerance trait data of the parents and the control varieties in the target combination is collected respectively, and the drought tolerance trait data set is generated after being summarized.

[0038] Further, the difference between the target seedling and the control variety is analyzed, the difference degree between two similar traits is obtained through similarity analysis after the drought tolerance trait data of the sugarcane seedling is obtained, and each drought tolerance trait is marked according to the difference degree;

[0039] The correlation between the difference degree and the drought resistance Hop is analyzed by using multiple linear regression, the corresponding correlation coefficient is obtained, the drought tolerance traits are sorted according to the correlation coefficient, and the concentration degree Jop of the first m correlation coefficients before sorting is calculated in the following manner:

[0040]

[0041] Wherein, ρ is a weight coefficient, 0≤ρ≤1, σ is the standard deviation of all correlation coefficients, m is the number of correlation coefficients, C i is the i th correlation coefficient before sorting, and C a is the mean of the m correlation coefficients.

[0042] Further, if the value of m is determined, and the corresponding concentration degree Jop exceeds the preset concentration threshold, the first m drought tolerance traits before sorting are taken as target traits, and a combination optimization instruction is issued outwardly;

[0043] After receiving the combination optimization instruction, after obtaining the drought tolerance trait data of the parents and the sugarcane seedling in each sugarcane hybrid combination, the concentration degree of the target trait of the sugarcane is taken as the optimization target, the parents of the sugarcane are recombined through the pre-trained genetic algorithm, and a plurality of sugarcane hybrid combinations are reacquired.

[0044] (Three) beneficial effects

[0045] The present application provides a drought tolerance evaluation method of sugarcane hybrid combination, which has the following beneficial effects:

[0046] 1. According to the drought coefficient Ghot, whether the target area is suitable for planting sugarcane is judged, and the current sugarcane variety is optimized; the drought data in the target area is collected and the drought coefficient Ghot is constructed, and the suitable crops are screened according to the drought coefficient Ghot.

[0047] 2. According to the actual environment mode, the corresponding sugarcane crossbreeding strategy is matched and constructed for the current sugarcane crossbreeding, which can make the test planting environment and the actual planting environment more matched during crossbreeding.

[0048] 3. According to the planting condition data, the condition abnormality degree Jtp is constructed to judge whether the current planting condition is abnormal, and when the planting condition is abnormal, the sugarcane planting environment under the test condition is automatically adjusted and accurately adjusted, so that the growth state of the sugarcane seedling can meet the expectation.

[0049] 4. The frequency and time node of recording the data of the sugarcane seedling are constrained, and the attention degree of the drought coefficient Ghot to the growth state of the sugarcane seedling is adjusted, so that when the drought scene changes, the data acquisition frequency is adjusted to avoid the situation that the growth data of the sugarcane seedling cannot be collected in time.

[0050] 5. The diversity of a plurality of sugarcane seedlings is evaluated and judged, and the difference analysis of the sugarcane seedlings in different groups is carried out to realize the screening of drought-resistant sugarcane seedlings; the drought resistance of different sugarcane seedlings is comprehensively evaluated, and the sugarcane seedlings with high drought resistance are screened out from a plurality of crossbred sugarcane seedlings, so that the actual comprehensiveness of crossbreeding evaluation is better.

[0051] 6. The drought resistance of the sugarcane seedlings in each group is evaluated, and after the drought test of the sugarcane seedlings in different groups, the target combination with better drought resistance is screened out from a plurality of sugarcane crossbreeding combinations, and the drought resistance evaluation of the sugarcane crossbreeding combination is completed. The evaluation result is consistent with the actual sugarcane planting condition, and the reliability is high.

[0052] 7. Different degrees of difference are obtained, and the key drought resistance traits are determined after sugarcane crossbreeding and are used as target traits; a plurality of key drought resistance traits are screened out according to the concentration degree Jop, and the subsequent sugarcane crossbreeding can be targeted for cultivation, thereby improving the targeting of sugarcane crossbreeding; the parents of the sugarcane are recombined by genetic algorithm, and a plurality of sugarcane crossbreeding combinations are obtained again, and the success rate of crossbreeding test can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 It is a structure schematic diagram of the drought resistance evaluation method of the sugarcane crossbreeding combination of the application. DETAILED DESCRIPTION

[0054] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0055] Please refer to Figure 1 The present application provides a drought tolerance evaluation method for sugarcane hybrid combinations, comprising,

[0056] Step one, collect drought data in the target area to generate a regional drought data set, construct a drought coefficient Ghot from the regional drought data set, and if the drought coefficient Ghot exceeds the drought threshold, issue a test command to the outside;

[0057] The step one includes the following contents:

[0058] Step 101, after determining the planting area of sugarcane, determine the planting area as the target area, collect drought data in the target area, including humidity data and precipitation data at each time node; if the humidity data and precipitation data are both lower than the expected value, determine the current planting condition as a drought scenario;

[0059] When the target area is in a drought scenario, obtain the difference between the humidity data and the expected value, and the difference between the precipitation data and the expected value, take the maximum value in the difference as the drought value, obtain the drought time and drought value that produce the drought scenario, and generate a regional drought data set by summarizing;

[0060] Step 102, under the dimensionless condition, generate a drought coefficient Ghot from the drought data in the regional drought data set, in the following manner:

[0061]

[0062] The weight coefficient, 0≤p i ≤1, p i is the weighted value of the i-th drought value, which falls within [0, 1]; k is the number of drought scenarios, Gh ij is the drought value difference between the i-th drought scenario and the j-th drought scenario, Gh a is the average value of the drought value difference;

[0063] According to historical data and the expected tolerance of the drought scenario, a drought threshold is set in advance; if the drought coefficient Ghot exceeds the drought threshold, it indicates that the drought degree in the target area is high, and the current sugarcane variety may not be able to adapt to the target area, and needs to be optimized, at this time, a test command is issued to the outside;

[0064] In use, the contents in steps 101 and 102 are combined:

[0065] When sugarcane planting is needed, the planting environment in the sugarcane planting area is monitored, for example, the drought scenario is monitored, the monitoring condition data is used to construct the drought coefficient Ghot, the planting environment in the target area can be evaluated according to the drought coefficient Ghot, whether it is suitable to plant sugarcane in the target area is judged, if not, the current sugarcane variety can be optimized; at the same time, the drought data in the target area is collected and the drought coefficient Ghot is constructed, and the suitable crops can also be screened according to the drought coefficient Ghot.

[0066] However, due to the more drought tolerance traits of sugarcane, there is no uniform standard for evaluating the drought tolerance of sugarcane, and there is a certain difficulty in selecting high drought tolerance sugarcane seedlings. In the existing evaluation method of drought tolerance of sugarcane hybrid combination, after completing the hybrid test, several drought tolerance parameters of sugarcane seedlings are collected, and the drought tolerance parameters are used as evaluation. This evaluation method is more direct, which can screen out part of the sugarcane seedlings with better drought tolerance, but it is difficult to screen out the key drought tolerance traits of the sugarcane seedlings according to the drought tolerance parameters, and it cannot effectively assist in improving the success rate of hybrid test.

[0067] Step two, after identifying the environment mode in the target area and selecting the sugarcane seedling, the corresponding sugarcane hybrid strategy is formulated and executed, and when the planting environment in the sugarcane cultivation area is abnormal, the trained condition automatic control model is used to automatically control the environment condition;

[0068] The step two includes the following contents:

[0069] Step 201, after receiving the test instruction, the planting environment data in the target area is collected, such as rainfall, soil moisture content and light, etc. After training the recurrent neural network with the labeled sample data, the trained planting mode recognition model is obtained; the trained planting mode recognition model is used to identify the planting environment data in the target area, and the corresponding environment mode is obtained;

[0070] The environment mode is used as the input, and the corresponding sugarcane hybrid strategy is matched for the target area from the pre-constructed sugarcane hybrid strategy library, which specifically includes irrigation conditions, light conditions and soil humidity control, etc.; after determining the parents in the sugarcane hybrid combination and selecting the corresponding healthy sugarcane seedlings, the sugarcane hybrid strategy is executed;

[0071] In use, after determining the planting environment data in the target area and the corresponding environment mode, the corresponding sugarcane hybrid strategy is matched and constructed according to the actual environment mode, which can make the test planting environment and the actual planting environment more matched in the hybrid cultivation process;

[0072] Step 202, when implementing the sugarcane crossing strategy, monitor the meteorological condition data in the sugarcane cultivation area, such as temperature, humidity, and precipitation, and generate a set of planting condition data after summarizing;

[0073] Generate a condition abnormality degree Jtp from the set of planting condition data to describe the abnormality of the current planting conditions, wherein the temperature Rt, humidity Rh, and precipitation Ry are linearly normalized to map the corresponding data values to the interval [0, 1], according to the following manner:

[0074]

[0075] Wherein, Rt i is the temperature at the i-th monitoring node, Rt b is the acceptable value of the temperature, Rh i is the humidity at the i-th monitoring node, Rh b is the acceptable value of the humidity, Ry i is the precipitation at the i-th monitoring node, Ry b is the acceptable value of the precipitation, the weight coefficients S1, S2, and S3 satisfy 0≤S1≤1, 0≤S2≤1, and 0≤S3≤1, and the weight coefficients can be obtained by referring to the analytic hierarchy process;

[0076] According to historical data and the expected abnormal management of planting conditions, set an abnormal threshold in advance;

[0077] If the obtained abnormality degree Jtp exceeds the abnormal threshold, it indicates that the current planting environment has a certain degree of abnormality, and the current planting environment needs to be adjusted. At this time, an automatic control instruction is sent to the outside;

[0078] When using, after continuously obtaining several sets of planting condition data under test environments, the condition abnormality degree Jtp is constructed according to the planting condition data. It can be judged whether the current planting conditions are abnormal according to the condition abnormality degree Jtp. Under abnormal planting conditions, sugarcane seedlings may not grow normally;

[0079] Step 203, train the neural convolution algorithm from the labeled sample data to obtain a trained conditional automatic control model;

[0080] After receiving the automatic control instruction, set the reference value of the planting condition data for each planting stage according to the sugarcane crossing strategy, and use the trained conditional automatic control model to automatically control the environmental conditions by taking the current planting condition data as input, for example, irrigate the sugarcane seedlings in the planting state and adjust the irrigation amount;

[0081] When using, combine the contents in steps 201 to 203:

[0082] After the planting conditions are obtained in real time, the environment conditions are automatically controlled using the trained condition automatic control model, and when the planting conditions are abnormal, the automatic adjustment and precise adjustment of the sugarcane planting environment under the test conditions are realized, so that the planting environment conditions under the test can meet the actual needs, and the growth state of the sugarcane seedlings can meet the expectation.

[0083] Step three, according to the drought coefficient Ghot, the recording frequency of each index is restricted, and after the trait data of the sugarcane seedlings are obtained, the similarity of the traits of the sugarcane seedlings in different groups is judged by similarity analysis, and a difference coefficient Yto is constructed, and if the difference coefficient Yto exceeds the expectation, a drought tolerance evaluation instruction is sent to the outside;

[0084] The step three includes the following contents:

[0085] Step 301, the sugarcane planting stage is divided into several sub-stages, the historical drought data of each sub-stage is obtained, the corresponding drought coefficient Ghot is generated, the recording frequency of each index is restricted according to the drought coefficient Ghot, and the restriction mode is as follows:

[0086]

[0087] The weight coefficient is 0≤α≤1, 0≤β≤1; the weight coefficient can be obtained by referring to the analytic hierarchy process; n is the number of data recording nodes, Po ij is the time interval from the i th recording node to the j th recording node, Po a is the average value of the time interval;

[0088] The sugarcane planting data are recorded on the recording nodes meeting the constraint conditions, for example, various growth indexes (plant height, stem circumference, etc.), physiological indexes, etc.; after being summarized, a set of sugarcane planting trait data is generated;

[0089] In use, the drought scene under the test conditions is divided into several stages, in different stages, the frequency and time node of recording the data of the sugarcane seedlings are restricted according to the drought coefficient Ghot, and the attention degree of the sugarcane seedlings to the growth state is adjusted according to the drought coefficient Ghot, when the drought scene changes, the data collection frequency is adjusted, so as to avoid the situation that the growth data of the sugarcane seedlings cannot be collected in time;

[0090] Step 302, after the trait data of the sugarcane seedlings in each group are obtained, the similarity of the trait data of different sugarcane seedlings is analyzed, the difference between different sugarcane hybrid combinations is compared, the corresponding similarity data is obtained, and the difference coefficient Yto is constructed from a plurality of similarity data, so as to judge the abnormal degree of the overall sugarcane seedlings, wherein,

[0091] The similarity Xy is linearly normalized, and the corresponding data value is mapped to the interval [0, 1] in the following manner:

[0092]

[0093] where Xy i is the i-th similarity data, Xy a is the mean value of the similarity, n is the number of similarity data, and p is a weight coefficient, 0≤p≤1.

[0094] According to historical data and the expected differences between different sugarcane seedlings, a difference threshold is set in advance.

[0095] If the difference coefficient Yto exceeds the difference threshold, it means that the trait differences between the sugarcane seedlings produced by different sugarcane hybrid combinations are large, and the diversity is high, and there may be drought-tolerant sugarcane varieties. At this time, a multiple comparison method is used to determine the significant differences between groups, provide charts (such as box plots, line graphs) to show the performance of various sugarcane hybrid combinations, and issue drought-tolerant evaluation instructions to the outside;

[0096] In use, the contents in steps 301 and 302 are combined:

[0097] After the sugarcane seedlings enter the mature stage, extract sugarcane seedlings as reference samples within each group. After obtaining the similarity data between different reference sample data, calculate the difference coefficient Yto, and evaluate and judge the diversity of a number of sugarcane seedlings according to the difference coefficient Yto. If the diversity is low and the traits of different reference samples are basically the same, the current hybrid seedling may not have the expected effect. If the diversity is high, there may be sugarcane seedlings that meet the conditions. In this case, difference analysis can be performed on the sugarcane seedlings in different groups to achieve the screening of drought-tolerant sugarcane seedlings.

[0098] Step four, using the trained drought-tolerant evaluation model to evaluate the drought tolerance of sugarcane seedlings, obtaining the drought-tolerance degree Hop after obtaining the drought-tolerance score of each sugarcane seedling, and screening the target combination from a number of sugarcane hybrid combinations according to the drought-tolerance degree Hop.

[0099] The step four includes the following contents:

[0100] Step 401, after training the convolutional neural network from the labeled sample data, a trained drought-tolerant evaluation model is obtained to evaluate the drought tolerance of different sugarcane hybrid combinations.

[0101] The growth traits data of the sugarcane are collected according to growth indexes (such as plant height, stem diameter, leaf area) and physiological indexes (such as leaf relative water content, net photosynthetic rate and stomatal conductance), and the like, and are summarized; the growth traits data of the sugarcane are taken as input, the drought tolerance of the sugarcane seedlings is evaluated by the trained drought tolerance evaluation model, and the corresponding drought tolerance score is output;

[0102] In use, on the basis of obtaining various data of the sugarcane seedlings, the trained drought tolerance evaluation model can realize comprehensive evaluation of the drought tolerance of different sugarcane seedlings, and according to the obtained drought tolerance score, the sugarcane seedlings with higher drought tolerance performance are screened out from the several hybridized sugarcane seedlings, so that the actual comprehensive evaluation of the hybridization is better;

[0103] Step 402, after obtaining the drought tolerance score of each sugarcane seedling, the drought degree Hop is generated, wherein the drought tolerance score Hy is linearly normalized, and the corresponding data value is mapped into the interval [0, 1], and then the following method is used:

[0104]

[0105] The weight coefficients are 0≤α≤1 and 0≤β≤1, and α+β=1, the values of the weight coefficients are consistent with the previous values; Hy i is the drought tolerance score of the i th sugarcane seedling, Hy a is the mean of the drought tolerance score, i = 1, 2, … k, and k is the number of sugarcane seedlings;

[0106] According to the drought degree Hop, each sugarcane seedling is sorted, and the sugarcane hybrid combination corresponding to the sugarcane seedling with the highest drought degree Hop is taken as the target combination, and the corresponding sugarcane seedling is taken as the target seedling;

[0107] The drought tolerance trait data of the parents and the control varieties in the target combination are collected, for example, thick cuticle, stomatal density, water use efficiency and osmotic adjustment substance accumulation, and the like, and are summarized to generate a drought tolerance trait data set;

[0108] In use, the contents in steps 401 and 402 are combined:

[0109] Considering that the differences between the sugarcane seedlings in each group may not be large, the drought degree Hop is constructed on the basis of several drought tolerance scores, the drought tolerance performance of the sugarcane seedlings in each group is evaluated according to the drought degree Hop, and after the drought tolerance test of the sugarcane seedlings in different groups, the target combination with better drought tolerance effect is screened out from the several sugarcane hybrid combinations, the drought tolerance evaluation of the sugarcane hybrid combination is completed, the evaluation result is consistent with the actual sugarcane planting condition, and the reliability is high.

[0110] Step five, analyze the difference degree of drought resistance traits between the target seedlings and the control varieties, screen the target traits in several drought resistance states according to the difference degree, and recombine the parents of sugarcane through the pre-trained genetic algorithm to reacquire several groups of sugarcane hybrid combinations;

[0111] The step five includes the following contents:

[0112] Step 501, difference analysis between the target seedlings and the control varieties, after obtaining the drought resistance trait data of the sugarcane seedlings, the difference degree between two similar traits is obtained through similarity analysis, and each drought resistance trait is marked with the difference degree;

[0113] The correlation between the difference degree and the drought resistance Hop is analyzed by using multiple linear regression, and the corresponding correlation coefficient is obtained;

[0114] When used, after completing the screening of the target combination, the difference between the different difference degrees, that is, the influence degree of different types and proportions of drought resistance traits on the drought resistance of sugarcane seedlings, such as the difference between the influence degrees of different stomatal densities on the drought resistance of sugarcane seedlings, is obtained, so that after sugarcane crossing, the key drought resistance traits can be determined through multiple linear regression analysis or correlation analysis, and they are used as target traits;

[0115] Step 502, sort each drought resistance trait according to the correlation coefficient, calculate the concentration of the first m correlation coefficients before sorting, and the method is as follows:

[0116]

[0117] Wherein, ρ is the weight coefficient, 0≤ρ≤1, the value is the same as the previous value; σ is the standard deviation of all correlation coefficients, m is the number of correlation coefficients, C i is the ith correlation coefficient before sorting, and C a is the mean of the m correlation coefficients;

[0118] If the value of m is determined, and the corresponding concentration Jop exceeds the preset concentration threshold, it means that these drought resistance traits have a greater impact on the drought resistance of sugarcane, and the first m drought resistance traits before sorting are used as target traits, which can further increase these traits during cultivation. At this time, the combination optimization instruction is sent out;

[0119] When used, the concentration Jop is constructed on the basis of the correlation coefficient, and several key drought resistance traits are screened according to the concentration Jop, which can be targeted for cultivation during subsequent sugarcane crossing, and the targeting of sugarcane crossing is improved.

[0120] Step 503, after receiving the combination optimization instruction, after obtaining the drought tolerance data of the parents and sugarcane seedlings in each sugarcane hybrid combination, taking increasing the concentration of the target traits of sugarcane as the optimization goal, recombining the parents of sugarcane through the pre-trained genetic algorithm, and reacquiring several groups of sugarcane hybrid combinations;

[0121] In use, in combination with the contents in steps 501 to 503:

[0122] In determining the target traits to be obtained, on the basis of the existing sugarcane trait data, the parents of sugarcane are recombined through the genetic algorithm and several sugarcane hybrid combinations are reacquired, and when hybridization experiments are carried out according to the reacquired sugarcane hybrid combinations, the success rate of the hybridization experiments is improved.

[0123] Analytic Hierarchy Process (AHP) is a decision-making method, which decomposes elements related to decision-making into target, criteria, scheme and other levels, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for processing target systems with hierarchical and staggered evaluation indexes, and when the target value is difficult to quantify, AHP is an effective decision-making tool.

[0124] The core of AHP is to decompose the decision-making problem into multiple levels to form a hierarchical structure, which usually includes the target layer, the criterion layer, the sub-criterion layer and the scheme layer. By solving the characteristic vector of the judgment matrix, the priority weight of each element in a level to a certain element in the previous level is obtained, and finally the weighted sum method is used to merge each alternative scheme to the final weight of the total target, so as to find the optimal scheme.

[0125] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0126] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0128] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0129] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0130] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0131] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0132] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for evaluating drought tolerance of sugarcane hybrid combinations, characterized by: include, Collect drought data in the target area and generate a regional drought data set, and then construct a drought coefficient from the regional drought data set. If the drought coefficient When the drought threshold is exceeded, a test instruction is issued externally; After identifying and acquiring environmental patterns within the target area and selecting sugarcane seedlings, a corresponding sugarcane hybridization strategy is formulated and implemented. When abnormalities occur in the planting environment within the sugarcane cultivation area, the trained conditional automatic control model is used to automatically control environmental conditions. Based on drought coefficient The recording frequency of each indicator is constrained, and after obtaining the trait data of sugarcane seedlings, the similarity of the traits between sugarcane seedlings in different groups is determined through similarity analysis and the difference coefficient is constructed. , if the coefficient of variation Exceeded expectations and issued external drought tolerance evaluation instructions; The drought tolerance evaluation model after training is used to evaluate the drought tolerance of sugarcane seedlings, and the drought tolerance score of each sugarcane seedling is generated after obtaining the drought tolerance score. , based on drought tolerance The target combination was screened out from several sugarcane hybrid combinations; among them, the drought resistance score was Perform linear normalization and map the corresponding data values ​​to the interval Then generate drought tolerance as follows : ; 、 is the weight coefficient, , ,and ; is the drought tolerance score of the i1th sugarcane seedling, is the mean drought tolerance score, , k1 is the number of sugarcane seedlings; Drought tolerance The sugarcane hybrid combination corresponding to the highest sugarcane seedling was used as the target combination, and the corresponding sugarcane seedling was used as the target seedling. The difference between the target seedling and the control variety was analyzed. After obtaining the drought resistance trait data of the sugarcane seedling, the difference between the two similar traits was obtained through similarity analysis, and multiple linear regression was used to analyze the difference and drought resistance. The correlation between them is used to sort the drought-resistant traits according to the obtained correlation coefficients, and the concentration of several correlation coefficients before sorting is calculated. , if the concentration If the concentration threshold is exceeded, the top drought-tolerance traits will be selected as target traits; After obtaining the drought-resistance trait data of the parents and sugarcane seedlings in each sugarcane hybrid combination, the sugarcane parents are recombined through a pre-trained genetic algorithm with the goal of increasing the concentration of the target sugarcane traits as the optimization goal, and several groups of sugarcane hybrid combinations are obtained again.

2. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 1, wherein: When drought data within the target area does not meet expectations, the current planting conditions are identified as a drought scenario; When the target area is in a drought scenario, the drought time and drought value that caused the drought scenario are obtained, and the regional drought data set is generated; Generate drought coefficients from regional drought data sets , as follows: ; is the weighted value of the i2th drought value, satisfy ; k2 is the number of drought scenarios, is the difference in drought value between the i2th drought scenario and the j2th drought scenario, is the average of the drought value differences.

3. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 2, wherein: After receiving the test instruction, the planting environment data in the target area is collected, and the recurrent neural network is trained with the labeled sample data to obtain the trained planting pattern recognition model; The trained planting pattern recognition model is used to identify the planting environment data in the target area to obtain the corresponding environmental pattern; using the environmental pattern as input, the pre-built sugarcane hybridization strategy library matches the corresponding sugarcane hybridization strategy for the target area.

4. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 1, wherein: When implementing the sugarcane hybridization strategy, the meteorological condition data is monitored in the sugarcane cultivation area and the planting condition data set is generated after aggregation; the condition anomaly degree is generated from the planting condition data set. , if the obtained abnormality If the abnormal threshold is exceeded, an automatic control instruction will be issued to the outside; After receiving the automatic control instructions, the reference values ​​of the planting condition data are set for each planting stage according to the sugarcane hybridization strategy. The current planting condition data is used as input, and the trained conditional automatic control model is used to automatically control the environmental conditions.

5. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 4, wherein: Temperature ,humidity and precipitation Perform linear normalization and map the corresponding data values ​​to the interval The conditional abnormality is generated as follows : ;in, is the temperature on the i3th monitoring node, is the acceptable value of temperature, is the humidity at the i3th monitoring node, is the acceptable value of humidity, is the precipitation at the i3th monitoring node, is the acceptable value of precipitation, 、 、 is the weight coefficient, , , .

6. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 5, wherein: The sugarcane planting stage is divided into several sub-stages, and the corresponding drought coefficient is generated after obtaining the historical regional drought data of each sub-stage , based on the drought coefficient The recording frequency of each indicator is constrained as follows: ; 、 is the weight coefficient, , ; n1 is the number of data recording nodes, is the time interval from the i3th record node to the j3th record node, is the time interval average; The sugarcane planting data are recorded at the record nodes that meet the constraints, and the sugarcane planting trait data set is generated after aggregation.

7. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 6, wherein: After obtaining the trait data of sugarcane seedlings in each group, similarity analysis is performed on the trait data of different sugarcane seedlings to obtain the corresponding similarity data, and the difference coefficient is constructed from several groups of similarity data. ,in, Similarity Perform linear normalization and map the corresponding data values ​​to the interval In the following way: ;in, is the i4th similarity data, is the mean of similarity, is the number of similarity data, 1 is the weight coefficient, .

8. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 7, wherein: Collect sugarcane growth trait data; use the sugarcane growth trait data as input, use the trained drought tolerance evaluation model to evaluate the drought tolerance of sugarcane seedlings, and output the corresponding drought tolerance score; obtain the drought tolerance score of each sugarcane seedling and generate the drought tolerance index. , based on drought tolerance Sort the sugarcane seedlings; Drought tolerance The sugarcane hybrid combination corresponding to the highest sugarcane seedling is used as the target combination, and the corresponding sugarcane seedling is used as the target seedling; the drought resistance trait data of the parents and the control varieties in the target combination are collected respectively, and the drought resistance trait data set is generated after aggregation.

9. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 8, wherein: Perform a difference analysis between the target seedlings and the control varieties. After obtaining the drought resistance trait data of the sugarcane seedlings, obtain the difference between two similar traits through similarity analysis, and mark each drought resistance trait with the difference; Multiple linear regression analysis of differences and drought tolerance The correlation between them is obtained, the corresponding correlation coefficient is obtained, the drought resistance traits are sorted according to the correlation coefficient, and the concentration of several correlation coefficients before sorting is calculated. , as follows: ;in, 2 is the weight coefficient, , The standard deviation of all correlation coefficients is shown in the ranking. is the number of correlation coefficients, is the i5th correlation coefficient within the ranking, for The mean of the correlation coefficients.

Images