Method for evaluating drought tolerance of sugarcane hybrid combination

Abstract

The invention discloses a drought tolerance evaluation method of a sugarcane hybrid combination, and relates to the technical field of drought tolerance evaluation, and the method comprises the steps: restraining the recording frequency of each index according to a drought coefficient, obtaining the character data of sugarcane seedlings, judging the similarity of the characters of the sugarcane seedlings in different groups through similarity analysis, constructing a difference coefficient, and calculating the drought tolerance of the sugarcane hybrid combination. If the difference coefficient exceeds the expectation, performing drought tolerance evaluation on the sugarcane seedlings by using the trained drought tolerance evaluation model, generating drought tolerance after obtaining a drought tolerance score of each sugarcane seedling, and screening out a target combination from the plurality of sugarcane hybrid combinations according to the drought tolerance; and screening out target characters in a plurality of drought tolerance states according to the difference degree, and recombining the parents of the sugarcane through a pre-trained genetic algorithm to reobtain a plurality of groups of sugarcane hybridized combinations. The target combination with a good drought-enduring effect is screened out from a plurality of sugarcane hybrid combinations, and the reliability of the evaluation result is high.

Description

Technical Field

[0001] The invention relates to the technical field of drought resistance evaluation, and in particular to a method for evaluating drought resistance of a sugarcane hybrid combination. Background Art

[0002] In sugarcane breeding, sexual hybridization technology occupies a core position. By carefully selecting parents and implementing hybridization, researchers can make full use of favorable variations on the complex genetic basis of sugarcane to cultivate new varieties with high yield, high sugar content and excellent stress resistance. Among them, drought tolerance, as a key trait for sugarcane to cope with drought challenges, has also made significant progress in research. Through molecular marker-assisted breeding and transgenic technology, scientists have not only revealed the genetic genes and physiological mechanisms closely related to drought tolerance, but also successfully bred a series of new sugarcane varieties that can still maintain excellent growth and yield in arid environments, injecting strong impetus into the sustainable development of agricultural production.

[0003] In the Chinese invention patent with application publication number CN116359436A, a method for evaluating drought resistance of garden plants is disclosed, the method comprising the following steps: selecting garden plants with consistent growth; subjecting the garden plants to water stress treatment, and transferring to normal maintenance after the water stress treatment; measuring the drought resistance index of the garden plants subjected to the water stress treatment to obtain drought resistance index measurement data; evaluating the drought resistance of the garden plants according to the drought resistance index measurement data; wherein: the drought resistance index includes morphological scores, leaf trait parameters, leaf photosynthetic gas exchange parameters and chlorophyll fluorescence parameters. An objective, accurate and reasonable comprehensive evaluation of plant drought resistance is performed.

[0004] Combined with the above application and the contents of the prior art:

[0005] Considering that the rainfall in sugarcane growing areas is usually low and often in a drought state, the drought resistance of sugarcane is particularly important. In order to improve the drought resistance of sugarcane varieties, it is necessary to hybridize sugarcane and select the most drought-resistant variety from the several types of sugarcane seedlings obtained.

[0006] However, since sugarcane has many drought-resistant traits and there is a lack of unified standards for evaluating the drought resistance of sugarcane, it is difficult to select sugarcane seedlings with high drought resistance. In the existing drought resistance evaluation method for sugarcane hybrid combinations, usually after completing the hybridization test, several drought resistance parameters of the sugarcane seedlings are collected and evaluated based on the drought resistance parameters. This evaluation method is relatively direct and can screen out the sugarcane seedlings with better drought resistance from the existing sugarcane seedlings, but it is difficult to screen out the key drought-resistant traits of the sugarcane seedlings based on the drought resistance parameters, which does not effectively assist in improving the success rate of the hybridization test.

[0007] To this end, the present invention provides a method for evaluating drought resistance of a sugarcane hybrid combination. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies of the prior art, the present invention provides a method for evaluating drought resistance of sugarcane hybrid combinations. The similarity of traits between sugarcane seedlings in different groups is determined by similarity analysis and a difference coefficient is constructed. If the difference coefficient exceeds expectations, the drought resistance of the sugarcane seedlings is evaluated using a trained drought resistance evaluation model. After obtaining the drought resistance score of each sugarcane seedling, a drought resistance is generated. A target combination is screened out from several sugarcane hybrid combinations based on the drought resistance; target traits are screened out from several drought resistance states based on the difference, and the sugarcane parents are recombined through a pre-trained genetic algorithm to obtain several groups of sugarcane hybrid combinations. A target combination with a better drought resistance effect is screened out from several sugarcane hybrid combinations, and the evaluation result has a high reliability, thereby solving the technical problems raised in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for evaluating drought tolerance of sugarcane hybrid combinations, comprising: collecting drought data in a target area and summarizing 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;

[0012] After identifying and acquiring the environmental patterns in the target area and selecting the sugarcane seedlings, the corresponding sugarcane hybridization strategy is formulated and implemented. When the planting environment in the sugarcane cultivation area is abnormal, the trained conditional automatic control model is used to automatically control the environmental conditions.

[0013] The recording frequency of each indicator is constrained according to the drought coefficient Ghot. 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 Yto is constructed. If the difference coefficient Yto exceeds expectations, a drought tolerance evaluation instruction is issued to the outside.

[0014] The drought tolerance evaluation model after training is used to evaluate the drought tolerance of sugarcane seedlings. After obtaining the drought tolerance score of each sugarcane seedling, the drought tolerance Hop is generated. According to the drought tolerance Hop, the target combination is screened out from several sugarcane hybrid combinations. Among them, the drought tolerance score Hy is linearly normalized, and the corresponding data value is mapped to the interval [0,1], and then the drought tolerance Hop is generated according to the following method:

[0015]

[0016] Weight coefficient, 0≤α≤1, 0≤β≤1, and α+β=1; Hy i is the drought tolerance score of the i-th sugarcane seedling, Hy a is the mean of drought tolerance score, i = 1, 2, ... k, k is the number of sugarcane seedlings;

[0017] The difference in drought resistance traits between the target seedlings and the control varieties was analyzed and obtained, and the target traits were screened out within several drought resistance states based on the difference. The sugarcane parents were recombined through a pre-trained genetic algorithm to obtain several groups of sugarcane hybrid combinations.

[0018] Furthermore, when the drought data in the target area does not meet expectations, the current planting conditions are determined as drought scenarios; when the target area is in a drought scenario, the drought time and drought value that produce the drought scenario are obtained, and the regional drought data set is summarized and generated; the drought coefficient Ghot is generated from the regional drought data set in the following manner:

[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 in drought value between the i-th drought scenario and the j-th drought scenario, Gh a is the average of the drought value differences.

[0021] Further, 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 a trained planting pattern recognition model;

[0022] The trained planting pattern recognition model is used to identify the planting environment data in the target area to obtain the corresponding environmental pattern; the environmental pattern is used as input to match the corresponding sugarcane hybridization strategy for the target area from the pre-built sugarcane hybridization strategy library.

[0023] Furthermore, when executing the sugarcane hybridization strategy, the meteorological condition data is monitored in the sugarcane cultivation area, and the planting condition data set is generated after being summarized; the condition abnormality Jtp is generated from the planting condition data set, and if the acquired abnormality Jtp exceeds the abnormal threshold, an automatic control instruction is issued 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 hybridization strategy, and the current planting condition data is used as input to automatically control the environmental conditions using the trained conditional automatic control model.

[0025] Furthermore, the temperature Rt, humidity Rh and precipitation Ry are linearly normalized, and the corresponding data values ​​are mapped to the interval [0,1], and the conditional anomaly Jtp is generated according to the following method:

[0026]

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

[0028] Furthermore, the sugarcane planting stage is divided into several sub-stages, and the corresponding drought coefficient Ghot is generated after obtaining the historical drought data of each sub-stage. The recording frequency of each indicator is constrained according to the drought coefficient Ghot. The constraint method 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 time interval average;

[0031] The sugarcane planting data are recorded at the record nodes that meet the constraints, and a sugarcane planting trait data set is generated after aggregation.

[0032] Furthermore, 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 corresponding similarity data, and a difference coefficient Yto is constructed from several groups of similarity data, where:

[0033] Perform linear normalization on the similarity Xy and map the corresponding data values ​​to the interval [0,1] as follows:

[0034]

[0035] Among them, Xy i is the i-th similarity data, Xy a is the mean of similarity, n is the number of similarity data, ρ is the weight coefficient, 0≤ρ≤1.

[0036] Furthermore, the sugarcane growth trait data is collected; the sugarcane growth trait data is used as input, the drought resistance evaluation model after training is used to evaluate the drought resistance of the sugarcane seedlings, and the corresponding drought resistance score is output; after obtaining the drought resistance score of each sugarcane seedling, the drought resistance degree Hop is generated, and each sugarcane seedling is sorted according to the drought resistance degree Hop;

[0037] The sugarcane hybrid combination corresponding to the sugarcane seedlings with the highest drought tolerance Hop was taken as the target combination, and the corresponding sugarcane seedlings were taken as the target seedlings; the drought tolerance trait data of the parents and the control varieties in the target combination were collected respectively, and the drought tolerance trait data set was generated after aggregation.

[0038] Furthermore, the target seedlings and the control varieties were analyzed for differences. After obtaining the drought resistance trait data of the sugarcane seedlings, the difference between two similar traits was obtained through similarity analysis, and each drought resistance trait was marked with the difference.

[0039] Use multiple linear regression to analyze the correlation between the difference and the drought tolerance Hop, obtain the corresponding correlation coefficient, sort the drought tolerance traits according to the correlation coefficient, and calculate the concentration Jop of several correlation coefficients before sorting, as follows:

[0040]

[0041] Among them, ρ is the 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 within the ranking, C a is the mean of m correlation coefficients.

[0042] Furthermore, if after determining the value of m, the corresponding concentration Jop exceeds the preset concentration threshold, the drought tolerance traits of m before sorting are taken as target traits, and a combination optimization instruction is issued externally;

[0043] After receiving the combination optimization instruction, after obtaining the drought resistance trait data of the parents and sugarcane seedlings in each sugarcane hybrid combination, the sugarcane parents are recombined through the pre-trained genetic algorithm with increasing the concentration of the sugarcane target traits as the optimization goal, and several groups of sugarcane hybrid combinations are obtained again.

[0044] (III) Beneficial effects

[0045] The present invention provides a method for evaluating drought tolerance of sugarcane hybrid combinations, which has the following beneficial effects:

[0046] 1. Determine whether the target area is suitable for growing sugarcane based on the drought coefficient Ghot, and optimize the current sugarcane varieties; collect drought data in the target area and construct the drought coefficient Ghot, and screen suitable crops based on the drought coefficient Ghot.

[0047] 2. Rapidly match and construct corresponding sugarcane hybridization strategies for current sugarcane hybridization according to actual environmental patterns, so that the experimental planting environment and the actual planting environment can be more closely matched during the hybridization process.

[0048] 3. Construct the condition abnormality degree Jtp based on the planting condition data to determine whether the current planting conditions are abnormal. When the planting conditions are abnormal, realize automatic and precise adjustment of the sugarcane planting environment under the test conditions so that the growth state of the sugarcane seedlings can meet expectations.

[0049] 4. Constrain the frequency and time nodes of recording various data of sugarcane seedlings, adjust the degree of attention to the growth status of sugarcane seedlings according to the drought coefficient Ghot, and adjust the data collection frequency when the drought scene changes to avoid the situation where the growth data of sugarcane seedlings cannot be collected in time.

[0050] 5. Evaluate and judge the diversity of several sugarcane seedlings, conduct difference analysis on sugarcane seedlings in different groups, and select drought-resistant sugarcane seedlings; comprehensively evaluate the drought resistance of different sugarcane seedlings, and select sugarcane seedlings with higher drought resistance from several hybridized sugarcane seedlings, so as to make the hybridization evaluation more comprehensive.

[0051] 6. Evaluate the drought resistance of sugarcane seedlings in each group. After conducting drought resistance tests on sugarcane seedlings in different groups, select target combinations with better drought resistance from several sugarcane hybrid combinations to complete the drought resistance evaluation of sugarcane hybrid combinations. The evaluation results are consistent with the actual sugarcane planting conditions and have high reliability.

[0052] 7. Obtain different degrees of difference, determine the key drought-resistant traits after sugarcane hybridization, and use them as target traits; screen out several key drought-resistant traits based on the concentration Jop, and cultivate them in a targeted manner in subsequent sugarcane hybridization to improve the targeting of sugarcane hybridization; recombine the sugarcane parents through genetic algorithms and obtain several sugarcane hybrid combinations again, which can improve the success rate of hybridization experiments when conducting hybridization experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 The diagram is a schematic diagram of the structure of the method for evaluating drought tolerance of sugarcane hybrid combinations of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] See also Figure 1 The present invention provides a method for evaluating drought resistance of a sugarcane hybrid combination, comprising:

[0056] Step 1: Collect drought data in the target area and generate a regional drought data set. The drought coefficient Ghot is constructed from the regional drought data set. If the drought coefficient Ghot exceeds the drought threshold, a test instruction is issued to the outside.

[0057] The step 1 includes the following contents:

[0058] Step 101: After determining the planting area of ​​sugarcane, the planting area is determined as a target area, and drought data is collected 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 expected, the current planting condition is determined as a drought scenario;

[0059] When the target area is in a drought scenario, the difference between the humidity data and precipitation data and the expected value is obtained respectively, and the maximum value of the difference is taken as the drought value. The drought time and drought value that produce the drought scenario are obtained, and the regional drought data set is generated by summarizing;

[0060] Step 102: Under dimensionless conditions, the drought coefficient Ghot is generated from the drought data in the regional drought data set in the following manner:

[0061]

[0062] Weight coefficient, 0≤p i ≤1, p i is the weighted value of the i-th drought value, and its value falls within [0, 1]; k is the number of drought scenes, Gh ij is the difference in drought value between the i-th drought scenario and the j-th drought scenario, Gh a is the average of the drought value differences;

[0063] The drought threshold is set in advance based on historical data and the tolerable expectations of drought scenarios. If the drought coefficient Ghot exceeds the drought threshold, it means that the drought level in the target area is high and the current sugarcane variety may be difficult to adapt to the target area and needs to be optimized. At this time, a test instruction is issued to the outside.

[0064] When using, combine the contents in steps 101 and 102:

[0065] When sugarcane planting is required, the planting environment in the sugarcane planting area, such as drought scenes, is first monitored, and the drought coefficient Ghot is constructed using the acquired monitoring condition data. Based on the drought coefficient Ghot, the planting environment in the target area can be evaluated, and whether the target area is suitable for planting sugarcane can be judged. If not suitable, the current sugarcane variety can be optimized. At the same time, drought data in the target area is collected and the drought coefficient Ghot is constructed. Crops suitable for planting can also be screened based on the drought coefficient Ghot.

[0066] However, since sugarcane has many drought-resistant traits and there is a lack of unified standards for evaluating the drought resistance of sugarcane, it is difficult to select sugarcane seedlings with high drought resistance. In the existing drought resistance evaluation method for sugarcane hybrid combinations, usually after completing the hybridization test, several drought resistance parameters of the sugarcane seedlings are collected and evaluated based on the drought resistance parameters. This evaluation method is relatively direct and can screen out the sugarcane seedlings with better drought resistance from the existing sugarcane seedlings, but it is difficult to screen out the key drought-resistant traits of the sugarcane seedlings based on the drought resistance parameters, which does not effectively assist in improving the success rate of the hybridization test.

[0067] Step 2: After identifying and acquiring the environmental pattern in the target area and selecting the sugarcane seedlings, formulate and implement the corresponding sugarcane hybridization strategy. When the planting environment in the sugarcane cultivation area is abnormal, the trained conditional automatic control model is used to automatically control the environmental conditions;

[0068] The step 2 includes the following contents:

[0069] Step 201: after receiving the test instruction, collect the planting environment data in the target area, such as rainfall, soil moisture content and light, etc., train the recurrent neural network with the labeled sample data, and obtain the trained planting pattern recognition model; use the trained planting pattern recognition model to identify the planting environment data in the target area and obtain the corresponding environment pattern;

[0070] Using the environmental model as input, the pre-built sugarcane hybridization strategy library matches the corresponding sugarcane hybridization strategy for the target area, including irrigation conditions, light conditions, and soil moisture control. After determining the parents in the sugarcane hybrid combination and selecting the corresponding healthy sugarcane seedlings, the sugarcane hybridization strategy is executed.

[0071] When in use, after determining the planting environment data and the corresponding environmental pattern in the target area, the corresponding sugarcane hybridization strategy can be quickly matched and constructed for the current sugarcane hybridization cultivation according to the actual environmental pattern, so that the experimental planting environment and the actual planting environment can be more matched during the hybridization cultivation process;

[0072] Step 202: When executing the sugarcane hybridization strategy, the meteorological condition data, such as temperature, humidity and precipitation, are monitored in the sugarcane cultivation area, and the data are summarized to generate a planting condition data set;

[0073] The condition anomaly Jtp describing the abnormality of the current planting conditions is generated from the planting condition data set, where the temperature Rt, humidity Rh and precipitation Ry are linearly normalized and the corresponding data values ​​are mapped to the interval [0,1] according to the following method:

[0074]

[0075] Among them, Rt i is the temperature at the i-th monitoring node, Rt b is the acceptable value of temperature, Rh i is the humidity at the i-th monitoring node, Rh b is the acceptable value of humidity, Ry i is the precipitation at the i-th monitoring node, Ry b is the acceptable value of precipitation, weight coefficient, 0≤S1≤1, 0≤S2≤1, 0≤S3≤1, the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0076] Pre-set abnormal thresholds based on historical data and expectations of abnormal management of planting conditions;

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

[0078] When in use, after continuously acquiring several groups of planting condition data under the test environment, the condition abnormality degree Jtp is constructed according to the planting condition data, and whether the current planting conditions are abnormal can be judged according to the condition abnormality degree Jtp. Under abnormal planting conditions, the sugarcane seedlings may be difficult to grow normally;

[0079] Step 203: training a neural convolution algorithm with the labeled sample data to obtain a trained conditional automatic control model;

[0080] After receiving the automatic control instruction, the reference value of planting condition data is set for each planting stage according to the sugarcane hybridization strategy, and the current planting condition data is used as input to automatically control the environmental conditions using the trained conditional automatic control model, for example, irrigating the sugarcane seedlings in the planting state and adjusting the irrigation amount;

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

[0082] After acquiring the planting conditions in real time, the trained conditional automatic control model is used to automatically control the environmental conditions. When abnormal planting conditions occur, the sugarcane planting environment under the test conditions can be automatically and precisely adjusted to ensure that the planting environment conditions under the test are consistent with actual needs and the growth status of the sugarcane seedlings can meet expectations.

[0083] Step 3: Constrain the recording frequency of each indicator based on the drought coefficient Ghot, and after obtaining the trait data of sugarcane seedlings, determine the similarity of the traits between sugarcane seedlings in different groups through similarity analysis and construct the difference coefficient Yto. If the difference coefficient Yto exceeds expectations, issue a drought tolerance evaluation instruction to the outside world;

[0084] The step three includes the following contents:

[0085] Step 301: divide the sugarcane planting stage into several sub-stages, obtain the historical drought data of each sub-stage, generate the corresponding drought coefficient Ghot, and constrain the recording frequency of each indicator according to the drought coefficient Ghot. The constraint method is as follows:

[0086]

[0087] Weight coefficient, 0≤α≤1, 0≤β≤1; weight coefficient can be obtained by referring to the hierarchical analysis method; n is the number of data record nodes, Po ij is the time interval from the i-th recording node to the j-th recording node, Po a is the time interval average;

[0088] Record the sugarcane planting data at the recording nodes that meet the constraints, such as various growth indicators (plant height, stem girth, etc.), physiological indicators, etc.; after aggregation, generate a sugarcane planting trait data set;

[0089] When in use, the drought scene under the test conditions is divided into several stages. In different stages, the frequency and time nodes of recording various data of sugarcane seedlings are constrained according to the drought coefficient Ghot, and the degree of attention to the growth status of sugarcane seedlings is adjusted according to the drought coefficient Ghot. When the drought scene changes, the data collection frequency is adjusted to avoid the situation where the growth data of sugarcane seedlings cannot be collected in time.

[0090] Step 302: After obtaining the trait data of the sugarcane seedlings in each group, similarity analysis is performed on the trait data of different sugarcane seedlings, and the differences between the sugarcane hybrid combinations treated differently are compared to obtain the corresponding similarity data. The difference coefficient Yto is constructed from several groups of similarity data to determine the degree of abnormality of the overall sugarcane seedlings.

[0091] Perform linear normalization on the similarity Xy and map the corresponding data values ​​to the interval [0,1] as follows:

[0092]

[0093] Among them, Xy i is the i-th similarity data, Xy a is the mean of similarity, n is the number of similarity data, ρ is the weight coefficient, 0≤ρ≤1;

[0094] Based on historical data and expected differences between different sugarcane seedlings, the difference threshold is set in advance;

[0095] If the coefficient of difference Yto exceeds the difference threshold, it means that the traits of sugarcane seedlings produced by crossbreeding different sugarcane hybrid combinations are quite different and diverse, and there may be drought-resistant sugarcane varieties among them; at this time, the multiple comparison method is used to determine the significant differences between the groups, and charts (such as box plots and line graphs) are provided to show the performance of various sugarcane hybrid combinations, and drought-resistant evaluation instructions are issued to the outside;

[0096] When used, combine the contents in steps 301 and 302:

[0097] After the sugarcane seedlings enter the mature stage, sugarcane seedlings are extracted as reference samples in each group. After obtaining the similarity data between different reference sample data, the difference coefficient Yto is calculated and obtained. The diversity of several sugarcane seedlings is evaluated and judged based on the difference coefficient Yto. If the diversity is low, the properties of different reference samples are basically the same, and the current hybrid seedling breeding may not achieve the expected effect; if the diversity is high, there may be sugarcane seedlings that meet the conditions. Under this condition, the difference analysis of sugarcane seedlings in different groups can be carried out to realize the screening of drought-resistant sugarcane seedlings;

[0098] Step 4: Use the trained drought tolerance evaluation model to evaluate the drought tolerance of sugarcane seedlings, generate the drought tolerance Hop after obtaining the drought tolerance score of each sugarcane seedling, and select the target combination from several sugarcane hybrid combinations based on the drought tolerance Hop;

[0099] The step 4 includes the following contents:

[0100] Step 401: After training the convolutional neural network with the labeled sample data, a trained drought tolerance evaluation model is obtained to evaluate the drought tolerance of different sugarcane hybrid combinations;

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

[0102] When in use, on the basis of obtaining various data of sugarcane seedlings, the drought tolerance of different sugarcane seedlings can be comprehensively evaluated by using the trained drought tolerance evaluation model. According to the obtained drought tolerance scores, sugarcane seedlings with higher drought tolerance can be selected from a number of hybridized sugarcane seedlings, so that the hybridization evaluation is more comprehensive.

[0103] Step 402: After obtaining the drought tolerance score of each sugarcane seedling, generate the drought tolerance Hop, wherein the drought tolerance score Hy is linearly normalized and the corresponding data value is mapped to the interval [0,1], and then in the following manner:

[0104]

[0105] Weight coefficient, 0≤α≤1, 0≤β≤1, and α+β=1, the value of the weight coefficient is consistent with the previous value; Hy i is the drought tolerance score of the i-th sugarcane seedling, Hy a is the mean of drought tolerance score, i = 1, 2, ... k, k is the number of sugarcane seedlings;

[0106] Sort the sugarcane seedlings according to the drought tolerance Hop, and take the sugarcane hybrid combination corresponding to the sugarcane seedling with the highest drought tolerance Hop as the target combination, and the corresponding sugarcane seedling as the target seedling;

[0107] The drought tolerance trait data of the parents and control varieties in the target combination are collected separately, such as thick cuticle, stomatal density, water use efficiency and accumulation of osmotic regulating substances, and then summarized to generate a drought tolerance trait data set;

[0108] When using, combine the contents in steps 401 and 402:

[0109] Taking into account that the differences between sugarcane seedlings in each group may not be large, the drought tolerance Hop was constructed on the basis of several drought tolerance scores. The drought resistance of sugarcane seedlings in each group was evaluated according to the drought tolerance Hop. After drought resistance tests were carried out on sugarcane seedlings in different groups, target combinations with better drought resistance were screened out from several sugarcane hybrid combinations to complete the drought resistance evaluation of sugarcane hybrid combinations. The evaluation results were consistent with the actual sugarcane planting conditions and had high reliability.

[0110] Step 5: Analyze and obtain the difference in drought resistance between the target seedlings and the control varieties, select the target traits within several drought resistance states according to the difference, and re-combine the sugarcane parents through the pre-trained genetic algorithm to re-obtain several groups of sugarcane hybrid combinations;

[0111] The step five includes the following contents:

[0112] Step 501: Perform 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;

[0113] Multiple linear regression was used to analyze the correlation between the difference and drought tolerance Hop, and the corresponding correlation coefficient was obtained;

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

[0115] Step 502: sort each drought-resistant trait according to the correlation coefficient, and calculate the concentration of several correlation coefficients before sorting, in the following manner:

[0116]

[0117] Among them, ρ is the weight coefficient, 0≤ρ≤1, and the value is consistent with the previous value; σ is the standard deviation of all correlation coefficients, m is the number of correlation coefficients, C i is the i-th correlation coefficient within the ranking, C a is the mean of m correlation coefficients;

[0118] If after determining the value of m, the corresponding concentration Jop exceeds the preset concentration threshold, it means that these drought-resistant traits have a greater impact on the drought resistance of sugarcane. The m drought-resistant traits before sorting are taken as target traits, and these traits can be further increased during cultivation. At this time, a combination optimization instruction is issued externally;

[0119] When in use, the concentration Jop is constructed based on the correlation coefficient, and several key drought-resistant traits are screened out based on the concentration Jop. In the subsequent sugarcane hybridization, targeted cultivation can be carried out to improve the targeting of sugarcane hybridization.

[0120] Step 503: after receiving the combination optimization instruction, after obtaining the drought resistance trait data of the parents and sugarcane seedlings in each sugarcane hybrid combination, the sugarcane parents are recombined by using the pre-trained genetic algorithm with the concentration of the target traits of the sugarcane as the optimization goal, and a plurality of groups of sugarcane hybrid combinations are re-obtained;

[0121] When using, combine the contents in steps 501 to 503:

[0122] When determining the target traits to be obtained, based on the existing sugarcane trait data, the sugarcane parents are recombined through genetic algorithms and several sugarcane hybrid combinations are obtained again. When hybridization experiments are carried out based on the re-obtained sugarcane hybrid combinations, the success rate of the hybridization experiments is improved.

[0123] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0124] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0125] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above 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 process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. 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 site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

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

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

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

[0131] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[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 who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for evaluating drought tolerance of sugarcane hybrid combinations, characterized in that: include, Collect drought data in the target area and generate a regional drought data set, and construct a drought coefficient Ghot from the regional drought data set. If the drought coefficient Ghot exceeds the drought threshold, issue a test instruction to the outside. After identifying and acquiring the environmental patterns in the target area and selecting the sugarcane seedlings, the corresponding sugarcane hybridization strategy is formulated and implemented. When the planting environment in the sugarcane cultivation area is abnormal, the trained conditional automatic control model is used to automatically control the environmental conditions. The recording frequency of each indicator is constrained according to the drought coefficient Ghot. 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 Yto is constructed. If the difference coefficient Yto exceeds expectations, a drought tolerance evaluation instruction is issued to the outside. The drought tolerance evaluation model after training is used to evaluate the drought tolerance of sugarcane seedlings. After obtaining the drought tolerance score of each sugarcane seedling, the drought tolerance Hop is generated. According to the drought tolerance Hop, the target combination is screened out from several sugarcane hybrid combinations. Among them, the drought tolerance score Hy is linearly normalized, and the corresponding data value is mapped to the interval [0,1], and then the drought tolerance Hop is generated according to the following method: Weight coefficient, 0≤α≤1, 0≤β≤1, and α+β=1; Hy i is the drought tolerance score of the i-th sugarcane seedling, Hy a is the mean of drought tolerance score, i = 1, 2, ... k, k is the number of sugarcane seedlings; The difference in drought resistance traits between the target seedlings and the control varieties was analyzed and obtained, and the target traits were screened out within several drought resistance states based on the difference. The sugarcane parents were recombined through a pre-trained genetic algorithm to obtain several groups of sugarcane hybrid combinations.

2. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 1, characterized in that: When drought data in the target area does not meet expectations, the current planting conditions are identified as drought scenarios; 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; The drought coefficient Ghot is generated from the regional drought data set as follows: 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 in drought value between the i-th drought scenario and the j-th drought scenario, Gh a is the average of the drought value differences.

3. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 2, characterized in that: 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; the environmental pattern is used as input to match the corresponding sugarcane hybridization strategy for the target area from the pre-built sugarcane hybridization strategy library.

4. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 1, characterized in that: When executing the sugarcane hybridization strategy, the meteorological condition data is monitored in the sugarcane cultivation area, and the planting condition data set is generated after being summarized; the condition abnormality Jtp is generated from the planting condition data set, and if the acquired abnormality Jtp exceeds the abnormal threshold, an automatic control instruction is issued to the outside; After receiving the automatic control instruction, the reference value of the planting condition data is set for each planting stage according to the sugarcane hybridization strategy, and the current planting condition data is used as input to automatically control the environmental conditions using the trained conditional automatic control model.

5. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 4, characterized in that: Perform linear normalization on temperature Rt, humidity Rh and precipitation Ry, map the corresponding data values ​​to the interval [0,1], and generate the conditional anomaly Jtp according to the following method: Among them, Rt i is the temperature at the i-th monitoring node, Rt b is the acceptable value of temperature, Rh i is the humidity at the i-th monitoring node, Rh b is the acceptable value of humidity, Ry i is the precipitation at the i-th monitoring node, Ry b is the acceptable value of precipitation, weight coefficient, 0≤S1≤1, 0≤S2≤1, 0≤S3≤1.

6. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 5, characterized in that: The sugarcane planting stage is divided into several sub-stages. After obtaining the historical drought data of each sub-stage, the corresponding drought coefficient Ghot is generated. The recording frequency of each indicator is constrained according to the drought coefficient Ghot. The constraint method is as follows: 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 time interval average; The sugarcane planting data are recorded at the record nodes that meet the constraints, and a 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, characterized in that: 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. The difference coefficient Yto is constructed from several groups of similarity data, where: Perform linear normalization on the similarity Xy and map the corresponding data values ​​to the interval [0,1] as follows: Among them, Xy i is the i-th similarity data, Xy a is the mean of similarity, n is the number of similarity data, ρ is the weight coefficient, 0≤ρ≤1.

8. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 7, characterized in that: Collecting sugarcane growth trait data; using the sugarcane growth trait data as input, the trained drought tolerance evaluation model evaluates the drought tolerance of the sugarcane seedlings and outputs the corresponding drought tolerance score; obtaining the drought tolerance score of each sugarcane seedling and generating the drought tolerance degree Hop, and sorting each sugarcane seedling according to the drought tolerance degree Hop; The sugarcane hybrid combination corresponding to the sugarcane seedling with the highest drought tolerance Hop was taken as the target combination, and the corresponding sugarcane seedling was taken as the target seedling; The drought resistance trait data of the parents and control varieties in the target combination are collected separately, and then summarized to generate a drought resistance trait data set.

9. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 8, characterized in that: 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; Use multiple linear regression to analyze the correlation between the difference and the drought tolerance Hop, obtain the corresponding correlation coefficient, sort the drought tolerance traits according to the correlation coefficient, and calculate the concentration Jop of several correlation coefficients before sorting, as follows: Among them, ρ is the 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 within the ranking, C a is the mean of m correlation coefficients.

10. The method for evaluating drought tolerance of a sugarcane hybrid combination according to claim 9, characterized in that: If after determining the value of m, the corresponding concentration Jop exceeds the preset concentration threshold, the drought-resistance traits of the first m ranked traits are used as target traits, and a combination optimization instruction is issued externally; After receiving the combination optimization instruction, after obtaining the drought resistance trait data of the parents and sugarcane seedlings in each sugarcane hybrid combination, the sugarcane parents are recombined through the pre-trained genetic algorithm with increasing the concentration of the sugarcane target traits as the optimization goal, and several groups of sugarcane hybrid combinations are obtained again.

Images