CN116381176B - Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm - Google Patents
Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm Download PDFInfo
- Publication number
- CN116381176B CN116381176B CN202310380483.1A CN202310380483A CN116381176B CN 116381176 B CN116381176 B CN 116381176B CN 202310380483 A CN202310380483 A CN 202310380483A CN 116381176 B CN116381176 B CN 116381176B
- Authority
- CN
- China
- Prior art keywords
- water
- dissolved
- concentration
- monitoring
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 184
- 238000012544 monitoring process Methods 0.000 title claims abstract description 69
- 230000002262 irrigation Effects 0.000 title claims abstract description 50
- 238000003973 irrigation Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 35
- 239000005431 greenhouse gas Substances 0.000 title claims abstract description 27
- 239000007789 gas Substances 0.000 claims abstract description 44
- 230000004907 flux Effects 0.000 claims abstract description 32
- MMDJDBSEMBIJBB-UHFFFAOYSA-N [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] Chemical compound [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] MMDJDBSEMBIJBB-UHFFFAOYSA-N 0.000 claims abstract description 15
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims abstract description 15
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000010276 construction Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 23
- 241000209094 Oryza Species 0.000 claims description 17
- 235000007164 Oryza sativa Nutrition 0.000 claims description 17
- 235000009566 rice Nutrition 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000007667 floating Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000004090 dissolution Methods 0.000 claims description 7
- 239000002352 surface water Substances 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000012800 visualization Methods 0.000 claims description 4
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 claims description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 3
- 101100031807 Rattus norvegicus Paics gene Proteins 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 9
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005188 flotation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000003621 irrigation water Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Food Science & Technology (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a system for monitoring greenhouse gases in a water body of a irrigated area based on a low-cost sensor and an intelligent algorithm, which monitors water environment parameters (flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen and CO) of a pond and a river in the irrigated area in real time 2 Dissolved concentration) and atmospheric environmental parameters (CO 2 Gas concentration), based on water environmental parameters and dissolved N 2 Construction of dissolved N from measured data set of O 2 O intelligent algorithm, and then realizing dissolved N of water environment of irrigation area through greenhouse gas-water gas interface exchange model 2 O and CO 2 And the emission flux is synchronously monitored, and the timing remote control and the dissolved state N of the water quality and the dissolved state N of the irrigation area water ecosystem are realized through an OneNET cloud server 2 O and CO 2 Visual display of the change in discharge flux. The design fully combines the advantages of the sensor technology and the intelligent algorithm, reduces the cost and realizes the rapid and effective irrigation area water ecological system N 2 O and CO 2 Emission assessment.
Description
Technical Field
The invention belongs to the technical field of greenhouse gas monitoring of water bodies in rice crop irrigation areas, relates to a monitoring technology for in-situ rapid quantitative evaluation of water pollution and greenhouse gas emission of non-point sources in the rice crop irrigation areas, and particularly relates to a irrigation area water body greenhouse gas monitoring system based on a low-cost sensor and an intelligent algorithm.
Background
The rice crop irrigation area is a typical multi-water agricultural area in China, and is distributed with a large number of wetland landscapes such as ditches, natural/culture ponds, rivers and the like. The fertilizer utilization rate of rice serving as a irrigated area at the lower reaches of Yangtze river is less than 40%, and a large amount of carbon and nitrogen are lost to the peripheral water body through runoff and converted into dissolved N 2 O and CO 2 And diffuse into the atmosphere through a water-gas interface, so that the loss of agricultural non-point source pollutants causes serious water environment pollution and atmospheric temperature chamber effect. In contrast to point source pollution, non-point source pollution has the characteristics of random and intermittent occurrence, complex mechanism and process, uncertain discharge channels and quantity, variable space-time pollution load, difficult monitoring, simulation and control and the like; these features place higher demands on the frequency and effectiveness of non-point source pollution monitoring.
In field experiments, a person usually carries a measuring instrument to visit a field to collect data, or a sampling device is used for manually sampling the data, and a chemical method is adopted in a laboratory to perform a test, so that the space-time resolution of the collected data is insufficient, and a great deal of manpower, financial resources and material resources are also spent. At present, researchers and enterprises at home and abroad develop different water quality or greenhouse gas on-line monitoring systems. For example, based on advanced technologies such as the Internet of things, big data, cloud computing and the like, and combining with the trace gas monitoring equipment of the Swiss ABB LGR water ecosystem, the water ecosystem N is built 2 O、CO 2 And (5) an emission online real-time monitoring system platform. Danish Unisens corporation developed a water-soluble N 2 And O is a real-time monitoring system. However, at present, automatic on-line monitoring systemThe special language programming is used for realizing communication with the brand sensor, and the cost is high; monitoring devices such as hydrologic, water quality or greenhouse gas emissions that have been deployed today require significant resources, infrastructure and expertise, limiting their deployment in many remote irrigated areas; widely used water environment remote sensing technology is also generally limited by the space-time resolution and weather conditions (cloudiness or raininess).
Disclosure of Invention
The invention aims to solve the existing problems and provides a irrigated area water body greenhouse gas monitoring system based on a low-cost sensor and an intelligent algorithm. The low-cost sensor is a sensor which is cheaper in price and mature in process in the market at present. The low-cost sensor used in the invention comprises a flow sensor, a water temperature sensor, a water depth sensor, a pH sensor, a nitrate nitrogen sensor, an ammonia nitrogen sensor and a water body CO 2 Dissolved concentration sensor and CO 2 A gas concentration sensor.
In order to achieve the above object, the technical scheme of the present invention is as follows:
the irrigation area water body greenhouse gas monitoring system based on the low-cost sensor and the intelligent algorithm sequentially comprises the following steps:
step one: the low-cost sensor monitoring system monitors water environment parameters (flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen, water body CO) of ponds and rivers in the irrigation area in real time 2 Dissolved concentration) and atmospheric environmental parameters (CO 2 Gas concentration);
step two: based on water environment parameters and dissolved N 2 Construction of dissolved N from measured data set of O concentration 2 An O concentration intelligent algorithm;
step three: realizing dissolved state N of water environment of irrigation area through greenhouse gas-water gas interface exchange model 2 O and CO 2 Synchronous emission monitoring;
step four: realizing timing remote control and water quality and dissolved state N of irrigation area water body through OneNET cloud server 2 O and CO 2 Visual display of the change in discharge flux.
The step one is lowThe construction architecture of the cost sensor monitoring system is a plurality of sensor integrated systems capable of realizing synchronous acquisition of free air exchange floating boxes and water-gas environment parameters, the monitoring system adopts a low-cost sensor to continuously monitor water in real time, and the monitored indexes are as follows: flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen and water CO 2 Concentration of dissolved state, CO 2 Gas concentration.
The second dissolution state N 2 The low-cost sensor can measure the indexes including nitrate nitrogen, ammonia nitrogen, pH and water temperature corresponding to the O concentration intelligent algorithm.
Step two, constructing a dissolved state N through a deep neural network model 2 O concentration (N) 2 O disc ) The intelligent algorithm sequentially comprises the following steps:
s1, randomly splitting water quality parameter data in an acquired sample set into a training sample (S, a) and a test sample (T, b) by adopting a tail_test_split () split data set of a Scikit-learn library based on Python, wherein S is the training sample set, a is the training sample data, T is the test sample set, and b is the test sample data;
s2, selecting a ReLU as an activation function in the neural network, comprising 4 layers of intermediate layers, optimizing by using Adam as an optimizer, and taking two indexes of Mean Square Error (MSE) and Mean Absolute Error (MAE) as a depth neural network model precision evaluation standard.
S3, carrying out iterative training on the training set data, and reducing Mean Square Error (MSE) and Mean Absolute Error (MAE) until the requirements are met;
s4, calculating a decision coefficient R of the deep neural network model 2 If R is 2 If the predicted performance of the model meets the requirement, if R is greater than or equal to the set threshold value 2 And if the set parameter is smaller than the set threshold, repeating the steps S1-S3 according to the MSE and the MAE adjustment parameters until the requirements are met.
In step S2, the Mean Square Error (MSE) is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured value of O concentration;
in step S2, the Mean Absolute Error (MAE) is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured value of O concentration;
in step S5, the R 2 Calculated by the following formula:
in the above-mentioned method, the step of,in the dissolved state N 2 The measured O concentration is averaged.
In the second step, the number of samples in the sample set is 100 or more.
In the third step, the greenhouse gas-water gas interface exchange model relates to the dissolved state N 2 The indexes which are corresponding to the O emission and can be measured by the low-cost sensor comprise water temperature, water depth and flow;
the greenhouse gas water gas interface exchange model relates to dissolved CO 2 The low cost sensor can measure the indexes including dissolved state and gaseous state CO corresponding to the emission 2 Concentration, water temperature, water depth, flow;
in the third step, parameters required by the greenhouse gas-water gas interface exchange model are obtained through a low-cost sensor monitoring system, and dissolved state N is obtained through a low-cost sensor monitoring system 2 O discharge fluxCalculated by the following formula:
wherein,is the discharge flux at the water-air interface (ug N/(m) 2 d))；N 2 O disc And N 2 O eqc Respectively dissolved N in surface water 2 O concentration (ug N) 2 O-N L -1 ) And N in the atmosphere 2 Theoretical concentration of O equilibrium (ug N 2 O-N L -1 )；/>Is N 2 O transfer rate (cm/h).
S1, N in formula 2 O eqc The calculation formula of (2) is as follows:
wherein A is i (i=1, 2,3, 4) is constant;is N 2 Molecular weight of N in O; t (T) k Is the water temperature (kelvin), which can be measured by a water temperature sensor; n (N) 2 O airc Is the moon atmosphere N 2 O concentration, comprehensive N according to NOAA/ESRL global monitoring department 2 O data is calculated.
S2, in the formulaThe calculation formula of (2) is as follows:
in the middle ofIs N 2 Schmitt number of O, determined by kinematic viscosity and N 2 The ratio of the O diffusion coefficients is defined, and is dependent on temperature; k (K) 600 Calculated as a function of wind speed, water flow rate < 0.5m/s, or as a function of water depth, flow rate and wind speed, water flow rate > 0.5m/s.
S3, in the formulaThe calculation formula of (2) is as follows:
wherein T is the temperature of river water (0-30 ℃), which can be measured by a water temperature sensor.
S4, K in formula 600 The calculation formula of (2) is as follows:
K 600 ＝3.3(±1.6)+4.3173*T 2 -0.054350*T 3 the water flow speed is less than 0.5m/s
K 600 ＝1.0+1.719*(V/H) 0.5 +2.58*W 10 The water flow speed is more than 0.5m/s
W in the formula 10 This data can be obtained by the local weather bureau for an average wind speed at 10 m; v is the water flow rate (m/s); h is the water depth (m), and these two parameter values can be measured by a flow sensor and a water depth sensor.
Dissolved CO 2 The discharge flux is calculated by the following formula:
wherein,is the discharge flux at the water-air interface (mg C/(m) 2 d))；/>And->Respectively, dissolving CO in surface water 2 Concentration (mg CO) 2 -C L -1 ) And CO in the atmosphere 2 Theoretical concentration of equilibrium (mg CO 2 -C L -1 ) Can be formed by CO in water body 2 Dissolved concentration sensor and CO 2 A gas concentration sensor; />Is CO 2 Transfer speed (cm/h).
The OneNET cloud server in the fourth step can realize a Web control program. The Web control program provides a visual control interface for setting and viewing the state of a user, the user can enter the OnneT webpage end to display and inquire the monitoring data in real time, and the free air of the floating box is replaced by the switching timing of the remote control relay.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to a rapid monitoring method for water greenhouse gas emission in a irrigated area based on a low-cost sensor and an intelligent algorithm, which comprises the steps of collecting required hydrological water quality and atmospheric environmental parameters through the low-cost sensor monitoring system, uploading the acquired hydrological water quality and atmospheric environmental parameters to an OnneT cloud server, and obtaining visual greenhouse gas emission flux in the irrigated area through the intelligent algorithm and a greenhouse gas-water gas interface exchange model. Therefore, the invention not only realizes low-cost monitoring, but also obviously improves the measurement frequency of greenhouse gases in the irrigation areas.
The rapid monitoring method for the greenhouse gas emission of the irrigated area water body based on the low-cost sensor and the intelligent algorithm constructs the deep neural network model through the intelligent algorithm, and compared with other conventional algorithms, the neural network has better adaptability, higher model precision and higher reliability.
Drawings
FIG. 1 shows a water-soluble N in a rice irrigated area according to the present invention 2 O and CO 2 The flow chart of steps of the emission flux calculation method.
FIG. 2 is a schematic diagram of the hardware of the low cost sensor monitoring system of the present invention.
FIG. 3 is a diagram of an on-line system architecture of a low cost sensor monitoring system in accordance with the present invention.
Fig. 4a, b, c, d, e is a diagram showing sensor accuracy verification in the present invention.
FIGS. 5a, b and c are diagrams showing the water-soluble N in a rice irrigated area 2 O concentration, N 2 O and CO 2 Discharge flux daily plot.
FIG. 6 is a diagram showing the water-soluble N in the rice irrigated area according to the present invention 2 O and CO 2 The structure of the discharge flux calculating device is schematically shown.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent.
Referring to FIG. 1, the method comprises the steps of using a pH sensor, a water temperature sensor, a water depth sensor, a flow sensor, a nitrate nitrogen sensor, an ammonia nitrogen sensor and a water body CO 2 Dissolved concentration sensor and CO 2 Low-cost sensor monitoring system composed of gas concentration sensors continuously monitors water body in rice crop irrigation areas because of water body dissolved state N 2 O concentration, N 2 O and CO 2 Chemical and physical correlation between the discharge flux and these sensor measurements has proven significant, so is based on water environmental parameters and dissolved N 2 Construction of dissolved N from measured data set of O concentration 2 O concentration intelligent algorithm, and calculating dissolved state N through a greenhouse gas-water gas interface exchange model based on the obtained parameters 2 O and CO 2 The flux is discharged.
The irrigation area water body greenhouse gas monitoring system based on the low-cost sensor and the intelligent algorithm sequentially comprises the following steps:
step one: low-cost sensor monitoring system real-time monitoring irrigationWater environment parameters (flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen, water body CO) of ponds and rivers in the region 2 Dissolved concentration) and atmospheric environmental parameters (CO 2 Gas concentration).
The built architecture of the low-cost sensor monitoring system is a ' terminal ' system consisting of a plurality of sensors, wherein the sensors can realize the synchronous acquisition of the floating box and the water-gas environmental parameters of free air exchange, and as shown in figure 2, the water quality sensor comprises flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen and water body dissolved CO at the ' terminal 2 A plurality of concentration sensors, CO is placed in the floatation tank 2 The gas concentration sensor is used for carrying out modularized control research on the openable flotation tank and the sensors and realizing the monitoring of water quality and greenhouse gas emission through the Internet of things. The hardware electronic equipment of the low-cost sensor monitoring system comprises a power supply control board, an Arduino Mega2560 main control development board and a GPRS module for network data transmission. The hardware non-electronic equipment comprises a floating box, an anti-tilting anchor, an inflatable inner tube and a waterproof box. Wherein, float case switching control implementation mode does: and (3) inflating the inner tube by using a pump to enable one side of the floating box to leave the water surface, realizing one-time exchange with air outside the box, discharging the air in the inner tube by using a valve, realizing that the floating box completely falls back to the water surface, and carrying out greenhouse gas collection, accumulation and emission flux calculation.
Step two: based on water environment parameters and dissolved N 2 Construction of dissolved N from measured data set of O concentration 2 O concentration intelligent algorithm.
The second dissolution state N 2 The low-cost sensor can measure the indexes including nitrate nitrogen, ammonia nitrogen, pH and water temperature corresponding to the O concentration intelligent algorithm.
Step two, constructing a dissolved state N through a deep neural network model 2 O concentration (N) 2 O disc ) The intelligent algorithm sequentially comprises the following steps:
s1, randomly splitting water quality parameter data in an acquired sample set into a training sample (S, a) and a test sample (T, b) by adopting a tail_test_split () split data set of a Scikit-learn library based on Python, wherein S is the training sample set, a is the training sample data, T is the test sample set, and b is the test sample data;
s2, selecting a ReLU as an activation function in the neural network, comprising 4 layers of intermediate layers, optimizing by using Adam as an optimizer, and taking two indexes of Mean Square Error (MSE) and Mean Absolute Error (MAE) as a depth neural network model precision evaluation standard.
S3, carrying out iterative training on the training set data, and reducing Mean Square Error (MSE) and Mean Absolute Error (MAE) until the requirements are met;
s4, calculating a decision coefficient R of the deep neural network model 2 If R is 2 If the predicted performance of the model meets the requirement, if R is greater than or equal to the set threshold value 2 And if the set parameter is smaller than the set threshold, repeating the steps S1-S3 according to the MSE and the MAE adjustment parameters until the requirements are met.
In step S2, the Mean Square Error (MSE) is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured value of O concentration;
in step S2, the Mean Absolute Error (MAE) is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured value of O concentration;
in step S5, the R 2 Calculated by the following formula:
in the above-mentioned method, the step of,in the dissolved state N 2 The measured O concentration is averaged.
In the second step, the number of samples in the sample set is 100 or more.
MSE, MAE, R of the model constructed during training and during verification 2 As shown in table 1. Table 1 shows the dissolved form N in the present invention 2 O concentration intelligent algorithm precision table.
| MSE | MAE | R 2 | |
| Training set | 0.08 | 0.20 | 0.80 |
| Test set | 0.10 | 0.25 | 0.63 |
Step three: irrigation area water realization through greenhouse gas-water gas interface exchange modelDissolved state N of environment 2 O and CO 2 Emission synchronization monitoring.
The parameters required by the greenhouse gas-water gas interface exchange model are obtained through a low-cost sensor monitoring system, and the greenhouse gas-water gas interface exchange model relates to dissolved N 2 The indexes which are corresponding to the O emission and can be measured by the low-cost sensor comprise water temperature, water depth and flow; the greenhouse gas water gas interface exchange model relates to dissolved CO 2 The low cost sensor can measure the indexes including dissolved state and gaseous state CO corresponding to the emission 2 Concentration, water temperature, water depth, flow. The sensor accuracy verification graph used is shown in fig. 4a, b, c, d, e. Dissolved state N 2 The O-emission flux is calculated by the following formula:
wherein,is the discharge flux at the water-air interface (ug N/(m) 2 d))；N 2 O disc And N 2 O eqc Respectively dissolved N in surface water 2 O concentration (ug N) 2 O-N L -1 ) And N in the atmosphere 2 Theoretical concentration of O equilibrium (ug N 2 O-N L -1 )；/>Is N 2 O transfer rate (cm/h).
S1, N in formula 2 O eqc The calculation formula of (2) is as follows:
wherein A is i (i=1, 2,3, 4) is constant;is N 2 Molecular weight of N in O; t (T) k Is the water temperature (kelvin), which can be measured by a water temperature sensor; n (N) 2 O airc Is the moon atmosphere N 2 O concentration, comprehensive N according to NOAA/ESRL global monitoring department 2 O data is calculated.
S2, in the formulaThe calculation formula of (2) is as follows:
in the middle ofIs N 2 Schmitt number of O, determined by kinematic viscosity and N 2 The ratio of the O diffusion coefficients is defined, and is dependent on temperature; k (K) 600 Calculated as a function of wind speed, water flow rate < 0.5m/s, or as a function of water depth, flow rate and wind speed, water flow rate > 0.5m/s.
S3, in the formulaThe calculation formula of (2) is as follows:
wherein T is the temperature of river water (0-30 ℃), which can be measured by a water temperature sensor.
S4, K in formula 600 The calculation formula of (2) is as follows:
K 600 ＝3.3(±1.6)+4.3173*T 2 -0.054350*T 3 the water flow speed is less than 0.5m/s
K 600 ＝1.0+1.719*(V/H) 0.5 +2.58*W 10 The water flow speed is more than 0.5m/s
W in the formula 10 This data can be obtained by the local weather bureau for an average wind speed at 10 m; v is the flow velocity of the water body(m/s); h is the water depth (m), and these two parameter values can be measured by a flow sensor and a water depth sensor.
Dissolved CO 2 The discharge flux is calculated by the following formula:
wherein,is the discharge flux at the water-air interface (mg C/(m) 2 d))；/>And->Respectively, dissolving CO in surface water 2 Concentration (mg CO) 2 -C L -1 ) And CO in the atmosphere 2 Theoretical concentration of equilibrium (mg CO 2 -C L -1 ) Can be formed by CO in water body 2 Dissolved concentration sensor and CO 2 A gas concentration sensor; />Is CO 2 Transfer speed (cm/h).
Step four: realizing timing remote control and water quality and dissolved state N of irrigation area water body through OneNET cloud server 2 O and CO 2 Visual display of the change in discharge flux.
The low-cost sensor monitoring system online system architecture shown in fig. 3 is designed, and the system architecture consists of the following terminals and cloud terminals: (1) a terminal consisting of a plurality of sensors for synchronously collecting the floating box and the water-gas environment parameters capable of realizing free air exchange; (2) the cloud end for timing remote control of the opening and closing of the floating box and real-time data transmission, storage and display can be realized. The design takes an Arduino Mega2560 controller as a core, adopts a low-cost sensor to collect water quality parameters (flow, water temperature and waterDeep pH, nitrate nitrogen, ammonia nitrogen and CO in water 2 Dissolved concentration) and the atmospheric environmental parameters (CO) in the flotation tank 2 Gas concentration); uploading the dissolved state N to an OneNET cloud server of the Internet of things through GPRS, wherein the dissolved state N is obtained through an intelligent algorithm and a water-air interface exchange model 2 O concentration, N 2 O and CO 2 The discharge flux is visually displayed. The user can enter the OnneT webpage end to display and inquire the monitoring data in real time, and free air replacement of the floating box is realized through the switching timing of the remote control relay.
In the practical application process of the invention, the method comprises the following specific steps:
1. running a low-cost sensor monitoring system, and collecting flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen, gaseous and dissolved CO of a rice-making irrigation area pond and a river 2 Concentration.
2. Taking the parameters of the quality of the nitrate nitrogen and ammonia nitrogen in ponds and rivers in rice irrigated areas as the dissolved N 2 Input information of an O concentration intelligent algorithm.
3. Taking the pH, water temperature, water depth and flow water quality parameters of ponds and rivers in rice irrigated areas as a greenhouse gas water-air interface exchange model for dissolving N 2 Input information of O; dissolving state and gaseous CO of pond and river in rice irrigation area 2 Concentration, pH, water temperature, water depth and flow water-gas environment parameters as a greenhouse gas-water-gas interface exchange model for dissolved CO 2 Is provided.
4. The water body dissolved state N of the rice irrigation area is obtained through the visual display of the OneNET cloud server 2 O concentration, N 2 O and CO 2 The emission flux daily variation time profile is shown in fig. 5a, b, c.
The invention further provides a water body dissolved state N of the rice irrigation area 2 O and CO 2 The discharge flux calculation apparatus, as shown in fig. 6, includes:
the water-gas environment parameter module is used for monitoring water-gas environment parameters of ponds and rivers in the irrigation area in real time by utilizing a low-cost sensor, and comprises flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen, gas and dissolved waterCO in state 2 Concentration;
irrigation area water body dissolved state N 2 O construction module for running dissolved N in step two 2 O concentration intelligent algorithm for water body dissolution state N in irrigation area 2 Calculating the O concentration;
irrigation area water N 2 O and CO 2 The emission monitoring module is used for operating the greenhouse gas-water gas interface exchange model in the third step and dissolving state N in the water body of the irrigation area 2 O and CO 2 Calculating the discharge flux;
the control and visualization module is used for realizing timing remote control and water quality and dissolved state N of the irrigation area water ecosystem by using the OneNET cloud server 2 O and CO 2 Visual display of the change in discharge flux.
Firstly, acquiring the water-gas environment parameters of the water body of the rice irrigation area through a water-gas environment parameter module, and taking the required water quality parameters as the water dissolution state N of the irrigation area 2 Input information of the O construction module, and then operate the irrigation area water body N 2 O and CO 2 Emission monitoring module, which realizes timing remote control and water quality and dissolved state N of rice irrigation area through control and visualization module 2 O and CO 2 Visual display of the change in discharge flux.
Claims (7)
1. A monitoring method of a irrigated area water body greenhouse gas monitoring system based on a low-cost sensor and an intelligent algorithm is characterized by comprising the following steps of: the method comprises the following steps:
step one: the low-cost sensor monitoring system monitors water environment parameters and atmospheric environment parameters of ponds and rivers in the irrigation area in real time;
step two: based on water environment parameters and dissolved N 2 Construction of dissolved N from measured data set of O concentration 2 An O concentration intelligent algorithm;
step three: realizing dissolved state N of water environment of irrigation area through greenhouse gas-water gas interface exchange model 2 O and CO 2 Synchronous emission monitoring;
step four: realizing timing remote control and water quality and dissolved state N of irrigation area water body through OneNET cloud server 2 O and CO 2 Visual display of discharge flux variation;
wherein, the dissolved N is constructed by a deep neural network model 2 O concentration, i.e. N 2 O disc An intelligent algorithm comprising the steps of:
s2.1, randomly splitting water quality parameter data in an acquired sample set into a training sample (S, a) and a test sample (T, b) by adopting a tail_test_split () split data set of a Scikit-learn library based on Python, wherein S is the training sample set, a is the training sample data, T is the test sample set, and b is the test sample data;
s2.2, selecting a ReLU in a neural network as an activation function, wherein the ReLU comprises 4 layers of intermediate layers, optimizing by using Adam as an optimizer, and taking two indexes of a mean square error MSE and a mean absolute error MAE as a model accuracy evaluation standard of the deep neural network;
s2.3, carrying out iterative training on training set data to reduce mean square error MSE and mean absolute error MAE until the requirements are met;
s2.4, calculating a determination coefficient R of the deep neural network model 2 If R is 2 If the predicted performance of the model meets the requirement, if R is greater than or equal to the set threshold value 2 If the value is smaller than the set threshold value, repeating S2.1-S2.3 after adjusting parameters according to MSE and MAE until the requirements are met;
parameters required by a greenhouse gas-water gas interface exchange model are obtained through a low-cost sensor monitoring system, and dissolved state N 2 The O-emission flux is calculated by the following formula:
wherein,is the discharge flux at the water-air interface (ug N/(m) 2 d))；N 2 O disc And N 2 O eqc Respectively dissolved N in surface water 2 O concentration (ug N) 2 O-N L -1 ) And N in the atmosphere 2 Theoretical concentration of O equilibrium (ug N 2 O-N L -1 )；/>Is N 2 O transfer rate (cm/h);
wherein N is 2 O eqc The calculation formula of (2) is as follows:
wherein A is i (i=1, 2,3, 4) is constant;is N 2 Molecular weight of N in O; t (T) k Is the water temperature, which is measured by a water temperature sensor; n (N) 2 O airc Is the moon atmosphere N 2 O concentration, comprehensive N according to NOAA/ESRL global monitoring department 2 O data is calculated;
the calculation formula of (2) is as follows:
in the middle ofIs N 2 Schmitt number of O, determined by kinematic viscosity and N 2 The ratio of the O diffusion coefficients is defined, and is dependent on temperature; k (K) 600 Calculating as a function of wind speed, water flow rate < 0.5m/s, or as a function of water depth, flow rate and wind speed, water flow rate > 0.5m/s;
the calculation formula of (2) is as follows:
wherein T is the temperature of river water of 0-30 ℃, and is measured by a water temperature sensor;
K 600 the calculation formula of (2) is as follows:
K 600 ＝3.3(±1.6)+4.3173*T 2 -0.054350*T 3 the water flow speed is less than 0.5m/s
K 600 ＝1.0+1.719*(V/H) 0.5 +2.58*W 10 The water flow speed is more than 0.5m/s
W in the formula 10 This data is obtained by the local weather bureau for an average wind speed at 10 m; v is the water flow rate (m/s); h is the water depth (m), and these two parameter values are measured by the flow sensor and the water depth sensor;
dissolved CO 2 The discharge flux is calculated by the following formula:
wherein,is the discharge flux at the water-air interface (mg C/(m) 2 d))；/>And->Respectively, dissolving CO in surface water 2 Concentration (mg CO) 2 -C L -1 ) And CO in the atmosphere 2 Theoretical concentration of equilibrium (mg CO 2 -C L -1 ) From water body CO 2 Dissolved concentration sensor and CO 2 A gas concentration sensor; />Is CO 2 Transfer speed (cm/h).
2. The method for monitoring the system for monitoring greenhouse gases in water in irrigation areas based on the low-cost sensor and the intelligent algorithm according to claim 1, wherein the method comprises the following steps: the construction architecture of the low-cost sensor monitoring system is a plurality of sensor integrated systems for realizing synchronous acquisition of floating boxes and water-gas environment parameters of free air exchange, the monitoring system adopts the low-cost sensor to continuously monitor water in real time, and the monitored indexes are as follows: flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen and water CO 2 Concentration of dissolved state, CO 2 Gas concentration.
3. The method for monitoring the system for monitoring greenhouse gases in water in irrigation areas based on the low-cost sensor and the intelligent algorithm according to claim 1, wherein the method comprises the following steps: the mean square error MSE is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured values of O concentration.
4. The method for monitoring the system for monitoring greenhouse gases in water in irrigation areas based on the low-cost sensor and the intelligent algorithm according to claim 1, wherein the method comprises the following steps: the average absolute error MAE is calculated by the following formula:
in the above formula, N is the number of samples in the training sample set, f (x i ) Dissolved N for the ith sample 2 Predicted value of O concentration, y i For dissolved N in the ith sample 2 Measured values of O concentration.
5. The method for monitoring the system for monitoring greenhouse gases in water in irrigation areas based on the low-cost sensor and the intelligent algorithm according to claim 1, wherein the method comprises the following steps: the R is 2 Calculated by the following formula:
in the above-mentioned method, the step of,in the dissolved state N 2 The measured O concentration is averaged.
6. The method for monitoring the system for monitoring greenhouse gases in water in irrigation areas based on the low-cost sensor and the intelligent algorithm according to claim 1, wherein the method comprises the following steps: the OneNET cloud server in the fourth step realizes a Web control program; the Web control program provides a visual control interface for setting and viewing the state of a user, the user enters the OneNET webpage end to display and inquire the monitoring data in real time, and the free air of the floating box is replaced by the switching timing of the remote control relay.
7. A computing device for a monitoring method of a system for monitoring greenhouse gases in a body of water in a irrigated area based on a low cost sensor and an intelligent algorithm as claimed in claim 1, comprising:
the water-gas environment parameter module is used for monitoring water-gas environment parameters of ponds and rivers in the irrigation area in real time by utilizing a low-cost sensor, and comprises flow, water temperature, water depth, pH, nitrate nitrogen, ammonia nitrogen, gaseous and dissolved CO 2 Concentration;
irrigation area water body dissolvingSolution state N 2 O building block for dissolved N 2 O concentration intelligent algorithm for water body dissolution state N in irrigation area 2 Calculating the O concentration;
irrigation area water N 2 O and CO 2 Emission monitoring module for greenhouse gas-water gas interface exchange model for water body dissolution state N in irrigation area 2 O and CO 2 Calculating the discharge flux;
the control and visualization module is used for realizing timing remote control and water quality and dissolved state N of the irrigation area water ecosystem by using the OneNET cloud server 2 O and CO 2 Visual display of discharge flux variation; wherein,
acquiring the water-gas environment parameters of the rice water in the irrigation area through a water-gas environment parameter module, and taking the required water quality parameters as the water dissolution state N of the irrigation area 2 Input information of the O construction module, and then operate the irrigation area water body N 2 O and CO 2 Emission monitoring module, which realizes timing remote control and water quality and dissolved state N of rice irrigation area through control and visualization module 2 O and CO 2 Visual display of the change in discharge flux.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310380483.1A CN116381176B (en) | 2023-04-11 | 2023-04-11 | Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310380483.1A CN116381176B (en) | 2023-04-11 | 2023-04-11 | Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116381176A CN116381176A (en) | 2023-07-04 |
| CN116381176B true CN116381176B (en) | 2024-04-12 |
Family
ID=86980378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310380483.1A Active CN116381176B (en) | 2023-04-11 | 2023-04-11 | Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116381176B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108956876A (en) * | 2018-07-12 | 2018-12-07 | 浙江大学 | A kind of measurement time delay correcting method of flue gas on-line continuous monitoring system |
| RU2690001C1 (en) * | 2017-12-29 | 2019-05-30 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Московский государственный университет имени М.В. Ломоносова" (МГУ) | Method of processing vector signals for pattern recognition based on wavelet analysis |
| CN111537023A (en) * | 2020-05-13 | 2020-08-14 | 浙江大学 | Diffusion simulation and source tracing method for atmospheric pollutants in industrial park |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611983A (en) * | 2020-06-29 | 2020-09-01 | 南京农业大学 | Handheld field wheat scab monitoring and early warning device and method |
| US20220357230A1 (en) * | 2021-05-05 | 2022-11-10 | Earthview Corporation | Gas leak quantization system |
-
2023
- 2023-04-11 CN CN202310380483.1A patent/CN116381176B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2690001C1 (en) * | 2017-12-29 | 2019-05-30 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Московский государственный университет имени М.В. Ломоносова" (МГУ) | Method of processing vector signals for pattern recognition based on wavelet analysis |
| CN108956876A (en) * | 2018-07-12 | 2018-12-07 | 浙江大学 | A kind of measurement time delay correcting method of flue gas on-line continuous monitoring system |
| CN111537023A (en) * | 2020-05-13 | 2020-08-14 | 浙江大学 | Diffusion simulation and source tracing method for atmospheric pollutants in industrial park |
Non-Patent Citations (1)
| Title |
|---|
| EMBEDDED ARTIFICIAL INTELLIGENCE APPROACH FOR GAS RECOGNITION IN SMART AGRICULTURE APPLICATIONS USING LOW COST MOX GAS SENSORS;Claudia Bruno等;Smart Systems Integration;20210930;1-5 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116381176A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Prediction of harmful algal blooms in large water bodies using the combined EFDC and LSTM models | |
| Menon et al. | Wireless sensor network for river water quality monitoring in India | |
| CN112651665A (en) | Surface water quality index prediction method and device based on graph neural network | |
| CN106529746A (en) | Method for dynamically fusing, counting and forecasting air quality based on dynamic and thermal factors | |
| CN112949167A (en) | Dynamic monitoring and early warning system and method for drinking water source | |
| CN115237896B (en) | Data preprocessing method and system based on deep learning forecast air quality | |
| CN112964843A (en) | Internet of things sensor system for monitoring water quality of sewage treatment facility and monitoring method | |
| CN109060023A (en) | A kind of the data quality control method and system of miniature environmental monitoring | |
| CN201615902U (en) | Bloom warning system | |
| Wang et al. | A new embedded estimation model for soil temperature prediction | |
| CN116381176B (en) | Irrigation area water body greenhouse gas monitoring system based on low-cost sensor and intelligent algorithm | |
| CN117010915A (en) | Carbon emission target identification and monitoring system based on Internet of things technology | |
| CN112394695A (en) | Drainage basin water ecological environment monitoring system | |
| CN113780177A (en) | Non-contact real-time in-situ water quality monitoring method | |
| CN117192063B (en) | Water quality prediction method and system based on coupled Kalman filtering data assimilation | |
| CN110222916A (en) | Domestic sewage in rural areas A2O processing terminal is discharged total nitrogen concentration flexible measurement method and device | |
| CN117247132B (en) | Intelligent precise aeration method based on AAO process | |
| CN117288254A (en) | System, method, device, processor and storage medium for realizing online monitoring of sewage treatment greenhouse gas emission based on water-gas two phases | |
| CN116665037A (en) | Water ecological flow monitoring method based on hyperspectrum | |
| CN106021884A (en) | Neural network principle-based method for predicting effluent concentration of subsurface flow wetland | |
| Cao et al. | Study on water quality inversion model of Dianchi Lake based on Landsat 8 data | |
| CN112707508B (en) | BP-ANN-based agricultural sewage facility COD treatment effect prediction method, device and platform | |
| CN212845010U (en) | In-situ monitoring device for total nitrogen content of soil | |
| Rymarczyk et al. | The use of LSTM networks in the detection of outliers in IoT-based air quality monitoring systems | |
| CN115753658B (en) | Multi-parameter water quality monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |