Comprehensive ecological improvement method for drought and flood saline-alkali soil based on internet-of-things dynamic monitoring technology

Abstract

The invention discloses a drought and flood saline-alkali soil ecological comprehensive improvement method based on an Internet of Things dynamic monitoring technology, which is used in the field of vegetation comprehensive improvement and comprises the following steps: dividing a preset ecological environment area; acquiring soil environment parameters in each area in the ecological environment by using detection equipment, and uploading the encrypted soil environment parameters to a cloud server of a cloud platform; the encrypted soil environment parameters are decrypted and analyzed; deploying an unmanned aerial vehicle for regional patrol; and according to a soil environment parameter evaluation result, an environment change rule and optimization information of equipment layout, combining real-time data of unmanned aerial vehicle patrol, comprehensively analyzing a change trend of a soil environment, and generating a comprehensive improvement plan. According to the method, the soil environment parameter evaluation result, the environment change rule and the equipment layout optimization information are combined, the change trend of the soil environment is obtained, and the soil improvement plan with high pertinence and predictable implementation effect is formulated.

Description

Technical Field

[0001] The present invention relates to the field of comprehensive vegetation improvement, and in particular to a method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things. Background Art

[0002] Drought-flood saline-alkali land ecology refers to a special ecosystem formed under conditions of alternating drought and flood and severe salinity. This ecosystem is mainly distributed in inland saline-alkali land, coastal tidal flats and artificial saline-alkali land. It is characterized by high soil salinity, sparse vegetation and low biodiversity. A notable feature of this ecosystem is the alternation of drought and flood. In the rainy season, heavy precipitation causes temporary waterlogging in the region, while in the dry season, due to low precipitation and high evaporation, drought will occur in the region. This alternating drought and flood environment has a significant impact on the physical and chemical properties of the soil and biodiversity. Another feature of drought-flood saline-alkali land is that the soil contains a large amount of salt, which mainly comes from dissolved salts in groundwater and seawater. The saline-alkali environment has a negative impact on the growth of most plants. Therefore, the vegetation in these areas is usually sparse and mainly consists of salt-tolerant plants.

[0003] Due to the dual influence of alternating drought and flood and saline-alkali environment, the biodiversity of drought-flood saline-alkali land is usually low. However, some unique biological populations in the area are of great value for studying biological adaptation to extreme environments and salt stress. The ecological restoration and improvement of drought-flood saline-alkali land is an important research direction. By selecting salt-tolerant plants for vegetation restoration and improving soil management measures, the ecological environment of drought-flood saline-alkali land can be improved and its ecological service functions can be increased.

[0004] However, traditional soil environmental monitoring methods may not be able to accurately capture all environmental change information. The choice of equipment placement often relies on experience, and cannot guarantee the comprehensiveness and accuracy of data collection. Traditional data analysis reports are often presented in the form of text and tables, which may make the information difficult to understand and operate, affecting the efficiency of environmental engineers in environmental assessment and improvement design. In addition, traditional soil environmental monitoring methods often collect data on a regular basis, and cannot track changes in the soil environment in real time, nor can they dynamically adjust the layout of monitoring equipment and improvement plans based on monitoring results. Traditional soil quality rating methods may not be able to accurately predict future soil quality changes, which may cause certain troubles for environmental improvement and soil management.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to overcome the above problems, the present invention aims to propose a comprehensive ecological improvement method for drought, flood and saline-alkali land based on the dynamic monitoring technology of the Internet of Things. The purpose is to solve the problem that traditional soil environment monitoring methods often collect data regularly, cannot track changes in the soil environment in real time, and cannot dynamically adjust the layout of monitoring equipment and improvement plans according to the monitoring results. Traditional soil quality rating methods may not be able to accurately predict future changes in soil quality, which may cause certain troubles for environmental improvement and soil management.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: The method for comprehensive ecological improvement of drought-waterlogged saline-alkali land based on dynamic monitoring technology of the Internet of Things comprises the following steps: S1. Divide the preset ecological environment areas and install detection equipment in the divided ecological environment areas; S2. Using detection equipment to collect soil environmental parameters in each area of ​​the ecological environment, and uploading the encrypted soil environmental parameters to the cloud server of the cloud platform; S3. Decrypt and analyze the encrypted soil environmental parameters and dynamically adjust the monitoring equipment layout according to the results; S4. Deploy drones to patrol the area, obtain ecological and environmental information in the area, and upload the ecological and environmental information and geographic coordinates to the cloud platform; S5. Based on the results of soil environmental parameter assessment, environmental change patterns and optimization information for equipment layout, combined with real-time data from drone patrols, a comprehensive analysis of soil environment change trends is conducted, and a comprehensive improvement plan is generated, which is then visualized on the cloud platform.

[0008] Preferably, dividing the preset ecological environment area and installing the detection equipment in the divided ecological environment area includes the following steps: S11. Divide the ecological environment area that needs to be improved into several working sections, and install corresponding testing equipment in each working section; S12. Dig a main sprinkling blind ditch and a branch sprinkling blind ditch in the ecological environment area that needs to be improved, and connect the branch sprinkling blind ditch with the main sprinkling blind ditch, wherein the main sprinkling blind ditch is dug in the middle of each working section; S13. Set up a strong drainage water collection well at the tail of the main water blind ditch, and dig several water collection wells; S14. Build ridges on both sides of each main irrigation blind ditch to prevent natural rainfall; S15, soil moisture penetrates the capillaries in the ridges and fields, and discharges the soil salt components to the branch irrigation blind ditch, then to the main irrigation blind ditch, and finally to the strong drainage water collection well; S16, fill the branch irrigation blind ditch with clean saltpeter, and backfill the soil dug out of the branch irrigation blind ditch to make it level; S17, dig sand holes at intervals from the surface of the main blind ditch to the saltpeter layer of the ditch; S18. To ensure smooth water flow between the branch sprinkler blind ditch and the main sprinkler blind ditch and between the main sprinkler blind ditch and the water collection well, the slopes of the branch sprinkler blind ditch, the main sprinkler blind ditch, the main sprinkler blind ditch and the water collection well are pre-set.

[0009] Preferably, the construction size of the main sprinkler blind ditch is 0.4m×0.8m, the construction size of the branch sprinkler blind ditch is 0.4m×0.4m, and the main sprinkler blind ditch intersects the branch sprinkler blind ditch vertically, and the depth of the main sprinkler blind ditch is 0.5m-0.8m, and the depth of the branch sprinkler blind ditch is 0.2m-0.4m.

[0010] Preferably, using detection equipment to collect soil environmental parameters in each area of ​​the ecological environment and uploading the encrypted soil environmental parameters to a cloud server of the cloud platform includes the following steps: S21. Determine the best placement location for the testing equipment based on the topography, soil type, expected water flow and environmental conditions of the working section in the ecological environment area; S22, evenly distribute the detection equipment at the best placement position in each working section, and according to the actual detection range of the equipment and the layout of the working section, make each device redundantly cover a part of the range of the surrounding working section; S23, start the detection equipment of each working section, and collect soil environmental parameters such as soil moisture, salinity, temperature and pH in each area through the detection equipment; S24, preprocessing the soil environmental parameters, using the PLPRE algorithm to encrypt the data, and uploading the preprocessed data to the cloud server of the cloud platform.

[0011] Preferably, preprocessing the soil environmental parameters, encrypting the data using the PLPRE algorithm, and uploading the preprocessed data to the cloud server of the cloud platform includes the following steps: S241, preprocessing the collected soil environmental parameters; S242. Generate a pair of public and private keys using the PLPRE algorithm, where the public key is used for encryption and the private key is used for decryption; S243, encrypting using the PLPRE encryption function, inputting the pre-processed soil environmental parameters and the public key, and generating a ciphertext; S244, using the transport layer security protocol to establish a secure connection with the cloud server; S245. Upload the soil environmental parameters encrypted using the PLPRE encryption function to the cloud server.

[0012] Preferably, decrypting and analyzing the encrypted soil environmental parameters and dynamically adjusting the monitoring equipment layout according to the results include the following steps: S31, using a re-encryption function, inputting the encrypted soil environment parameters and the re-encryption key, and generating a ciphertext decrypted by a preset authorized user; S32, the authorized user uses the decryption function to input the re-encrypted soil environment parameters and the private key to obtain the soil environment parameters; S33. Analyze the decrypted soil environmental parameters using machine learning algorithms, and evaluate the health status and quality level of the soil environment in each region by building a prediction model; S34. Based on the evaluation results, combined with chaos optimization algorithm and particle swarm optimization, formulate adaptive adjustment strategies and dynamically adjust the layout of monitored equipment; S35. Re-evaluate and adjust the monitoring strategy based on the adjusted equipment layout and continuous monitoring data; S36. Develop an interactive data visualization interface on the cloud platform to display real-time monitoring data, updated equipment layout and monitoring strategies; Among them, based on the evaluation results, combined with chaos optimization algorithm and particle swarm optimization, an adaptive adjustment strategy is formulated, and the layout of the monitored equipment is dynamically adjusted, including the following steps: S341. Integrate the obtained soil environmental assessment results; S342, setting parameters of chaos optimization algorithm and particle swarm optimization algorithm; S343, using a particle swarm optimization algorithm to generate a corresponding equipment layout plan according to the current equipment layout and soil environment assessment results; S344, introduce chaos optimization algorithm to increase the diversity of the search process, and use nonlinear dynamic characteristics to avoid local optimality in the solution space; S345. Evaluate each generated equipment layout plan, select the optimal equipment layout plan based on the evaluation results, and actually adjust the position of the monitoring equipment according to the plan. Use the machine learning algorithm to analyze the decrypted soil environmental parameters.

[0013] Preferably, the decrypted soil environmental parameters are analyzed using a machine learning algorithm, and by constructing a prediction model, the health status and quality level of the soil environment in each region are evaluated, including the following steps: S331, collecting the decrypted soil environmental parameters of the user, using the soil environmental parameters of soil moisture, salinity, temperature and pH as the input of the BP neural network model, and collecting the corresponding soil quality rating as the output of the BP neural network model; S332, dividing the collected soil environmental parameters into a training set, a validation set and a test set; S333, determining the architecture of the BP neural network model, where the architecture of the BP neural network model includes an input layer, a hidden layer, and an output layer; S334, training the BP neural network model on the training set, and optimizing the parameters of the BP neural network model using the validation set; S335, evaluating the prediction performance of the BP neural network model on the test set, and calculating the prediction error; S336, using the optimized BP neural network model to predict the new decrypted soil environmental parameters to obtain the soil environment assessment results; S337, comparing the predicted results with the actual soil quality rating and calculating the error percentage; S338. Determine the quality grade of the soil based on the error percentage and soil quality rating standards.

[0014] Preferably, using statistical methods to analyze the evaluation results of soil environmental parameters to find out the law of environmental changes includes the following steps: S341, collecting soil environmental assessment results predicted by the BP neural network model and actual soil quality ratings; S342, arranging the collected prediction results and actual ratings in chronological order to form time series data; S343. Preprocess the collected data and then conduct statistical analysis, which includes calculating various descriptive statistics (such as mean, median, standard deviation, etc.), conducting trend analysis and seasonal analysis, and finding out the changing patterns of soil environmental assessment results; S344. Based on the results of statistical analysis, summarize and explain the changing patterns of soil environmental parameters, including the trend and periodicity of the assessment results and the relationship between the changing patterns and soil quality ratings; S345. Organize the results of statistical analysis, summarized patterns and explanations into a report.

[0015] Preferably, deploying drones to patrol a region, obtaining ecological environment information in the region, and uploading the ecological environment information and geographic coordinates to a cloud platform includes the following steps: S41. Deploy drones to patrol the area and collect ecological and environmental information data on terrain and vegetation coverage at each patrol point; S42, transmitting the collected ecological environment information data to the cloud platform via a wireless network, and the ecological environment information data at least includes the geographical coordinates of each patrol point and the environmental information of the current geographical coordinates; S43, pre-processing the ecological environment information data on the cloud platform and storing it in a database; S45. On the map of the cloud platform, the geographical coordinates of the patrol points are used to visualize the ecological environment information data.

[0016] Preferably, based on the soil environmental parameter assessment results, environmental change rules and optimization information for equipment layout, combined with the real-time data of drone patrol, the soil environment change trend is comprehensively analyzed, and a comprehensive improvement plan is generated, and a visual display is performed on the cloud platform, including the following steps: S51. Collect all relevant soil environmental parameter assessment results, environmental change patterns, equipment layout optimization information, real-time ecological environment information collected by drone patrols, and related unstructured text data; S52, preprocessing the unstructured text data, and extracting numerical features of the preprocessed unstructured text data; S53. Use topic modeling techniques to identify themes in numerical features and combine them with structured data for comprehensive analysis to obtain the changing trends of soil environment; S54. Develop a soil improvement plan based on the analysis results and change trends, and visualize it on the cloud platform; S55. Implement soil improvement plans and track the implementation of the soil improvement plans, collect new data regularly, and evaluate the effectiveness of the improvement plans.

[0017] Compared with the prior art, this application has the following beneficial effects: 1. The present invention determines the optimal placement of the detection equipment according to the terrain, soil type, expected water flow and environmental conditions, so that data collection is more accurate and the reliability of the analysis results is improved. By using the PLPRE algorithm to encrypt data, the security of the data transmission process can be guaranteed to prevent the data from being illegally stolen or tampered with. By decrypting and analyzing the encrypted soil environmental parameters, the layout of the monitoring equipment is dynamically adjusted according to the results, so that the monitoring is more precise and efficient. The information is visualized on the cloud platform, which makes the information easier to operate and is convenient for environmental engineers to conduct environmental assessment and improvement design. By finding out the laws of environmental changes, the equipment layout and key areas of key monitoring can be optimized, so that resource allocation is more reasonable and the efficiency of monitoring is improved. By regularly collecting new data, the changes in the soil environment can be continuously tracked to support long-term environmental monitoring and assessment.

[0018] 2. The present invention obtains accurate soil quality rating predictions through the BP neural network model, and uses training sets and validation sets to effectively train and optimize the neural network model to improve its prediction performance. By collecting prediction results and real ratings to form time series data, the changing patterns of soil environmental assessment results are discovered, which helps to predict the future state of the soil environment.

[0019] 3. Through statistical analysis, the present invention can know the trend and periodicity of soil environmental assessment results and their relationship with soil quality rating, obtain changes in soil environment, and organize the results of statistical analysis, summarized rules and explanations into a report, providing decision makers with a detailed soil environmental change report, which helps decision makers make better decisions. According to the error percentage and soil quality rating standards, real-time adjustments and improvements can be made according to actual results, thereby improving the flexibility of soil management.

[0020] 4. The drone in the present invention can patrol a specific area in real time and obtain ecological and environmental information of terrain and vegetation coverage. By uploading the collected data to the cloud platform and visually displaying it, the data can be understood and analyzed more intuitively. By combining the soil environmental parameter evaluation results, environmental change laws and equipment layout optimization information, a comprehensive analysis can be performed to obtain the changing trend of the soil environment. According to the results of the comprehensive analysis, a soil improvement plan with strong pertinence and predictable implementation effect can be formulated. In the process of implementing the improvement plan, data can be collected in real time and the effect of the improvement plan can be evaluated, so as to adjust the improvement plan in real time and improve the improvement effect. By identifying themes in unstructured text data through topic modeling technology, the data can be understood and analyzed more comprehensively.

[0021] 5. In this application, particle swarm optimization and chaos optimization algorithms help determine the optimal equipment layout plan, which can not only maximize the coverage, but also ensure the efficient use of resources, such as reducing unnecessary repeated deployment of equipment, reducing maintenance costs, and adapting adjustment strategies so that the monitoring system can be flexibly adjusted according to real-time data and environmental changes. The introduction of chaos optimization algorithm uses its nonlinear dynamic characteristics to help the algorithm jump out of the local optimum, explore a wider solution space, and increase the possibility of finding the global optimal solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown: Figure 1 It is a flow chart of a method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] According to an embodiment of the present invention, a method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things is provided.

[0025] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the method for comprehensive ecological improvement of drought-waterlogged saline-alkali land based on the dynamic monitoring technology of the Internet of Things in an embodiment of the present invention, the method for comprehensive ecological improvement of drought-waterlogged saline-alkali land includes the following steps: S1. Divide the preset ecological environment areas and install detection equipment in the divided ecological environment areas.

[0026] Optionally, dividing the preset ecological environment area and installing the detection equipment in the divided ecological environment area includes the following steps: S11. Divide the ecological environment area that needs to be improved into several working sections, and install corresponding testing equipment in each working section; S12. Dig a main sprinkling blind ditch and a branch sprinkling blind ditch in the ecological environment area that needs to be improved, and connect the branch sprinkling blind ditch with the main sprinkling blind ditch, wherein the main sprinkling blind ditch is dug in the middle of each working section; S13. Set up a strong drainage water collection well at the tail of the main water blind ditch, and dig several water collection wells; S14. Build ridges on both sides of each main irrigation blind ditch to prevent natural rainfall; S15, soil moisture penetrates the capillaries in the ridges and fields, and discharges the soil salt components to the branch irrigation blind ditch, then to the main irrigation blind ditch, and finally to the strong drainage water collection well; S16, fill the branch irrigation blind ditch with clean saltpeter, and backfill the soil dug out of the branch irrigation blind ditch to make it level; S17, dig sand holes at intervals from the surface of the main blind ditch to the saltpeter layer of the ditch; S18. To ensure smooth water flow between the branch sprinkler blind ditch and the main sprinkler blind ditch and between the main sprinkler blind ditch and the water collection well, the slopes of the branch sprinkler blind ditch, the main sprinkler blind ditch, the main sprinkler blind ditch and the water collection well are pre-set.

[0027] Optionally, the construction size of the main sprinkler blind ditch is 0.4m×0.8m, the construction size of the branch sprinkler blind ditch is 0.4m×0.4m, and the main sprinkler blind ditch intersects the branch sprinkler blind ditch vertically, and the depth of the main sprinkler blind ditch is 0.5m-0.8m, and the depth of the branch sprinkler blind ditch is 0.2m-0.4m.

[0028] It needs to be explained that by dividing the work area and installing monitoring equipment, personalized improvement and management are carried out for different soil environments. The design and layout of the sprinkler blind ditch, the connection method, size and depth of the main sprinkler blind ditch and the branch sprinkler blind ditch can achieve effective drainage and salt removal and improve the physical and chemical properties of the soil. In addition, the setting of forced drainage collection wells and water collection wells can help improve the soil environment, increase soil aeration and permeability, and reduce soil salt content. The preset slope can ensure smooth water flow and prevent water accumulation and soil erosion.

[0029] In addition, the detection equipment includes at least an integrated environmental detection machine, a negative oxygen ion monitor, a hydrological monitor, a water quality monitor and a soil moisture monitoring station.

[0030] Among them, the integrated environmental detection machine and negative oxygen ion monitor are responsible for real-time monitoring of environmental factors such as atmospheric temperature, atmospheric humidity, light intensity, UV index, atmospheric pressure, wind speed, wind direction, rainfall, PM2.5, PM10, and negative oxygen ions.

[0031] Hydrological monitoring instruments and water quality monitoring instruments are responsible for real-time monitoring of water level, flow rate, dissolved oxygen, turbidity, conductivity, ammonia nitrogen, pH value, water temperature and other data, analyzing the concentration and changing trends of water pollutants, and evaluating water quality conditions.

[0032] The soil moisture monitoring station is responsible for real-time monitoring of soil temperature, soil moisture, pH value, EC value, judging plant root growth and evaluating plant drought resistance physiological effects.

[0033] S2. Use detection equipment to collect soil environmental parameters in each area of ​​the ecological environment, and upload the encrypted soil environmental parameters to the cloud server of the cloud platform.

[0034] Optionally, using detection equipment to collect soil environmental parameters in each area of ​​the ecological environment, and uploading the encrypted soil environmental parameters to a cloud server of the cloud platform includes the following steps: S21. Determine the best placement location for the testing equipment based on the topography, soil type, expected water flow and environmental conditions of the working section in the ecological environment area; S22, evenly distribute the detection equipment at the best placement position in each working section, and according to the actual detection range of the equipment and the layout of the working section, make each device redundantly cover a part of the range of the surrounding working section; S23, start the detection equipment of each working section, and collect soil environmental parameters such as soil moisture, salinity, temperature and pH in each area through the detection equipment; S24, preprocessing the soil environmental parameters, using the PLPRE algorithm to encrypt the data, and uploading the preprocessed data to the cloud server of the cloud platform.

[0035] Optionally, preprocessing the soil environmental parameters, encrypting the data using the PLPRE algorithm, and uploading the preprocessed data to a cloud server of the cloud platform includes the following steps: S241, preprocessing the collected soil environmental parameters; S242. Generate a pair of public and private keys using the PLPRE algorithm, where the public key is used for encryption and the private key is used for decryption; S243, encrypting using the PLPRE encryption function, inputting the pre-processed soil environmental parameters and the public key, and generating a ciphertext; S244, using the transport layer security protocol to establish a secure connection with the cloud server; S245. Upload the soil environmental parameters encrypted using the PLPRE encryption function to the cloud server.

[0036] It needs to be explained that in the above-mentioned ecological environment improvement plan, detection equipment is used to collect key soil parameters such as soil moisture, salinity, temperature and pH, and the data is uploaded to the cloud server of the cloud platform to monitor and evaluate the effectiveness of the improvement plan in real time, providing data support for decision-making and optimization. The steps of preprocessing and encrypting data reflect the quality and security of the data. Preprocessing can eliminate noise and outliers and improve the availability and accuracy of data. The use of the PLPRE algorithm ensures the security of data during transmission and prevents data from being tampered with or stolen. In addition, by establishing a secure connection and uploading the encrypted data to the cloud server, secure storage and remote access of data can be achieved, thereby providing efficient and convenient data management and sharing methods.

[0037] S3. Decrypt and analyze the encrypted soil environmental parameters, and dynamically adjust the monitoring equipment layout based on the results.

[0038] Optionally, decrypting and analyzing the encrypted soil environmental parameters and dynamically adjusting the monitoring equipment layout according to the results include the following steps: S31, using a re-encryption function, inputting the encrypted soil environment parameters and the re-encryption key, and generating a ciphertext decrypted by a preset authorized user; S32, the authorized user uses the decryption function to input the re-encrypted soil environment parameters and the private key to obtain the soil environment parameters; S33. Analyze the decrypted soil environmental parameters using machine learning algorithms, and evaluate the health status and quality level of the soil environment in each region by building a prediction model; S34. Based on the evaluation results, combined with chaos optimization algorithm and particle swarm optimization, formulate adaptive adjustment strategies and dynamically adjust the layout of monitored equipment; S35. Re-evaluate and adjust the monitoring strategy based on the adjusted equipment layout and continuous monitoring data; S36. Develop an interactive data visualization interface on the cloud platform to display real-time monitoring data, updated equipment layout and monitoring strategies; The method of formulating an adaptive adjustment strategy based on the evaluation results, combining the chaos optimization algorithm and the particle swarm optimization, and dynamically adjusting the layout of the monitored equipment includes the following steps: S341. Integrate the obtained soil environmental assessment results.

[0039] S342. Setting parameters of the chaos optimization algorithm and the particle swarm optimization algorithm.

[0040] It needs to be explained that soil environmental parameters from different monitoring stations, including soil moisture, pH value, salt content, organic matter content, etc., are collected, soil environmental parameters are cleaned, missing values ​​or outliers are processed to ensure the accuracy of the analysis, and statistical methods are used to identify and extract key features. The key features reflect the main changing trends and regional differences in the soil environment, and the extracted features are integrated into a comprehensive evaluation result.

[0041] Determine the control parameters in the chaos optimization algorithm, such as the type of chaotic mapping (such as Logistic mapping), number of iterations, initial conditions of the system, etc., select the appropriate group size, learning factor (individual learning factor and social learning factor), maximum number of iterations, etc. for the particle swarm optimization algorithm, adjust these parameters through experiments or based on previous empirical data to achieve the best search efficiency and optimization results, and apply the set parameters to the actual optimization process.

[0042] Chaotic optimization algorithm uses the sensitive dependence of chaotic system on initial conditions and ergodic properties to explore the solution space, which can effectively escape from local optimum and find global optimum.

[0043] Particle swarm optimization is a swarm-based optimization technique that optimizes the solution to a problem by simulating the foraging behavior of a flock of birds. Particles search in the solution space and update their positions by tracking the historical optimal positions of individuals and groups.

[0044] S343. Generate a corresponding equipment layout plan based on the current equipment layout and soil environment assessment results using a particle swarm optimization algorithm.

[0045] It needs to be explained that the size of the particle swarm (i.e. the number of particles) is defined; each particle represents a monitoring equipment layout plan, and the position (i.e. the layout of each device in the monitoring area) and speed (i.e. the direction and amplitude of the plan adjustment) of each particle are randomly initialized; a fitness function is designed to evaluate the effect of each particle (layout plan). Based on factors such as coverage, expected accuracy of monitoring data, and cost, the purpose of the fitness function is to quantify the effect of each layout plan.

[0046] In each iteration, the speed and position of each particle are updated according to the individual best historical position (individual extreme value) and the group best historical position (global extreme value). The adjustment parameters include the learning factor, which determines the tendency of the particle to move toward the individual extreme value and the global extreme value. After each iteration, the fitness of the layout scheme corresponding to the current position of all particles is evaluated, and the optimal layout scheme found is recorded and updated. If the current iteration provides a better solution, the global optimal solution is updated, and the number of iterations or fitness threshold is set as the termination condition of the algorithm; once the condition is met, the algorithm stops iterating. After the algorithm is completed, the device layout scheme evaluated as the best is output for actual deployment and use.

[0047] S344. Chaos optimization algorithm is introduced to increase the diversity of the search process and nonlinear dynamic characteristics are used to avoid local optimality in the solution space.

[0048] S345. Evaluate each generated equipment layout plan, select the optimal equipment layout plan based on the evaluation results, and adjust the location of the monitoring equipment according to the plan. Use machine learning algorithms to analyze the decrypted soil environmental parameters. It should be explained that the type of chaotic mapping suitable for this scenario is determined. Commonly used ones include Logistic mapping, Tent mapping, etc., which are selected according to specific needs. An initial value is set for each chaotic variable. The chaotic variable will be used to generate new points in the solution space to help escape the local optimum. During the optimization process, the chaotic variables are periodically used to perturb the particle positions to increase the exploration capability of the solution space. The rules for updating chaotic variables are defined to ensure that the chaotic search can continuously provide new search directions and avoid the algorithm from falling into the local optimum. Changes in the optimization process are tracked, the impact of chaotic perturbations on the search effect is evaluated, and the intensity and frequency of the perturbations are adjusted in a timely manner.

[0049] Set evaluation criteria, such as coverage, data collection accuracy, cost efficiency, etc. Each criterion corresponds to a certain weight. Apply the evaluation criteria to each device layout plan, calculate its score using a predetermined evaluation model, compare the evaluation scores of all plans, and select the plan with the highest score as the final plan. Based on the selected optimal plan, actually adjust the location of the monitoring equipment, including physical re-layout and software configuration updates, monitor the results after implementation, and make necessary adjustments and optimizations based on actual conditions.

[0050] In addition, it should be noted that in the ecological environment improvement plan, the encrypted soil environmental parameters are decrypted and analyzed, and the layout of the monitoring equipment is dynamically adjusted according to the results to further enhance the intelligence and adaptability of the system. By using re-encryption functions and decryption functions, the security of the data is protected, and the original and analyzed soil environmental parameters are obtained at the same time. The above data are deeply analyzed using machine learning and statistical methods to obtain the laws of soil environmental changes. At the same time, it is of great significance to obtain the dynamic changes of the ecological environment, predict future environmental change trends, and formulate corresponding response strategies. According to the analysis results, the layout of the monitoring equipment is dynamically adjusted to monitor environmental changes in key areas more accurately and effectively.

[0051] Optionally, the decrypted soil environmental parameters are analyzed using a machine learning algorithm, and a prediction model is constructed to evaluate the health status and quality level of the soil environment in each region, including the following steps: S331, collecting the decrypted soil environmental parameters of the user, using the soil environmental parameters of soil moisture, salinity, temperature and pH as the input of the BP neural network model, and collecting the corresponding soil quality rating as the output of the BP neural network model; S332, dividing the collected soil environmental parameters into a training set, a validation set and a test set; S333, determining the architecture of the BP neural network model, where the architecture of the BP neural network model includes an input layer, a hidden layer, and an output layer; S334, training the BP neural network model on the training set, and optimizing the parameters of the BP neural network model using the validation set; S335, evaluating the prediction performance of the BP neural network model on the test set, and calculating the prediction error; S336, using the optimized BP neural network model to predict the new decrypted soil environmental parameters to obtain the soil environment assessment results; S337, comparing the predicted results with the actual soil quality rating and calculating the error percentage; S338. Determine the quality grade of the soil based on the error percentage and soil quality rating standards.

[0052] Optionally, using statistical methods to analyze the evaluation results of soil environmental parameters to find out the law of environmental changes includes the following steps: S341, collecting soil environmental assessment results predicted by the BP neural network model and actual soil quality ratings; S342, arranging the collected prediction results and actual ratings in chronological order to form time series data; S343. Preprocess the collected data and then conduct statistical analysis, which includes calculating various descriptive statistics (such as mean, median, standard deviation, etc.), conducting trend analysis and seasonal analysis, and finding out the changing patterns of soil environmental assessment results; S344. Based on the results of statistical analysis, summarize and explain the changing patterns of soil environmental parameters, including the trend and periodicity of the assessment results and the relationship between the changing patterns and soil quality ratings; S345. Organize the results of statistical analysis, summarized patterns and explanations into a report.

[0053] It needs to be explained that machine learning algorithms and statistical methods are used to analyze soil environmental parameters. First, the decrypted soil environmental parameters are deeply learned and predicted through the BP neural network model. The above process includes steps such as data collection, model training, model optimization, model evaluation and prediction. The above process establishes a model for accurately predicting soil quality. According to parameters such as soil moisture, salinity, temperature and pH, the soil quality grade can be quickly evaluated. Then, statistical methods are used to analyze the prediction results, including descriptive statistical analysis, trend analysis and seasonal analysis, to find out the changing patterns of soil environmental assessment results and obtain the relationship between the above patterns and soil quality ratings.

[0054] S4. Deploy drones to patrol the area, obtain ecological and environmental information in the area, and upload the ecological and environmental information and geographic coordinates to the cloud platform.

[0055] Optionally, deploying drones to patrol the area, obtaining ecological environment information of the terrain and vegetation coverage in the area, uploading the ecological environment information and geographic coordinates to the cloud platform, and visually displaying it on the cloud platform includes the following steps: S41. Deploy drones to patrol the area and collect ecological and environmental information data on terrain and vegetation coverage at each patrol point; S42, transmitting the collected ecological environment information data to the cloud platform via a wireless network, and the ecological environment information data at least includes the geographical coordinates of each patrol point and the environmental information of the current geographical coordinates; S43, pre-processing the ecological environment information data on the cloud platform and storing it in a database; S45. On the map of the cloud platform, the geographical coordinates of the patrol points are used to visualize the ecological environment information data.

[0056] It needs to be explained that deploying drones to conduct regional patrols and collect ecological and environmental information is undoubtedly an important way to improve the efficiency and accuracy of environmental monitoring. Drones can quickly and flexibly conduct large-scale environmental patrols and collect ecological and environmental information including terrain, vegetation cover, etc. The above information is key data for improving the ecological environment. Through wireless networks, the collected data can be uploaded to the cloud platform in real time to improve the efficiency of data processing and analysis. Data preprocessing, storage and management are performed on the cloud platform to ensure data security and availability. Finally, on the map of the cloud platform, the geographic coordinates of the patrol points are used to visualize the ecological and environmental information, so that the environmental conditions of each area can be intuitively seen.

[0057] S5. Based on the results of soil environmental parameter assessment, environmental change patterns and optimization information for equipment layout, combined with real-time data from drone patrols, a comprehensive analysis of soil environment change trends is conducted, and a comprehensive improvement plan is generated, which is then visualized on the cloud platform.

[0058] Optionally, based on the soil environmental parameter assessment results, environmental change patterns, and optimization information for equipment layout, combined with real-time data from drone patrols, a comprehensive analysis of soil environmental change trends is conducted, and a comprehensive improvement plan is generated, including the following steps: S51. Collect all relevant soil environmental parameter assessment results, environmental change patterns, equipment layout optimization information, real-time ecological environment information collected by drone patrols, and related unstructured text data; S52, preprocessing the unstructured text data, and extracting numerical features of the preprocessed unstructured text data; S53. Use topic modeling techniques to identify themes in numerical features and combine them with structured data for comprehensive analysis to obtain the changing trends of soil environment; S54. Develop a soil improvement plan based on the analysis results and change trends, and visualize it on the cloud platform; S55. Implement soil improvement plans and track the implementation of the soil improvement plans, collect new data regularly, and evaluate the effectiveness of the improvement plans.

[0059] It needs to be explained that based on the assessment results of soil environmental parameters, environmental change patterns, optimization information of equipment layout and real-time data collected by drone patrols, a comprehensive analysis is conducted and an improvement plan is generated. At the same time, all relevant data and information are collected, including unstructured text data. The unstructured data is then preprocessed and numerical features are extracted. The topic modeling technology is used to find themes in the above features, and a comprehensive analysis is conducted in combination with structured data to obtain the changing trends of the soil environment, the analysis results and changing trends, and a scientific and targeted soil improvement plan is formulated. At the same time, it is visualized on the cloud platform. In the process of implementing the improvement plan, the execution status is continuously tracked, new data is collected, and the effectiveness of the improvement plan is evaluated.

[0060] In summary, with the help of the above technical scheme of the present invention, the present invention determines the optimal placement position of the detection equipment according to the terrain, soil type, expected water flow and environmental conditions, so that data collection is more accurate and the reliability of the analysis results is improved. By using the PLPRE algorithm to encrypt data, the security of the data transmission process can be guaranteed to prevent the data from being illegally stolen or tampered with. By decrypting and analyzing the encrypted soil environmental parameters, the layout of the monitoring equipment is dynamically adjusted according to the results, so that the monitoring is more precise and efficient. The information is visualized on the cloud platform, making the information easier to understand and operate, which is convenient for environmental engineers to perform environmental assessment and improvement design. By finding out the law of environmental changes, the equipment layout and key areas of key monitoring can be optimized, so that resource allocation is more reasonable and the efficiency of monitoring is improved. By regularly collecting new data, the changes in the soil environment can be continuously tracked to support long-term environmental monitoring and assessment. The present invention obtains accurate soil quality rating predictions through the BP neural network model, uses training sets and validation sets to effectively train and optimize the neural network model to improve its prediction performance, and forms time series data by collecting prediction results and real ratings to find the law of changes in soil environmental assessment results, which is helpful for prediction. The state of the soil environment in the future; the present invention knows the trend, periodicity and relationship between the soil environment assessment results and the soil quality rating through statistical analysis, obtains the changes in the soil environment, organizes the results of the statistical analysis, the summarized laws and explanations into a report, and provides a detailed soil environment change report for decision makers, which helps decision makers make better decisions. According to the error percentage and the soil quality rating standard, real-time adjustments and improvements can be made according to the actual results to improve the flexibility of soil management; in the present invention, the drone can patrol a specific area in real time and obtain ecological environment information of the terrain and vegetation coverage. By uploading the collected data to the cloud platform and visually displaying it, the data can be understood and analyzed more intuitively. By combining the soil environment parameter assessment results, the law of environmental changes and the equipment layout optimization information, a comprehensive analysis can be performed to obtain the change trend of the soil environment. According to the results of the comprehensive analysis, a soil improvement plan with strong pertinence and predictable implementation effect can be formulated. In the process of implementing the improvement plan, data can be collected in real time and the effect of the improvement plan can be evaluated, so as to adjust the improvement plan in real time and improve the improvement effect. The theme in the unstructured text data is identified through the theme modeling technology, so that the data can be understood and analyzed more comprehensively.

[0061] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A comprehensive ecological improvement method for drought-waterlogged saline-alkali land based on dynamic monitoring technology of the Internet of Things, characterized in that: The method for comprehensive ecological improvement of drought-waterlogged saline-alkali land comprises the following steps: S1. Divide the preset ecological environment areas and install detection equipment in the divided ecological environment areas; S2. Using detection equipment to collect soil environmental parameters in each area of ​​the ecological environment, and uploading the encrypted soil environmental parameters to the cloud server of the cloud platform; S3. Decrypt and analyze the encrypted soil environmental parameters and dynamically adjust the monitoring equipment layout according to the results; S4. Deploy drones to patrol the area, obtain ecological and environmental information in the area, and upload the ecological and environmental information and geographic coordinates to the cloud platform; S5. Based on the results of soil environmental parameter assessment, environmental change patterns, and optimization information for equipment layout, combined with real-time data from drone patrols, a comprehensive analysis of soil environment change trends is conducted, and a comprehensive improvement plan is generated, which is then visualized on the cloud platform.

2. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 1 is characterized in that: The step of dividing the preset ecological environment area and installing the detection equipment in the divided ecological environment area includes the following steps: S11. Divide the ecological environment area that needs to be improved into several working sections, and install corresponding testing equipment in each working section; S12. Dig a main sprinkling blind ditch and a branch sprinkling blind ditch in the ecological environment area that needs to be improved, and connect the branch sprinkling blind ditch with the main sprinkling blind ditch, wherein the main sprinkling blind ditch is dug in the middle of each working section; S13. Set up a strong drainage water collection well at the tail of the main water blind ditch, and dig several water collection wells; S14. Build ridges on both sides of each main irrigation blind ditch to prevent natural rainfall; S15, soil moisture penetrates the capillaries in the ridges and fields, and discharges the soil salt components to the branch irrigation blind ditch, then to the main irrigation blind ditch, and finally to the strong drainage water collection well; S16, fill the branch irrigation blind ditch with clean saltpeter, and backfill the soil dug out of the branch irrigation blind ditch to make it level; S17, dig sand holes at intervals from the surface of the main blind ditch to the saltpeter layer of the ditch; S18. To ensure smooth water flow between the branch sprinkler blind ditch and the main sprinkler blind ditch and between the main sprinkler blind ditch and the water collection well, the slopes of the branch sprinkler blind ditch, the main sprinkler blind ditch, the main sprinkler blind ditch and the water collection well are pre-set.

3. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 2 is characterized in that: The construction size of the main sprinkler blind ditch is 0.4m×0.8m, and the construction size of the branch sprinkler blind ditch is 0.4m×0.4m. The main sprinkler blind ditch intersects the branch sprinkler blind ditch vertically, and the depth of the main sprinkler blind ditch is 0.5m-0.8m, and the depth of the branch sprinkler blind ditch is 0.2m-0.4m.

4. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 3 is characterized in that: The method of collecting soil environmental parameters in each area of ​​the ecological environment by using the detection equipment and uploading the encrypted soil environmental parameters to the cloud server of the cloud platform includes the following steps: S21. Determine the best placement location for the testing equipment based on the topography, soil type, expected water flow and environmental conditions of the working section in the ecological environment area; S22, evenly distribute the detection equipment at the best placement position in each working section, and according to the actual detection range of the equipment and the layout of the working section, make each device redundantly cover a part of the range of the surrounding working section; S23, start the detection equipment of each working section, and collect soil environmental parameters such as soil moisture, salinity, temperature and pH in each area through the detection equipment; S24, preprocessing the soil environmental parameters, using the PLPRE algorithm to encrypt the data, and uploading the preprocessed data to the cloud server of the cloud platform.

5. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on the Internet of Things dynamic monitoring technology according to claim 4 is characterized in that: The method of preprocessing the soil environmental parameters, encrypting the data using the PLPRE algorithm, and uploading the preprocessed data to the cloud server of the cloud platform includes the following steps: S241, preprocessing the collected soil environmental parameters; S242. Generate a pair of public and private keys using the PLPRE algorithm, where the public key is used for encryption and the private key is used for decryption; S243, encrypting using the PLPRE encryption function, inputting the pre-processed soil environmental parameters and the public key, and generating a ciphertext; S244, using the transport layer security protocol to establish a secure connection with the cloud server; S245. Upload the soil environmental parameters encrypted using the PLPRE encryption function to the cloud server.

6. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 5, characterized in that: Decrypting and analyzing the encrypted soil environmental parameters and dynamically adjusting the monitoring equipment layout according to the results include the following steps: S31, using a re-encryption function, inputting the encrypted soil environment parameters and the re-encryption key, and generating a ciphertext decrypted by a preset authorized user; S32, the authorized user uses the decryption function to input the re-encrypted soil environment parameters and the private key to obtain the soil environment parameters; S33. Analyze the decrypted soil environmental parameters using machine learning algorithms, and evaluate the health status and quality level of the soil environment in each region by building a prediction model; S34. Based on the evaluation results, combined with chaos optimization algorithm and particle swarm optimization, formulate adaptive adjustment strategies and dynamically adjust the layout of monitored equipment; S35. Re-evaluate and adjust the monitoring strategy based on the adjusted equipment layout and continuous monitoring data; S36. Develop an interactive data visualization interface on the cloud platform to display real-time monitoring data, updated equipment layout and monitoring strategy; The method of formulating an adaptive adjustment strategy based on the evaluation results, combining the chaos optimization algorithm and the particle swarm optimization, and dynamically adjusting the layout of the monitored equipment includes the following steps: S341. Integrate the obtained soil environmental assessment results; S342, setting parameters of chaos optimization algorithm and particle swarm optimization algorithm; S343, using a particle swarm optimization algorithm to generate a corresponding equipment layout plan according to the current equipment layout and soil environment assessment results; S344, introduce chaos optimization algorithm to increase the diversity of the search process, and use nonlinear dynamic characteristics to avoid local optimality in the solution space; S345. Evaluate each generated equipment layout plan, select the optimal equipment layout plan based on the evaluation results, and actually adjust the position of the monitoring equipment according to the plan.

7. The method for comprehensive ecological improvement of drought-waterlogged saline-alkali land based on the Internet of Things dynamic monitoring technology according to claim 6 is characterized in that: The method of analyzing the decrypted soil environmental parameters by using a machine learning algorithm and building a prediction model to evaluate the health status and quality level of the soil environment in each region includes the following steps: S331, collecting the decrypted soil environmental parameters of the user, using the soil environmental parameters of soil moisture, salinity, temperature and pH as the input of the BP neural network model, and collecting the corresponding soil quality rating as the output of the BP neural network model; S332, dividing the collected soil environmental parameters into a training set, a validation set and a test set; S333, determining the architecture of the BP neural network model, wherein the architecture of the BP neural network model includes an input layer, a hidden layer, and an output layer; S334, training the BP neural network model on the training set, and optimizing the parameters of the BP neural network model using the validation set; S335, evaluating the prediction performance of the BP neural network model on the test set, and calculating the prediction error; S336, using the optimized BP neural network model to predict the new decrypted soil environmental parameters to obtain the soil environment assessment results; S337, comparing the predicted results with the actual soil quality rating and calculating the error percentage; S338. Determine the quality grade of the soil based on the error percentage and soil quality rating standards.

8. The method for comprehensive ecological improvement of drought-waterlogged saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 7, characterized in that: The method of analyzing the evaluation results of soil environmental parameters using statistical methods to find out the law of environmental changes includes the following steps: S341, collecting soil environmental assessment results predicted by the BP neural network model and actual soil quality ratings; S342, arranging the collected prediction results and actual ratings in chronological order to form time series data; S343, pre-processing the collected data, and then conducting statistical analysis to find out the changing pattern of soil environmental assessment results; S344. Based on the results of statistical analysis, summarize and explain the changing patterns of soil environmental parameters, including the trend and periodicity of the assessment results and the relationship between the changing patterns and soil quality ratings; S345. Organize the results of statistical analysis, summarized patterns and explanations into a report.

9. The method for comprehensive ecological improvement of drought-waterlogged saline-alkali land based on dynamic monitoring technology of the Internet of Things according to claim 1, characterized in that: The deployment of drones to patrol the area, obtain ecological environment information in the area, and upload the ecological environment information and geographic coordinates to the cloud platform includes the following steps: S41. Deploy drones to patrol the area and collect ecological and environmental information data on terrain and vegetation coverage at each patrol point; S42, transmitting the collected ecological environment information data to the cloud platform via a wireless network, and the ecological environment information data at least includes the geographical coordinates of each patrol point and the environmental information of the current geographical coordinates; S43, pre-processing the ecological environment information data on the cloud platform and storing it in a database; S45. On the map of the cloud platform, the geographical coordinates of the patrol points are used to visualize the ecological environment information data.

10. The method for comprehensive ecological improvement of drought, flood and saline-alkali land based on the Internet of Things dynamic monitoring technology according to claim 1, characterized in that: The method of comprehensively analyzing the changing trend of the soil environment based on the soil environmental parameter assessment results, the law of environmental change and the optimization information of the equipment layout, combined with the real-time data of the drone patrol, and generating a comprehensive improvement plan, and visually displaying it on the cloud platform includes the following steps: S51. Collect all relevant soil environmental parameter assessment results, environmental change patterns, equipment layout optimization information, real-time ecological environment information collected by drone patrols, and related unstructured text data; S52, preprocessing the unstructured text data, and extracting numerical features of the preprocessed unstructured text data; S53. Use topic modeling techniques to identify themes in numerical features and combine them with structured data for comprehensive analysis to obtain the changing trends of soil environment; S54. Develop a soil improvement plan based on the analysis results and change trends, and visualize it on the cloud platform; S55. Implement soil improvement plans and track the implementation of the soil improvement plans, collect new data regularly, and evaluate the effectiveness of the improvement plans.

Images