Early warning system and method for real-time water and soil data monitoring

Abstract

The invention belongs to the field of water and soil monitoring, and particularly discloses an early warning system and method for real-time water and soil data monitoring. A processing prediction module; a judgment early warning module; according to the method, comprehensive water and soil data in a monitoring area is monitored, then the collected water and soil data are analyzed, a normal model is established, and the normal model can predict normal water and soil data changes in a short time in the future based on historical normal data; the difference between the normal water and soil data and the real-time water and soil data can be obtained by comparing and calculating the predicted normal water and soil data change with the detected real-time water and soil data, meanwhile, an early warning threshold value is set, when the difference is larger than the early warning threshold value, it is indicated that the water and soil parameter data change at the moment is abnormal, and the early warning threshold value is abnormal. At the moment, early warning information is automatically generated and sent to a user terminal, related personnel are helped to take measures in time, and potential risks such as water and soil loss are reduced.

Description

Technical Field

[0001] The present invention belongs to the field of soil and water monitoring, and in particular relates to an early warning system and method for real-time soil and water data monitoring. Background Art

[0002] Water and soil resources are important components of the ecological environment and are also basic resources for agricultural production, urban and rural construction, and ecological protection. With the intensification of global climate change and the increasing impact of human activities on the ecological environment, the problem of soil and water erosion has become increasingly prominent, seriously threatening food security, ecological security, and sustainable development;

[0003] Soil and water loss monitoring is a systematic observation and assessment of soil and water loss phenomena. Its main purpose is to understand the extent and type of soil and water loss and its impact on the ecological environment.

[0004] However, the traditional method mainly relies on manual sampling and laboratory analysis. The manual sampling cycle is long, the data is not updated in a timely manner, it is difficult to reflect the dynamic changes of water and soil parameters, and it is difficult to achieve real-time monitoring and early warning of abnormal situations. Summary of the invention

[0005] The purpose of the present invention is to provide an early warning system and method for real-time soil and water data monitoring to solve the problems of long traditional manual sampling cycle, untimely data update, and difficulty in achieving real-time monitoring and early warning of abnormal situations.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A real-time soil and water data monitoring early warning system, comprising:

[0008] Data collection module, used to collect real-time soil and water parameters of the soil in the monitoring area;

[0009] A processing prediction module, used for deeply analyzing the real-time water and soil parameters, constructing a normal model, predicting normal water and soil parameters according to the normal model, and identifying the difference between the real-time water and soil parameters and the normal water and soil parameters;

[0010] The judgment warning module is used to preset a warning threshold value, and send a warning message to the user terminal when the difference reaches the warning threshold value.

[0011] Preferably, the data collection module comprises a sensor network, wherein the sensor network comprises a soil moisture sensor, a rainfall sensor and a flow rate sensor;

[0012] The soil moisture sensor is used to collect the moisture of the soil in the monitoring area;

[0013] The rainfall sensor is used to collect rainfall in the monitoring area;

[0014] The flow velocity sensor is used to collect the flow velocity of water in the monitoring area.

[0015] Preferably, the processing prediction module includes a data cleaning unit, a data storage unit, a model building unit, a prediction unit and an anomaly detection unit;

[0016] The data cleaning unit is used to filter the real-time soil and water parameters to remove noise and obtain processed data;

[0017] The data storage unit is used to store the processed data and historical data;

[0018] The model building unit is used to capture the time series characteristics of the historical data, establish the change law of the data under normal circumstances, and train the normal model using the change law of the data under normal circumstances;

[0019] The prediction unit is used to predict normal water and soil parameters through the normal model;

[0020] The anomaly detection unit is used to calculate the difference between the processed data and the normal water and soil parameters.

[0021] Preferably, the warning information includes detailed information of abnormal data, possible causes and suggested countermeasures;

[0022] The abnormal data detailed information is the specific data point where the abnormality occurs and the specific difference between it and the normal model;

[0023] The possible reasons are factors that may cause abnormalities based on statistical analysis of data;

[0024] The suggested countermeasures are targeted suggestions based on abnormal situations.

[0025] Preferably, the data cleaning unit uses the following formula to filter the real-time water and soil parameters:

[0026]

[0027] P k =(1-K k ) k-1

[0028]

[0029] in is the k-th estimated value, i.e. the processed data, is the k-1th estimated value, i.e. the processed data mentioned last time, z k is the kth measurement value, i.e., the real-time soil and water parameters, P kis the k-th estimation error covariance, which represents the covariance of the error between the estimated value and the true value, P k-1 is the k-1th estimation error covariance, K k is the kth Kalman gain, which is used to weigh the predicted value and the measured value, and R is the measurement noise covariance, which indicates the intensity of the real-time water and soil parameter noise;

[0030] Implementation steps:

[0031] Initialize the estimates and error covariance;

[0032] Predict the state estimate and error covariance at the next moment;

[0033] Receive new measurements, perform filtering calculations, and update estimates and error covariances.

[0034] Preferably, the normal model uses the following formula to predict normal water and soil parameters:

[0035]

[0036] Where X t is the value of the time series at time t, c is the constant term, p is the number of autoregressive terms, is the autoregressive coefficient, which indicates the relationship between different lag terms in the time series, q is the number of moving average terms, and θ i is the moving average coefficient, which represents the relationship between different lagged error terms in the time series, ∈ t is the error term, which represents the part that cannot be explained by the model.

[0037] Preferably, the anomaly detection unit uses the following formula to calculate the difference between the processed data and the normal water and soil parameters:

[0038]

[0039] where e t is the difference between the normal water and soil parameters and the processed data, x t is the processed data, are the normal water and soil parameters.

[0040] Preferably, the system also includes a data transmission module, which is used to transmit real-time water and soil parameters to the processing and prediction module via LoRa.

[0041] A real-time soil and water data monitoring early warning method, comprising:

[0042] S1. Collect real-time soil and water parameters of the soil in the monitoring area;

[0043] S2, performing in-depth analysis on the real-time water and soil parameters, constructing a normal model, predicting normal water and soil parameters according to the normal model, and identifying the difference between the real-time water and soil parameters and the normal water and soil parameters;

[0044] S3. Preset a warning threshold, and send a warning message to the user terminal when the difference reaches the warning threshold.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention realizes the monitoring of comprehensive soil and water data in the monitoring area, and then analyzes the collected soil and water data to establish a normal model. The normal model predicts the changes of normal soil and water data in the future within a short period of time based on historical normal data. By comparing and calculating the predicted changes of normal soil and water data with the detected real-time soil and water data, the difference between the normal soil and water data and the real-time soil and water data can be obtained, and an early warning threshold is set at the same time. When the difference is greater than the early warning threshold, it indicates that the changes of soil and water parameter data at this time are abnormal. At this time, early warning information will be automatically generated and sent to the user terminal to help relevant personnel take measures in time to reduce potential risks such as soil erosion. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0048] Figure 1 is a system module block diagram of the present invention;

[0049] Figure 2 The figure is a flowchart of the method steps of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0053] As attached Figure 1 As shown:

[0054] Embodiment 1: This embodiment provides an early warning system for real-time soil and water data monitoring, including:

[0055] Data collection module, used to collect real-time soil and water parameters of the soil in the monitoring area;

[0056] A processing and prediction module is used to conduct in-depth analysis of real-time water and soil parameters, build a normal model, predict normal water and soil parameters based on the normal model, and identify the differences between real-time water and soil parameters and normal water and soil parameters;

[0057] The judgment warning module is used to preset the warning threshold and send warning information to the user terminal when the difference reaches the warning threshold.

[0058] By arranging a sensor network in the monitoring area to collect key water and soil parameters such as soil moisture, rainfall, and flow rate in real time, comprehensive water and soil data monitoring in the monitoring area can be achieved. Then, the collected water and soil data are analyzed to establish a normal model. The normal model will predict the normal water and soil data changes in the future in a short period of time based on historical normal data. By comparing and calculating the predicted normal water and soil data changes with the detected real-time water and soil data, the difference between the normal water and soil data and the real-time water and soil data can be obtained. At the same time, an early warning threshold is set. The early warning threshold can be dynamically adjusted according to the season, weather, and crop production stage, such as analyzing the demand of crops for water and soil resources. When the difference is less than the early warning threshold, it means that the real-time monitored water and soil parameter data is within the normal change range. When the difference is greater than the early warning threshold, it means that the water and soil parameter data changes at this time are abnormal. At this time, an early warning message will be automatically generated and sent to the user terminal to help relevant personnel take timely measures to reduce potential risks such as soil erosion.

[0059] Specifically, the data collection module includes a sensor network, which includes a soil moisture sensor, a rainfall sensor, and a flow rate sensor;

[0060] Soil moisture sensors are used to collect soil moisture in the monitoring area, help assess soil moisture status, and understand crop moisture requirements;

[0061] Precipitation sensors are used to collect rainfall in the monitoring area and provide data support for water management and irrigation regulation;

[0062] The flow velocity sensor is used to collect the flow velocity of water in the monitoring area to determine the flow conditions of the water body and its impact on soil moisture.

[0063] Specifically, the processing prediction module includes a data cleaning unit, a data storage unit, a model building unit, a prediction unit, and an anomaly detection unit;

[0064] The data cleaning unit is used to filter the real-time water and soil parameters, remove noise, obtain processed data, and ensure the accuracy of subsequent analysis by eliminating unnecessary background noise;

[0065] The data storage unit is used to store processed data and historical data, providing a sufficient data basis for model analysis;

[0066] The model building unit is used to capture the time series characteristics of historical data, establish the changing rules of data under normal circumstances, and train the normal model using the changing rules of data under normal circumstances;

[0067] The prediction unit is used to predict normal water and soil parameters through the normal model;

[0068] The anomaly detection unit is used to calculate the difference between the processed data and the normal water and soil parameters.

[0069] Specifically, the warning information includes details of abnormal data, possible causes, and recommended countermeasures;

[0070] Detailed information of abnormal data includes the specific data point where the abnormality occurs and its specific difference compared with the normal model, such as time, location, data value, etc.

[0071] Possible causes are factors that may cause abnormalities based on data statistical analysis, such as excessive rainfall, abnormal soil moisture, and excessively fast water flow.

[0072] The recommended response measures are targeted suggestions based on abnormal situations, such as strengthening monitoring, activating drainage systems, adjusting irrigation plans, etc.

[0073] Specifically, the data cleaning unit uses the following formula to filter the real-time water and soil parameters:

[0074]

[0075] P k =(1-K k ) k-1

[0076]

[0077] in is the k-th estimated value, i.e. the processed data, is the k-1th estimated value, i.e. the data after the last processing, z k is the kth measurement value, i.e., the real-time soil and water parameters, P k is the k-th estimation error covariance, which represents the covariance of the error between the estimated value and the true value, P k-1 is the k-1th estimation error covariance, K k is the kth Kalman gain, which is used to weigh the predicted value and the measured value. R is the measurement noise covariance, which indicates the intensity of the real-time water and soil parameter noise.

[0078] Implementation steps:

[0079] Initialize the estimates and error covariance;

[0080] Predict the state estimate and error covariance at the next moment;

[0081] Receive new measurements, perform filtering calculations, and update estimates and error covariances.

[0082] Specifically, the normal model uses the following formula to predict normal water and soil parameters:

[0083]

[0084] Where X t is the value of the time series at time t, c is the constant term, p is the number of autoregressive terms, is the autoregressive coefficient, which indicates the relationship between different lag terms in the time series, q is the number of moving average terms, and θ i is the moving average coefficient, which represents the relationship between different lagged error terms in the time series, ∈ t is the error term, which represents the part that cannot be explained by the model.

[0085] Specifically, the anomaly detection unit uses the following formula to calculate the difference between the processed data and the normal water and soil parameters:

[0086]

[0087] where e t is the difference between normal water and soil parameters and processed data, x t For processed data, Normal water and soil parameters.

[0088] Specifically, the system also includes a data transmission module, which is used to transmit real-time water and soil parameters to the processing and prediction module through LoRa. LoRa has the advantages of long transmission distance, low power consumption, strong signal penetration, and is suitable for deployment in large-area monitoring areas in the field. It can transmit the collected water and soil parameters to the processing and prediction module in real time, quickly and accurately for processing, thereby improving efficiency and accuracy.

[0089] As attached Figure 2 As shown:

[0090] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that a warning method for real-time soil and water data monitoring includes:

[0091] S1. Collect real-time soil and water parameters of the soil in the monitoring area;

[0092] S2. Conduct in-depth analysis of real-time water and soil parameters, build a normal model, predict normal water and soil parameters based on the normal model, and identify the differences between real-time water and soil parameters and normal water and soil parameters;

[0093] S3. Preset a warning threshold, and send a warning message to the user terminal when the difference reaches the warning threshold.

[0094] Example 3: Using the above-mentioned real-time soil and water data monitoring early warning system and method to monitor and warn a corn field:

[0095] The monitoring area is a cornfield and is currently in the rainy season;

[0096] Step 1: Data Collection:

[0097] The sensor collects the following data:

[0098] Soil moisture: 25% (normally it should be 20%);

[0099] Rainfall: 50mm (normally it should be 20mm);

[0100] Flow rate: 0.5m / s (should be 0.2m / s under normal circumstances);

[0101] Step 2: Data Processing:

[0102] The data cleaning unit performs filtering processing on the data to obtain processed data;

[0103] The model building unit predicts normal soil moisture of 20%, rainfall of 20 mm, and flow velocity of 0.2 m / s;

[0104] The anomaly detection unit calculates the difference:

[0105] Soil moisture difference: 25% to 20% = 5%;

[0106] Rainfall difference: 50mm-20mm=30mm;

[0107] Flow velocity difference: 0.5m / s-0.2m / s=0.3m / s;

[0108] Step 3: Determine the warning:

[0109] Assume that the warning threshold is:

[0110] Soil moisture difference > 3%;

[0111] The rainfall difference is >20 mm;

[0112] Flow velocity difference>0.2m / s;

[0113] Since the soil moisture difference, rainfall difference and flow velocity difference all exceed the threshold, it is judged as abnormal and triggers an early warning;

[0114] Step 4: Send warning information:

[0115] Generate warning information:

[0116] Abnormal data details:

[0117] Time: 10:00 on XX / XX / XXXX;

[0118] Location: Cornfield;

[0119] Soil moisture: 25% (5% difference);

[0120] Rainfall: 50mm (30mm difference);

[0121] Flow rate: 0.5m / s (difference 0.3m / s);

[0122] Possible reasons: excessive rainfall, resulting in excessive soil moisture and excessively fast water flow;

[0123] Recommended response measures: Start drainage systems to prevent waterlogging in fields; strengthen monitoring to prevent flooding;

[0124] The warning information is sent to the user terminal through the MQTT protocol.

[0125] It can identify abnormal situations in a timely manner and trigger early warnings. It can also effectively improve the efficiency and accuracy of soil and water resources management and provide scientific decision-making basis for relevant personnel.

[0126] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0127] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0128] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0129] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time soil and water data monitoring early warning system, characterized in that: include: Data collection module, used to collect real-time soil and water parameters of the soil in the monitoring area; A processing prediction module, used for deeply analyzing the real-time water and soil parameters, constructing a normal model, predicting normal water and soil parameters according to the normal model, and identifying the difference between the real-time water and soil parameters and the normal water and soil parameters; The judgment warning module is used to preset a warning threshold value, and send a warning message to the user terminal when the difference reaches the warning threshold value.

2. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The data collection module includes a sensor network, and the sensor network includes a soil moisture sensor, a rainfall sensor, and a flow rate sensor; The soil moisture sensor is used to collect the moisture of the soil in the monitoring area; The rainfall sensor is used to collect rainfall in the monitoring area; The flow velocity sensor is used to collect the flow velocity of water in the monitoring area.

3. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The processing prediction module includes a data cleaning unit, a data storage unit, a model building unit, a prediction unit and an anomaly detection unit; The data cleaning unit is used to filter the real-time soil and water parameters to remove noise and obtain processed data; The data storage unit is used to store the processed data and historical data; The model building unit is used to capture the time series characteristics of the historical data, establish the change law of the data under normal circumstances, and train the normal model using the change law of the data under normal circumstances; The prediction unit is used to predict normal water and soil parameters through the normal model; The anomaly detection unit is used to calculate the difference between the processed data and the normal water and soil parameters.

4. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The warning information includes detailed information of abnormal data, possible causes and suggested countermeasures; The abnormal data detailed information is the specific data point where the abnormality occurs and the specific difference between it and the normal model; The possible reasons are factors that may cause abnormalities based on statistical analysis of data; The suggested countermeasures are targeted suggestions based on abnormal situations.

5. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The data cleaning unit uses the following formula to filter the real-time water and soil parameters: P k =(1-Kk)Pk-1 in is the k-th estimated value, i.e. the processed data, is the k-1th estimated value, i.e. the processed data mentioned last time, z k is the kth measurement value, i.e., the real-time soil and water parameters, P k is the k-th estimation error covariance, which represents the covariance of the error between the estimated value and the true value, P k-1 is the k-1th estimation error covariance, K k is the kth Kalman gain, which is used to weigh the predicted value and the measured value, and R is the measurement noise covariance, which indicates the intensity of the real-time water and soil parameter noise; Implementation steps: Initialize the estimates and error covariance; Predict the state estimate and error covariance at the next moment; Receive new measurements, perform filtering calculations, and update estimates and error covariances.

6. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The normal model uses the following formula to predict normal water and soil parameters: Where X t is the value of the time series at time t, c is the constant term, p is the number of autoregressive terms, is the autoregressive coefficient, which indicates the relationship between different lag terms in the time series, q is the number of moving average terms, and θ i is the moving average coefficient, which represents the relationship between different lagged error terms in the time series, ∈ t is the error term, which represents the part that cannot be explained by the model.

7. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The anomaly detection unit calculates the difference between the processed data and the normal water and soil parameters using the following formula: where e t is the difference between the normal water and soil parameters and the processed data, x t is the processed data, are the normal water and soil parameters.

8. The early warning system for real-time soil and water data monitoring according to claim 1 is characterized in that: The system also includes a data transmission module, which is used to transmit real-time water and soil parameters to the processing and prediction module via LoRa.

9. A real-time soil and water data monitoring early warning method, characterized in that: include: S1. Collect real-time soil and water parameters of the soil in the monitoring area; S2, performing in-depth analysis on the real-time water and soil parameters, constructing a normal model, predicting normal water and soil parameters according to the normal model, and identifying the difference between the real-time water and soil parameters and the normal water and soil parameters; S3. Preset a warning threshold, and send a warning message to the user terminal when the difference reaches the warning threshold.

Images