A soil environment monitoring and alarming system based on Internet of Things

Abstract

The application relates to the field of intelligent agriculture and environment monitoring technology, in particular to a soil environment monitoring and alarming system based on the Internet of Things; the system comprises a data acquisition module, a first processing module, a second processing module and an alarming module; the data acquisition module is used for acquiring the monitoring values of key indexes of soil in real time; the first processing module is used for determining a soil ecological debt index based on the monitoring values, weight coefficients and reference benchmark values; the second processing module is used for calculating an ecological risk index according to the ecological debt index and a critical alarming threshold value; the alarming module is used for comparing the risk index with grading threshold values, generating and outputting corresponding alarming states; the soil ecological debt index model is constructed, and multiple independent monitoring indexes are fused into a comprehensive index which can directly reflect the overall health condition of soil; the defects that the prior art relies on isolated indexes and is difficult to comprehensively evaluate are overcome; the soil degradation degree is accurately and quantitatively recognized for managers, and the accuracy and scientificity of monitoring are improved.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture and environmental monitoring technology, specifically to a soil environmental monitoring and alarm system based on the Internet of Things. Background Technology

[0002] In the complex engineering practice of saline-alkali land ecological improvement, dynamic monitoring and management of the soil environment are crucial. Currently, the evaluation of improvement effects mainly relies on low-frequency periodic manual sampling and laboratory analysis. Technicians determine the physicochemical state of the soil by analyzing isolated indicators such as soil conductivity, pH value, and organic matter content. However, this method has significant drawbacks. It provides discrete, multi-dimensional data snapshots and lacks a unified quantitative indicator that can comprehensively assess the overall health of the soil ecosystem. The inherent delays in manual sampling and analysis lead to management decisions being based on past conditions, failing to capture the dynamic process of soil degradation in real time, and causing intervention measures to lag significantly. Furthermore, this method cannot quantitatively assess or prospectively predict the risk of irreversible damage to the ecosystem.

[0003] Therefore, how to establish an intelligent monitoring and management system that can achieve real-time comprehensive assessment, quantitative risk warning, and forward-looking intervention decision-making has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a soil environment monitoring and alarm system based on the Internet of Things (IoT). Specifically, the technical solution of this invention includes:

[0005] The data acquisition module is used to acquire monitoring values ​​of key indicators characterizing soil conditions in real time.

[0006] The first processing module is used to determine the soil ecological debt index based on the monitoring value, the preset weight coefficient and the preset reference benchmark value.

[0007] The second processing module is used to calculate the ecological risk index based on the soil ecological debt index and the preset critical alarm threshold.

[0008] The alarm module is used to compare the ecological risk index with the preset first and second level thresholds, and generate and output the corresponding alarm status.

[0009] Preferably, the first processing module is specifically used for:

[0010] Retrieve monitoring values, weighting coefficients, and reference benchmark values;

[0011] By normalizing the monitoring values ​​and linearly combining them with weighting coefficients, the soil ecological debt index is output.

[0012] Preferably, the second processing module is specifically used for:

[0013] Dividing the soil ecological debt index by the critical alarm threshold yields the normalized ecological risk index.

[0014] Preferably, the alarm module is specifically used for:

[0015] When the ecological risk index is not greater than the first level threshold, the alarm status is determined to be a safe status.

[0016] When the ecological risk index is greater than the first level threshold but not greater than the second level threshold, the alarm status will be determined as a warning status.

[0017] When the ecological risk index exceeds the second-level threshold, the alarm status will be determined as an alarm status.

[0018] Preferably, the prediction module is used to integrate historical time series data of the soil ecological debt index with external environmental influencing factors to predict the probability of system collapse at future moments.

[0019] Preferably, the prediction module is specifically used for:

[0020] A basic prediction model for the increase in ecological debt is established based on an autoregressive moving average model with exogenous variables.

[0021] By combining statistical analysis of historical prediction errors, a probability density function for the ecological liability value at future moments is generated through Monte Carlo simulation.

[0022] The probability of system collapse is calculated based on the probability density function.

[0023] Preferably, the decision module is activated when the alarm state is in an alarm state to select and execute the optimal intervention strategy.

[0024] Preferably, the decision module is specifically used for:

[0025] The expected value of the debt increment at the next time step is calculated based on the basic forecasting model;

[0026] When the expected increase in debt exceeds the preset intervention trigger threshold, an optimization process for selecting the optimal intervention strategy is initiated.

[0027] Preferably, when selecting the optimal intervention strategy, the decision-making module is specifically used for:

[0028] For each alternative intervention strategy, quantify the short-term economic costs.

[0029] For each alternative intervention strategy, the prediction module is invoked to calculate the corresponding conditional system collapse probability.

[0030] Based on short-term economic costs, the probability of system collapse, and a pre-set risk aversion coefficient, the generalized total cost of each alternative intervention strategy is calculated.

[0031] The alternative intervention strategy with the lowest generalized total cost is determined as the optimal intervention strategy.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. This invention constructs a soil ecological debt index model, which integrates multiple independent monitoring indicators with different physical dimensions into a comprehensive indicator that can intuitively reflect the overall health status of the soil ecosystem. This overcomes the shortcomings of existing technologies that rely on isolated indicators and are difficult to comprehensively assess, and provides managers with a precise and quantitative understanding of the degree of soil degradation, thereby improving the accuracy and scientific nature of monitoring.

[0034] 2. This invention generates a standardized ecological risk index by comparing the ecological debt index with a threshold representing the critical point of ecosystem collapse, and establishes a three-level response mechanism of safety, early warning, and alarm based on this index. Compared with traditional methods that rely on manual judgment and delayed analysis, this invention realizes automatic risk assessment and timely early warning, and can issue clear warnings to managers before the soil condition deteriorates to an irreversible degree, significantly enhancing the initiative and timeliness of risk prevention and control.

[0035] 3. This invention introduces an ARMAX prediction model that combines historical data with the influence of the external environment, and combines it with Monte Carlo simulation to predict the probability of soil ecosystem collapse at a certain point in the future; this makes monitoring and management no longer limited to the assessment of the current state, but has a forward-looking risk insight capability, realizing a fundamental shift from post-event remediation to pre-event prevention.

[0036] 4. This invention integrates a decision-making module that can weigh short-term economic costs against long-term ecological risks, and automatically selects the optimal intervention strategy by minimizing the generalized total cost function. This overcomes the limitations of traditional decision-making, which relies on subjective experience and is difficult to balance multiple objectives. It provides a scientific and quantitative basis for making management decisions that can control ecological risks and conform to economic rationality under limited resources, and achieves the goal of sustainable improvement. Attached Figure Description

[0037] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0038] Figure 1 This is a structural diagram of the system of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0040] Example 1:

[0041] Please see Figure 1 A soil environment monitoring and alarm system based on the Internet of Things, comprising:

[0042] The data acquisition module is used to acquire monitoring values ​​of key indicators characterizing soil conditions in real time.

[0043] The first processing module is used to determine the soil ecological debt index based on the monitoring value, the preset weight coefficient and the preset reference benchmark value.

[0044] The second processing module is used to calculate the ecological risk index based on the soil ecological debt index and the preset critical alarm threshold.

[0045] The alarm module is used to compare the ecological risk index with the preset first and second level thresholds, and generate and output the corresponding alarm status.

[0046] This invention provides an Internet of Things-based soil environment monitoring and alarm system, comprising a data acquisition module, a first processing module, a second processing module, and an alarm module; the system is deployed in saline-alkali land improvement areas to monitor and assess the health status of the soil environment in real time;

[0047] The data acquisition module acquires real-time monitoring values ​​of n key indicators characterizing soil condition via an IoT sensor network deployed within the improvement zone. Where i = 1, 2, ..., n; this monitoring value The real-time measurement data of the i-th key indicator serves as the basic input for the ecological debt quantification model. These indicators encompass both soil physicochemical and biological indicators; the former includes soil electrical conductivity, pH, and organic matter content, while the latter includes key enzyme activity and microbial biomass carbon. All collected monitoring values... It is transmitted to the system's central processing unit in real time;

[0048] The first processing module transforms the multi-dimensional raw monitoring data with different physical dimensions into a single quantitative indicator that comprehensively reflects the overall degree of soil degradation; this module is based on monitoring values. Preset weighting coefficients and preset reference values Determine the soil ecological debt index Weighting coefficients Let be the dimensionless quantitative value representing the importance of the i-th indicator to the overall soil health. This value is determined using the Analytic Hierarchy Process (AHP) combined with the experience of experts in the field of agricultural ecology, and the sum of all weight coefficients is 1. Reference baseline value The value of the i-th indicator under ideal soil conditions provides a health benchmark for assessing the deviation of monitoring values. This benchmark is derived from national agricultural ecology standards and long-term experimental data analysis for specific improvement areas. This module outputs a dimensionless soil ecological liability index via a specific algorithm. ;

[0049] The second processing module transforms the absolute ecological liability metric into a standardized relative risk level for risk assessment; this module is based on the soil ecological liability index output by the first processing module. Compared with the preset critical alarm threshold Calculate the ecological risk index Critical alarm threshold It is a dimensionless critical threshold that defines the tipping point at which the resilience of soil microbial systems may undergo irreversible collapse. It is derived from in-depth analysis of historical data to identify the ecological liability index that leads to a significant decline in crop yield or a sharp reduction in microbial diversity. The module sets the value and combines it with a safety margin setting; this module achieves this by... and By comparing and calculating, a standardized ecological risk index is obtained. This index visually represents how close the current soil condition is to a critical danger level;

[0050] The alarm module issues clear and tiered warning signals to management personnel based on the assessed risk level; this module also processes the ecological risk index calculated by the second processing module. The alarm status is generated and output by comparing it with the preset first and second level thresholds. The two thresholds are set according to risk management principles, which aim to divide the risk level into different management intervals to trigger corresponding response measures.

[0051] Example 2:

[0052] The first processing module is specifically used for:

[0053] Retrieve monitoring values, weighting coefficients, and reference benchmark values;

[0054] By normalizing the monitoring values ​​and linearly combining them with weighting coefficients, the soil ecological debt index is output.

[0055] This is a further limitation of the system in Example 1. The first processing module integrates multi-dimensional monitoring data into a single debt index, using the following mathematical model.

[0056] To quantify soil ecological liability, the first processing module introduces a soil ecological liability index. The calculation method is as follows:

[0057] ;

[0058] in, The soil ecological debt index is a dimensionless index, calculated using this formula; The total number of key monitoring indicators participating in the calculation is preset according to the system configuration; This is the number for the specific monitoring indicator; The dimensionless weight coefficient of the i-th indicator is preset in the system using the Analytic Hierarchy Process (AHP) combined with expert experience. The real-time monitoring value of the i-th indicator is collected in real time by the data acquisition module; This is the reference benchmark value, or ideal value, for the i-th indicator, which is preset in the system based on agricultural ecology standards and long-term experimental data.

[0059] The technical motivation behind this formula lies in addressing the problem of inconsistent physical dimensions and varying importance to soil health among different monitoring indicators; its underlying logic is that it first calculates each monitoring value through normalization. The deviation rate relative to its ideal benchmark eliminates the dimensional influence of the original data; specifically, normalization is based on the reference benchmark value. To determine whether the value is zero, the following conditional logic is used:

[0060] When the reference value When, the deviation rate is calculated as ;

[0061] When the reference value When, the deviation rate is calculated as ,in This is the upper limit allowed for this indicator;

[0062] By linearly combining the deviation rates of all indicators with preset weighting coefficients, the deviation rates of all indicators are integrated into a single, dimensionless index; this design enables a comprehensive and complete reflection of the overall degree of soil degradation.

[0063] Example 3:

[0064] The second processing module is specifically used for:

[0065] Dividing the soil ecological debt index by the critical alarm threshold yields the normalized ecological risk index.

[0066] This is a further limitation of the system in Example 1. The second processing module converts the absolute liability value into a relative risk level, using the following standardized conversion logic.

[0067] To standardize the alarm logic, the second processing module incorporates an ecological risk index. The calculation method, the logical basis of this transformation is to convert an absolute measurement value... Transformed into a critical point of danger The relative risk level is calculated as follows:

[0068] ;

[0069] in, This is a dimensionless ecological risk index, calculated using this formula; The soil ecological debt index is calculated in real time by the first processing module and is obtained from the previous steps. The preset dimensionless critical alarm threshold is preset in the system based on historical data analysis and safety margin.

[0070] The technical motivation behind this formula is to establish a unified risk measurement standard to facilitate subsequent tiered alerts; the calculation logic is to use the real-time calculated ecological debt index... As a molecule, the preset critical alarm threshold As the denominator; because and All are dimensionless, and their calculation results It is also dimensionless; its physical meaning is defined as the degree to which the current ecological debt approaches a critical danger state; in this way, the output ecological risk index is... It can be used directly and in a standardized manner to trigger subsequent hierarchical alarm logic.

[0071] Example 4:

[0072] The alarm module is specifically used for:

[0073] When the ecological risk index is not greater than the first level threshold, the alarm status is determined to be a safe status.

[0074] When the ecological risk index is greater than the first level threshold but not greater than the second level threshold, the alarm status will be determined as a warning status.

[0075] When the ecological risk index exceeds the second-level threshold, the alarm status will be determined as an alarm status.

[0076] This further defines the system in Example 1, and the alarm module incorporates an ecological risk index. The risk status classification logic is as follows: Here, the first classification threshold is set to 0.8, and the second classification threshold is set to 1.0. The values ​​of these two thresholds are based on risk management principles, which aim to divide the continuous risk index into three discrete status intervals with clear management implications.

[0077] The judgment logic of the alarm module is as follows:

[0078] when When this happens, the system will determine the current state as safe, display a green safety icon on the system interface, and will not issue an alarm.

[0079] when When the system determines the current state as an early warning state, it issues a primary warning, such as sending a prompt message or displaying a yellow warning icon on the interface, to remind managers to pay attention to the changing trend of the soil condition.

[0080] when When the system determines the current state as an alarm state, it will issue an advanced alarm, such as through audible and visual alarms, sending an emergency notification, and can automatically trigger the intervention decision module.

[0081] Example 5:

[0082] It also includes a prediction module, which integrates historical time-series data of the soil ecological debt index with external environmental influencing factors to predict the probability of system collapse at future moments.

[0083] The prediction module is specifically used for:

[0084] A basic prediction model for the increase in ecological debt is established based on an autoregressive moving average model with exogenous variables.

[0085] By combining statistical analysis of historical prediction errors, a probability density function for the ecological liability value at future moments is generated through Monte Carlo simulation.

[0086] The probability of system collapse is calculated based on the probability density function.

[0087] This is a further extension of the system in Example 1. The system also includes a prediction module to integrate historical time series data of the soil ecological debt index with external environmental influencing factors to predict the probability of system collapse at future moments. The prediction module establishes a basic prediction model for the increase in ecological debt based on an autoregressive moving average model with exogenous variables. Combined with statistical analysis of historical prediction errors, a probability density function for the ecological debt value at future moments is generated through Monte Carlo simulation. Based on this probability density function, the probability of system collapse is calculated.

[0088] To achieve proactive risk management, the forecasting module assesses the future of soil ecosystems based on historical data and future external conditions. The risk of constant collapse;

[0089] The prediction module continuously records and stores the ecological debt index calculated by the first processing module. Historical time series data ;in, This represents the current ecological debt index. for The system calculates the ecological debt index at any given time; simultaneously, it integrates external environmental parameters, primarily weather forecast data for the near future, and quantifies them into a comprehensive, dimensionless external environmental impact factor. ;

[0090] To achieve cumulative trend and probability distribution prediction, the system employs an ARMAX model combined with Monte Carlo simulation; the prediction module establishes a mechanism to predict the increase in ecological debt at the next moment. The basic prediction model is expressed mathematically as follows:

[0091] ;

[0092] in, From Time's up Moment Ecological Debt Index The expected incremental forecast; for Ecological debt index; for Prediction error white noise; The external environmental influencing factors at time t; For model parameters, This refers to the order of the model; to determine the model parameters, historical time series data is required. The calibration dataset, in which, This is a historical dataset for the ecological debt index. For historical datasets of external environmental influencing factors, the model is fitted and calibrated using statistical methods such as least squares or maximum likelihood estimation.

[0093] The probability density function of the future ecological liability value is generated through Monte Carlo simulation; and the historical prediction errors are analyzed. Statistical analysis was performed to determine that it follows a mean of 0 and a variance of . normal distribution By performing extensive random sampling from this error distribution and iterative calculations based on the ARMAX model, a large number of future ecological debt indices can be simulated. Possible evolutionary paths; and the future evolution of these paths. By statistically analyzing the endpoint values ​​at each time point, we can obtain... probability density function ;

[0094] Based on this probability density function, calculate the system collapse probability. That is, in the future At any given time, the ecological debt index Exceeding the critical alarm threshold The probability of; where This is the number of the alternative intervention strategy; it is calculated using the obtained probability density function. In the interval Integrating the results.

[0095] Example 6:

[0096] It also includes a decision module, which is activated when the alarm status is in an alarm state, to select and execute the optimal intervention strategy.

[0097] The decision-making module is specifically used for:

[0098] The expected value of the debt increment at the next time step is calculated based on the basic forecasting model;

[0099] When the expected increase in debt exceeds the preset intervention trigger threshold, an optimization process for selecting the optimal intervention strategy is initiated.

[0100] When selecting the optimal intervention strategy, the decision-making module is specifically used for:

[0101] For each alternative intervention strategy, quantify the short-term economic costs.

[0102] For each alternative intervention strategy, the prediction module is invoked to calculate the corresponding conditional system collapse probability.

[0103] Based on short-term economic costs, the probability of system collapse, and a pre-set risk aversion coefficient, the generalized total cost of each alternative intervention strategy is calculated.

[0104] The alternative intervention strategy with the lowest generalized total cost is determined as the optimal intervention strategy.

[0105] This is a further extension of the system in Example 5. The system also includes a decision module, which is activated when the alarm state is active, to select and execute the optimal intervention strategy. The decision module calculates the expected value of the debt increment at the next moment based on the basic prediction model. When the expected value of the debt increment exceeds the preset intervention trigger threshold, an optimization process for selecting the optimal intervention strategy is initiated. When selecting the optimal intervention strategy, the decision module quantifies the short-term economic cost for each alternative intervention strategy. It calls the prediction module to calculate the corresponding conditional system collapse probability. Based on the short-term economic cost, the conditional system collapse probability, and the preset risk aversion coefficient, it calculates the generalized total cost of each alternative intervention strategy. The alternative intervention strategy with the lowest generalized total cost is determined as the optimal intervention strategy.

[0106] To build a closed loop from prediction to action, when the decision-making module predicts that the risk is accumulating at an accelerated pace, it automatically selects the optimal strategy from multiple alternative intervention strategies to execute.

[0107] The decision-making module has an intervention decision-making trigger mechanism; this module uses the ARMAX basic prediction model to calculate the expected value of the debt increase in the next time step in real time. The system has a preset intervention trigger threshold. This represents the upper limit of the acceptable natural growth rate of ecological debt; when When this indicates that the risk is accumulating rapidly, the system will automatically initiate the selection process for the optimal intervention strategy.

[0108] Once the optimization process is activated, the decision module will solve for a solution that aims to minimize the generalized total cost. Optimization problem;

[0109] For each alternative intervention strategy, the decision-making module quantifies its short-term economic costs. The calculation model is as follows:

[0110] ;

[0111] in, The short-term economic costs, denominated in monetary terms, resulting from the execution of strategy k; The market price per unit of agricultural product; The expected output loss resulting from executing strategy k; The unit price of key resources; The physical quantity of additional critical resource consumption caused by executing strategy k; all parameters are obtained from an external database or a preset model;

[0112] For each alternative intervention strategy, the decision-making module calls the prediction module to calculate the corresponding conditional system collapse probability. ;

[0113] Based on short-term economic costs Conditional system crash probability and the preset risk aversion coefficient Calculate the generalized total cost of each alternative intervention strategy. The decision function is as follows:

[0114] ;

[0115] in, The generalized total cost of implementing intervention strategy k; For short-term economic costs; This is the risk aversion coefficient, and its dimension is monetary units; Given the probability of system collapse, this decision-making logic uses a single cost function to weigh the deterministic short-term economic costs against the uncertain future ecological risks.

[0116] The decision module iterates through all alternative strategies k and calculates their respective... Value, and select to make The minimum strategy is taken as the optimal intervention strategy, and instructions are output for execution.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An Internet of Things based soil environment monitoring alarm system, characterized in that , comprising: a data acquisition module, configured to acquire monitoring values of key indicators representing soil state in real time; a first processing module, configured to determine a soil ecological debt index based on the monitoring values, preset weight coefficients and preset reference benchmark values; a second processing module, configured to calculate an ecological risk index according to the soil ecological debt index and a preset critical alarm threshold; an alarm module, configured to compare the ecological risk index with preset first and second classification thresholds, and generate and output a corresponding alarm state; the first processing module is specifically configured to: call the monitoring values, the weight coefficients and the reference benchmark values; normalize the monitoring values, and perform linear combination with the weight coefficients to output the soil ecological debt index; further comprising: a prediction module, configured to integrate historical time series data of the soil ecological debt index and external environmental influence factors to predict a system collapse probability at a future time; the prediction module is specifically configured to: establish a basic prediction model of the ecological debt increment based on an autoregressive moving average model with exogenous variables; combine statistical analysis of historical prediction errors to generate a probability density function of the ecological debt value at the future time through Monte Carlo simulation; calculate the system collapse probability based on the probability density function; The prediction module establishes a mechanism to predict the increase in ecological debt in the next moment. The basic prediction model is expressed mathematically as follows: ； in, From Time's up Moment Ecological Debt Index The expected incremental forecast; for Ecological debt index; for Prediction error white noise; The external environmental influencing factors at time t; For model parameters, This refers to the order of the model; to determine the model parameters, historical time series data is required. The calibration dataset, in which, This is a historical dataset for the ecological debt index. This is a historical dataset of external environmental influencing factors; further comprising: a decision module, configured to be activated when the alarm state is an alarm state to select and execute an optimal intervention strategy; the decision module is specifically configured to: calculate an expected value of the debt increment at the next time based on the basic prediction model; start an optimization process for selecting the optimal intervention strategy when the expected value of the debt increment exceeds a preset intervention trigger threshold; the decision module is specifically configured to: quantify short-term economic costs for each candidate intervention strategy; invoke the prediction module to calculate corresponding conditional system collapse probabilities for each candidate intervention strategy; calculate generalized total costs of each candidate intervention strategy based on the short-term economic costs, the conditional system collapse probabilities and a preset risk aversion coefficient; determine the candidate intervention strategy with the smallest generalized total cost as the optimal intervention strategy; the decision function is as follows: ； wherein, is the generalized total cost of executing intervention strategy k; is the short-term economic cost; is the risk aversion coefficient, which has the dimension of monetary units; is the conditional system collapse probability.

2. The soil environment monitoring and alarming system based on the Internet of Things according to claim 1, characterized in that the second processing module is specifically configured to: divide the soil ecological debt index by the critical alarm threshold to obtain a normalized ecological risk index.

3. The soil environment monitoring and alarming system based on the Internet of Things according to claim 1, characterized in that the alarm module is specifically configured to: determine the alarm state as a safe state when the ecological risk index is not greater than the first classification threshold; determine the alarm state as a warning state when the ecological risk index is greater than the first classification threshold and not greater than the second classification threshold; determine the alarm state as an alarm state when the ecological risk index is greater than the second classification threshold.

Images