A forestry ecological environment monitoring system and method

Abstract

The application discloses a kind of forestry ecological environment monitoring system and method, related to forestry environment monitoring technical field, the system includes: forestry environment monitoring comb module, for establishing forestry environment monitoring matrix;Plant environment expectation prediction module is used to carry out ecological environment expectation prediction;Plant environment fitness detection module is used to carry out plant growth environment fitness detection to forestry area;Plant environment intervention optimization module is used to carry out self-adapting environment intervention optimization, and each plant growth environment intervention strategy is determined;Plant environment intervention module is used to carry out plant growth environment intervention to forestry area.The present application solves the technical problems that the ecological environment of the forestry area is not comprehensively monitored in the prior art, resulting in poor quality of the forestry ecological environment, and the level of plant growth and health is difficult to guarantee.The technical effect of achieving comprehensive monitoring of the ecological environment of the forestry area is achieved, and the quality of the forestry ecological environment and the level of plant growth and health are improved.

Description

Technical Field

[0001] This invention relates to the field of forestry environmental monitoring technology, specifically to a forestry ecological environment monitoring system and method. Background Technology

[0002] In the field of traditional forestry ecological environment management, existing technologies often rely on single-dimensional environmental monitoring data, lacking a systematic assessment of the ecological environment of forestry areas. This makes it difficult to accurately match the climate, land, and bio-human environmental conditions required for plant growth. Due to the inability to comprehensively obtain data on the desired environment for plants and the lack of quantitative methods for measuring the actual environmental adaptability of plants, environmental intervention strategies are often based on experience-based judgments, leading to resource waste and poor intervention effects. Furthermore, the lack of synergistic optimization mechanisms among various plant environmental intervention measures makes it difficult to effectively resolve conflicts caused by resource competition and spatial constraints, resulting in slow improvement in the quality of the forestry ecological environment and difficulty in ensuring the health of plant growth.

[0003] Existing technologies suffer from incomplete monitoring of the ecological environment in forestry areas, leading to poor quality of the forestry ecological environment and difficulty in ensuring the health of plant growth. Summary of the Invention

[0004] This application provides a forestry ecological environment monitoring system and method to address the technical problem that the existing technology does not provide comprehensive monitoring of the ecological environment in forestry areas, resulting in poor quality of the forestry ecological environment and difficulty in ensuring the health of plant growth.

[0005] In view of the above problems, this application provides a forestry ecological environment monitoring system and method.

[0006] A first aspect of this application provides a forestry ecological environment monitoring system, the system comprising:

[0007] The forestry environment monitoring and sorting module is used to sort the real-time environmental monitoring dataset of the forestry area according to predetermined ecological environment factors and establish a forestry environment monitoring matrix; the plant environment expectation prediction module is used to predict the ecological environment expectation based on the predetermined ecological environment factors and the growth status data of each plant in the forestry area, and obtain the expected environment matrix of each plant; the plant environment adaptability detection module is used to detect the plant growth environment adaptability of the forestry area according to the forestry environment monitoring matrix and the expected environment matrix of each plant, and establish a plant environment adaptability detection sequence; the plant environment intervention optimization module is used to construct the plant environment intervention guidance vector of each plant according to the plant environment adaptability detection sequence, and perform adaptive environment intervention optimization according to the plant environment intervention guidance vector of each plant to determine the plant growth environment intervention strategy; the plant environment intervention module is used to intervene in the plant growth environment of the forestry area according to the plant growth environment intervention strategy.

[0008] A second aspect of this application provides a method for monitoring forestry ecological environment, the method comprising:

[0009] Based on predetermined ecological and environmental factors, a real-time environmental monitoring dataset of the forestry area is analyzed to establish a forestry environmental monitoring matrix. Based on these predetermined ecological and environmental factors, ecological and environmental expectations are predicted according to the growth status data of each plant in the forestry area, resulting in an expected environmental matrix for each plant. Based on the forestry environmental monitoring matrix and the expected environmental matrices of each plant, plant growth environment adaptability is detected in the forestry area, establishing a plant environment adaptability detection sequence. Based on the plant environment adaptability detection sequence, an environmental intervention guidance vector is constructed for each plant, and adaptive environmental intervention optimization is performed based on the plant environment intervention guidance vectors to determine the intervention strategy for each plant's growth environment. Finally, plant growth environment intervention is implemented in the forestry area according to the intervention strategies for each plant's growth environment.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The forestry environment monitoring and sorting module is used to sort real-time environmental monitoring datasets in forestry areas and establish a forestry environment monitoring matrix. The plant environment expectation prediction module is used to predict the ecological environment expectation based on the growth status data of each plant in the forestry area, obtaining the expected environment matrix for each plant. The plant environment adaptability detection module is used to detect the plant growth environment adaptability in the forestry area and establish a plant environment adaptability detection sequence. The plant environment intervention optimization module is used to construct environmental intervention guidance vectors for each plant based on the plant environment adaptability detection sequence, and perform adaptive environmental intervention optimization based on these guidance vectors to determine the intervention strategy for each plant's growth environment. The plant environment intervention module is used to intervene in the plant growth environment in the forestry area. This achieves the technical effect of comprehensive monitoring of the ecological environment of forestry areas, improving the quality of the forestry ecological environment and the health level of plant growth. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0013] Figure 1 A schematic diagram of the structure of a forestry ecological environment monitoring system provided in this application embodiment;

[0014] Figure 2This is a flowchart illustrating a forestry ecological environment monitoring method provided in an embodiment of this application.

[0015] Explanation of the attached diagram labels: Forestry environment monitoring and sorting module 10, plant environment expectation prediction module 20, plant environment adaptability detection module 30, plant environment intervention optimization module 40, plant environment intervention module 50. Detailed Implementation

[0016] This application provides a forestry ecological environment monitoring system and method to address the technical problem that the existing technology does not provide comprehensive monitoring of the ecological environment in forestry areas, resulting in poor quality of the forestry ecological environment and difficulty in ensuring the health of plant growth.

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0018] Example 1, as Figure 1 As shown, this application provides a forestry ecological environment monitoring system, the system comprising:

[0019] The forestry environment monitoring and sorting module 10 is used to sort out the real-time environmental monitoring dataset of the forestry area according to the predetermined ecological environment factors and establish a forestry environment monitoring matrix.

[0020] Specifically, firstly, the monitoring scope is defined by identifying predetermined ecological and environmental factors, which encompass climate, land, and bio-human environments. Next, the forestry environmental monitoring data acquisition unit collects data from real-time environmental monitoring datasets in the forestry area and performs filtering and noise reduction to remove interference and outliers, generating a high-quality forestry environmental monitoring data stream. Then, the monitoring matrix acquisition unit, based on the predetermined ecological and environmental factors, performs feature identification on the data stream, extracting the climate environment monitoring matrix, land environment monitoring matrix, and bio-human environment monitoring matrix. Since the collection times of various monitoring data may differ, the time synchronization alignment unit performs time synchronization operations on these three types of matrices to ensure data consistency across time dimensions. Finally, this is integrated to generate a comprehensive and accurate forestry environmental monitoring matrix, providing reliable data support for subsequent stages such as the plant environment expectation prediction module and the plant environment adaptability detection module. This is a crucial prerequisite for achieving precise monitoring and effective intervention in the forestry ecological environment.

[0021] The plant environment expectation prediction module 20 is used to predict the ecological environment expectation based on the predetermined ecological environment factors and the growth status data of each plant in the forestry area, and obtain the expected environment matrix of each plant.

[0022] Specifically, this goal is achieved through in-depth analysis of plant growth status data and predetermined ecological environment factors. The growth status data extraction unit precisely extracts the growth status data of each specific plant (i.e., the first plant) from the plant growth status data of the forestry area. Subsequently, the expected registration space establishment unit begins its work, first retrieving data from the plant's normal ecological environment record database. This database contains multiple record groups, each encompassing normal ecological environment samples, basic information samples, and growth status samples. Based on the first plant's basic information and growth status data, the registration evaluation unit performs registration evaluation on each record group, obtaining registration coefficients for each plant's environmental records. The optimization selection unit, based on these coefficients and according to a set plant environmental record registration threshold, selects the environmental samples most suitable for the first plant, thereby generating the expected registration space for the first plant's ecological environment. The trend analysis unit performs a central trend analysis on this registration space based on predetermined ecological environment factors, obtaining the expected vectors of the first plant in terms of climate, land, and bio-human environment. Finally, the expected environment matrix construction unit integrates these expected vectors to construct the first plant expected environment matrix, and adds it to the set of expected environment matrices for each plant, thus completing the prediction of the ideal growth environment for each plant and providing a key basis for subsequent evaluation of the plant's growth environment adaptability.

[0023] The plant environmental adaptability detection module 30 is used to detect the plant growth environment adaptability in the forestry area based on the forestry environment monitoring matrix and the expected environment matrix of each plant, and to establish a plant environmental adaptability detection sequence.

[0024] Specifically, the plant environmental adaptability detection module 30 is used to assess the suitability of the growing environment for plants in forestry areas. Based on the forestry environment monitoring matrix and the desired environment matrix for each plant, it comprehensively detects the environmental adaptability of plants within the forestry area. For each specific first plant, the feature recognition unit first extracts the corresponding climate environment monitoring vector, land environment monitoring vector, and bio-human environment monitoring vector from the forestry environment monitoring matrix. Subsequently, the climate environment adaptability acquisition unit, through a supervised training unit, uses the plant climate environment adaptability detection record set to supervise and train M learners, obtaining M plant climate environment adaptability detection models. The desired climate environment vector and monitoring vector of the first plant are then input into these models to obtain M plant climate environment adaptability detection coefficients. The ensemble value calculation unit calculates the ensemble value of these coefficients, thereby determining the climate environment adaptability of the first plant. Similarly, the land environment adaptability acquisition unit and the human environment adaptability acquisition unit determine the land environment adaptability and bio-human environment adaptability of the first plant, respectively. Finally, the fitness test result acquisition unit integrates these three fitness values ​​into the first plant environmental fitness test result, and adds them sequentially to the plant environmental fitness test sequence to form a complete sequence reflecting the environmental fitness of each plant in the forestry area, providing strong data support for subsequent precise intervention in the plant growth environment.

[0025] The plant environment intervention optimization module 40 is used to construct the plant environment intervention guidance vector for each plant based on the plant environment adaptability detection sequence, and to perform adaptive environment intervention optimization based on the plant environment intervention guidance vector to determine the plant growth environment intervention strategy.

[0026] Specifically, the deviation factor determination unit first compares the sequence with the preset plant environmental fitness constraint sequence to identify the differences and determine the deviation factor for each plant's environmental fitness. The compensation feature analysis unit then performs in-depth analysis of the deviation factor based on the desired environment matrix for each plant, obtaining the environmental compensation vector for each plant. Considering the complex spatial distribution of plants within the forestry area, the conflict detection unit performs conflict detection on the environmental compensation vectors of each plant, drawing a plant environmental compensation conflict relationship diagram. The conflict reconciliation and optimization unit optimizes the compensation vectors based on this diagram, generating the environmental intervention guidance vector for each plant. For each plant, the intervention decision unit extracts its environmental intervention guidance vector and, combined with predetermined ecological environment factors, makes a growth environment intervention decision, constructing the first plant environmental intervention space. The optimization analysis unit performs optimization analysis on this space based on the plant environmental recovery efficiency threshold, obtaining the first plant environmental intervention optimization space. Finally, the cost minimization optimization unit performs intervention cost minimization optimization within the optimization space, generating the first plant growth environment intervention strategy and incorporating it into the set of intervention strategies for each plant's growth environment, to achieve precise and efficient intervention in the plant growth environment of the forestry area.

[0027] The plant environment intervention module 50 is used to intervene in the plant growth environment of the forestry area according to the plant growth environment intervention strategies.

[0028] Specifically, the module determines intervention strategies for each plant's growth environment and makes targeted environmental adjustments to the forestry area to promote healthy plant growth. Upon receiving these intervention strategies, the module takes specific measures for each plant within the forestry area according to the corresponding strategy. For example, if the intervention strategy for a particular plant is to improve soil fertility, it directs relevant equipment or personnel to fertilize the soil around the plant; if adjusting light conditions is necessary, it arranges for pruning of surrounding branches and leaves that are obstructing light, or, if necessary, installing auxiliary lighting equipment. During the implementation of the intervention, predetermined operating procedures and processes are followed to ensure the accuracy and effectiveness of the intervention measures. Simultaneously, the module tracks and provides feedback on the intervention effects in real time to adjust the intervention plan promptly, continuously optimize the plant's growth environment, and ultimately achieve the goal of improving the overall ecological environment quality and plant growth status of the forestry area.

[0029] In one possible implementation, the forestry environment monitoring and sorting module 10 further includes:

[0030] The forestry environmental monitoring data stream acquisition unit is used to filter and reduce noise based on the real-time environmental monitoring dataset to obtain the forestry environmental monitoring data stream. The monitoring matrix acquisition unit is used to perform feature recognition on the forestry environmental monitoring data stream based on the predetermined ecological environment factors to obtain a climate environment monitoring matrix, a land environment monitoring matrix, and a bio-human environment monitoring matrix. The time synchronization and alignment unit is used to perform time synchronization and alignment on the climate environment monitoring matrix, the land environment monitoring matrix, and the bio-human environment monitoring matrix to generate the forestry environmental monitoring matrix.

[0031] Specifically, the forestry environmental monitoring data stream acquisition unit uses wavelet transform algorithm to filter and denoise the real-time environmental monitoring dataset, thereby obtaining the forestry environmental monitoring data stream. Wavelet transform is a time-frequency analysis method that decomposes a signal into components of different frequencies and time scales. The frequency characteristics of noise in real-time environmental monitoring datasets often differ from those of the actual environmental monitoring signals. When applying wavelet transform, the dataset is first decomposed into wavelet components, transforming the signal from the time domain to the wavelet domain. In the wavelet domain, noise typically manifests as coefficients with small amplitudes, while the coefficients of the actual environmental monitoring signal have relatively large amplitudes. By setting an appropriate threshold, the wavelet coefficients are processed, setting coefficients below the threshold to zero, which is equivalent to removing the wavelet components corresponding to the noise. After processing the wavelet coefficients, wavelet reconstruction is performed to transform the signal back from the wavelet domain to the time domain, obtaining the filtered and denoised forestry environmental monitoring data stream. This algorithm not only effectively removes noise but also preserves the detailed features of the signal, ensuring that the forestry environmental monitoring data stream accurately reflects the true state of the forestry environment.

[0032] The monitoring matrix acquisition unit utilizes a convolutional neural network (CNN) algorithm to identify features in the forestry environmental monitoring data stream based on predetermined ecological and environmental factors, thereby acquiring climate environment monitoring matrices, land environment monitoring matrices, and bio-human environment monitoring matrices. First, the forestry environmental monitoring data stream is encoded according to time series and feature dimensions, transforming it into a tensor form suitable for CNN processing. The convolutional layers in the CNN automatically extract local features by sliding convolutions on the data tensor using different kernels. For example, for climate environment data, the convolutional kernels can capture local patterns of temperature, humidity, and other variables changing over time; for land environment data, they can identify features such as soil nutrients and topographic changes. Pooling layers downsample the convolutional features, reducing the amount of data and computational complexity while retaining key features. Fully connected layers integrate the features after multiple convolutions and pooling processes and perform classification prediction using the Softmax classification function. Based on the classification criteria of predetermined ecological and environmental factors, the model outputs feature vectors corresponding to the climate environment, land environment, and bio-human environment, respectively. Finally, these feature vectors are arranged and combined according to time and space dimensions to construct climate environment monitoring matrix, land environment monitoring matrix and bio-human environment monitoring matrix, providing structured data support for subsequent forestry ecological environment analysis.

[0033] The time synchronization and alignment unit is responsible for integrating the climate environment monitoring matrix, land environment monitoring matrix, and bio-human environment monitoring matrix to generate a complete and unified forestry environment monitoring matrix. Because the sampling frequency and start time of various monitoring devices may differ, these three types of matrices cannot be directly matched and merged in the time dimension. The time synchronization and alignment unit first extracts and analyzes the timestamp information of each matrix to determine the offset and interval differences of each matrix on the time axis. Then, based on these differences, a linear interpolation method is selected. For missing data points in the time series, linear calculations are performed on data from adjacent time points to complete the time series, ensuring that the matrices are consistent in time. Through this processing, the climate environment monitoring matrix, land environment monitoring matrix, and bio-human environment monitoring matrix are precisely aligned in the time dimension, eliminating errors caused by time differences. Finally, a comprehensive, coherent, and time-synchronized forestry environment monitoring matrix is ​​generated according to a unified time order, providing an accurate and reliable data foundation for subsequent in-depth analysis of the forestry ecological environment, assessment of environmental change trends, and formulation of scientific and reasonable forestry management decisions.

[0034] In one possible implementation, the forestry environment monitoring and sorting module 10 further includes:

[0035] A predetermined ecological environment factor determination unit is used for determining the predetermined ecological environment factors, including climate environment, land environment, and biological and human environment.

[0036] Specifically, the predetermined ecological environment factor determination unit is a crucial preliminary step in the forestry ecological environment monitoring system, clearly defining the monitoring scope. The predetermined ecological environment factors are divided into three main categories: climate environment, land environment, and bio-human environment. The climate environment encompasses factors such as temperature, humidity, sunshine duration and intensity, precipitation, and wind speed and direction. These meteorological conditions directly affect plant growth cycles, photosynthetic efficiency, and the probability of pests and diseases. The land environment focuses on soil characteristics, such as soil moisture, pH, fertility, and topography. These are fundamental for plant root growth, nutrient and water acquisition, and play a crucial role in the stability of the forestry ecosystem. The bio-human environment involves both animal and human activities. Animal activities, such as bird habitats and insect reproduction, affect plant pollination, seed dispersal, and pest and disease control. Human activities, including deforestation, afforestation projects, and tourism, have a wide-ranging and profound impact on the forestry ecological environment, potentially altering the structure and function of the ecosystem. The predetermined ecological environment factor determination unit clearly defines these factors, ensuring that the entire monitoring system accurately reflects the true state of the forestry ecological environment.

[0037] In one possible implementation, the plant environment expectation prediction module 20 further includes:

[0038] The growth status data extraction unit is used to extract the growth status data of the first plant corresponding to the first plant based on the growth status data of each plant. The first plant includes any plant in the forestry area. The expected registration space establishment unit is used to perform normal ecological environment registration based on the growth status data of the first plant to establish the expected ecological environment registration space of the first plant. The trend analysis unit is used to perform central trend analysis on the expected ecological environment registration space of the first plant based on the predetermined ecological environment factors to obtain the expected climate environment vector, the expected land environment vector, and the expected bio-human environment vector of the first plant. The expected environment matrix construction unit is used to construct the expected environment matrix of the first plant based on the expected climate environment vector, the expected land environment vector, and the expected bio-human environment vector of the first plant, and add the expected environment matrix of the first plant to the expected environment matrices of each plant.

[0039] Specifically, when faced with a large and complex amount of data on the growth status of various plants in forestry areas, this unit filters data for specific plants by traversing the entire plant growth status database and randomly selecting the first plant. Once the target plant is identified, all corresponding growth status data are quickly locked. This data covers all aspects of plant growth, including intuitive growth indicators such as plant height, stem thickness, number and color of leaves, and flowering and fruiting status, as well as data reflecting the plant's physiological health status, such as chlorophyll content and photosynthetic efficiency.

[0040] The ecological environment record database acquisition unit retrieves data from a pre-established database of normal plant ecological environment records. This database contains a large amount of sample information on different plants under various normal ecological environments, covering normal ecological environment samples, basic plant information samples, and plant growth status samples. Next, the registration evaluation unit performs a detailed registration evaluation of each record group in the database based on the basic information and growth status data of the first plant. During the evaluation process, the similarity between each record group and the first plant is considered, and the registration coefficient for each plant's environmental record is calculated. Finally, based on these registration coefficients and a pre-set plant environmental record registration threshold, the environmental samples that best match the first plant are selected from the database. These samples, when integrated, constitute the expected registration space for the first plant's ecological environment, providing an important reference standard for subsequent analysis of the first plant's growth suitability in the current environment and prediction of the ideal growth environment.

[0041] The trend analysis unit conducts central trend analysis guided by predetermined ecological and environmental factors, encompassing multiple key dimensions such as climate, land environment, and bio-human environment. Regarding the climate environment, the trend analysis unit extracts data related to temperature, humidity, light duration, and wind speed from the desired registration space. Using statistical methods, such as calculating the mean and median, it analyzes the central trend of this data to determine the ideal climate state for the first plant, ultimately generating a climate environment expectation vector for the first plant. This vector accurately reflects the plant's desired characteristics for climate conditions. For land environment analysis, the trend analysis unit focuses on indicators such as soil pH, fertility, moisture content, and permeability. Through central trend analysis of these land environment data within the desired registration space, it derives the first plant's expectations for the land environment, forming a land environment expectation vector for the first plant, providing a scientific basis for assessing and improving the soil growth conditions for the first plant. For the bio-human environment, the trend analysis unit collects information on animal and human activities within the desired registration space, such as the types, numbers, and activity patterns of surrounding animals, and the impact of human forestry management and tourism activities. By analyzing the central trends of this information, the expected status of the first plant in terms of its biological and humanistic environment was clarified, resulting in the expected vector of the first plant's biological and humanistic environment. This helps to comprehensively consider the impact of biological and human factors on the growth of the first plant. Through this systematic analysis, three key expected vectors were successfully extracted from the ecological environment expected registration space of the first plant, thus laying the foundation for accurate assessment and effective intervention of the plant's growth environment.

[0042] The expected environment matrix construction unit constructs the expected environment matrix for the first plant based on the obtained expected vectors for the climate environment, land environment, and bio-human environment of the first plant. These three expected vectors accurately describe the various ecological environment requirements of the first plant under ideal growth conditions from three key dimensions: climate, land, and bio-human. The expected environment matrix construction unit arranges and integrates these expected vectors in an orderly manner to form a structured matrix. In this matrix, different rows and columns represent different environmental factors and their corresponding expected values, thus comprehensively and systematically presenting the expected growth environment characteristics of the first plant. After constructing the expected environment matrix for the first plant, this unit adds this matrix to the expected environment matrix set for all plants. This set covers the expected environment matrices of all plants in the forestry area, which helps to achieve precise regulation and scientific management of the plant growth environment throughout the entire forestry area.

[0043] In one possible implementation, the desired registration space establishment unit further includes:

[0044] An ecological environment record acquisition unit is used to obtain a normal ecological environment record database for plants. This database includes multiple normal ecological environment record groups, each comprising a normal ecological environment sample, a basic plant information sample, and a plant growth status sample. A registration evaluation unit is used to perform registration evaluation on each normal ecological environment record group based on the first plant's basic information and growth status data, obtaining registration coefficients for each plant's environmental records. An optimization selection unit is used to perform environmental sample optimization selection on the normal ecological environment record database based on the registration coefficients and a plant environmental record registration threshold, generating the desired registration space for the first plant's ecological environment.

[0045] Specifically, the core task of the ecological environment record acquisition unit is to acquire a normal ecological environment record database for plants. This database contains multiple normal ecological environment record groups, each of which is a detailed record of the ecological environment of a specific plant under normal growth conditions. Within each record group, the normal ecological environment sample records various environmental information such as climate conditions, soil characteristics, light intensity, and water status, comprehensively reflecting the external ecological environment of plant growth. The basic plant information sample covers fundamental attributes such as plant species, variety, age, and genetic characteristics, which are intrinsic factors affecting plant growth and environmental adaptability. The plant growth status sample records growth indicators of the plant under the corresponding environment, such as plant height, stem thickness, number of leaves, and flowering and fruiting status, visually demonstrating the actual growth performance of the plant under that ecological environment.

[0046] The registration evaluation unit employs a weighted Euclidean distance-based algorithm. Based on the basic information and growth status data of the first plant, it performs registration evaluation on each plant's normal ecological environment record group to obtain the registration coefficient for each plant's environmental records. First, the basic information and growth status data of the first plant are quantified and converted into numerical vectors along with the plant basic information samples and plant growth status samples within each record group. For example, basic information such as plant species and age, as well as growth status information such as height and number of leaves, are represented by specific numerical values. Next, weights are assigned to each dimension of information based on their impact on the plant's growth environment. Information with a significant impact, such as the plant species' preference for its growth environment, is given a higher weight; information with a smaller impact is given a lower weight. Then, for each plant's normal ecological environment record group, the weighted Euclidean distance between it and the first plant in terms of basic information and growth status data is calculated. The calculation formula is: Where D is the weighted Euclidean distance, w i It is the weight of the information in the i-th dimension, x i It is the information value of the first plant in the i-th dimension, y iis the information value of the record group in the i-th dimension, and n is the total number of information dimensions. Finally, the weighted Euclidean distance is normalized, and the resulting value is used as the registration coefficient for each plant's environmental record. The closer the registration coefficient is to 1, the higher the similarity between the first plant and the record group; the closer the coefficient is to 0, the lower the similarity.

[0047] The optimization and selection unit uses the calculated registration coefficients of each plant's environmental records as a basis, combined with pre-set registration thresholds, to meticulously screen the normal ecological environment record database of plants. In this database, each record group corresponds to a registration coefficient, representing the degree of similarity between that record group and the first plant in terms of basic information and growth status. The entire database is traversed, comparing each registration coefficient with the threshold. Once a record group's registration coefficient is found to be greater than or equal to the plant's environmental record registration threshold, the corresponding normal ecological environment sample is selected. These selected samples contain rich ecological environment information, covering multiple aspects such as climate, soil, and organisms. They all have a high degree of compatibility with the first plant's growth status and basic information. These selected samples are integrated to gradually construct the expected registration space for the first plant's ecological environment. This space brings together ecological environment samples that best match the growth requirements of the first plant, providing solid data support for subsequent analysis of the ideal growth environment of the first plant, prediction of the impact of environmental changes on its growth, and formulation of targeted environmental intervention measures. This will help to manage the forestry ecological environment more scientifically and accurately, and promote the healthy growth of the first plant.

[0048] In one possible implementation, the plant environmental adaptability detection module further includes:

[0049] The system includes three components: a feature recognition unit, a climate environment monitoring unit, and a bio-human environment monitoring unit. The first plant's climate environment monitoring vector, land environment monitoring vector, and bio-human environment monitoring vector are identified based on the forestry environment monitoring matrix. A climate environment fitness acquisition unit performs fitness detection on the first plant's climate environment monitoring vector based on the first plant's expected climate environment vector to obtain the first plant's climate environment fitness. A land environment fitness acquisition unit performs fitness detection on the first plant's land environment monitoring vector based on the first plant's expected land environment vector to obtain the first plant's land environment fitness. A human environment fitness acquisition unit performs fitness detection on the first plant's bio-human environment monitoring vector based on the first plant's expected bio-human environment vector to obtain the first plant's bio-human environment fitness. A fitness detection result acquisition unit outputs the first plant's climate environment fitness, land environment fitness, and bio-human environment fitness as a first plant environment fitness detection result and adds this result to the plant environment fitness detection sequence.

[0050] Specifically, the feature recognition unit uses a convolutional neural network (CNN) algorithm to process the forestry environment monitoring matrix to obtain the relevant monitoring vectors for the first plant. First, the forestry environment monitoring matrix is ​​transformed into a tensor form suitable for CNN processing. Each element in the matrix corresponds to a dimension of the tensor, representing environmental data at different times and spaces. The CNN's convolutional layers contain multiple convolutional kernels that slide across the tensor to perform convolution operations. For feature recognition of the first plant, the convolutional kernels automatically learn and extract local features related to the first plant based on its known feature patterns. For example, for climate environment data, the convolutional kernels can capture patterns of temperature and humidity changes over time and space, extracting climate features closely related to the growth of the first plant. The pooling layer downsamples the convolutional features, reducing the amount of data while retaining key features and preventing overfitting. After multiple convolutional and pooling operations, the fully connected layer integrates these features and classifies them using a classifier. Classification targets are set for climate environment, land environment, and bio-human environment, and the model outputs corresponding feature vectors based on these targets. For example, the first set of output feature vectors corresponds to the climate environment monitoring vector of the first plant, which includes key climate information such as temperature change trends and humidity fluctuation range; the second set of feature vectors constitutes the land environment monitoring vector of the first plant, which covers land environment data such as soil nutrient content and pH; the third set of feature vectors is the biological and human environment monitoring vector of the first plant, which includes information such as the types and quantities of surrounding plants and animals and the intensity of human activities, thereby achieving accurate acquisition of different environmental monitoring vectors of the first plant.

[0051] To effectively evaluate the adaptability of the first plant to different environments, a random forest model was used. First, a large amount of data related to the plant's environmental adaptability was collected. For the climatic environment, data included temperature, humidity, and light duration; for the land environment, information included soil pH, fertility, and water content; and for the bio-human environment, information included the surrounding flora and fauna species and the frequency of human activities. Each data record included the plant's adaptability label in these environments and the corresponding environmental feature vector. This data was then divided into training and testing sets.

[0052] A random forest model, consisting of multiple decision trees, is used. During training, samples are randomly drawn with replacement from the training dataset (bootstrapping), and a subset of features are randomly selected to construct each decision tree. For training climate environment fitness, the difference between the expected and monitored climate environment vectors of the first plant is used as the input feature, and the corresponding plant climate environment fitness is used as the label. Training for land environment and bio-human environment fitness is similar, using the difference between the corresponding expected and monitored vectors as the input feature, and the corresponding fitness as the label. Through multiple iterative training iterations, the random forest model learns the complex relationships between different environmental factors and plant fitness.

[0053] Climate environment fitness acquisition: The difference vector between the expected climate environment vector and the monitored vector of the first plant is input into the trained random forest model. The model will perform a comprehensive vote or average based on the output results of each decision tree, and finally output the climate environment fitness of the first plant. Land environment fitness acquisition: The difference vector between the expected land environment vector and the monitored vector of the first plant is input into the model. After calculation and judgment by the model, the land environment fitness of the first plant is obtained. Bio-human environment fitness acquisition: The difference vector between the expected bio-human environment vector and the monitored vector of the first plant is used as input, and the model outputs the bio-human environment fitness of the first plant. The model is evaluated using a test set, and its performance is measured by calculating metrics such as mean squared error and accuracy. If the model performance is not ideal, the parameters of the random forest can be adjusted, such as the number of decision trees, the number of features used in each decision tree, etc., or more data can be collected for retraining to improve the model's accuracy and generalization ability. Through such an integrated random forest machine learning model, the fitness of the first plant in climate, land and bio-human environment can be calculated relatively accurately based on the expected vector and monitoring vector of different environments, providing strong support for the monitoring and management of forestry ecological environment.

[0054] After the climate environment adaptability acquisition unit, land environment adaptability acquisition unit, and human environment adaptability acquisition unit have completed the adaptability tests of the first plant in different environments, obtaining the climate environment adaptability, land environment adaptability, and bio-human environment adaptability of the first plant, the adaptability test result acquisition unit integrates these three values ​​reflecting different environmental adaptations, arranging them according to a certain format and order to form a comprehensive result reflecting the overall environmental adaptability of the first plant, namely, the environmental adaptability test result of the first plant. This result comprehensively demonstrates the degree of adaptation of the first plant in the current climate, land, and bio-human environment, providing intuitive data basis for subsequent analysis. Subsequently, the adaptability test result acquisition unit adds the generated first plant environmental adaptability test result to the plant environmental adaptability test sequence. This sequence is like a continuously updated database, storing the environmental adaptability test results of various plants in the forestry area. Each new test result added enriches the data content of the sequence.

[0055] In one possible implementation, the climate adaptability acquisition unit includes:

[0056] A supervised training unit is used to supervise the training of M learners based on a set of plant climate environment adaptability detection records, obtaining M plant climate environment adaptability detection models, where M is a positive integer greater than 1. A climate environment adaptability detection coefficient acquisition unit is used to input the first plant climate environment expectation vector and the first plant climate environment monitoring vector into the M plant climate environment adaptability detection models to obtain M plant climate environment adaptability detection coefficients. A lumped value calculation unit is used to calculate the lumped value of the M plant climate environment adaptability detection coefficients to obtain the first plant climate environment adaptability.

[0057] Specifically, the supervised training unit is based on a set of plant climate environment fitness detection records. These records contain a large amount of plant fitness information under different climate environments and corresponding climate environment parameters, serving as data resources for model training. A random forest model is used to supervise the training of M learners, each consisting of multiple decision trees. During training, each learner (decision tree) learns from the plant climate environment fitness detection records, uncovering the potential relationship between climate environment factors and plant fitness. After multiple iterations and optimizations, M high-performance plant climate environment fitness detection models are finally obtained.

[0058] The climate environment adaptability detection coefficient acquisition unit is responsible for conducting actual detection using the trained model. It takes the expected climate environment vector and the monitored climate environment vector of the first plant as inputs, and feeds them into M plant climate environment adaptability detection models. Each model analyzes and processes the input vector data based on its learned knowledge and patterns, outputting a corresponding plant climate environment adaptability detection coefficient. In this way, M detection coefficients are obtained, which reflect the adaptability of the first plant to the current climate environment from different perspectives.

[0059] The scalar convergence (SCL) calculation unit comprehensively processes the climate adaptability detection coefficients of M plants. Since the output of a single model may have certain biases or limitations, the SCL of these M detection coefficients is calculated to obtain more accurate and representative results. Common SCL calculation methods include calculating the mean and median. By calculating the SCL, the detection results of multiple models can be comprehensively considered, eliminating errors that may be introduced by a single model, and ultimately obtaining the climate adaptability of the first plant. This value can accurately quantify the degree to which the first plant adapts to the current climate environment.

[0060] In one possible implementation, the plant environment intervention optimization module 40 includes:

[0061] The system includes a fitness deviation factor determination unit, used to compare the plant environmental fitness detection sequence with the plant environmental fitness constraint sequence to determine the environmental fitness deviation factor for each plant. An environmental compensation vector determination unit is used to perform compensation feature analysis on the environmental fitness deviation factors of each plant based on the expected environment matrix of each plant, and to determine the environmental compensation vector for each plant. An environmental compensation conflict relationship diagram acquisition unit is used to perform conflict detection on the environmental compensation vectors of each plant based on the spatial distribution of plants in the forestry area, and to obtain a plant environmental compensation conflict relationship diagram. An intervention guidance vector generation unit is used to perform conflict reconciliation and optimization on the environmental compensation vectors of each plant based on the plant environmental compensation conflict relationship diagram, and to generate the environmental intervention guidance vector for each plant.

[0062] Specifically, the task of the fitness deviation factor determination unit is to accurately identify the gap between the actual environmental fitness of each plant and its ideal state. Based on the plant environmental fitness detection sequence, which records the fitness values ​​of each plant in the current climate, land, and bio-human environment, a plant environmental fitness constraint sequence serves as a reference standard, containing the ideal fitness indicators for each plant in terms of climate, land, and bio-human environment. During comparison, the fitness deviation factor determination unit conducts a detailed analysis of each plant. For the climate environment, it compares the plant's climate environment fitness in the detection sequence with the plant's climate environment fitness constraints in the constraint sequence, calculating the difference between the two. The same method is used for the land environment and bio-human environment, comparing the plant's land environment fitness with its constraints, and the plant's bio-human environment fitness with its constraints, respectively. Through these comparisons, the fitness deviation of each plant under different environmental dimensions is determined. Subsequently, based on the importance of each environmental dimension to plant growth, corresponding weights were assigned to the deviations in each dimension. After weighted calculation, a comprehensive deviation factor for the environmental adaptability of each plant was obtained. These deviation factors provide an important basis for subsequent assessment of the plant's growth environment and the development of targeted environmental adjustment strategies, contributing to improved management of forestry ecological environment and the quality of plant growth.

[0063] The desired environment matrix and environmental fitness deviation factors for each plant were digitized. Association rule mining algorithms were used to identify potential relationships between different environmental factors and environmental fitness deviation factors in the desired environment matrix. For example, if a plant showed a large environmental fitness deviation when soil fertility was low, and the desired environment matrix clearly indicated requirements for soil fertility, then soil fertility was identified as a key compensating feature. Regression analysis models, combined with extensive historical data, were used to predict the impact of adjusting different environmental factors on reducing environmental fitness deviation. Taking temperature adjustment as an example, the regression model calculated the specific impact of each temperature increase or decrease on the plant's environmental fitness deviation. Based on these analysis results, weights were assigned to each compensating feature according to pre-defined weighting rules. These weights reflected the importance of the feature in improving the plant's growth environment. Then, each compensating feature and its corresponding weight were integrated and transformed into a vector form. Each dimension in the vector represents an environmental factor, and its value represents the adjustment range determined based on the analysis results. For example, if a plant needs to increase soil fertility by 10 units and adjust the temperature by 2 degrees Celsius, the dimensions of soil fertility and temperature in the vector would be 10 and 2 respectively (the sign and specific values ​​are determined based on the actual calculation results). Ultimately, these vectors constitute the environmental compensation vector for each plant, providing precise direction and quantitative basis for subsequent environmental interventions.

[0064] The environmental compensation conflict relationship map acquisition unit first processes the spatial distribution data of plants in the forestry area to construct a plant spatial distribution matrix, clearly presenting the specific location and adjacent relationships of each plant. Simultaneously, it analyzes the environmental compensation vectors of each plant in depth, clarifying the compensation needs and adjustment ranges of each plant in terms of climate, land, and bio-human environmental factors. Subsequently, conflict detection is conducted, considering the spatial location and compensation vector of each pair of plants. If two adjacent plants, one requiring increased light while the other requires increased shading, or if multiple adjacent plants require a large amount of water resources but the area has limited supply, a conflict is identified. The conflicting plant pairs are recorded, and the conflict type and degree are labeled. Finally, a plant environmental compensation conflict relationship map is generated based on the conflict detection results. Using plants as nodes, if two plants conflict, they are connected by edges; the thickness or color intensity of the edges indicates the degree of conflict. This map visually displays the overall picture of plant environmental compensation conflicts within the forestry area.

[0065] The intervention guidance vector generation unit utilizes a genetic algorithm to reconcile and optimize the environmental compensation vectors of each plant, thereby generating intervention guidance vectors for each plant. The genetic algorithm simulates the process of biological evolution, gradually optimizing the population to approach the optimal solution through selection, crossover, and mutation operations. Each plant's environmental compensation vector is encoded into an individual in the genetic algorithm. These individuals form the initial population. Based on the plant environmental compensation conflict relationship graph, the fitness of each individual is evaluated. Fitness represents the effectiveness of the combination of environmental compensation vectors represented by that individual in resolving conflicts. For example, individuals that can meet the needs of more plants and reduce resource competition conflicts have higher fitness. Then, the genetic algorithm enters an iterative process. The selection operation uses methods such as roulette wheel selection and tournament selection based on individual fitness to select better individuals for the next generation. The selected individuals are paired up and crossover occurs, randomly exchanging some gene fragments to generate new individuals. For example, information related to soil fertility adjustment and light duration adjustment in different plant environmental compensation vectors is exchanged. Simultaneously, mutations are performed on some individuals with a certain probability, randomly altering certain genes within them, such as fine-tuning a plant's water requirements. Through multiple iterations, the population continuously evolves, and individuals gradually tend towards better solutions. The iteration ends when preset termination conditions are met, such as the average fitness of the population no longer increasing over multiple generations, or the set number of iterations is reached. At this point, the individual with the highest fitness is selected from the final population, and its environmental intervention guidance vector is decoded and restored to represent each plant. These vectors clearly define the specific environmental intervention content for each plant, such as adjusting light duration, changing soil pH, and controlling the range of surrounding biological activity, providing precise guidance for actual plant growth environment interventions.

[0066] In one possible implementation, the plant environment intervention optimization module further includes:

[0067] An intervention guidance vector extraction unit is used to extract a first plant environmental intervention guidance vector based on the environmental intervention guidance vectors of each plant. An intervention space construction unit is used to make growth environment intervention decisions for the first plant based on the first plant environmental intervention guidance vector, and construct a first plant environmental intervention space. An intervention optimization space acquisition unit is used to perform optimization analysis on the first plant environmental intervention space based on a plant environmental recovery efficiency threshold, and obtain a first plant environmental intervention optimization space. An intervention strategy generation unit is used to perform intervention cost minimization optimization on the first plant environmental intervention optimization space, generate a first plant growth environment intervention strategy, and add the first plant growth environment intervention strategy to the existing plant growth environment intervention strategies.

[0068] Specifically, the intervention guidance vector extraction unit takes as input the environmental intervention guidance vectors of numerous plants, each containing detailed information about the plants. Each vector specifies the direction and extent of environmental intervention for a particular plant. The unit scans each plant's environmental intervention guidance vector one by one, quickly locating the vector information corresponding to the first plant based on preset recognition rules. These rules are based on plant identification information such as number, species, and location, ensuring accurate identification of the specific vector for the first plant. Once identified, this vector is extracted from the numerous vectors to generate the first plant's environmental intervention guidance vector. This vector carries key instructions for precise intervention in the first plant's growth environment, encompassing guidance information on aspects such as adjusting light duration and intensity, optimizing soil fertility, and improving the surrounding biological and human environment, providing a basis for subsequent environmental intervention work targeting the first plant.

[0069] Based on the environmental intervention guidance vector for the first plant, the intervention space construction unit conducts comprehensive growth environment intervention decision-making and planning for the first plant, constructing an environmental intervention space for the first plant containing multiple feasible solutions. Upon receiving the environmental intervention guidance vector for the first plant, the unit analyzes the information within the vector in detail. The guidance vector covers the direction and degree of intervention in various aspects, including climate, land, and bio-human factors. For example, in terms of climate, it may involve suggestions for adjusting light duration, temperature, and humidity; in terms of land, it includes instructions related to soil pH and fertility improvement; and in terms of bio-human factors, it may include content on reducing interference from surrounding human activities and optimizing the symbiotic environment between plants and animals. Based on this information, specific intervention decisions are formulated, considering multiple feasible operational methods for each environmental factor. For example, in terms of light adjustment, not only are plans to extend or shorten light duration formulated, but also the use of different types of supplemental lighting equipment to change light intensity is considered; for improving soil fertility, in addition to selecting different types of fertilizers, different combinations of fertilization frequencies and amounts are planned. These different operational methods for each environmental factor are combined to form a large number of different plant environmental intervention decisions. Numerous decisions collectively constitute the environmental intervention space for the first plant, providing a wealth of options for subsequently selecting the most suitable intervention strategy for the first plant, in order to meet the optimization needs of the first plant's growth environment under different circumstances.

[0070] The intervention optimization space acquisition unit utilizes a combination of Monte Carlo simulation and a greedy algorithm to perform optimization analysis on the first plant environmental intervention space based on a plant environmental recovery efficiency threshold, thereby obtaining the first plant environmental intervention optimization space. First, Monte Carlo simulation is used to predict each plant environmental intervention decision within the first plant environmental intervention space. This simulation involves multiple random samplings, taking into account the uncertainty and complex interactions of environmental factors. For example, environmental factors such as soil moisture and light intensity are assigned random values ​​consistent with their actual distribution in each simulation. Then, a model constructed based on historical data simulates the environmental recovery of the first plant after adopting the intervention decision. Through numerous simulations, the probability distribution of the plant environmental recovery efficiency under each intervention decision is obtained. Next, the plant environmental recovery efficiency of each intervention decision obtained from the simulation is compared with the plant environmental recovery efficiency threshold. If the predicted plant environmental recovery efficiency is greater than or equal to the threshold, this intervention decision is marked as a potentially effective decision. Next, a greedy algorithm is used for further screening. Potentially effective decisions are first sorted from highest to lowest according to their predicted plant environment restoration efficiency. The greedy algorithm selects from the highest-efficiency decisions sequentially, considering constraints such as resource limitations and compatibility between decisions. For example, if two decisions require a large amount of the same resource, but the total resource quantity is limited, only the better decision can be selected. As the greedy algorithm progresses, decisions that meet the plant environment restoration efficiency threshold and the constraints are added one by one to the first plant environment intervention optimization space. Finally, the algorithm stops when all potentially effective decisions have been traversed or a certain stopping condition is met (such as the number of decisions in the optimization space reaching a preset value). The result at this point is the first plant environment intervention optimization space, which contains the better plant environment intervention decisions that meet the efficiency threshold and constraints.

[0071] The intervention strategy generation unit performs deep optimization with the goal of minimizing intervention costs, thereby generating the first plant growth environment intervention strategy. This unit first calculates the cost of each plant environment intervention decision within the optimization space. This cost includes human costs (time and effort required for staff to implement intervention measures), material costs (costs of fertilizers, irrigation equipment, etc.), and financial costs (purchase of equipment, payment of labor costs, etc.). Then, optimization algorithms, such as dynamic programming, are used to comprehensively consider the cost of each decision and the expected plant environment restoration effect. Dynamic programming decomposes the optimization problem into multiple sub-problems, gradually approaching the global optimum by solving the optimal solutions to the sub-problems. During this process, the costs and benefits of different decision combinations are compared to find a solution that satisfies the plant's environmental restoration needs while minimizing intervention costs. Once the optimal decision combination is found, it is determined as the first plant growth environment intervention strategy. This strategy details specific intervention measures for the first plant's growth environment, such as fertilizing at specific times and adjusting irrigation frequency. Finally, the unit will add the generated first plant growth environment intervention strategy to the plant growth environment intervention strategies of each plant, so that the environmental intervention strategies for each plant in the entire forestry ecosystem form a complete system, providing comprehensive and precise guidance for subsequent unified implementation and management.

[0072] Example 2, based on the same inventive concept as the forestry ecological environment monitoring system in the foregoing examples, such as... Figure 2 As shown, this application provides a method for monitoring forestry ecological environment. The method and system embodiments in this application are based on the same inventive concept. The method includes:

[0073] Step S100: Organize the real-time environmental monitoring dataset of the forestry area according to predetermined ecological environment factors to establish a forestry environmental monitoring matrix. Step S200: Based on the predetermined ecological environment factors, predict the expected ecological environment of each plant in the forestry area according to its growth status data to obtain the expected environment matrix for each plant. Step S300: Detect the plant growth environment adaptability in the forestry area according to the forestry environmental monitoring matrix and the expected environment matrix for each plant, and establish a plant environment adaptability detection sequence. Step S400: Construct an environmental intervention guidance vector for each plant according to the plant environment adaptability detection sequence, and perform adaptive environmental intervention optimization based on the plant environmental intervention guidance vector to determine the intervention strategy for each plant's growth environment. Step S500: Implement plant growth environment intervention in the forestry area according to the intervention strategy for each plant's growth environment.

[0074] Furthermore, step S200 also includes:

[0075] Based on the growth status data of each plant, the growth status data of the first plant corresponding to the first plant is extracted. The first plant includes any plant in the forestry area. Normal ecological environment registration is performed based on the growth status data of the first plant to establish the ecological environment expectation registration space of the first plant. Central trend analysis is performed on the ecological environment expectation registration space of the first plant based on the predetermined ecological environment factors to obtain the climate environment expectation vector, land environment expectation vector, and bio-human environment expectation vector of the first plant. Based on the climate environment expectation vector, land environment expectation vector, and bio-human environment expectation vector of the first plant, the expected environment matrix of the first plant is constructed, and the expected environment matrix of the first plant is added to the expected environment matrices of each plant.

[0076] Furthermore, step S200 also includes:

[0077] A normal ecological environment record library for plants is obtained, comprising multiple normal ecological environment record groups. Each normal ecological environment record group includes a normal ecological environment sample, a basic plant information sample, and a plant growth status sample. Registration evaluation is performed on each normal ecological environment record group based on the basic plant information and the first plant growth status data to obtain registration coefficients for each plant environmental record. Based on these registration coefficients and a plant environmental record registration threshold, environmental samples are optimized and selected from the normal ecological environment record library to generate the desired registration space for the first plant ecological environment.

[0078] Furthermore, step S300 also includes:

[0079] Based on feature identification of the first plant in the forestry environment monitoring matrix, the climate environment monitoring vector, land environment monitoring vector, and bio-human environment monitoring vector of the first plant are obtained. The climate environment monitoring vector of the first plant is then subjected to fitness testing based on the expected climate environment vector of the first plant to obtain the climate environment fitness of the first plant. Similarly, the land environment monitoring vector of the first plant is subjected to fitness testing based on the expected land environment vector of the first plant to obtain the land environment fitness of the first plant. The bio-human environment monitoring vector of the first plant is then subjected to fitness testing based on the expected bio-human environment vector of the first plant to obtain the bio-human environment fitness of the first plant. The climate environment fitness of the first plant, the land environment fitness of the first plant, and the bio-human environment fitness of the first plant are output as the first plant environment fitness detection result, and this result is added to the plant environment fitness detection sequence.

[0080] Furthermore, step S300 also includes:

[0081] Supervised training is performed on M learners based on the plant climate environment adaptability detection record set to obtain M plant climate environment adaptability detection models, where M is a positive integer greater than 1; the first plant climate environment expectation vector and the first plant climate environment monitoring vector are input into the M plant climate environment adaptability detection models to obtain M plant climate environment adaptability detection coefficients; the set value of the M plant climate environment adaptability detection coefficients is calculated to obtain the first plant climate environment adaptability.

[0082] Furthermore, step S400 also includes:

[0083] By comparing the plant environmental fitness detection sequence with the plant environmental fitness constraint sequence, the environmental fitness deviation factor of each plant is determined; the environmental fitness deviation factor of each plant is analyzed for compensation features based on the expected environment matrix of each plant to determine the environmental compensation vector of each plant; the environmental compensation vector of each plant is conflict detected based on the spatial distribution of plants in the forestry area to obtain a plant environmental compensation conflict relationship diagram; the environmental compensation vector of each plant is reconciled and optimized based on the plant environmental compensation conflict relationship diagram to generate the environmental intervention guidance vector of each plant.

[0084] Furthermore, step S400 also includes:

[0085] Based on the environmental intervention guidance vectors of each plant, the first plant environmental intervention guidance vector is extracted; based on the first plant environmental intervention guidance vector, the first plant is used to make a growth environment intervention decision and construct the first plant environmental intervention space; based on the plant environment recovery efficiency threshold, the first plant environmental intervention space is optimized to obtain the first plant environmental intervention optimization space; the first plant environmental intervention optimization space is optimized by minimizing the intervention cost to generate the first plant growth environment intervention strategy, and the first plant growth environment intervention strategy is added to the plant growth environment intervention strategies.

[0086] Furthermore, step S100 also includes:

[0087] The forestry environmental monitoring data stream is obtained by filtering and denoising the real-time environmental monitoring dataset; the forestry environmental monitoring data stream is then characterized by the predetermined ecological environment factors to obtain the climate environment monitoring matrix, the land environment monitoring matrix, and the bio-human environment monitoring matrix; the climate environment monitoring matrix, the land environment monitoring matrix, and the bio-human environment monitoring matrix are then time-synchronized and aligned to generate the forestry environmental monitoring matrix.

[0088] Furthermore, step S100 also includes:

[0089] The predetermined ecological and environmental factors include climate, land, and bio-human environment.

[0090] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0091] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0092] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A forestry ecological environment monitoring system, characterized in that, include: The forestry environment monitoring and sorting module is used to sort the real-time environmental monitoring dataset of forestry areas according to predetermined ecological and environmental factors and establish a forestry environment monitoring matrix. The plant environment expectation prediction module is used to predict the ecological environment expectation based on the predetermined ecological environment factors and the growth status data of each plant in the forestry area, and obtain the expected environment matrix of each plant. The plant environment expectation prediction module also includes: The growth status data extraction unit is used to extract the growth status data of the first plant corresponding to the first plant based on the growth status data of each plant, wherein the first plant includes any plant in the forestry area. The expected registration space establishment unit is used to perform normal ecological environment registration based on the growth status data of the first plant and establish the expected registration space of the first plant's ecological environment. The trend analysis unit is used to perform a central trend analysis on the ecological environment expectation registration space of the first plant according to the predetermined ecological environment factors, and obtain the first plant climate environment expectation vector, the first plant land environment expectation vector, and the first plant bio-human environment expectation vector; the expectation environment matrix construction unit is used to construct the first plant expectation environment matrix according to the first plant climate environment expectation vector, the first plant land environment expectation vector, and the first plant bio-human environment expectation vector, and add the first plant expectation environment matrix to each plant expectation environment matrix; The plant environmental adaptability detection module is used to detect the plant growth environment adaptability in the forestry area based on the forestry environment monitoring matrix and the expected environment matrix of each plant, and to establish a plant environmental adaptability detection sequence. The plant environment intervention optimization module is used to construct the plant environment intervention guidance vector for each plant based on the plant environment adaptability detection sequence, and to perform adaptive environment intervention optimization based on the plant environment intervention guidance vector to determine the plant growth environment intervention strategy. The plant environment intervention optimization module also includes: The fitness deviation factor determination unit is used to compare the plant environmental fitness detection sequence with the plant environmental fitness constraint sequence to determine the environmental fitness deviation factor of each plant. The environmental compensation vector determination unit is used to perform compensation feature analysis on the environmental fitness deviation factor of each plant according to the expected environment matrix of each plant, and determine the environmental compensation vector of each plant. The environmental compensation conflict relationship diagram acquisition unit is used to perform conflict detection on the environmental compensation vectors of each plant according to the spatial distribution of the plants in the forestry area, and obtain the plant environmental compensation conflict relationship diagram. An intervention guidance vector generation unit is used to perform conflict reconciliation and optimization on each plant environment compensation vector according to the plant environment compensation conflict relationship diagram, and generate each plant environment intervention guidance vector; an intervention guidance vector extraction unit is used to extract the first plant environment intervention guidance vector according to each plant environment intervention guidance vector. An intervention space construction unit is used to make growth environment intervention decisions for the first plant based on the first plant's environmental intervention guidance vector, and to construct the first plant's environmental intervention space. The intervention optimization space acquisition unit is used to perform optimization analysis on the first plant environment intervention space based on the plant environment recovery efficiency threshold to obtain the first plant environment intervention optimization space. An intervention strategy generation unit is used to minimize the intervention cost in the first plant environment intervention optimization space, generate a first plant growth environment intervention strategy, and add the first plant growth environment intervention strategy to each plant growth environment intervention strategy. The plant environment intervention module is used to intervene in the plant growth environment of the forestry area according to the plant growth environment intervention strategies.

2. The forestry ecological environment monitoring system as described in claim 1, characterized in that, The desired registration space establishment unit further includes: An ecological environment record database acquisition unit is used to obtain a normal ecological environment record database of plants. The normal ecological environment record database of plants includes multiple normal ecological environment record groups of plants. Each normal ecological environment record group of plants includes a normal ecological environment sample of plants, a basic information sample of plants, and a growth status sample of plants. The registration evaluation unit is used to perform registration evaluation on each plant's normal ecological environment record group based on the basic information of the first plant and the growth status data of the first plant, and to obtain the registration coefficient of each plant's environmental record. The optimization selection unit is used to optimize the environmental samples of the plant normal ecological environment record library based on the registration coefficient of each plant environmental record and the registration threshold of the plant environmental record, and generate the first plant ecological environment expected registration space.

3. The forestry ecological environment monitoring system as described in claim 1, characterized in that, The plant environmental adaptability detection module also includes: The feature recognition unit is used to perform feature recognition on the forestry environment monitoring matrix based on the first plant to obtain the climate environment monitoring vector of the first plant, the land environment monitoring vector of the first plant, and the biological and human environment monitoring vector of the first plant. The climate environment fitness acquisition unit is used to perform fitness detection on the climate environment monitoring vector of the first plant according to the climate environment expectation vector of the first plant, and obtain the climate environment fitness of the first plant. The land environment fitness acquisition unit is used to perform fitness detection on the land environment monitoring vector of the first plant based on the land environment expectation vector of the first plant, and obtain the land environment fitness of the first plant. The human environment adaptability acquisition unit is used to perform adaptability detection on the first plant biological human environment monitoring vector based on the first plant biological human environment expectation vector, and obtain the first plant biological human environment adaptability. The fitness detection result acquisition unit is used to output the first plant's climate environment fitness, the first plant's land environment fitness, and the first plant's biological and human environment fitness as the first plant's environmental fitness detection result, and add the first plant's environmental fitness detection result to the plant's environmental fitness detection sequence.

4. A forestry ecological environment monitoring system as described in claim 3, characterized in that, The climate and environmental adaptability acquisition unit includes: The supervised training unit is used to supervise the training of M learners based on the plant climate environment adaptability detection record set, so as to obtain M plant climate environment adaptability detection models, where M is a positive integer greater than 1. The climate environment adaptability detection coefficient acquisition unit is used to input the first plant climate environment expectation vector and the first plant climate environment monitoring vector into the M plant climate environment adaptability detection model to obtain the M plant climate environment adaptability detection coefficients. The lumped value calculation unit is used to calculate the lumped value of the climate environment adaptability detection coefficients of the M plants, and to obtain the climate environment adaptability of the first plant.

5. A forestry ecological environment monitoring system as described in claim 1, characterized in that, The forestry environment monitoring and sorting module also includes: The forestry environmental monitoring data stream acquisition unit is used to filter and reduce noise based on the real-time environmental monitoring dataset to obtain the forestry environmental monitoring data stream; The monitoring matrix acquisition unit is used to perform feature identification on the forestry environment monitoring data stream based on the predetermined ecological environment factors, and to obtain the climate environment monitoring matrix, the land environment monitoring matrix, and the bio-human environment monitoring matrix. The time synchronization alignment unit is used to perform time synchronization alignment on the climate environment monitoring matrix, the land environment monitoring matrix, and the bio-human environment monitoring matrix to generate the forestry environment monitoring matrix.

6. A forestry ecological environment monitoring system as described in claim 1, characterized in that, The forestry environment monitoring and sorting module also includes: The predetermined ecological environment factor determination unit is used to determine that the predetermined ecological environment factors include climate environment, land environment and biological and human environment.

7. A method for monitoring forestry ecological environment, characterized in that, The method is implemented using a forestry ecological environment monitoring system as described in any one of claims 1-6, and the method includes: Based on predetermined ecological and environmental factors, the real-time environmental monitoring dataset of the forestry area is sorted out to establish a forestry environmental monitoring matrix; Based on the predetermined ecological environment factors, ecological environment expectation prediction is performed according to the growth status data of each plant in the forestry area to obtain the expected environment matrix of each plant. Based on the forestry environment monitoring matrix and the expected environment matrix of each plant, the plant growth environment adaptability of the forestry area is detected, and a plant environment adaptability detection sequence is established. Based on the plant environmental adaptability detection sequence, construct environmental intervention guidance vectors for each plant, and perform adaptive environmental intervention optimization based on the plant environmental intervention guidance vectors to determine the plant growth environment intervention strategy. The plant growth environment intervention was carried out in the forestry area according to the plant growth environment intervention strategies described above.

Images