Grading and directional transformation method for low-quality poplar man-made forest

Abstract

The invention relates to the technical field of man-made forest directional reconstruction, in particular to a low-quality poplar man-made forest grading directional reconstruction method, which comprises the steps of deploying a plurality of sensors at different positions in a man-made forest area to construct a sensor network for data collection, and performing data processing on data collected by the sensors by utilizing a fusion algorithm; constructing a man-made forest degradation grading model, respectively extracting index data and sub-index data from the fused data, constructing a constraint function in a constraint layer for constraint, and constructing a stability index function and a degradation index function under an optimal weight coefficient; setting a non-degradation index threshold value in the target layer to realize grade division of artificial forest degradation; and a comprehensive transformation target function is constructed, directional transformation is performed according to the divided artificial forest degradation levels, and directional transformation of different degrees under different levels is realized by adjusting the adjustment coefficients under different levels.

Description

Technical Field

[0001] The invention relates to the technical field of directional transformation of artificial forests, and in particular to a method for grading and directional transformation of low-quality poplar artificial forests. Background Art

[0002] Traditional plantation reconstruction methods usually focus only on planting a single tree species, lacking the introduction of diverse vegetation structures, resulting in single ecological functions and poor stress resistance. Although some reconstruction plans have tried to introduce a variety of plants, most have failed to achieve effective ecological structure reconstruction, and in complex environments, they have poor stability and are difficult to maintain long-term ecological benefits; Traditional forest land transformation methods lack pertinence and dynamic adjustment mechanisms, and usually rely on only one fixed transformation method, resulting in insignificant transformation effects, especially in severely degraded forest stands, where the effects are not as good as expected. In existing technologies, differentiated measures have not been taken according to different degrees of degradation, nor have the complexity and sustainability of the ecosystem been fully considered. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for grading and directional transformation of low-quality poplar plantations, comprising the following steps: Deploy multiple sensors at different locations in the artificial forest area to build a sensor network for data collection, and use fusion algorithms to process the data collected by the sensors, including: Deployment of sensors is limited according to the sensor network coverage of the artificial forest area, and weight coefficients of sensors are dynamically adjusted based on the confidence of each sensor; A plantation forest degradation classification model composed of an input layer, a constraint layer, and a target layer was constructed. The index data and sub-index data were extracted from the fused data, and a constraint function was constructed in the constraint layer for constraint. At the same time, the adjustment result of the optimal weight coefficient was selected through a reward algorithm, and a stability index function and a degradation index function under the optimal weight coefficient were constructed. The classification of plantation forest degradation was achieved by setting a non-degraded index threshold in the target layer. Targeted transformation is carried out according to the level of plantation forest degradation, specifically: A comprehensive transformation objective function is constructed, and targeted transformation is carried out according to the divided degradation levels of artificial forests. By adjusting the adjustment coefficients at different levels, targeted transformation of different degrees at different levels can be achieved.

[0005] As a preferred solution of the method for hierarchical and directional transformation of low-quality poplar plantations described in the present invention, the deployment of sensors is limited according to the sensor network coverage rate of the plantation area, as follows: Set the size of the plantation area to , deployed in the current plantation area sensor nodes, the coordinates of each sensor node are , then there is, in, Indicates that in the artificial forest area The coordinates of the sensors, Indicates that in the artificial forest area The coordinates of the sensors, represents the constructed sensor network; Set the coverage radius of each sensor To achieve all-round data monitoring of the entire artificial forest area, there are, For any coordinate point in the artificial forest , the coverage condition of the sensor is: And, for the sensor coordinate point Satisfies the formula, At the same time, in order to achieve dynamic optimization of the sensor coverage radius, the coverage area of ​​the sensor network is restricted twice, then, in, Indicates The coverage radius of the sensor, Indicates the current area of ​​artificial forests, Indicates the total number of sensors deployed in the current artificial forest area, Represents the sensor network coverage of the plantation area.

[0006] As a preferred solution of the method for grading and directional transformation of low-quality poplar plantations described in the present invention, the weight coefficient of the sensor dynamically adjusted based on the confidence of each sensor is specifically as follows: The signal-to-noise ratio highlights the confidence level of the corresponding sensor. in, Indicates The data collected by the sensors, Indicates The average value of the data collected by the sensors, Indicates The standard deviation of the data collected by each sensor is Indicates The confidence level corresponding to each sensor is used to initialize the sensor weight coefficient, then, Initialize the weight coefficient of the sensor, specifically: in, Indicates The confidence level corresponding to each sensor is Indicates to remove The sensor outside The confidence level corresponding to each sensor is Represents the total number of sensors, Indicates Initialization weight coefficients of sensors; For sensors with initialized weight coefficients, when the sensor collects new data, the weight coefficients are dynamically updated according to the collected data, then, in, Indicates The sensor The weight coefficient after iterations, represents the learning rate during the weight coefficient update process, Indicates The sensor in The confidence level corresponding to the iteration is Indicates to remove The sensor outside The sensor in The confidence level corresponding to the iteration is Indicates The sensor The weight coefficient after iterations.

[0007] As a preferred solution of the method for grading and directional transformation of low-quality poplar plantations described in the present invention, the weight coefficient is updated by setting a weight coefficient change threshold. , to limit the number of weight coefficient updates, specifically: For The weight coefficient of each sensor is updated, and the weight coefficient of two consecutive as well as The difference between them is compared with the weight coefficient change threshold, and the weight coefficient update corresponding to the current sensor is judged according to the comparison result to determine whether it reaches the maximum number of iterations. Then, If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is less than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has reached the maximum number, and the weight coefficient update of the current sensor is stopped. For the subsequent collected data, the weight coefficient of the current sensor is the weight coefficient of the last update; If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is greater than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has not reached the maximum number of times, and the weight coefficient of the current sensor continues to be updated until the change in the weight coefficient iteration results for two consecutive times is less than the weight coefficient change threshold until.

[0008] As a preferred solution of the method for hierarchical and directional transformation of low-quality poplar plantations described in the present invention, the constraint function constructed in the constraint layer is specifically as follows: Based on the input data, the stability index function and the degradation index function are constructed for constraints. The specific constraint process is as follows: Stability index function, Degradation index function, At the same time, set the maximum value of the stability index , minimum And the maximum degradation index , and set constraints to constrain, then we have, in, Indicates Indicator data, Indicates Sub-indicator data, Indicates The weight coefficient corresponding to the indicator data is: Indicates The weight coefficient corresponding to the indicator data is: represents the constructed stability index function, Represents the constructed degradation indicator function.

[0009] As a preferred solution of the method for grading and directional transformation of low-quality poplar plantations described in the present invention, the adjustment result of selecting the best weight coefficient by the reward algorithm is as follows: Setting standard status for plantation forests based on historical data At the same time, based on the standard state of the plantation, set the standard weight coefficients corresponding to the index data and sub-index data as well as ; Calculate the initial state of the plantation according to the standard weight coefficient corresponding to the set indicator data and sub-indicator data ; Define weight coefficient adjustment actions , is the weight coefficient corresponding to the index data and sub-index data adjusted based on the current state of artificial forests, then, in, , Respectively expressed in time The weight coefficient adjustment result at the moment is time Adjustment actions taken at all times; Calculate the time based on the adjustment actions taken The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state , while calculating the time The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state .

[0010] As a preferred solution of the method for grading and directional transformation of low-quality poplar plantations described in the present invention, if the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to be close to the initial state, then the adjustment action taken at the next moment is a positive adjustment action; If the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to deviate from the initial state, then the adjustment action taken at the next moment is a reverse adjustment action, the current reverse adjustment action is recorded, and this action is deleted; For the positive adjustment actions taken, calculate the plantation state after all positive actions, select the plantation state closest to the initial state, the corresponding adjustment action is the optimal adjustment action, and select the corresponding weight coefficient as well as , and construct a stability index function based on the adjusted weight coefficient And the degradation index function , and verify the constraints according to the constructed stability index function and degradation index function. If the verification is successful, it means that the current weight coefficient meets the requirements. Otherwise, it does not meet the requirements. The artificial forest state closest to the initial state is reselected, and the corresponding weight coefficient under the adjustment action is also verified until the verification result is met.

[0011] As a preferred solution of the method for grading and directional transformation of low-quality poplar plantations described in the present invention, the grading of plantation degradation by setting a non-degraded index threshold is specifically as follows: According to the constructed stability index function And the degradation index function The degradation levels of artificial forests are classified as follows: According to the constructed stability index function And the degradation index function , and by determining the weight coefficient as well as , the degradation index is calculated by weighted summation , then there is, in, , represents the weight coefficient under the optimal adjustment action, , represents the stability index function and degradation index function constructed by the weight coefficients under the optimal adjustment action, Represents the calculated degradation index, which is used to achieve the classification of plantation forest degradation, specifically: Setting thresholds for plantation non-degradation index , according to the set index threshold, the artificial forest degradation level is divided into: If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of plantation degradation is not degraded; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the level of degradation of artificial forests is the first level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current degradation level of artificial forests is the second level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of artificial forest degradation is the third level of degradation.

[0012] A computer device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of a method for grading and directional transformation of low-quality poplar plantations when executing the computer program.

[0013] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for grading and directional transformation of low-quality poplar plantations.

[0014] Beneficial effects of the present invention: The present invention maximizes the stability of forest ecosystems (such as tree growth, species diversity, carbon storage, etc.) through reinforcement learning, while effectively reducing degradation indicators (such as mortality rate, dieback rate, etc.). Through the reward mechanism, the system can identify and optimize the weight combination that is conducive to the health and sustainable development of the ecosystem, thereby improving long-term stability and reducing the risk of degradation; By dynamically adjusting the weight coefficients corresponding to the sensors and performing data fusion according to the confidence of each sensor, it is not only possible to improve the accuracy of the data, but also to cope with the problem of changes in the quality of data from different sensors; Through the sensor network and fusion algorithm, sensor errors can be eliminated, providing an accurate data basis, and providing a reliable basis for the subsequent poplar quality grade classification and directional transformation; By building a model for the classification of plantation forest degradation levels and combining stability indicators with degradation indicators, the degradation levels of plantation forests can be accurately classified, providing a scientific basis for targeted transformation. Formulate different transformation plans (such as felling, replanting, grass seed restoration, and nurturing management) according to the different levels of tree degradation to ensure the effectiveness and pertinence of the transformation measures; Through targeted transformation, the ecological functions of artificial forests can be gradually restored, the ecological stability of the forest land and its ability to resist wind and fix sand can be enhanced, and the poplar artificial forests can be promoted to develop in the direction of positive succession of mixed coniferous and broad-leaved forests. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 The present invention is a schematic diagram of the overall method steps of a method for grading and directional transformation of low-quality poplar plantations. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0018] 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0019] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0020] Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0021] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] Example 1 Reference Figure 1 , as an embodiment of the present invention, provides a method for grading and directional transformation of low-quality poplar plantations, comprising the following steps: S1: Collect relevant data of poplar trees in the current artificial forest area and process the collected data.

[0023] Specifically, the collection of poplar-related data in the current area is achieved by constructing a sensor network. The sensor network is achieved by deploying multiple sensors at different locations in the artificial forest area, and collecting different data using the characteristics of the sensors, thereby achieving all-round collection of poplar quality grade data. The data processing of the collected data is to process the data collected by the sensor network through a fusion algorithm so as to eliminate the data collected by the sensor error, thereby providing an accurate data basis for the subsequent poplar quality grade classification.

[0024] Furthermore, the use of sensor characteristics to collect different data is to deploy a sensor network consisting of multiple types of sensors in the artificial forest, and collect different types of poplar data in real time through wireless sensor nodes, as follows: The multi-type sensors include environmental sensors for monitoring the impact of the external environment on the growth of poplar trees, growth monitoring sensors for measuring tree height, wood structure sensors for monitoring tree density, leaf spectrum sensors for monitoring tree growth health, and soil sensors for monitoring the impact of soil on tree growth; According to the size of the artificial forest area, a sensor network is constructed to realize real-time monitoring of poplar data, specifically: Set the size of the plantation area to , deployed in the current plantation area sensor nodes, the coordinates of each sensor node are , then there is, in, Indicates that in the artificial forest area The coordinates of the sensors, In the artificial forest area The coordinates of the sensors, represents the constructed sensor network; Set the coverage radius of each sensor , in order to achieve all-round data monitoring of the entire artificial forest area, then there are, For any coordinate point in the artificial forest , the coverage condition of the sensor is: And, for the sensor coordinate point Satisfies the formula, At the same time, in order to achieve dynamic optimization of the sensor coverage radius, the coverage area of ​​the sensor network is restricted twice, then, in, Indicates The coverage radius of the sensor, Indicates the current area of ​​artificial forests, Indicates the total number of sensors deployed in the current artificial forest area, represents the sensor network coverage rate of the artificial forest area. The secondary limitation of the sensor network is achieved by controlling the coverage rate. In this embodiment, In actual application, the implementation personnel can set it according to the actual application scenario.

[0025] Furthermore, the data processing of the collected data is to process the data collected by different sensors in the sensor network separately using a fusion algorithm to improve the accuracy of the collected data. The specific processing is as follows: Set the data collected by the sensor to ,in, Indicates The data collected by the sensors, Represents the data set collected by all sensors; According to the sensor weight, the data collected by different sensors are fused, and then, in, Indicates The weight coefficient corresponding to each sensor is: Indicates The data collected by the sensors, Represents the fused plantation poplar related data.

[0026] It should be noted that in order to improve the accuracy of each sensor in the data fusion process, the weight coefficient of each sensor is dynamically adjusted as follows: Since the sensor collects time series data, the signal-to-noise ratio is used to highlight the confidence of the corresponding sensor. in, Indicates The data collected by the sensors, Indicates The average value of the data collected by the sensors, Indicates The standard deviation of the data collected by each sensor is Indicates The confidence level corresponding to each sensor is used to initialize the sensor weight coefficient, then, Initialize the weight coefficient of the sensor, specifically: in, Indicates The confidence level corresponding to each sensor is Indicates to remove The sensor outside The confidence level corresponding to each sensor is Represents the total number of sensors, Indicates Initialization weight coefficients of sensors; For sensors with initialized weight coefficients, when the sensor collects new data, the weight coefficients are dynamically updated according to the collected data, then, in, Indicates The sensor The weight coefficient after iterations, represents the learning rate during the weight coefficient update process, Indicates The sensor in The confidence level corresponding to the iteration is Indicates to remove The sensor outside The sensor in The confidence level corresponding to the iteration is Indicates The sensor The weight coefficient after iterations; For updating the weight coefficient, by setting the weight coefficient change threshold , to limit the number of weight coefficient updates, specifically: For The weight coefficient of each sensor is updated, and the weight coefficient of two consecutive as well as The difference between them is compared with the weight coefficient change threshold, and the weight coefficient update corresponding to the current sensor is judged according to the comparison result to determine whether it reaches the maximum number of iterations. Then, If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is less than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has reached the maximum number, and the weight coefficient update of the current sensor is stopped. For the subsequent collected data, the weight coefficient of the current sensor is the weight coefficient of the last update; If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is greater than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has not reached the maximum number of times, and the weight coefficient of the current sensor continues to be updated until the change in the weight coefficient iteration results of two consecutive times is less than the weight coefficient change threshold until.

[0027] It should be noted that by dynamically adjusting the weight coefficients corresponding to the sensors and performing data fusion according to the confidence of each sensor, not only can the accuracy of the data be improved, but also the problem of changes in the quality of data from different sensors can be addressed.

[0028] S2: Classify the degradation level of artificial forests based on the processed data.

[0029] Specifically, the artificial forest degradation level classification based on the processed data is achieved by constructing an artificial forest degradation level classification model, using the fused processed data as the input of the model, and classifying the artificial forest degradation level according to the output result of the model.

[0030] Furthermore, the plantation forest degradation classification model is a classification model composed of multiple levels, including an input layer, a constraint layer and a target layer. The input layer extracts index data and sub-index data based on the fusion-processed data, and inputs the extracted data into the model. The constraint layer constrains the data of the input layer by constructing evaluation indicators. The evaluation indicators include stability indicators and degradation indicators. The target layer classifies the degree of plantation forest degradation based on the evaluation indicators of the constraint layer. The specific implementation is as follows: For fused data , extract indicator data from the data respectively ,in, Represents a set of indicator data. Indicates 8 indicator data, including forest stand structure, stand site, species diversity, dieback rate and dieback rate; Sub-indicator data ,in, represents a sub-index data set, Indicates The sub-indicator data included forest age, average tree height, average diameter at breast height, density, canopy density, groundwater depth, soil water content, soil bulk density, soil porosity and soil organic matter, and the extracted data were used as input data into the artificial forest degradation grade classification model; Based on the input data, the stability index function and the degradation index function are constructed for constraints. The specific constraint process is as follows: Stability index function, Degradation index function, At the same time, set the maximum value of the stability index , minimum And the maximum degradation index , and set constraints to constrain, then we have, in, Indicates Indicator data, Indicates Sub-indicator data, Indicates The weight coefficient corresponding to the indicator data is: Indicates The weight coefficient corresponding to the indicator data is: represents the constructed stability index function, represents the constructed degradation index function; For the constructed constraint function, the reward algorithm is used to update the weight coefficient corresponding to the input data to ensure that the updated weight coefficient is the optimal weight coefficient, providing an accurate data basis for the subsequent artificial forest degradation grade conversion. The specific implementation is as follows: Setting standard status for plantation forests based on historical data At the same time, based on the standard state of the plantation, set the standard weight coefficients corresponding to the index data and sub-index data as well as ; Calculate the initial state of the plantation according to the standard weight coefficient corresponding to the set indicator data and sub-indicator data ; Define weight coefficient adjustment actions , is the weight coefficient corresponding to the index data and sub-index data adjusted based on the current state of artificial forests, then, in, , Respectively expressed in time The weight coefficient adjustment result at the moment is time Adjustment actions taken at all times; Calculate the time based on the adjustment actions taken The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state , while calculating the time The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state ; According to the comparison results between two consecutive adjustment actions, it is judged whether the adjustment action at the next moment is a positive adjustment action, specifically: If the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to be close to the initial state, then the adjustment action taken at the next moment is a positive adjustment action; If the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to deviate from the initial state, then the adjustment action taken at the next moment is a reverse adjustment action, the current reverse adjustment action is recorded, and this action is deleted; For the positive adjustment actions taken, calculate the plantation state after all positive actions, select the plantation state closest to the initial state, the corresponding adjustment action is the optimal adjustment action, and select the corresponding weight coefficient as well as , and construct a stability index function based on the adjusted weight coefficient And the degradation index function , and verify the constraints according to the constructed stability index function and degradation index function. If the verification is successful, it means that the current weight coefficient meets the requirements. Otherwise, it does not meet the requirements. The artificial forest state closest to the initial state is reselected, and the corresponding weight coefficient under the adjustment action is also verified until the verification result is met. According to the constructed stability index function And the degradation index function The degradation levels of artificial forests are classified as follows: According to the constructed stability index function And the degradation index function , and by determining the weight coefficient as well as , the degradation index is calculated by weighted summation , then there is, in, , represents the weight coefficient under the optimal adjustment action, , represents the stability index function and degradation index function constructed by the weight coefficients under the optimal adjustment action, Represents the calculated degradation index, which is used to achieve the classification of plantation forest degradation, specifically: Setting thresholds for plantation non-degradation index , according to the set index threshold, the artificial forest degradation level is divided into: If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of plantation degradation is not degraded; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the level of degradation of artificial forests is the first level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current degradation level of artificial forests is the second level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of artificial forest degradation is the third level of degradation.

[0031] S3: Carry out targeted transformation according to the level of plantation forest degradation.

[0032] Specifically, the directional transformation according to the grade of plantation forest degradation is based on the output result of the target layer of the plantation forest degradation grade classification model, and the trees of different quality grades are directional transformed respectively. The specific transformation is as follows: Constructing comprehensive transformation objective function in, Indicates the levels of plantation forest degradation, including non-degraded, first-level degradation, second-level degradation and third-level degradation, which are used to achieve the classification of plantation forest degradation. represents the comprehensive transformation objective function, represents the felling operation function, represents the tree planting operation function, represents the grass seed recovery operation function, Represents the nurturing management function.

[0033] It should be noted that the directional transformation of trees of different quality grades is to formulate different operation functions for trees of different quality grades for directional transformation, specifically: Felling operation function, in, represents the felling operation function, represents the calculated degradation index, It represents the felling operation coefficient, which has different values ​​according to the trees of different quality grades, specifically: For plantations in the non-degraded class, the value is 0; For plantations with the first level of degradation, the value is , is a constant term, and in this embodiment, the value is taken as 0.2 for illustration; For plantations with secondary degradation level, the value is , For plantations with three levels of degradation, the value is ; Tree planting operation function, in, represents the tree planting operation function, represents the calculated degradation index, It represents the operation coefficient of replanting trees. It has different values ​​according to the trees of different quality levels. Specifically: For plantations of non-degraded quality class, the value is 0; For plantations with the first level of degradation, the value is , is a constant term, and in this embodiment, the value is taken as 0.3 for illustration; For plantations with secondary degradation level, the value is , For plantations with three levels of degradation, the value is ; Grass seed recovery operation function, in, represents the grass seed recovery operation function, represents the calculated degradation index, It represents the operation coefficient of replanting trees. It has different values ​​according to the trees of different quality levels. Specifically: For plantations of non-degraded quality class, the value is 0; For plantations with the first level of degradation, the value is , is a constant term, and in this embodiment, the value is taken as 0.4 for illustration; For plantations with secondary degradation level, the value is , For plantations with three levels of degradation, the value is ; Nurturing management function, represents the nurturing management function, represents the calculated degradation index, It represents the coefficient of tending management operation, and its value varies according to the trees of different quality grades, specifically: For plantations of non-degraded quality class, the value is 0; For plantations with the first level of degradation, the value is , is a constant term, and in this embodiment, the value is taken as 0.5 for illustration; For plantations with secondary degradation level, the value is , For plantations with three levels of degradation, the value is .

[0034] It should be noted that in order to enhance the understanding of the targeted transformation of artificial forests, additional explanations are given based on specific practical application scenarios, as follows: For non-degraded plantations, no transformation is necessary, and real-time monitoring of tree growth status is sufficient; For the first-level degradation level of plantation trees, the specific transformation is as follows: From August to October of the same year, the degradation type evaluation system was used to determine the degradation type of the poplar plantations in the target area, and it was determined that the degree of degradation was mild. Then, a sanitary felling method was adopted according to the degree of degradation. In the spring of the following year, targeted transformation work was implemented. In the forest stand, dead standing trees were felled, and trees with survival potential were retained. For weak trees such as fallen trees, diseased and insect-infested trees, the method of pruning and rejuvenation was used to deal with them, that is, the main trunk of the poplar was cut off at 0.1m above the ground. , and apply 2% to 5% copper sulfate solution to the cut part for disinfection, and apply protective agent at the same time. In the spring of the same year, aerial seeding is used to restore the understory vegetation. Select sheepgrass, alfalfa, and buffalo grass, and evenly sow them at a rate of 1-1.5 kg per mu; in mid-to-late May, replant coniferous tree species, select 4-6 year-old Larix gmelinii seedlings, and plant 80-100 plants per mu according to the planting standard of 2×3m spacing between rows and plants to ensure that the replanted seedlings are evenly distributed to form a good growth space.

[0035] After the replanting is completed, the newly planted seedlings will be nurtured and managed for 2 to 3 consecutive years, including regular weeding, watering and pest and disease control every year, to ensure the survival rate and healthy growth of the seedlings, and gradually form a mixed coniferous and broad-leaved forest structure.

[0036] In the 1-2 years after implementation, two types of understory ground cover increased, and in the 3-5 years after implementation, a multi-level vegetation structure combining trees, shrubs and grasses was formed, further enhancing the ecological function and stability of the forest land. In the 6-8 years after implementation, the survival rate of replanted Larix gmelinii seedlings reached more than 90%, the forest stand structure was gradually optimized, the strip felling areas were effectively integrated with the reserved forest stands, the forest stand degradation trend was curbed, and the positive succession of poplar plantations towards mixed coniferous and broad-leaved forests was promoted.

[0037] For trees in the second-level degradation level of plantations, the specific transformation is as follows: From August to September of the growing season of that year, a systematic assessment of the poplar plantations in the target area was conducted using the degradation type evaluation index system, and it was determined that the degree of degradation was moderate. For the moderately degraded forest stands, a strip-renewal felling method was adopted, and the transformation work began in the autumn of that year. In the forest stands, strip felling was carried out every 20 meters to form a structure in which strip open spaces and reserved trees were arranged alternately; in mid-September, coniferous trees were replanted in the felled areas, and 6-8-year-old Scots pine and 3-4-year-old Pinus tabulaeformis seedlings were selected for mixed planting. According to the standard of 2*3m spacing, 90-100 plants were replanted per mu to ensure that the seedlings were evenly distributed. The size of the pit was 0.5*0.5m, and the excavated soil was piled at the bottom of the seedling pit, which was consistent with the height of the seedlings above the ground, to reduce the harm of cold winds, provide sufficient growth space, and promote the balanced development of subsequent forest stands. After the replanting is completed, the newly planted seedlings will be nurtured and managed for 6 to 8 consecutive years. Specifically, in June each year, weeding, watering, and disease and pest control will be carried out within 1 meter of the seedling hole, and 0.5 kg of compound fertilizer will be applied to promptly replant dead seedlings. At the same time, in the replanting area, combined with the restoration of understory vegetation, the method of sowing grass seeds is adopted, and a mixture of gray hedge, buffalo grass, sheep grass, and alfalfa seeds is selected and evenly sown at a sowing rate of 3 kg per mu.

[0038] In the 1-2 years after implementation, the number of understory ground cover species increased by 3. In the 3-7 years after implementation, Caragana korshinskii and Hippophae rhamnoides were planted in the forest windows, forming a multi-level vegetation structure combining trees, shrubs and grasses between the strip open spaces and the reserved forests, further enhancing the ecological function and stability of the forest land. In the 8-10 years, the survival rate of the replanted Larix gmelinii seedlings reached more than 85%, the forest stand structure was gradually optimized, the strip felling areas were effectively integrated with the reserved forest stands, the forest stand degradation trend was curbed, and the positive succession of poplar plantations towards mixed coniferous and broad-leaved forests was promoted.

[0039] For trees in plantation forests at the third level of degradation, the specific transformation is as follows: From August to October of the same year, a systematic assessment of the poplar plantations in the target area was conducted using the degradation type evaluation index system, and it was determined that the degree of degradation was severe. In the spring of the following year, the poplar plantations in the area were clear-cut to completely remove the degraded trees. Planting work was carried out after the rain in mid-to-late May. Local Scots pine seedlings with a forest age of at least 8 years were selected as the main afforestation tree species. In the clearings between the trees after clear-cutting, land preparation was carried out in the form of strips, and the land preparation was carried out in strict accordance with the standard operation of the pit specifications of 0.35*0.35*0.4m.

[0040] The planting density is arranged according to the standard of plant spacing (3.5-4m)* (3.5-4m) to ensure that the seedlings are evenly distributed and provide sufficient space for the growth of seedlings. It is used to adapt to the difficult local site conditions. In order to improve the ecological stability and structural diversity of the forest stand, Caragana korshinskii and Haloxylon ammodendron are mixed in the gaps between the Scots pine trees. Before the spring rain in the third year, a mixed grass seed of alfalfa, sheep grass and buffalo grass is sown at a rate of 5kg per mu to form a multi-layer forest structure combining trees, shrubs and grasses, and enhance the forest stand's ability to resist wind and sand fixation and soil and water conservation. After the planting is completed, drones are used to sow compound fertilizer particles at a rate of 10-15kg per mu before the spring rain for three consecutive years. In the spring of each year for five consecutive years, loosening and weeding are carried out within 1m of the young trees, and then the closed-off management is continued for 5-8 consecutive years.

[0041] Furthermore, 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0042] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0043] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0044] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0045] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0046] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for hierarchical and directional transformation of low-quality poplar plantations, characterized in that: The following steps are included: Deploy multiple sensors at different locations in the artificial forest area to build a sensor network for data collection, and use fusion algorithms to process the data collected by the sensors, including: Deployment of sensors is limited according to the sensor network coverage of the artificial forest area, and weight coefficients of sensors are dynamically adjusted based on the confidence of each sensor; A plantation forest degradation classification model composed of an input layer, a constraint layer, and a target layer was constructed. The index data and sub-index data were extracted from the fused data, and a constraint function was constructed in the constraint layer for constraint. At the same time, the adjustment result of the optimal weight coefficient was selected through a reward algorithm, and a stability index function and a degradation index function under the optimal weight coefficient were constructed. The classification of plantation forest degradation was achieved by setting a non-degraded index threshold in the target layer. Targeted transformation is carried out according to the level of plantation forest degradation, specifically: A comprehensive transformation objective function is constructed, and targeted transformation is carried out according to the divided degradation levels of artificial forests. By adjusting the adjustment coefficients at different levels, targeted transformation of different degrees at different levels can be achieved.

2. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 1, characterized in that: The deployment of sensors is limited according to the sensor network coverage rate of the artificial forest area, as follows: Set the size of the plantation area to , deployed in the current plantation area sensor nodes, the coordinates of each sensor node are , then there is, in, Indicates that in the artificial forest area The coordinates of the sensors, Indicates that in the artificial forest area The coordinates of the sensors, represents the constructed sensor network; Set the coverage radius of each sensor To achieve all-round data monitoring of the entire artificial forest area, there are, For any coordinate point in the artificial forest , the coverage condition of the sensor is: And, for the sensor coordinate point Satisfies the formula, At the same time, in order to achieve dynamic optimization of the sensor coverage radius, the coverage area of ​​the sensor network is restricted twice, then, in, Indicates The coverage radius of the sensors, Indicates the current area of ​​artificial forests, Indicates the total number of sensors deployed in the current artificial forest area, Represents the sensor network coverage of the plantation area.

3. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 2, characterized in that: The specific method of dynamically adjusting the weight coefficient of the sensor based on the confidence level of each sensor is as follows: The signal-to-noise ratio highlights the confidence level of the corresponding sensor. in, Indicates The data collected by the sensors, Indicates The average value of the data collected by the sensors, Indicates The standard deviation of the data collected by each sensor is Indicates The confidence level corresponding to each sensor is used to initialize the sensor weight coefficient, then, Initialize the weight coefficient of the sensor, specifically: in, Indicates The confidence level corresponding to each sensor is Indicates to remove The sensor outside The confidence level corresponding to each sensor is Represents the total number of sensors, Indicates Initialization weight coefficients of sensors; For sensors with initialized weight coefficients, when the sensor collects new data, the weight coefficients are dynamically updated according to the collected data, then, in, Indicates The sensor The weight coefficient after iterations, represents the learning rate during the weight coefficient update process, Indicates The sensor in The confidence level corresponding to the iteration is Indicates to remove The sensor outside The sensor in The confidence level corresponding to the iteration is Indicates The sensor The weight coefficient after iterations.

4. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 3, characterized in that: For updating the weight coefficient, by setting the weight coefficient change threshold , to limit the number of weight coefficient updates, specifically: For The weight coefficient of each sensor is updated, and the weight coefficient of two consecutive as well as The difference between them is compared with the weight coefficient change threshold, and the weight coefficient update corresponding to the current sensor is judged according to the comparison result to determine whether it reaches the maximum number of iterations. Then, If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is less than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has reached the maximum number, and the weight coefficient update of the current sensor is stopped. For the subsequent collected data, the weight coefficient of the current sensor is the weight coefficient of the last update; If the comparison result satisfies the formula , indicating that the change in the weight coefficient iteration results of the current sensor for two consecutive times is greater than the weight coefficient change threshold, and the number of weight coefficient iterations corresponding to the current sensor has not reached the maximum number of times, and the weight coefficient of the current sensor continues to be updated until the change in the weight coefficient iteration results of two consecutive times is less than the weight coefficient change threshold until.

5. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 4, characterized in that: The construction of constraint functions in the constraint layer to constrain is as follows: Based on the input data, the stability index function and the degradation index function are constructed for constraints. The specific constraint process is as follows: Stability index function, Degradation index function, At the same time, set the maximum value of the stability index , minimum And the maximum degradation index , and set constraints to constrain, then we have, in, Indicates Indicator data, Indicates Sub-indicator data, Indicates The weight coefficient corresponding to the indicator data is: Indicates The weight coefficient corresponding to the indicator data is: represents the constructed stability index function, Represents the constructed degradation indicator function.

6. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 5, characterized in that: The adjustment result of selecting the best weight coefficient through the reward algorithm is as follows: Setting standard status for plantation forests based on historical data At the same time, based on the standard state of the plantation, set the standard weight coefficients corresponding to the index data and sub-index data as well as ; Calculate the initial state of the plantation according to the standard weight coefficient corresponding to the set indicator data and sub-indicator data ; Define weight coefficient adjustment actions , is the weight coefficient corresponding to the index data and sub-index data adjusted based on the current state of artificial forests, then, in, , Respectively, in time The weight coefficient adjustment result at the moment is time Adjustment actions taken at all times; Calculate the time based on the adjustment actions taken The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state , while calculating the time The state of the plantation after constant adjustment , and calculate the time The difference between the state of the plantation after the adjustment action and the initial state .

7. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 6, characterized in that: If the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to be close to the initial state, then the adjustment action taken at the next moment is a positive adjustment action; If the state comparison after two adjustment actions satisfies the formula , indicating that the adjustment action taken at the next moment causes the state of the plantation to deviate from the initial state, then the adjustment action taken at the next moment is a reverse adjustment action, the current reverse adjustment action is recorded, and this action is deleted; For the positive adjustment actions taken, calculate the plantation state after all positive actions, select the plantation state closest to the initial state, the corresponding adjustment action is the optimal adjustment action, and select the corresponding weight coefficient as well as , and construct a stability index function based on the adjusted weight coefficient And the degradation index function , and verify the constraints according to the constructed stability index function and degradation index function. If the verification is successful, it means that the current weight coefficient meets the requirements. Otherwise, it does not meet the requirements. The artificial forest state closest to the initial state is reselected, and the corresponding weight coefficient under the adjustment action is also verified until the verification result is met.

8. A method for grading and directional transformation of low-quality poplar plantations as claimed in claim 7, characterized in that: The classification of plantation forest degradation by setting the non-degraded index threshold is as follows: According to the constructed stability index function And the degradation index function The degradation levels of artificial forests are classified as follows: According to the constructed stability index function And the degradation index function , and by determining the weight coefficient as well as , the degradation index is calculated by weighted summation , then there is, in, , represents the weight coefficient under the optimal adjustment action, , represents the stability index function and degradation index function constructed by the weight coefficients under the optimal adjustment action, Represents the calculated degradation index, which is used to achieve the classification of plantation forest degradation, specifically: Setting thresholds for plantation non-degradation index , according to the set index threshold, the artificial forest degradation level is divided into: If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of plantation degradation is not degraded; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the level of degradation of artificial forests is the first level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current degradation level of artificial forests is the second level of degradation; If the calculated degradation index and the index threshold value are compared to satisfy the formula , indicating that the current level of artificial forest degradation is the third level of degradation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images