Water-gas interface greenhouse gas flux in-situ monitoring system and monitoring method

Abstract

The embodiment of the invention discloses a water-gas interface greenhouse gas flux in-situ monitoring system and a monitoring method. The system comprises: a sample introduction device module, which is used for alternately collecting gas in water and gas on the surface of a water body; the meteorological sensor and the temperature sensor are respectively used for collecting the air speed, the air pressure, the gas Kelvin temperature and the water body centigrade temperature of the monitoring points; the optical sensor is used for being matched with the sampling device module to alternately detect the contents of CO2, CH4 and N2O in water and the contents of CO2, CH4 and N2O in air on the surface of the water body; the industrial personal computer module is used for controlling the operation of the sampling device module and each sensor; and the calculation module is used for determining the greenhouse gas flux of the water-gas interface according to the collected data. According to the embodiment of the invention, the water-gas interface flux of various greenhouse gases under actual conditions can be accurately monitored.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of gas flux monitoring, and in particular to an in-situ monitoring system and method for greenhouse gas flux at a water-air interface. Background Art

[0002] The monitoring and estimation of long-term changes in greenhouse gas fluxes in water bodies is not only of great significance for the study of the biogeochemical cycles of carbon and nitrogen and global climate change, but can also provide effective data support for predicting the carbon fixation capacity of water bodies on a longer time scale and promoting ecological governance of the water environment.

[0003] At present, the main equipment for observing greenhouse gas emission flux in water bodies is the floating chamber technology on the water surface. It collects greenhouse gases emitted by the surface water in a diffused manner by placing a flux chamber with a sealed top on the surface of the water body and a hole at the bottom. The concentration of the gas to be measured in the flux chamber is measured at regular intervals, and the emission flux of the gas to be measured in the covered water area is calculated based on the rate of change of the concentration over time. Both the static floating chamber method and the dynamic floating chamber method are difficult to distinguish the impact of the wind field on the gas exchange rate at the water-air interface, especially for waters with large water flow velocities, which can easily cause gas flux monitoring errors. For example, patent application CN221350771U discloses a greenhouse gas emission sampling device, which adopts static floating box technology; patent application CN113358426A discloses a collection device and a measurement method for measuring the contribution of endogenous greenhouse gas emissions in shallow water bodies, which adopts fixed closed box technology; both collect greenhouse gases emitted by water bodies, but because the gas released by the water body accumulates continuously in the box, it will greatly change the concentration gradient of the actual water body gas-liquid interface, resulting in changes in the Henry equilibrium of gas-liquid exchange, especially when the gas release of the water body is high, which is easy to cause an underestimate of the gas exchange flux. Patent application CN114354290A discloses a device and method for dynamically measuring the greenhouse gas emission flux of water bodies. Although it overcomes the defects of the water body greenhouse gas emission flux measurement technology represented by the static floating box technology, the closed floating box space destroys the original water-gas interface equilibrium mode, which will cause a huge error between the measured data and the actual data. Patent application CN114689794A discloses a greenhouse gas flux monitoring device and monitoring method for water areas, which uses a disturbance component inserted into the water body to simulate a wind field signal to interfere with the water body fluctuations within the coverage area of ​​the buoyancy tank. However, this agitation destroys the original water environment and water dynamics, and destroys the equilibrium mode of dissolved gases in the water body. The above methods only measure the greenhouse gas flux in the water vapor balancer, while the greenhouse gas flux in the environment is a long-term change. These methods ignore the interference of the external environment (such as artificial turbulence generated by friction with the contacting water body, superimposed on the influence of the water body flow rate, which will cause huge errors in the parameters measured in the balancer, such as water surface atmospheric pressure, saturated water vapor pressure, and equilibrium gas), and have certain limitations.

[0004] Therefore, existing observation equipment, technology and methods are unable to accurately observe changes in greenhouse gas fluxes in water-air two-phase media in water bodies. Summary of the invention

[0005] The embodiments of the present invention provide a system and method for in-situ monitoring of greenhouse gas flux at a water-air interface to solve the above technical problems.

[0006] In a first aspect, an embodiment of the present invention provides an in-situ monitoring system for greenhouse gas flux at a water-air interface, comprising: A sampling device module, used for alternately collecting gas in water and gas on the surface of a water body; wherein, the sampling device module comprises a gas-liquid separator, wherein a waterproof and breathable membrane in the gas-liquid separator divides the gas-liquid separator into a first part for storing liquid and a second part for separating gas; the first part is connected to a water sampling tube and a water inlet of a peristaltic pump; the second part is connected to a first gas collection vacuum pump, and the gas in the first gas collection vacuum pump passes through a gas booster valve and a gas one-way valve and then enters a gas collector; the gas collector is connected to a second gas collection vacuum pump, and the gas outlet of the second gas collection vacuum pump is connected to one end of a three-way solenoid valve, and the other two ends of the three-way solenoid valve are respectively connected to an air inlet and a sample outlet, and the three-way solenoid valve realizes alternate collection of gas in water and gas on the surface of a water body by switching the connecting ports; Meteorological sensors and temperature sensors are used to collect air velocity, air pressure, gas Kelvin temperature, and water temperature in Celsius at the monitoring point respectively; An optical sensor, used to cooperate with the sampling device module to alternately detect the content of CO2, CH4 and N2O in the water, and the content of CO2, CH4 and N2O in the air on the surface of the water body; An industrial computer module, used to control the operation of the sample injection device module and each sensor; A calculation module is used to determine the greenhouse gas flux at the water-air interface based on the collected data.

[0007] In a second aspect, an embodiment of the present invention provides a method for in-situ monitoring of greenhouse gas flux at a water-air interface, which is applied to the above-mentioned in-situ monitoring system for greenhouse gas flux at a water-air interface; The method comprises: The sampling device module is floated and fixed at the water body to be monitored, and the water sampling tube and the water outlet of the peristaltic pump are inserted into the water body; The industrial computer module controls the three-way solenoid valve to connect the gas outlet of the second gas collection vacuum pump with the air inlet, closes the sample outlet, and controls each gas collection vacuum pump to start, extracting the gas in the closed pipeline to form a negative pressure vacuum; After the extraction is completed, the industrial computer module controls the second gas collection vacuum pump to turn off and the peristaltic pump to turn on to collect greenhouse gases in the water; After the collection is completed, the industrial computer module controls the second gas collection vacuum pump to start in sequence, controls the three-way solenoid valve to connect the gas outlet of the second gas collection vacuum pump with the sample outlet, and closes the air inlet, so that the greenhouse gas in the water enters the optical sensor for detection; After the detection is completed, the industrial computer module controls the three-way solenoid valve to connect the air inlet and the sample outlet, closes the outlet of the second gas collection vacuum pump, and controls the second gas collection vacuum pump to be closed, so that the greenhouse gases in the air on the surface of the water body enter the optical sensor for detection; The industrial computer module synchronously collects data from the optical sensor, wind speed sensor and temperature sensor and transmits the data to the calculation module for the calculation module to determine the greenhouse gas flux at the water-air interface.

[0008] In a third aspect, an embodiment of the present invention provides a method for predicting greenhouse gas flux distribution at a water-air interface, comprising: S210, dividing the water area to be monitored into a plurality of grids; S220, taking each grid as a monitoring point, respectively installing the above-mentioned water-air interface greenhouse gas flux in-situ monitoring system, and monitoring the flux of any greenhouse gas at the water-air interface of each grid in real time; and taking the flux of each grid at the same time as a sample to construct a finite sample set; S230, averaging the flux distribution monitored over a period of time, taking multiple extreme value grids and large gradient grids in the averaged flux distribution as multiple initial grids; and constructing a neural network model with the flux of the multiple initial grids at the same time as input and the flux distribution of all grids at the same time as output; S240, training and testing the neural network model using the finite sample set, if the model accuracy does not meet the requirements, clustering the grids whose flux prediction values ​​and monitoring values ​​in the test results differ by more than a set threshold according to their geographical locations, and incorporating the cluster centers into the model input; S250, returning to S240 according to the new neural network model, and repeating the process until the model accuracy meets the requirements; S260. Using a genetic algorithm, select an optimal input grid combination from the input grid set of the final model that can meet the model accuracy requirements and has the least number of grids, and use the optimal model corresponding to the optimal input grid combination to predict the water-air interface flux distribution.

[0009] In summary, the embodiment of the present invention discloses an in-situ monitoring system and method for greenhouse gas flux at a water-air interface, which can achieve the following beneficial effects: 1. Through the specific sampling device module, the gas in the water and the gas on the surface of the water body are alternately collected, and the optical sensor is used to alternately detect the content of two greenhouse gases, methane and nitrous oxide, in the water and air, providing comprehensive data support for the long-term monitoring of greenhouse gas fluxes in inland water bodies; 2. When calculating the gas flux, the correction coefficient of the ideal gas state equation is introduced to take into account the influence of the actual air pressure and temperature of the water interface on the gas flux, so as to obtain more accurate gas flux data; 3. The entire system does not collect water or gas samples, does not change the original water environment, and does not use expensive and complex equipment. It maintains the gas-liquid exchange balance mode of the water body itself, further ensuring that the gas flux data is consistent with the actual situation; 4. The flux distribution prediction method based on the in-situ monitoring system of greenhouse gas flux at the water-air interface, through the combination of partial point monitoring and overall water area prediction, uses as few in-situ monitoring devices of greenhouse gas flux at the water-air interface as possible to obtain the greenhouse gas flux distribution of the entire water area, reduce the number of equipment used in long-term monitoring, improve equipment utilization, and reduce the monitoring cost of greenhouse gas flux. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 is a schematic diagram of an in-situ monitoring system for greenhouse gas flux at a water-air interface provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the installation of an in-situ monitoring device provided by an embodiment of the present invention; Figure 3 is a schematic structural diagram of an in-situ monitoring device provided by an embodiment of the present invention; Figure 4 It is a flow chart of a method for predicting greenhouse gas flux distribution at a water-air interface provided by an embodiment of the present invention; Figure 5 is a schematic diagram of grid division of a water area to be monitored provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0013] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0014] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0015] Figure 1 Schematic diagram of an in-situ monitoring system for greenhouse gas flux at a water-air interface provided by an embodiment of the present invention. Figure 1 As shown, the system includes an in-situ monitoring device and a computing module.

[0016] Figure 2 Schematic diagram of the installation of an in-situ monitoring device provided by an embodiment of the present invention. Figure 2 The in-situ monitoring device mainly includes a floating box, a power supply device module, a sensor assembly, a sampling device module and an industrial computer module.

[0017] Among them, the power supply device module mainly provides power to the on-site monitoring device through the photovoltaic panels above and the batteries under the panels, and the alarm is used to prevent collisions with water vehicles.

[0018] The sampling device module is used to alternately collect gas in the water and gas on the surface of the water. Figure 3The sampling device module includes a gas-liquid separator, a waterproof and breathable membrane is arranged inside the gas-liquid separator, and the waterproof and breathable membrane divides the gas-liquid separator into a first part for storing liquid and a second part for separating gas. The first part is connected to the water sampling tube and the water inlet of the peristaltic pump, and a filter funnel is arranged at the end of the water sampling tube; the second part is connected to the air inlet of the first gas collection vacuum pump, the air outlet of the first gas collection vacuum pump is connected to the gas booster valve and the gas check valve, and the gas output from the air outlet enters the gas collector after passing through the gas booster valve and the gas check valve; the gas collector is connected to the air inlet of the second gas collection vacuum pump, the air outlet of the second gas collection vacuum pump is connected to one end of the three-way solenoid valve, and the other two ends of the three-way solenoid valve are respectively connected to the air inlet and the sample outlet, and the three-way solenoid valve realizes the alternating collection of gas in the water body and gas on the surface of the water body by switching the connecting port.

[0019] Combination Figure 2 ,The meteorological sensor is used to collect the air speed, air pressure and gas Kelvin temperature at the monitoring point, and the temperature sensor is used to collect the water temperature in Celsius.

[0020] The optical sensor cooperates with the sampling device module to alternately detect the content of CO2, CH4 and N2O in water. , and the content of CO2, CH4 and N2O in the air on the surface of the water .

[0021] The industrial computer module is used to control the operation of the sampling device module and each sensor, and the calculation module is used to determine the greenhouse gas flux at the water-air interface according to the collected data.

[0022] In one embodiment, before the system is used, Figure 2 As shown, the floating box can be fixed at the location of the water body to be monitored with reinforced concrete anchor points in the field. By fixing the float and cable adjustment, the filter funnel and the temperature sensor probe of the water body are located 5-10cm below the water surface to obtain the physical and chemical parameters of the surface water body. The transmission signal of the temperature sensor (model PT100) is the water temperature in °C at the monitoring point, the transmission signal of the meteorological sensor (model LufftWS600) The wind speed (unit, m / s), air pressure (unit, Pa) and gas temperature (unit, °K) of the air at the monitoring point, the transmission signal of the optical sensor (model Picarro G2508 or Gasboard-3000GHG) as well as They are the contents of CO2, CH4 and N2O in surface water and air above the water surface (unit: ppm), respectively.

[0023] Furthermore, the filter funnel in the injection device module is to prevent the pipeline from being blocked by debris in the water. The gas-liquid separator and the waterproof breathable membrane are used to separate the gas in the water body. The outlet pipeline of the peristaltic pump extends below the water surface to maintain the original water environment state of the water body. The first gas collection vacuum pump and the second gas collection vacuum pump are driven by the power supply device to perform electric gas collection, and collect and transport the gas by forming a vacuum negative pressure. The gas booster valve is to avoid the small amount of gas affecting the collection of the gas collector, and the gas check valve is to prevent the gas collected by the gas collector from flowing back. The three ports of the three-way solenoid valve are respectively connected to the gas in the water delivered by the outlet of the second gas collection vacuum pump, the air on the surface of the water body delivered by the air inlet, and the optical sensor connected to the sample outlet. By controlling the connection of the three ports, the gas in the water or the air on the surface of the water body can be controlled to be input into the optical sensor respectively. The function of the dryer 6 is to prevent water vapor from entering the air inlet of the optical sensor and affecting the test data quality of greenhouse gases.

[0024] During the use of the system, the industrial computer model controls the operation of the sample injection device module and the optical sensor in the following ways: First, make sure the filter funnel and the outlet of the peristaltic pump are 5-10cm below the water surface.

[0025] Then, the three-way solenoid valve is controlled to connect the outlet channel of the second gas collection vacuum pump with the air inlet channel and close the sample outlet channel. At the same time, the first gas collection vacuum pump and the second gas collection vacuum pump are turned on to extract the existing gas in the closed pipeline to form a negative pressure vacuum.

[0026] After the extraction is completed, the second gas collection vacuum pump is turned off, and the peristaltic pump is turned on at the same time to start collecting greenhouse gases from the surface water. When the pressure gauge on the second gas collection vacuum pump shows that the air pressure in the gas collector is close to atmospheric pressure, the optical sensor and the second gas collection vacuum pump are turned on in sequence, and the three-way solenoid valve is controlled at the same time to connect the outlet channel of the second gas collection vacuum pump with the sample outlet channel and close the air inlet channel, so that the greenhouse gases in the surface water enter the optical sensor and generate stable test data.

[0027] Next, the three-way solenoid valve is controlled to connect the air inlet channel with the sample outlet channel, and the outlet channel of the second gas collection vacuum pump is closed. At the same time, the second gas collection vacuum pump is turned off to allow greenhouse gases in the surface air of the water surface to enter the optical sensor and generate stable test data.

[0028] At the same time, the analysis and test data of the optical sensor, the meteorological sensor data on the water surface, and the temperature sensor data of the surface water are collected in real time, stored, and transmitted to the calculation module through the signal transmitter. The above control process steps are automatically repeated to achieve long-term continuous in-situ monitoring of greenhouse gas fluxes at the water-air interface.

[0029] Furthermore, after receiving the real-time in-situ monitoring data sent by the communication base station, the calculation module (such as the user's computer) determines the greenhouse gas flux per unit time and per unit area at the water-air interface of the water body by the following method: S110. Calculate the solubility of CO2, CH4 and N2O in surface water (Unit, mole·L -1 ·atm -1 ), and the water-gas exchange rate (Unit: cm·h -1 ).

[0030] Optionally, this embodiment calculates the data collected by the meteorological sensor and the temperature sensor to obtain the changes in the CO2, CH4 and N2O fluxes at the water-air interface caused by different physical and chemical effects. The calculation formula is:

[0031] In the formula, is the Kelvin temperature (unit, °K), through Calculated; s is the salinity of the water body (unit, ‰), the value of inland water is 0, and for the ocean or plateau salt lake, a sensor for on-site salt monitoring can be added to collect the salinity signal value s; is the wind speed on the water surface, .

[0032] S120. Calculate the greenhouse gas flux at the water-air interface per unit area and per unit time at the monitoring point (Unit: mg·m -2 ·h -1 ): Optionally, the data collected by the optical sensor can be ,and (unit, ppm) were calculated respectively to obtain the flux of CO2, CH4 and N2O at the water-air interface of the monitored waters. The calculation formula is:

[0033] in, , which is the correction coefficient of the ideal gas state equation, is used to correct the ideal gas equation to the real gas equation, so as to obtain the accurate gas flux at the water interface under the actual air pressure and actual temperature.

[0034] In summary, this embodiment provides an in-situ monitoring system for greenhouse gas flux at a water-air interface, which can achieve the following beneficial effects: 1. Through a specific sampling device module, it is used to alternately collect gases in the water and gases on the surface of the water body, and cooperates with optical sensors to alternately detect the content of two greenhouse gases, methane and nitrous oxide, in the water and air, providing comprehensive data support for the monitoring of greenhouse gas fluxes in inland water bodies; 2. When calculating the gas flux, the correction coefficient of the ideal gas state equation is introduced to take into account the influence of the actual air pressure and temperature of the water interface on the gas flux, so as to obtain more accurate gas flux data; 3. The entire system does not collect water or gas samples, does not change the original water environment, and does not use expensive and complex equipment. It maintains the gas-liquid exchange balance mode of the water body itself, further ensuring that the gas flux data is consistent with the actual situation.

[0035] Based on the above-mentioned in-situ monitoring system of greenhouse gas flux at water-air interface, Figure 4 This is a flow chart of a method for predicting greenhouse gas flux distribution at the water-air interface. This method can predict the greenhouse gas flux distribution of the entire water area through as few monitoring points as possible, thus reducing the number of in-service equipment in long-term monitoring. Figure 4 As shown, the method specifically includes: S210, dividing the water area to be monitored into a plurality of grids.

[0036] Figure 4 Taking a regular rectangle as an example, a plane top view of a water area to be monitored is shown. As shown in the figure, the plane can be divided into multiple grids for zoned monitoring. For irregularly shaped water areas, the division method is similar.

[0037] S220. Each grid is used as a monitoring point, and the above-mentioned water-air interface greenhouse gas flux in-situ monitoring system is installed respectively to monitor the flux of any greenhouse gas at the water-air interface of each grid in real time; and the flux of each grid at the same time is used as a sample to construct a finite sample set.

[0038] Combination Figure 2 , in each grid according to Figure 2 In the manner shown, in-situ monitoring devices are installed respectively to transmit various sensor data collected in real time. Each in-situ monitoring device can share a computing module to calculate the greenhouse gas flux of each grid at each time in real time.

[0039] After monitoring for a period of time, for any greenhouse gas, the greenhouse gas flux of each grid at the same time in the monitoring data is taken as a sample, and multiple samples can be obtained from the data of multiple historical moments to form a finite sample set. The finiteness of the sample set is emphasized here because, for waters with larger areas, the cost of installing a set of in-situ monitoring devices for each grid is very high. Therefore, this embodiment can only achieve sample collection for a limited time while ensuring that all grids have equipment. In subsequent steps, the limited samples will be used to train a prediction model for the greenhouse gas flux distribution, and the flux distribution of the entire water area will be predicted by the monitoring flux of some grids, thereby reducing the number of equipment in service for a long time and reducing the flux monitoring cost of the entire water area.

[0040] S230, averaging the flux distribution monitored over a period of time, taking multiple extreme value grids and large gradient grids in the averaged flux distribution as multiple initial grids; and constructing a neural network model with the flux of the multiple initial grids at the same time as input and the flux distribution of all grids at the same time as output.

[0041] The time period can be selected as a period of time when the wind speed, temperature, etc. are relatively stable. The flux distribution at each moment in the period is taken as a two-dimensional matrix arranged according to the geographical location of the grid (in irregular waters, the grid elements corresponding to the land position are permanently set to 0). The two-dimensional matrices of multiple moments are added and then divided by the number of moments in the period to obtain the average flux distribution in the period. From the average flux distribution, the grids where the extreme points are located and the grids where the gradient of change exceeds the set threshold are selected to form the initial set of input grids of the neural network model. For ease of description, the grids in these initial sets are referred to as initial grids in this embodiment. The reason for selecting these grids is that these grids often represent the key positions where turning points or mutations occur in the flux distribution of the entire water area, and can provide key information for the later prediction of the flux distribution of the entire water area.

[0042] A neural network model is constructed based on the initial set. This embodiment will train the model so that after inputting the greenhouse gas fluxes of these initial grids at the same time, it can output the greenhouse gas flux distribution of all grids at that time. Optionally, the model can use a multi-layer convolutional neural network, and a fully connected layer is connected after the convolutional neural network to generate results of specific dimensions; the dimensions of the input layer and the output layer can be adjusted according to the amount of input data and output data; the number of convolutional layers is greater than 7 layers, and the convolution kernel can use 3´3 to expand or extract data features layer by layer; the fully connected layer is used to connect the dimensions of the last convolutional layer and the output layer.

[0043] S240, using the finite sample set to train and test the neural network model. If the model accuracy does not meet the requirements, the grids in the test results where the difference between the flux prediction value and the monitoring value exceeds a set threshold are clustered according to the geographical location, and each cluster center is included in the model input.

[0044] As mentioned above, the model needs to learn the data relationship between some grid fluxes and all grid fluxes. Due to the large amount of missing grid data, the learning difficulty of the model is very large. In the case of a limited number of samples, the accuracy of the trained model is likely to fail to meet the ideal requirements. For this reason, in the case of poor model accuracy, this embodiment provides more data information for the model by increasing the number of input grids, thereby gradually reducing the learning difficulty.

[0045] In a specific implementation, in order to make full use of limited sample data, model training can be completed through the following steps: Step 1: Divide the finite sample set into a first training set, a second training set and a test set. The first training set and the second training set are used to correspond to and distinguish the two subsequent training stages. The samples in the two training sets can be the same, different or partially the same, and this embodiment does not impose any specific restrictions.

[0046] Step 2: Use the first training set to train the neural network model once, and update the model parameters by minimizing the flux change of adjacent grids during the training. This step corresponds to the first training stage of the model. This stage uses the rules followed by the input data itself to update the model parameters so that the model output has a certain regularity. It can be seen from the above system embodiments that the parameters such as gas concentration and temperature environment used to calculate the flux are continuously changing in space, so the change of greenhouse gas flux along the water-air interface should also be relatively uniform. Therefore, this embodiment updates the model parameters by constraining the flux change of adjacent grids to be minimal, so as to minimize random changes without any rules. Optionally, the following loss function can be constructed:

[0047] in, represents the loss function value, and Represent the grid index along the horizontal and vertical directions respectively, Indicates Line The flux prediction values ​​for the column grid, represents the sum of all grids at the water-air interface (excluding land grids where the flux is permanently 0), Indicates taking the absolute value. The model parameters are updated by minimizing the loss function.

[0048] Step 3: Use the second training set to perform a second training on the model after the first training. In the second training, the model parameters are updated by minimizing the difference between the flux prediction value and the monitoring value of each grid. This step corresponds to the second training stage of the model. In this stage, the actual monitored flux data is used as the true value, and the model output is constrained to continuously approach the true value to perform supervised learning on the model after the first training. Optionally, the following loss function can be constructed:

[0049] in, represents the loss function value, Indicates Line The true value of the flux of the column grid.

[0050] Furthermore, this embodiment also takes into account the situation where some grids have empty true value data due to equipment failure or communication failure. In this case, although the sample data lacks data of some grids, it can still be used for secondary training of the model. It is only necessary to constrain the flux change between the said partial grid and the adjacent grids to be minimized, and the difference between the flux prediction value and the monitoring value of other grids to be minimized in the loss function. Optionally, the following loss function can be constructed for such samples:

[0051] in, represents the loss function value, A two-dimensional index representing the complete grid of data represents the two-dimensional index of the data missing grid, represents the flux prediction value of the corresponding grid, represents the flux monitoring value of the corresponding grid, Represent the weight coefficients respectively. In this way, for samples with complete data, we can use Update network parameters. For samples with missing data, you can use Update network parameters to further avoid waste of sample data.

[0052] The above two training stages first allow the model to learn the rules of the input data itself, and then perform one-to-one supervised training through the true value of each grid. Compared with directly using true value data for supervised training, the training method of this embodiment can accelerate the convergence speed of the model and achieve the best possible training effect using a limited sample set.

[0053] Step 4: After training, use the test set to test the model after the second training. If the model accuracy still does not meet the requirements, the grids whose flux prediction values ​​and monitoring values ​​in the test results differ by more than the set threshold are clustered according to their geographical locations, and the centers of each cluster are included in the model input. This step is aimed at the situation where good model accuracy has not been achieved after two training stages. The grids with large prediction errors are selected from the prediction results of each test sample as the input grids of the model.

[0054] Optionally, if some grids have large errors in multiple test samples, these grids are clustered according to their geographical locations to obtain multiple spatial clusters. Each spatial cluster represents a relatively close area. The grids in this area have repeatedly experienced large measurement errors, indicating that the model cannot effectively learn the data patterns of this area from the existing input grids. Therefore, it is necessary to select one or more grids from this area as model inputs to provide the model with effective information about this area. Optionally, the DBSCAN clustering method can be used to finally select the cluster center of each cluster as the model input.

[0055] Furthermore, when adding new model inputs, you can add convolution kernels connected to the newly added network and subsequent calculation layers in the first convolution layer based on the original model; or add a fully connected layer between the input layer and the first convolution layer to transform the new input layer dimension to the dimension of the original hidden layer; the rest of the structure in the model remains unchanged and inherits the original parameters as the initial parameters.

[0056] S250, returning to S240 according to the new neural network model, and repeating this process until the model accuracy meets the requirements.

[0057] Specifically, the finite sample set is used again to train and test the new neural network model; if the accuracy of the new model still does not meet the requirements, the grids in the test results where the difference between the flux prediction value and the monitoring value exceeds the set threshold are clustered according to the geographical location, and each cluster center is included in the model input to obtain an updated neural network, and then return to S240. This cycle is repeated until the final model accuracy reaches the required index. At this time, the neural network model has enough valid grid data, and based on these data and the change law of the flux itself, it can more accurately predict the flux distribution of the entire water plane. For the sake of distinction and description, the neural network model obtained at this time is called a full model.

[0058] S260. Using a genetic algorithm, select an optimal input grid combination from the input grid set of the full model that can meet the model accuracy requirements and has the least number of grids, and use the optimal model corresponding to the optimal input grid combination to predict the water-air interface flux distribution.

[0059] As mentioned above, in multiple cycles of S240-S250, the model accuracy is improved by continuously increasing the number of input grids. In order to prevent redundancy in the final input grids, this step uses a genetic algorithm to screen the input grids of the full model to remove redundant grids, and realize the flux distribution prediction of the entire water plane with the least model input and the greenhouse gas flux in-situ monitoring system.

[0060] In a specific implementation, the above screening process can be completed in the following manner: Step 1: Construct a chromosome sequence structure of equal length according to the number of grids in the full model input grid set. For example, if the number of input grids of the full model is 15, a vector of length 15 can be constructed as the chromosome sequence structure in the genetic algorithm, where each bit in the vector corresponds to a grid in the input grid set; the numerical bit is 1, which means that the corresponding grid is retained as the input of the neural network model, and 0 means that the corresponding grid is deleted from the input grid of the neural network model.

[0061] Step 2: Generate the current population of the genetic algorithm according to the chromosome sequence structure. Exemplarily, a random initialization method can be used to generate multiple chromosomes to form the current population.

[0062] Step 3: Prune the full model according to each chromosome in the current population, and train the pruned model three times using the finite sample set. Specifically, for a certain chromosome, the grid corresponding to the bit with a value of 0 in the chromosome is deleted from the input grid of the full model, and all branches connecting the first hidden layer in the model with the input grid are deleted to obtain a new model; then, the new model is trained using the finite sample set. This training is referred to as three trainings in this embodiment.

[0063] Step 4: Determine whether the model after three trainings meets the optimal goal. If not, select, cross, and mutate the current population according to the genetic algorithm, select excellent chromosomes from the mutated current population to form a new current population, and return to step 3. Prune the full model according to each chromosome in the new current population, and use the limited sample set to train the pruned model three more times. This cycle is repeated until the model after three trainings finally meets the optimal goal. Among them, the optimal goal is: the accuracy of the model after three trainings meets the requirements, and the model with the least number of input grids has been obtained in the three trainings currently accumulated.

[0064] Optionally, after each chromosome that meets the model accuracy requirements is obtained, the one with the least number of input grids can be selected as the optimal chromosome from all the chromosomes that meet the model accuracy requirements currently accumulated; if the optimal chromosome remains unchanged after three consecutive trainings, it is considered that the model with the least number of input grids has been obtained. Of course, it is also possible to directly iterate to the maximum number of iterations, and after the iteration is terminated, the model with the model accuracy that meets the requirements and the least number of input grids is selected as the optimal model.

[0065] Furthermore, when selecting excellent chromosomes, a fitness function can be constructed according to the variation of the predicted value of the air flux between each input grid in the chromosome; according to the fitness function, excellent chromosomes are selected from the mutated current population to construct a new current population. Optionally, the following fitness function can be constructed:

[0066] in, is the fitness value, Indicates the number of extreme value grids in the flux distribution predicted by the model after three trainings, where the input grid with the current chromosome value of 1 is the extreme value grid. is the two-dimensional index of the input grid whose value is 1 for the current chromosome, represents the flux prediction value of the corresponding grid, Indicates the number of grids with a value of 0 in the current chromosome. Represent weight coefficients respectively. The larger the fitness value, the better the chromosome.

[0067] Through the above fitness function, chromosomes with fewer input grids and input grids covering more extreme grids and large gradient grids (these grids represent key morphological changes in flux distribution) can be preferentially selected to evolve the new current population, which helps to obtain the optimal chromosome and the optimal model as soon as possible.

[0068] Finally, after obtaining the optimal input grid combination, only the water-air interface greenhouse gas flux in-situ monitoring system of each grid in the combination is retained, and the water-air interface greenhouse gas flux in-situ monitoring system of the remaining grids is removed; the gas flux of each target grid is monitored in real time using the remaining system, and the optimal model is input to obtain the real-time flux distribution of all grids. The removed equipment system can be used for flux monitoring ensemble prediction in other waters, improving equipment utilization and reducing the monitoring cost of greenhouse gas flux.

[0069] Furthermore, the above method takes a certain greenhouse gas as an example to illustrate a specific method for predicting the greenhouse gas flux distribution of the entire water area using as few monitoring points as possible. In practical applications, operations S220-S260 can be performed for each greenhouse gas; wherein, when the optimal model corresponding to the optimal input grid combination is used in S260 to predict the water-air interface flux distribution, the optimal input grid combination corresponding to various greenhouse gases is taken as a union, and the water-air interface greenhouse gas flux in-situ monitoring system of each target grid in the union is retained, and the water-air interface greenhouse gas flux in-situ monitoring system of the remaining grids is removed; the greenhouse gas flux of each target grid is monitored in real time using the remaining system, and the optimal model corresponding to each greenhouse gas is input respectively to obtain the real-time greenhouse gas flux distribution of all grids. In this way, the flux distribution of the three greenhouse gases in the entire water area can be predicted using as few monitoring points as possible.

[0070] It should be noted that in the above-mentioned method for predicting greenhouse gas flux distribution at the water-air interface, except for the steps of installing and dismantling the in-situ monitoring system for greenhouse gas flux at the water-air interface, the remaining steps can be automatically executed by electronic equipment.

[0071] In summary, this embodiment provides a method for predicting greenhouse gas flux distribution at a water-air interface, which can achieve the following beneficial effects: 1. By combining partial point monitoring with overall water area prediction, using as few in-situ monitoring devices of greenhouse gas flux at the water-air interface as possible, the greenhouse gas flux distribution of the entire water area can be obtained, the number of devices used for long-term monitoring can be reduced, the utilization rate of equipment can be improved, and the monitoring cost of greenhouse gas flux can be reduced; 2. Since the neural network model needs to learn complex flux distribution rules based on some grids, the learning difficulty is high and the number of samples is limited, it is difficult for the accuracy of the trained model to reach the ideal requirement at one time. In view of this difficulty, in the case of poor model accuracy, this embodiment selectively selects representative grids from areas with large prediction errors as model inputs, and provides more effective information for the model by increasing the number of input grids, thereby gradually reducing the learning difficulty; 3. In view of the limited number of data samples in the entire grid, this embodiment uses multi-stage training to enable the model to first learn the rules of the input data itself, and then conducts one-to-one supervised training through the monitoring values ​​of each grid. Compared with directly using monitoring data for supervised training, this method can accelerate the convergence of the model and achieve the best possible training effect using a limited sample set; 4. For data missing samples caused by some grid equipment or communication failures, this embodiment integrates the flux uniform change and the monitoring value, adopts different loss value calculation methods for different grids, fully utilizes the remaining data information in the sample, and further avoids sample waste; 5. After obtaining a full model including sufficient valid input grids, in order to prevent redundancy in the input grids of the full model, this embodiment uses a genetic algorithm to screen the input grids, remove the redundant grids, and realize the flux distribution prediction of the entire water plane with the minimum model input and the greenhouse gas flux in-situ monitoring system. This can greatly reduce the number of final equipment and reduce the monitoring cost when the water area is large and the flux distribution of each greenhouse gas is predicted.

[0072] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. An in-situ monitoring system for greenhouse gas flux at a water-air interface, characterized in that: include: A sampling device module, used for alternately collecting gas in water and gas on the surface of a water body; wherein, the sampling device module comprises a gas-liquid separator, wherein a waterproof and breathable membrane in the gas-liquid separator divides the gas-liquid separator into a first part for storing liquid and a second part for separating gas; the first part is connected to a water sampling tube and a water inlet of a peristaltic pump; the second part is connected to a first gas collection vacuum pump, and the gas in the first gas collection vacuum pump passes through a gas booster valve and a gas one-way valve and then enters a gas collector; the gas collector is connected to a second gas collection vacuum pump, and the gas outlet of the second gas collection vacuum pump is connected to one end of a three-way solenoid valve, and the other two ends of the three-way solenoid valve are respectively connected to an air inlet and a sample outlet, and the three-way solenoid valve realizes alternate collection of gas in water and gas on the surface of a water body by switching the connecting ports; Meteorological sensors and temperature sensors are used to collect air velocity, air pressure, gas Kelvin temperature, and water temperature in Celsius at the monitoring point respectively; An optical sensor, used to cooperate with the sampling device module to alternately detect the content of CO2, CH4 and N2O in the water, and the content of CO2, CH4 and N2O in the air on the surface of the water body; An industrial computer module, used to control the operation of the sample injection device module and each sensor; A calculation module is used to determine the greenhouse gas flux at the water-air interface based on the collected data.

2. The system according to claim 1, characterized in that Each gas collection vacuum pump is used to form a vacuum negative pressure under electric drive to drive gas collection; The gas boost valve is used to boost the gas pressure to prevent the gas volume from being too small and affecting the collection of the gas collector; The gas one-way valve is used to realize one-way flow of gas and prevent the gas collected by the gas collector from flowing back.

3. A method for in-situ monitoring of greenhouse gas flux at a water-air interface, characterized in that: Applicable to the in-situ monitoring system for greenhouse gas flux at the water-air interface as claimed in claim 1 or 2; The method comprises: The sampling device module is floated and fixed at the water body to be monitored, and the water sampling tube and the water outlet of the peristaltic pump are inserted into the water body; The industrial computer module controls the three-way solenoid valve to connect the gas outlet of the second gas collection vacuum pump with the air inlet, closes the sample outlet, and controls each gas collection vacuum pump to start, extracting the gas in the closed pipeline to form a negative pressure vacuum; After the extraction is completed, the industrial computer module controls the second gas collection vacuum pump to turn off and the peristaltic pump to turn on to collect greenhouse gases in the water; After the collection is completed, the industrial computer module controls the second gas collection vacuum pump to start in sequence, controls the three-way solenoid valve to connect the gas outlet of the second gas collection vacuum pump with the sample outlet, and closes the air inlet, so that the greenhouse gas in the water enters the optical sensor for detection; After the detection is completed, the industrial computer module controls the three-way solenoid valve to connect the air inlet and the sample outlet, closes the outlet of the second gas collection vacuum pump, and controls the second gas collection vacuum pump to be closed, so that the greenhouse gases in the air on the surface of the water body enter the optical sensor for detection; The industrial computer module synchronously collects data from the optical sensor, wind speed sensor and temperature sensor and transmits the data to the calculation module for the calculation module to determine the greenhouse gas flux at the water-air interface.

4. The method according to claim 3, characterized in that The calculation module determines the greenhouse gas flux at the water-air interface by: S110. Calculate the solubility of CO2, CH4 and N2O in water based on air velocity and water temperature in Celsius , and the water-gas exchange rate ; S120. Calculate the greenhouse gas flux per unit area and per unit time at the water-air interface of the monitoring point according to the following formula: : ； in, is the content of CO2, CH4 and N2O in water, is the content of CO2, CH4 and N2O in the air above the water surface, is the gas temperature in Kelvin, is the air pressure; is the correction coefficient of the ideal gas state equation, which is used to correct the ideal gas equation to the real gas equation.

5. A method for predicting greenhouse gas flux distribution at a water-air interface, characterized in that: include: S210, dividing the water area to be monitored into a plurality of grids; S220, taking each grid as a monitoring point, respectively installing the water-air interface greenhouse gas flux in-situ monitoring system as described in claim 1 or 2, and monitoring the flux of any greenhouse gas at the water-air interface of each grid in real time; and taking the flux of each grid at the same time as a sample to construct a finite sample set; S230, averaging the flux distribution monitored over a period of time, and taking multiple extreme value grids and large gradient grids in the averaged flux distribution as multiple initial grids; and constructing a neural network model that takes the fluxes of the multiple initial grids at the same time as input and takes the flux distribution of all grids at the same time as output; S240, training and testing the neural network model using the finite sample set, if the model accuracy does not meet the requirements, clustering the grids whose flux prediction values ​​and monitoring values ​​in the test results differ by more than a set threshold according to their geographical locations, and incorporating the cluster centers into the model input; S250, returning to S240 according to the new neural network model, and repeating the process until the model accuracy meets the requirements; S260. Using a genetic algorithm, select an optimal input grid combination from the input grid set of the final model that can meet the model accuracy requirements and has the least number of grids, and use the optimal model corresponding to the optimal input grid combination to predict the water-air interface flux distribution.

6. The method according to claim 5, characterized in that The method of training and testing the neural network model using the finite sample set includes: Dividing the finite sample set into a first training set, a second training set and a test set; Using the first training set to train the neural network model once, during which model parameters are updated by minimizing flux changes of adjacent grids; The second training set is used to perform a second training on the model after the first training, and in the second training, the model parameters are updated by minimizing the difference between the flux prediction value and the monitoring value of each grid; The test set is used to test the model after secondary training.

7. The method according to claim 6, characterized in that The method of performing a second training on the model after the first training using the second training set, wherein the model parameters are updated by minimizing the difference between the flux prediction value and the monitoring value of each grid in the second training, comprises: If some grids in the samples of the second training set are missing monitoring data, the model parameters are updated in the secondary training by minimizing the flux changes between the partial grids and adjacent grids, and minimizing the difference between the flux prediction value and the monitoring value of other grids.

8. The method according to claim 5, characterized in that The method of using a genetic algorithm to select an optimal input grid combination from the input grid set of the final model that can satisfy the model accuracy requirements and has the least number of grids includes: According to the size of the input grid set of the final model, a chromosome sequence structure of equal length is constructed, wherein each numerical bit in the sequence structure corresponds to each grid in the set one by one, and the 1 / 0 value of the numerical bit represents whether the corresponding grid is used as the input grid of the neural network model; Generating a current population of a genetic algorithm according to the chromosome sequence structure; Pruning the final model according to each chromosome in the current population, and training the pruned model three times using the limited sample set; Determine whether the model after three trainings meets the optimal goal. If not, generate a new current population according to the genetic algorithm and return to the model pruning operation until the model after three trainings meets the optimal goal. The optimal goal is that the model accuracy after three trainings meets the requirements, and a model with the least number of input grids has been obtained in the three trainings conducted so far.

9. The method according to claim 8, characterized in that The generating a new current population according to the genetic algorithm comprises: According to the changing form of the flux prediction value between each input grid in the chromosome, a fitness function is constructed; According to the fitness function, excellent chromosomes are selected from the mutated current population to construct a new current population.

10. The method according to claim 5, characterized in that The method of using the optimal model corresponding to the optimal input grid combination to predict the water-air interface flux distribution includes: Only the water-air interface greenhouse gas flux in-situ monitoring system of each target grid in the optimal input grid combination is retained, and the water-air interface greenhouse gas flux in-situ monitoring system of the remaining grids is removed; The remaining system is used to monitor the gas flux of each target grid in real time, and input into the optimal model to obtain the real-time flux distribution of all grids.

Images