A method and system for evaluating the adaptability of a yew seedling transplanting area

Abstract

The application discloses a kind of yew seedling transplanting area adaptability evaluation method and system, it is related to forestry planting technical field, including seedling batch as basic evaluation object, according to seedling age, seedling way and root system integrity degree to the yew seedling to be transplanted is divided into batch, forms unified seedling batch data;Select multiple candidate transplanting areas, and each region is divided into continuous transplanting time window in transplanting period, collect meteorological and soil environment data in each region each time window, construct the environment state reflecting the actual transplanting condition of region in corresponding time window;The stability and fluctuation of environment state in each region time window are analyzed, form transplanting window sensitivity index, transplanting window sensitivity and seedling batch characteristics are combinedly analyzed, and the adaptability score of seedling batch under each region each time window is calculated.The application improves yew seedling transplanting survival rate, and enhances the scientificity and reliability of transplanting scheme.

Description

Technical Field

[0001] This invention relates to the field of forestry planting technology, and in particular to a method and system for assessing the regional adaptability of yew seedlings for transplantation. Background Technology

[0002] The yew is a rare tree species under key protection in my country, and it has great value in ecological restoration, artificial cultivation, and resource conservation. With the decline of wild yew resources, off-site conservation and large-scale planting through seedling transplantation have become an important technical means in forestry engineering.

[0003] Currently, most techniques for transplanting yew seedlings are based on an assessment of a region's overall climate and soil characteristics—such as multi-year average temperature, precipitation, soil pH, and organic matter content—to determine its suitability for transplantation. Some methods also utilize meteorological monitoring data for quantitative environmental analysis, which makes site selection more scientific to some extent.

[0004] However, existing methods still have two significant shortcomings: First, current evaluations typically only consider the entire region or the tree species itself, failing to address the actual management units involved in seedling transplantation. This makes it difficult to directly guide seedling allocation and on-site construction, resulting in inefficient transplantation decisions. In actual projects, seedlings are often transplanted in batches, with variations in age, lifting methods, and root system integrity between batches, but current technology does not take these differences into account. Second, existing evaluations are mostly based on static environmental conditions, failing to adequately consider the impact of environmental changes over time on seedling survival, leading to insufficient targeting when selecting transplanting timing. After transplanting yew trees, short-term temperature fluctuations and rainfall changes significantly affect survival rates. Relying solely on long-term average climate data can easily lead to incorrect transplanting times, impacting survival outcomes. Summary of the Invention

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, this invention provides a method and system for assessing the regional adaptability of yew seedlings for transplantation, which solves the shortcomings of existing technologies for assessing the regional adaptability of yew seedlings for transplantation in both batch management and transplantation timing decision-making.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for assessing the regional adaptability of yew seedlings for transplantation, comprising,

[0009] Using seedling batches as the basic evaluation object, the yew seedlings to be transplanted are divided into batches according to seedling age, digging method and root system integrity, forming unified seedling batch data;

[0010] Multiple candidate transplantation areas were selected, and each area was divided into consecutive transplantation time windows during the transplantation period. Meteorological and soil environmental data were collected in each area and within each time window to construct an environmental status that reflects the actual transplantation conditions of the area within the corresponding time window.

[0011] The stability and fluctuation of environmental conditions within time windows in each region are analyzed to form a transplant window sensitivity index. The transplant window sensitivity is then combined with the characteristics of seedling batches to calculate the adaptability score of seedling batches in each region and time window.

[0012] Based on the adaptability score, each region and time window is sorted and filtered to generate recommendations for transplanting regions and timing for different batches of seedlings.

[0013] As a preferred embodiment of the method for assessing the regional adaptability of yew seedlings for transplantation according to the present invention, the steps for forming uniform batch data of seedlings are as follows:

[0014] According to the actual outbound organization method of the nursery, the yew seedlings to be transplanted are divided into multiple seedling batches, and each batch is used as the smallest management unit. Each seedling batch is numbered and registered to form a seedling batch set.

[0015] The seedling age, digging method, root system integrity, and tolerance-related attributes of each batch of seedlings were collected, and batch-level original characteristic parameters were formed through fixed sampling and statistical summarization.

[0016] The seedling age and root system integrity were normalized, and the normalized seedling age, root system integrity, seedling lifting method, and seedling lifting season were used to construct a batch feature vector for seedlings.

[0017] As a preferred embodiment of the method for assessing the adaptability of yew seedlings to transplantation areas according to the present invention, the step of dividing each area into consecutive transplantation time windows during the transplantation period is as follows:

[0018] By uniformly numbering multiple candidate transplantation regions and dividing the entire transplantation period into transplantation time windows according to continuous and non-overlapping natural weeks, a spatiotemporal index framework of "region × time window" is constructed.

[0019] As a preferred embodiment of the method for assessing the regional adaptability of yew seedlings for transplantation as described in this invention, the meteorological and soil environmental data include regional-scale temperature data, precipitation data, soil moisture content data, and soil physicochemical property data.

[0020] As a preferred embodiment of the method for assessing the adaptability of yew seedlings for transplantation areas according to the present invention, the steps for constructing an environmental state reflecting the actual transplantation conditions of the area within a corresponding time window are as follows:

[0021] Daily meteorological data in each region and time window are aggregated temporally and spatially to form temperature and precipitation status quantities for the corresponding time window. Stability indicators reflecting environmental fluctuation characteristics within the corresponding time window are calculated based on daily meteorological data.

[0022] Simultaneously, soil moisture content and soil physicochemical properties in each region are collected and solidified. Meteorological state quantities, meteorological stability indicators, and soil environmental characteristics are combined to form the environmental state of the region within the corresponding transplantation time window.

[0023] As a preferred embodiment of the method for assessing the adaptability of yew seedlings to transplantation areas according to the present invention, the steps for forming the transplantation window sensitivity index are as follows:

[0024] Based on the environmental status already established in each region within different transplantation time windows, the key indicators reflecting meteorological fluctuations and uncertainties are analyzed, and the basic transplantation window sensitivity, which characterizes the environmental stability and fluctuation characteristics of the corresponding time window, is calculated.

[0025] Based on the basic transplantation window sensitivity, the temperature mutation amplitude within the time window is introduced, and mechanical stability decay correction is applied to the time window that exceeds the preset mutation tolerance threshold to form a window risk index that comprehensively reflects the impact of continuous fluctuations and mutation shocks.

[0026] The window risk index is mapped to a transplantation window risk correction coefficient and solidified as the sole quantitative result of the environmental risk of the region within the corresponding transplantation time window.

[0027] As a preferred embodiment of the method for assessing the regional adaptability of yew seedlings in this invention, the steps for calculating the adaptability score of seedling batches in each region and time window are as follows:

[0028] Based on the fixed transplanting window risk correction coefficient, combined with the key indicators reflecting the recovery ability of seedlings in the characteristics of seedling batches, and the environmental conditions of the corresponding regions and time windows, a joint analysis was conducted on the transplanting response of seedling batches in different regions and different transplanting time windows.

[0029] Based on the joint analysis results, adaptability scores of seedling batches were generated for each region and transplanting time window.

[0030] As a preferred embodiment of the method for assessing the transplantability of yew seedlings according to the present invention, the steps for generating recommended transplanting areas and timings for different batches of seedlings are as follows:

[0031] Based on the established environmental risks in each region and transplanting time window, and the obtained adaptability scores of seedling batches in each region and time window, a quantity allocation optimization model is constructed with seedling batches, regions, and transplanting time windows as units.

[0032] Under the constraints of the number of seedling batches and the construction capacity of the regional time window, the optimization model is solved to form the allocation scheme of transplanting area and transplanting time window for seedling batches, and the final result is stored.

[0033] As a preferred embodiment of the method for assessing the adaptability of yew seedlings to transplantation areas described in this invention, the step of storing the final results refers to storing the recommended transplantation areas and timings for different batches of seedlings in a structured manner according to batch number, area number, and transplantation time window to form a result dataset.

[0034] Secondly, this invention provides a system for assessing the adaptability of yew seedlings to transplantation areas, comprising,

[0035] The seedling batch modeling module is used to divide the yew seedlings to be transplanted into batches and construct seedling batch feature data.

[0036] The environmental status construction module is used to summarize meteorological and soil data and construct environmental status in each region and within each transplantation time window.

[0037] The window sensitivity assessment module is used to analyze the stability and fluctuation of the environmental state and generate a migration window risk correction coefficient.

[0038] The adaptability scoring module is used to calculate the adaptability score of a seedling batch by combining the characteristics of the seedling batch with the risk of the transplanting window.

[0039] The transplantation decision module is used to generate and store recommendations for transplantation areas and timing for seedling batches based on adaptability scores.

[0040] The beneficial effects of this invention are as follows: This invention uses seedling batches as the basic object for assessing the regional adaptability of yew seedlings. It models seedling batches according to tolerance-related attributes such as seedling age, digging method, and root system integrity, ensuring that the assessment object is consistent with the actual seedling release, allocation, and construction organization methods. This allows the assessment results to be directly used in seedling transplantation planning, effectively improving the overall efficiency and feasibility of transplantation decisions. Simultaneously, by dividing the transplantation period into continuous transplantation time windows, it quantitatively analyzes the stability and fluctuation risks of environmental conditions in different regions within different time windows. Furthermore, by jointly assessing the sensitivity of the transplantation window with seedling batch characteristics, it can distinguish the suitability of the same region at different transplanting times, avoiding the problem of inappropriate transplanting timing caused by selecting regions solely based on static environmental conditions. This improves the survival rate of transplanted yew seedlings and the scientific validity and reliability of transplantation plans. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of the method for assessing the regional adaptability of yew seedlings in Example 1.

[0043] Figure 2 This is a structural diagram of the yew seedling transplantation area adaptability assessment system in Example 1.

[0044] Figure 3 This is a data input and combination structure diagram for the environmental state construction in Example 1.

[0045] Figure 4 This is a diagram illustrating the mechanism of adaptability score formation in Example 1. Detailed Implementation

[0046] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0049] Example 1, referring to Figures 1-4 This is the first embodiment of the present invention, which provides a method for assessing the adaptability of yew seedlings to transplantation areas, including the following steps:

[0050] S1. Using seedling batches as the basic evaluation object, the yew seedlings to be transplanted are divided into batches according to seedling age, digging method and root system integrity, forming unified seedling batch data.

[0051] S1.1: According to the actual outbound organization method of the nursery, the yew seedlings to be transplanted are divided into multiple seedling batches, and each batch is numbered and registered as the smallest management unit to form a seedling batch set;

[0052] Specifically, based on the seedling delivery slip, the yew seedlings to be transplanted are divided into: Each batch is numbered according to its outbound order. Create one record for each batch to form the batch master data table, and fix the following field: batch number. Nursery plot number, planned delivery date, total number of seedlings in the batch ;

[0053] To ensure the repeatability and controllable error of the root system integrity assessment, a fixed sample of 20 plants was taken from each batch: 20 plants were randomly selected at equal intervals from different packing locations / stack positions within the batch to form the sample set. Record the sample serial number and corresponding photo number in the table (for dispute tracing) to complete the "Batch Objects and Their Sampling Baselines" register;

[0054] S1.2: Collect the seedling age, digging method, root system integrity and tolerance-related attributes of each batch of seedlings, and form batch-level original characteristic parameters through fixed sampling and statistical summary.

[0055] Specifically, four attributes of each batch i are collected at once according to fixed rules, including: seedling age. Seedling raising method Seedling raising season and root system integrity ;

[0056] It should be noted that the seedling age is obtained as follows: the sowing / cutting date and the date of delivery are directly read from the nursery production record, converted to monthly and rounded to the nearest 0.5 month; if the record contains multiple batches of mixed planting, the seedling age of the batch with the highest proportion is used as the batch seedling age; the seedling lifting method is verified on-site by checking the delivery form and coding it: container seedlings are coded as follows. Bare-root seedlings are recorded as (This code is used for subsequent model input and facilitates system implementation); the seedling raising season is coded according to the season to which the seedlings were released from storage: spring / autumn is coded as follows: The rest are recorded as This is used to characterize the differences in seedling recovery caused by seasonal variations; the method for obtaining root integrity is: [the method involves analyzing the sample set]. Each seedling A standardized measurement was conducted: First, the roots were gently shaken to remove loose soil and photographed. The retention ratio was estimated based on the visible length of the "main root + lateral root". (For example, use a standard root system photo before seedling removal or a nursery cultivation standard as a reference), and then take the average of 20 seedlings as the batch root system integrity. ;

[0057] S1.3: Normalize the seedling age and root system integrity, and construct the normalized seedling age, root system integrity, seedling lifting method, and seedling lifting season into a seedling batch feature vector.

[0058] Specifically, to eliminate the dimensional differences between seedling age and root integrity, Min-Max normalization (deterministic, simplest to implement, requires no assumptions about the distribution, and is easy to deploy to the management system) is used. and Scaling is performed to obtain normalized features. and ;

[0059] Solidify the final batch features into vectors The data is written into fixed fields of the batch master data table, including relative seedling age, seedling lifting method, relative root integrity, and seedling lifting season category.

[0060] S2. Select multiple candidate transplantation areas and divide each area into consecutive transplantation time windows during the transplantation period. Collect meteorological and soil environmental data in each area and time window to construct an environmental status that reflects the actual transplantation conditions of the area in the corresponding time window.

[0061] S2.1: By uniformly numbering multiple candidate transplantation regions and dividing the entire transplantation period into transplantation time windows according to continuous and non-overlapping natural weeks, a spatiotemporal index framework of "region × time window" is constructed.

[0062] Specifically, based on the project plan and the scope of the yew seedling transplantation, the boundary data of all candidate plots to be used for transplantation were imported into the geographic information system. The boundary integrity of each candidate plot was checked to ensure that its spatial range was clear and free from self-intersection or overlap, and a unique area number was assigned to each plot in turn. This completes the identification of candidate transplantation regions; the overall transplantation period is defined using the transplantation start and end dates determined in the project plan as the time baseline. The transplantation period is divided into consecutive, non-overlapping natural weeks, with each 7-day period constituting a transplantation time window, and these windows are numbered sequentially. Each time window corresponds to a fixed start and end date range; this ensures that any point in time belongs to only one time window, thus avoiding time overlap or double counting in subsequent evaluations; each candidate transplantation region With each transplantation time window By combining them one by one, a basic index structure of "region × time window" is formed. Thus, the candidate transplantation regions were identified and the continuous time windows during the transplantation period were constructed, providing a clear, stable, and executable basic structure for subsequent environmental state construction and adaptability assessment.

[0063] S2.2: Meteorological and soil environmental data include regional-scale temperature data, precipitation data, soil moisture content data, and soil physicochemical property data.

[0064] It should be noted that meteorological data refers to environmental information reflecting the climate conditions of the region collected within the candidate transplantation area and during the corresponding transplantation time window. It is used to describe the external climate background during the transplantation period. Temperature data is used to reflect the thermal environment level and low temperature characteristics of the region during the corresponding time window, and precipitation data is used to reflect the water supply status of the region during the corresponding time window.

[0065] Soil data refers to environmental information reflecting the physicochemical characteristics and moisture status of the soil in the candidate transplantation area, used to describe the basic growth conditions of seedling roots after transplantation; soil moisture content data is used to characterize the soil moisture status within the transplantation time window; soil physicochemical property data includes soil pH and soil organic matter content, used to reflect the long-term basic fertility and physicochemical environmental characteristics of the regional soil.

[0066] S2.3: In each region and time window, the daily meteorological data is summarized in time and space to form the temperature and precipitation status quantities of the corresponding time window, and the stability index reflecting the environmental fluctuation characteristics within the corresponding time window is calculated based on the daily meteorological data.

[0067] Specifically, daily meteorological data are spatially aggregated according to regional boundaries, unifying multi-source meteorological observations distributed within the region into a unified daily representative value at the regional scale, thus forming a continuous daily meteorological sequence for the region within the time window. A time-based aggregation operation is performed on the daily meteorological sequence within the window. Specifically, the daily temperature sequence is averaged to generate the average temperature state quantity for the region within the corresponding time window, and the lowest temperature within the time window is simultaneously extracted to characterize potential low-temperature stress features. The daily precipitation sequence is accumulated to generate the precipitation state quantity for the region within the corresponding time window. Based on the daily meteorological sequences within the same time window, a stability index reflecting the magnitude of meteorological changes within the time window is calculated. This stability index is obtained by statistically analyzing the dispersion of the daily temperature and precipitation sequences, and is used to quantify the fluctuation characteristics of meteorological conditions within the time window.

[0068] It should be noted that the degree of dispersion is preferably calculated using the standard deviation method.

[0069] S2.4: Simultaneously collect and solidify the soil moisture content and soil physicochemical properties of each region, and combine meteorological state quantities, meteorological stability indicators and soil environmental characteristics to form the environmental state of the region within the corresponding transplantation time window.

[0070] Specifically, for each "region × time window" index unit, soil moisture content data within the corresponding time window is read, and the moisture content data from multiple times is aggregated according to a unified time aggregation rule to form the soil moisture content state quantity of the region within that time window. For each candidate transplantation region, the acquired soil physicochemical property data is directly called, and this type of data is solidified and stored as a region-level static attribute. During the solidification process, the soil physicochemical properties are not repeatedly updated with each time window, but are directly referenced in different time windows as shared environmental features across time windows to avoid redundant calculations and data redundancy in the state construction process. After completing the soil moisture content state construction and soil physicochemical property solidification, the meteorological state quantity and meteorological stability index output in the previous step are combined with the soil moisture content state quantity and soil physicochemical property data obtained in the current step according to a preset data structure to generate the environmental state set of the region within the corresponding transplantation time window. .

[0071] It should be noted that the preset data structure refers to the predefined organization form of environmental state data. Its field composition and field meaning are determined when constructing the environmental state, and it is used to uniformly describe the meteorological state, meteorological stability characteristics and soil environmental characteristics of the region in different transplantation time windows.

[0072] S3. Analyze the stability and fluctuation of the environmental state within the time window of each region to form a transplant window sensitivity index. Combine the transplant window sensitivity with the characteristics of seedling batches to calculate the adaptability score of seedling batches in each region and time window.

[0073] S3.1: Based on the environmental status already constructed in each region within different transplantation time windows, analyze the key indicators reflecting meteorological fluctuations and uncertainties, and calculate the basic transplantation window sensitivity that characterizes the environmental stability and fluctuation characteristics of the corresponding time window.

[0074] Specifically, the set of regional × time window environment states output from the previous step is used as input, with index units composed of regional numbers and time window numbers. As the smallest computational granularity, the temperature fluctuation index, precipitation fluctuation index, and precipitation state quantity within the time window that have been constructed in the corresponding environmental state are read one by one.

[0075] For the same The unit calculates the precipitation variation coefficient using the precipitation fluctuation index within a time window and the average precipitation level of the corresponding time window; it also statistically analyzes the temperature fluctuation and precipitation variation coefficient ranges (minimum and maximum values ​​of the two parameters) for all regions and time windows within the current task scope, and uses this data to analyze each... The two types of indicators under the unit are normalized by Min–Max, and temperature fluctuation and precipitation uncertainty are linearly weighted and synthesized according to a pre-set fixed weight to form a basic window sensitivity index.

[0076] The expression for the coefficient of variation of precipitation is:

[0077]

[0078] In the formula, The average daily rainfall is It is the standard deviation of the daily precipitation series of region r within the time window t. It is the coefficient of variation of precipitation. It is a numerical stabilizing term to prevent the denominator from being zero. It is a fixed constant (e.g., 0.1) used to ensure the numerical stability of the formula calculation under extremely low or no precipitation conditions, and does not participate in the environmental risk assessment itself.

[0079] The basic window sensitivity index expression is:

[0080]

[0081] In the formula, It is the basic portability window sensitivity index of region r within time window t. It is the standard deviation of the daily temperature series of region r within the time window t. , It is the temperature fluctuation index corresponding to all regions and time windows. The minimum and maximum values, , It is the precipitation uncertainty index corresponding to all regions and time windows. The minimum and maximum values, and These are the weights for temperature fluctuations and the coefficient of variation. It is a fixed small constant to prevent the denominator from being zero;

[0082] It should be noted that, Based on the sensitivity of yew tree transplantation to temperature conditions, this indicator reflects the dominant role of temperature fluctuations in the window sensitivity calculation. In the early stages of transplantation, the seedling root system has not fully recovered, and its physiological activities are more sensitive to low temperatures and temperature fluctuations. Compared to precipitation fluctuations of the same scale, temperature anomalies are more likely to cause frost damage or physiological stress. Therefore, temperature fluctuations need to be given a higher weight in the comprehensive sensitivity index. The value of is preferably limited to the range of 0.55 to 0.7; when it is desirable to highlight the importance of temperature stability in window sensitivity evaluation, For example, 0.6 can be taken, and the basis for this value is to ensure that the temperature factor plays a dominant role in the overall sensitivity without excessively suppressing other environmental factors;

[0083] It is set based on the auxiliary constraint effect of precipitation process on transplant stability. When used in conjunction with temperature weight and the weight sum is 1, it can be set to 0.4 for example. The value is based on reflecting the supplementary influence of precipitation uncertainty on transplant window stability.

[0084] The precipitation variation coefficient is used to characterize the instability of precipitation conditions in a region within a given time window. By introducing the variation coefficient form, the characterization of precipitation fluctuations is not affected by the differences in the total precipitation scale in different regions and time windows, thus ensuring the comparability of precipitation uncertainty between different windows. This basic window sensitivity is used to comprehensively reflect the instability of environmental conditions at the "continuous fluctuation level" within the transplantation time window, with temperature fluctuations having a higher weight than precipitation uncertainty, to reflect the objective characteristic that yew seedlings are more sensitive to thermal environment fluctuations.

[0085] S3.2: Based on the basic transplantation window sensitivity, the temperature mutation amplitude within the time window is introduced, and mechanical stability decay correction is applied to the time window that exceeds the preset mutation tolerance threshold to form a window risk index that comprehensively reflects the impact of continuous fluctuations and mutation shocks.

[0086] Specifically, the daily minimum temperature sequence within each transplantation time window is retrieved, and the difference between the maximum and minimum minimum temperatures within the time window is calculated to represent the temperature mutation amplitude. A temperature mutation tolerance threshold is set. When the temperature mutation amplitude within the time window does not exceed this threshold, the mutation is considered to have a limited impact on the stability of the transplantation window, and the basic window sensitivity remains unchanged. When the mutation amplitude exceeds the threshold, the basic window sensitivity is nonlinearly corrected through a mechanical stability decay function to obtain the final window risk index, so that the larger the mutation amplitude, the more significant the destructive effect on the stability of the transplantation window.

[0087] The mechanical stability decay function expression is:

[0088]

[0089] In the formula, It is the mechanical stability decay coefficient of region r within the time window t, used to characterize the nonlinear amplification effect on the stability of the transplantation window after a sudden temperature change exceeds the tolerable range. It is the temperature change tolerance threshold. It is the attenuation intensity coefficient. It represents the magnitude of temperature abrupt change in region r within time window t;

[0090] Final Window Risk Index The expression is:

[0091]

[0092] It should be noted that, This setting is based on the amplification rate of the impact of temperature mutations on the stability of the transplanting window. It is used to characterize the nonlinear increase in risk as the magnitude of the temperature mutation exceeds the tolerance threshold. Engineering experience and historical meteorological data analysis show that the survival rate of transplanted yew trees does not immediately and sharply decrease after the temperature mutation exceeds the threshold, but rather exhibits a "slow first, then rapid" decay trend. Therefore... The value of should not be too large, so as to avoid a sharp increase in the risk index due to slight mutations exceeding the threshold. Taking into account the continuity requirements of transplantation window decision-making, The value of is preferably limited to the range of 0.1 to 0.2; when it is desired to make the risk amplification process smoother and avoid frequent switching of the transplantation plan between adjacent time windows, For example, 0.15 can be taken, and its value is based on the principle of achieving a gradual amplification of the impact of mutation, rather than a step-like penalty;

[0093] This threshold is set based on engineering experience regarding the transplantation window's tolerance to short-term temperature fluctuations. It distinguishes between "normal fluctuation ranges" and "mutation shock ranges." In transplantation practices of yew and similar evergreen trees in multiple locations, it has been observed that weekly changes in minimum temperature within a certain range typically do not significantly affect transplant survival. However, when the minimum temperature experiences a significant jump in a short period, seedlings with unstable root systems are more prone to physiological stress. Therefore... The value should cover regular meteorological fluctuations, but should be able to effectively identify anomalous sudden changes, taking into account both meteorological statistical results and engineering feasibility. The optimal value is limited to the range of 6℃ to 10℃; when using weeks as the transplantation time window... An 8°C threshold can be used as an example. The reason for this value is that this threshold can filter out normal day and night and weather changes, and can also effectively capture sudden cooling or warming processes that have a substantial impact on transplant safety.

[0094] Temperature abrupt change amplitude is used to characterize the sudden cooling or rapid warming process that may occur within the time window; this temperature abrupt change amplitude index is only used to reflect the extreme change characteristics within a short time scale, and is functionally distinguished from the aforementioned temperature fluctuation index, thereby avoiding repeated description of the same risk source.

[0095] S3.3: Map the window risk index to the transplantation window risk correction coefficient, and solidify it as the sole quantitative result of the environmental risk of the region within the corresponding transplantation time window.

[0096] Specifically, using the window risk index as input and the index unit composed of the region number and the transplantation time window number as a unique identifier, the corresponding window risk index value is read one by one and the index mapping operation is performed to map the risk index into a transplantation window risk correction coefficient with a limited value range and a clear safety meaning. During the mapping process, the larger the risk index, the smaller the risk correction coefficient is obtained; conversely, when the risk index is small, the risk correction coefficient tends to approach the preset upper limit value. Using "region × transplantation time window" as the primary key, the corresponding transplantation window risk correction coefficient is written into a dedicated risk result table, and the risk correction coefficient is marked in the data structure as the unique quantitative result of the environmental risk of the region within the corresponding transplantation time window. The generation status of the risk correction coefficient is recorded in the risk result table, clearly indicating that the risk result has been calculated and solidified.

[0097] The expression for the exponential mapping operation is:

[0098]

[0099] In the formula, It is the window risk correction coefficient for region r within time window t. It is the risk penalty coefficient;

[0100] It should be noted that, It is set based on the distribution scale of the comprehensive risk index of transplantation window in different regions and time windows. When it is desired that the risk correction coefficient presents a smooth and distinguishable exponential decay relationship with the change of environmental risk, it can be set to 1 for example. The basis for its value is to ensure that the risk levels of different transplantation windows have stable comparability in subsequent assessments.

[0101] The window risk correction coefficient is used to characterize the overall environmental safety level of the region within the corresponding transplantation time window. The closer the value is to 1, the more stable the environmental conditions and the lower the transplantation risk within the time window. The smaller the value, the more significant the adverse impact of environmental fluctuations and sudden changes on transplantation survival. This risk correction coefficient is calculated and stored once in this step. Subsequent steps will only use it as an exogenous input and will not conduct any further assessment or correction of environmental risk.

[0102] S3.4: Based on the fixed transplanting window risk correction coefficient, combined with the key indicators reflecting the recovery ability of seedlings in the characteristics of seedling batches, and the environmental conditions of the corresponding regions and time windows, a joint analysis of the transplanting response of seedling batches under different regions and different transplanting time windows is conducted.

[0103] Specifically, normalized root integrity and seedling age indices are extracted from the batch feature vectors of each seedling batch. Using a linear combination with fixed weights, these two features are mapped to a single seedling recovery capacity index, which serves as the seedling-side response variable. Simultaneously, environmental state vectors under the corresponding region and time window are read, and a window risk correction coefficient is introduced. Through a logistic regression model (i.e., a survival probability model), all types of inputs are uniformly mapped to the survival probability of seedlings under a specific region and time window. Monotonic consistency constraints are applied to the parameters corresponding to the window risk correction coefficient in the model to obtain stable survival probability results.

[0104] Seedling recovery capacity index The expression is:

[0105]

[0106] In the formula, It is the normalized root system integrity of batch i. It is the normalized seedling age of batch i. It is the root system integrity weighting coefficient. It is the seedling age weighting coefficient;

[0107] The survival probability expression is:

[0108]

[0109]

[0110] In the formula, It is a linear predictor used to combine multiple factors into an explainable risk-return driver. It is the predicted survival probability (0–1) of batch i in region r and time window t. It is the intercept term. These are the weighting coefficients representing the degree to which each characteristic of a seedling batch affects the survival probability. These are the weights of the influence of each environmental state component on the survival probability of seedlings. It is the weight of the window risk correction coefficient. It is the weight of the seedling recovery capacity index. It is a region × time window environment state vector;

[0111] The monotonic consistency constraint is expressed as:

[0112]

[0113] It should be noted that the reason for prioritizing root integrity and seedling age indices is that, during the post-transplant recovery period, root integrity directly determines the ability to absorb water and nutrients, while seedling age affects its tolerance to transplant stress. In the logistic regression model, the environmental state vector describes the objective environmental conditions of the region within the given time window, the window risk correction coefficient reflects the overall stability level under these environmental conditions, and the seedling recovery capacity index characterizes the seedlings' adaptation and recovery potential to these environmental conditions. Each of these three elements plays its specific role in the model, neither redundantly describing environmental risks nor substituting for each other's functions. The monotonic consistency constraint ensures that, given unchanged batch characteristics and environmental states, a higher window risk correction coefficient does not lead to an abnormal decrease in the survival probability, thus avoiding the decision conflict of "more stable environmental conditions but lower scores." This consistency constraint is added in the form of an inequality during parameter solving or model configuration, without changing the model structure or introducing additional calculation steps.

[0114] S3.5: Based on the joint analysis results, generate the adaptability scores of seedling batches in each region and at each transplanting time window.

[0115] Specifically, for each combination of "seedling batch - region - time window", the survival probability is mapped to a percentage score according to a fixed ratio to obtain an adaptability score.

[0116] Adaptability score The expression is:

[0117]

[0118] It should be noted that, It is used to characterize the contribution weight of seedling age in the batch recovery ability index, with a value range of [0,1] and is consistent with... satisfy The example value is 0.3. The basis for this value is that seedling age has an impact on seedling recovery but is weaker than root integrity. It should be regarded as an auxiliary factor rather than the dominant factor.

[0119] It is used to characterize the contribution weight of root integrity in the batch recovery capacity index, with a value range of [0,1]. An example value is 0.7. The basis for this value is that root integrity directly determines the basis for water absorption, regeneration, and survival, and should play a dominant role in the recovery capacity assessment.

[0120] The value range is (-∞, +∞) (each component is a real number). The value is based on the maximum likelihood estimation training of historical batch features and actual survival label data, so that the marginal contribution of seedling side features to the survival probability is determined by the data adaptively.

[0121] The value range is (-∞, +∞) (each component is a real number). The value is based on the maximum likelihood estimation training of historical environmental conditions and actual survival label data, and the data is used to fit the direction and intensity of environmental factors on the survival probability.

[0122] The value range is [0, +∞), and the value is determined by applying a monotonic consistency constraint to ensure that "the safer the window, the lower the survival probability", and the value is estimated by training data under the constraint.

[0123] The value range is (-∞, +∞), and the value is determined by training the maximum likelihood estimation based on the correlation between the recovery ability index and the actual survival label, so that the contribution of "seedling self-recovery ability" to the survival probability is determined by the sample data.

[0124] The percentage-based scoring system makes the scoring results more intuitive on a numerical scale, which facilitates sorting, comparison and screening in subsequent allocation and decision-making modules. The score is uniformly and solidified as a comprehensive quantitative result of the suitability of seedlings for transplantation in a specific region and time window.

[0125] S4. Based on the adaptability score, sort and filter the regions and time windows to form recommendations for transplanting regions and timing for different batches of seedlings.

[0126] S4.1: Based on the solidification of environmental risks in each region and transplantation time window and the acquisition of adaptability scores of seedling batches in each region and time window, construct a quantity allocation optimization model with seedling batches, regions and transplantation time windows as units.

[0127] Specifically, based on the seedling batch number Candidate transplantation region number and transplantation time window number Constructing allocation decision-making units The adaptive score is directly mapped to the risk cost in the allocation decision. A seedling quantity allocation variable is defined, with the product of risk cost and quantity variable serving as the basic component of the optimization objective. A weighted summation of all decision units forms an optimization function with the objective of minimizing overall transplanting risk. For each seedling batch, a quantity conservation constraint is introduced. For each region within each transplanting time window, a maximum construction capacity constraint is introduced to limit the actual number of transplants that can be completed within that time window. Finally, a non-negative integer constraint is applied to the allocation quantity variable to ensure that the optimization result conforms to the basic requirements of actual seedling allocation and planting operations in terms of quantity expression. After the objective function and engineering constraints are determined, the quantity allocation problem of "batch-region × time window" is formalized into a solvable minimum cost flow optimization model to ensure that subsequent processing of "multiple batch supply," "multiple region and time window capacity," and "minimizing risk cost" requirements can be carried out simultaneously within a unified framework.

[0128] Risk Cost The expression is:

[0129]

[0130] The expression for the quantity conservation constraint is:

[0131]

[0132] In the formula, It refers to the number of seedlings allocated to region r and time window t. This represents the total number of seedlings in batch i. This indicates "for all seedling batches i";

[0133] The maximum construction capacity constraint expression is:

[0134]

[0135] In the formula, This refers to the actual number of transplants scheduled within region r and time window t. This represents the maximum number of seedlings that can be planted in this area within this time window. This represents "the combination of all regions r and all transplantation time windows t";

[0136] It should be noted that the seedling quantity allocation variable is used to represent the actual allocation quantity of each seedling batch in a specific region and a specific transplanting time window. This variable directly corresponds to the number of seedlings that can be allocated on-site and is the core result of the subsequent production scheduling plan. The objective function means that, under the premise of meeting the project implementation conditions, seedlings should be allocated to regions and time windows with high adaptability scores and low risk costs as much as possible. The introduction of quantity conservation constraints ensures that all seedlings in this batch are fully included in the allocation plan to avoid omissions or duplicate allocations. This constraint guarantees the integrity of the allocation results at the seedling batch level.

[0137] The maximum construction capacity constraint stems from engineering conditions such as the number of construction teams, work efficiency, and available land area, and is a key limitation for the allocation plan to be implemented.

[0138] The steps for constructing the minimum cost flow optimization model are as follows: Construct a directed network. : Each batch of seedlings As a supply node Add to node set And combine each "region × time window" As a demand / bearing node Add to node set ; at each batch node With each bearer node Establish a feasible allocation edge between them , used to indicate "batch" Available in window Assigned to region "This allocation selection; for each side" Assigning edge costs as risk costs The number of allocations is represented by the flow on the edge. This allows "choosing a lower-risk combination" to be reflected in the model as "choosing a lower-cost path and allocating a larger flow"; the total batch size... Write the supply quantity for the corresponding batch node, and specify the maximum number of constructable plants for the region within the corresponding window. By writing the capacity limits of the corresponding bearer nodes, the model structure can directly express the hard engineering constraints of "the batch quantity must be fully distributed" and "the region window cannot exceed the capacity"; thus, a system is formed. As the basic unit, with As decision variables, with For expense items, and An optimization model for quantity allocation under capacity / supply constraints.

[0139] S4.2: Under the constraints of the number of seedling batches and the construction capacity of the regional time window, solve the optimization model to form the allocation scheme of the transplanting area and transplanting time window for the seedling batches, and store the final result.

[0140] Specifically, the solution aims to minimize the total cost by allocating traffic to each edge of the network, ensuring that the total traffic output by each node in a batch equals the supply of that batch. And each bearer node The total flow received does not exceed its construction capacity. At the same time, it ensures that the flow rate is a non-negative integer, thus obtaining the optimal allocation result that satisfies the project's executable conditions; after the solution is completed, each allocation edge in the network is... The optimal flow rate is read out and mapped back to the corresponding quantity allocation variables to form an initial allocation and production scheduling plan. After obtaining the allocation and production scheduling results, the optimization results are further decomposed into a structured breakdown to form an operational list that can be directly implemented.

[0141] Furthermore, based on Generate the following two types of implementation plans:

[0142] One type is the "seedling batch - region - time window" allocation list, which is used to specify when and to which region each batch of seedlings will be transplanted;

[0143] Another type is the "Time Window - Area" summary list, which is used to assist on-site construction teams in developing weekly work plans.

[0144] It should be noted that, This is used to describe the recommended allocation of seedling batches in different transplanting areas and transplanting time windows under the premise of meeting project capacity constraints. In other words, it clarifies when, to which area, and the corresponding recommended transplanting quantity of each batch of seedlings. The initial allocation and production scheduling plan minimizes risk and cost at the global level and naturally meets the hard constraints of "complete batch allocation" and "regional window capacity not exceeding the limit". Therefore, it can be directly used as the output of the transplanting area and transplanting time window allocation results for seedling batches.

[0145] Furthermore, storing the final results refers to structuring and storing the recommended transplanting areas and timings for different seedling batches according to batch number, area number, and transplanting time window, forming a result dataset that can be used for transplanting implementation and historical decision tracing.

[0146] This embodiment also provides a system for assessing the adaptability of yew seedlings to transplantation areas, including:

[0147] The seedling batch modeling module is used to divide the yew seedlings to be transplanted into batches and construct seedling batch feature data.

[0148] The environmental status construction module is used to summarize meteorological and soil data and construct environmental status in each region and within each transplantation time window.

[0149] The window sensitivity assessment module is used to analyze the stability and fluctuation of the environmental state and generate a migration window risk correction coefficient.

[0150] The adaptability scoring module is used to calculate the adaptability score of a seedling batch by combining the characteristics of the seedling batch with the risk of the transplanting window.

[0151] The transplantation decision module is used to generate and store recommendations for transplantation areas and timing for seedling batches based on adaptability scores.

[0152] In summary, this invention uses seedling batches as the basic object for assessing the regional adaptability of yew seedlings. It models seedling batches based on tolerance-related attributes such as seedling age, digging method, and root system integrity, ensuring consistency between the assessment object and the actual seedling release, allocation, and construction organization methods. This allows the assessment results to be directly used in seedling transplantation planning, effectively improving the overall efficiency and feasibility of transplantation decisions. Furthermore, by dividing the transplantation period into continuous transplantation time windows, it quantitatively analyzes the stability and fluctuation risks of environmental conditions in different regions within different time windows. The sensitivity of the transplantation window is jointly assessed with seedling batch characteristics, enabling the differentiation of suitability for the same region at different transplanting times. This avoids the problem of inappropriate transplanting timing caused by selecting regions solely based on static environmental conditions, thereby improving the survival rate of transplanted yew seedlings and the scientific validity and reliability of the transplantation plan.

[0153] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for evaluating the adaptability of a Taxus nursery stock transplanting area, characterized by comprising the following steps: include, ​ Using seedling batches as the basic evaluation object, the yew seedlings to be transplanted are divided into batches according to seedling age, digging method and root system integrity, forming unified seedling batch data; Multiple candidate transplantation areas were selected, and each area was divided into consecutive transplantation time windows during the transplantation period. Meteorological and soil environmental data were collected in each area and within each time window to construct an environmental status that reflects the actual transplantation conditions of the area within the corresponding time window. The stability and fluctuation of environmental conditions within time windows in each region are analyzed to form a transplant window sensitivity index. The transplant window sensitivity is then combined with the characteristics of seedling batches to calculate the adaptability score of seedling batches in each region and time window. Based on the adaptability score, each region and time window is sorted and filtered to generate recommendations for transplanting regions and timing for different batches of seedlings.

2. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 1, characterized in that: The steps to generate unified batch data for seedlings are as follows: According to the actual outbound organization method of the nursery, the yew seedlings to be transplanted are divided into multiple seedling batches, and each batch is used as the smallest management unit. Each seedling batch is numbered and registered to form a seedling batch set. The seedling age, digging method, root system integrity, and tolerance-related attributes of each batch of seedlings were collected, and batch-level original characteristic parameters were formed through fixed sampling and statistical summarization. The seedling age and root system integrity were normalized, and the normalized seedling age, root system integrity, seedling lifting method, and seedling lifting season were used to construct a batch feature vector for seedlings.

3. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 2, characterized in that: The steps for dividing each region into consecutive transplantation time windows during the transplantation period are as follows: By uniformly numbering multiple candidate transplantation regions and dividing the entire transplantation period into transplantation time windows according to continuous and non-overlapping natural weeks, a spatiotemporal index framework of "region × time window" is constructed.

4. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 3, characterized in that: The meteorological and soil environmental data include regional-scale temperature data, precipitation data, soil moisture content data, and soil physicochemical property data.

5. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 4, characterized in that: The steps for constructing the environmental state reflecting the actual transplantation conditions of the region within the corresponding time window are as follows. Daily meteorological data in each region and time window are aggregated temporally and spatially to form temperature and precipitation status quantities for the corresponding time window. Stability indicators reflecting environmental fluctuation characteristics within the corresponding time window are calculated based on daily meteorological data. Simultaneously, soil moisture content and soil physicochemical properties in each region are collected and solidified. Meteorological state quantities, meteorological stability indicators, and soil environmental characteristics are combined to form the environmental state of the region within the corresponding transplantation time window.

6. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 5, characterized in that: The steps for forming the transplantation window sensitivity index are as follows: Based on the environmental status already established in each region within different transplantation time windows, the key indicators reflecting meteorological fluctuations and uncertainties are analyzed, and the basic transplantation window sensitivity, which characterizes the environmental stability and fluctuation characteristics of the corresponding time window, is calculated. Based on the basic transplantation window sensitivity, the temperature mutation amplitude within the time window is introduced, and mechanical stability decay correction is applied to the time window that exceeds the preset mutation tolerance threshold to form a window risk index that comprehensively reflects the impact of continuous fluctuations and mutation shocks. The window risk index is mapped to a transplantation window risk correction coefficient and solidified as the sole quantitative result of the environmental risk of the region within the corresponding transplantation time window.

7. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 6, characterized in that: The steps for calculating the adaptability score of seedling batches in different regions and time windows are as follows. Based on the fixed transplanting window risk correction coefficient, combined with the key indicators reflecting the recovery ability of seedlings in the characteristics of seedling batches, and the environmental conditions of the corresponding regions and time windows, a joint analysis was conducted on the transplanting response of seedling batches in different regions and different transplanting time windows. Based on the joint analysis results, adaptability scores of seedling batches were generated for each region and transplanting time window.

8. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 7, characterized in that: The steps for generating recommendations on transplanting areas and timing for different batches of seedlings are as follows: Based on the established environmental risks in each region and transplanting time window, and the obtained adaptability scores of seedling batches in each region and time window, a quantity allocation optimization model is constructed with seedling batches, regions, and transplanting time windows as units. Under the constraints of the number of seedling batches and the construction capacity of the regional time window, the optimization model is solved to form the allocation scheme of transplanting area and transplanting time window for seedling batches, and the final result is stored.

9. The method for assessing the adaptability of yew seedlings to transplantation areas as described in claim 8, characterized in that: The term "storing the final results" refers to storing the recommended transplanting areas and timings for different seedling batches in a structured manner according to batch number, area number, and transplanting time window, forming a result dataset.

10. A system for assessing the adaptability of yew seedlings to transplantation areas, based on the method for assessing the adaptability of yew seedlings to transplantation areas according to any one of claims 1 to 9, characterized in that: include, The seedling batch modeling module is used to divide the yew seedlings to be transplanted into batches and construct seedling batch feature data. The environmental status construction module is used to summarize meteorological and soil data and construct environmental status in each region and within each transplantation time window. The window sensitivity assessment module is used to analyze the stability and fluctuation of the environmental state and generate a migration window risk correction coefficient. The adaptability scoring module is used to calculate the adaptability score of a seedling batch by combining the characteristics of the seedling batch with the risk of the transplanting window. The transplantation decision module is used to generate and store recommendations for transplantation areas and timing for seedling batches based on adaptability scores.

Images