CN111561972A - Soil water content prediction system and method based on time sequence - Google Patents
Soil water content prediction system and method based on time sequence Download PDFInfo
- Publication number
- CN111561972A CN111561972A CN202010561600.0A CN202010561600A CN111561972A CN 111561972 A CN111561972 A CN 111561972A CN 202010561600 A CN202010561600 A CN 202010561600A CN 111561972 A CN111561972 A CN 111561972A
- Authority
- CN
- China
- Prior art keywords
- soil
- data
- related information
- module
- water content
- 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.)
- Pending
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a soil water content prediction system and method based on time series, the system includes: the system comprises a remote server, a data transmission gateway, a meteorological station in a preset range and a plurality of soil information acquisition nodes arranged in the preset range; and the remote server calculates and outputs a predicted value of the soil water content in the preset range within the future preset duration according to the soil related information acquired by the soil information acquisition nodes at the same time and the weather related information acquired by the weather station. The system has the advantages of high response speed, convenient arrangement, flexibility, reliability and high efficiency; the method can adaptively adjust the soil water content prediction related parameters according to the soil characteristics and the climatic conditions of different regions, and then carry out analysis processing according to the atmospheric environment data and the soil environment data to give a predicted value of the soil water content for guiding irrigation operation, thereby effectively improving the irrigation efficiency and reducing the water resource waste.
Description
Technical Field
The invention relates to the technical field of agricultural condition information acquisition and application, in particular to a soil water content prediction system and method based on a time sequence.
Background
China is a big agricultural country, agricultural water accounts for 68% of the total water consumption of China, wherein the water consumption for irrigation accounts for more than 90% of the agricultural water, but the utilization rate is only 43% due to the backward irrigation technology, and the water consumption of developed countries reaches 70-80%. Untimely acquisition of agricultural condition information, insufficient mastering of change rules of soil information, especially change rules of water content, lack of scientific basis for irrigation, and the corresponding automation technology cannot be applied to an irrigation system, so that low irrigation efficiency is directly caused, and the improvement of crop yield is restricted. The existing soil moisture content prediction methods, for example: the remote sensing technology is used for predicting the water content of the soil, and the soil is difficult to obtain and utilize for farmers or farmers. The soil moisture balance method and the simple deduction method of the soil moisture loss speed all need fine data acquisition hardware facilities and carry out a series of operations. The methods are often required to be assisted by a specific environment, or data acquisition and calculation are difficult, and the general applicability is poor.
Therefore, how to efficiently acquire soil information, grasp the change rule of the soil environment, and further predict and estimate the soil information, such as water content, becomes a problem to be solved urgently by researchers in the field.
Disclosure of Invention
Aiming at the problems that the existing soil water content prediction method is lack of general applicability, the soil information utilization rate is low and the like, the invention provides a soil water content prediction system and method based on a time sequence.
The embodiment of the invention provides a soil water content prediction system based on a time sequence, which comprises: the system comprises a remote server, a data transmission gateway, a meteorological station in a preset range and a plurality of soil information acquisition nodes arranged in the preset range;
the soil information acquisition node sends the acquired soil related information to the remote server through the data transmission gateway; the soil-related information includes: temperature, humidity, EC and PH values;
the weather station sends the collected weather related information to the remote server through the data transmission gateway; the weather-related information includes: wind speed, wind volume, rainfall, air temperature and humidity and illumination data;
and the remote server calculates and outputs a predicted value of the soil water content in the preset range within the future preset duration according to the obtained soil related information and weather related information at the same time.
In one embodiment, the soil information collecting node includes: the device comprises a first core processor, and a soil temperature and humidity EC value sensor, a soil PH value sensor, a soil water potential sensor, a first wireless communication module and a first power module which are connected with the first core processor.
In one embodiment, the weather station comprises: the second core processor, and the wind speed and wind quantity sensor, the rain gauge, the air temperature and humidity meter, the illumination meter, the second wireless communication module and the second power module which are connected with the second core processor.
In one embodiment, the soil information collection node and/or the meteorological station further comprises an MOS transistor power control module;
the first core processor is respectively in control connection with a soil temperature and humidity EC value sensor, a soil PH value sensor and a soil water potential sensor through an MOS tube power supply control module;
and the second core processor is respectively connected with the wind speed and wind quantity sensor, the rain gauge, the air hygrothermograph and the illumination meter through an MOS tube power supply control module.
In one embodiment, the data transmission gateway comprises: the TF card, the GSM module and the third wireless communication module are connected with the third core processor;
the third wireless communication module is in wireless communication with the first wireless communication module and the second wireless communication module respectively; and the data transmission gateway sends the data to the remote server.
In one embodiment, the remote server comprises: the device comprises a data storage module, a data processing module and a prediction module;
the data storage module is used for storing original data of soil related information and weather related information transmitted by the data gateway, time series data of the soil related information and the weather related information processed by the data processing module and a soil water content prediction value output by the prediction module;
the data processing module is used for preprocessing the original data;
and the prediction module is used for predicting the soil water content in the future preset time according to the time sequence data processed by the data processing module.
In one embodiment, the data processing module includes:
the removing submodule is used for removing abnormal data of the soil related information and the weather related information;
the interpolation submodule is used for supplementing the value of the removed data and carrying out Lagrange interpolation; the interpolation method is as follows:
n time points { x ] around the interpolation time are taken0,x1,x2…xn-1Corresponding sensor data of { y }0,y1,y2…yn-1Form a point set { (x)0,y0),(x1,y1),(x2,y2)…(xn-1,yn-1)}；
Set DnIs a corner mark relating to point (x, y)Set of (2), DnN polynomials p are plotted as {0,1,2 … n-1}j(x)，j∈DnAll have any k ∈ DnAll have pk(x),Bk＝{i|i≠k,i∈DnMake
pk(x) Is a polynomial of degree n-1 and satisfies
pk(xm) 0, and pk(xk)＝1；
To obtain
The required interpolation data is obtained;
the expansion submodule is used for expanding data dimensions and constructing new characteristic feedback soil information; the new characteristics comprise time variation of soil humidity, time variation of soil temperature and time variation of soil water potential;
the numerical value standardization submodule is used for carrying out standardization processing on data, and a conversion formula is as follows:
wherein x is the original data of the soil-related information and the weather-related information,
is the mean of the raw data, σ is the standard deviation of the raw data, x*Is the converted data.
In one embodiment, the prediction module is a time series based soil moisture content prediction model; the prediction model is a deep neural network composed of a preset number of fully-connected layers and LSTM layers.
In a second aspect, an embodiment of the present invention provides a method for predicting soil water content based on a time series, including the following steps:
s100, a data transmission gateway sends acquisition instructions to soil information acquisition nodes and a meteorological station within a preset range at intervals of a preset period; after the soil information acquisition node and the meteorological station receive the corresponding instructions, the corresponding sensors are controlled to continuously acquire preset duration data and send the preset duration data to the data transmission gateway according to a preset format;
s200, the data transmission gateway adds the received soil related information and weather related information to a data segment of the current time and then sends the data segment to a remote server;
s300, the remote server preprocesses the received soil related information and the received weather related information, inputs the soil water content prediction model, and outputs the predicted value of the soil water content within the preset range within the preset time length in the future.
Further, still include:
and S400, comparing the predicted value with a future measured value to realize the correction of the soil water content prediction model parameter.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the soil water content prediction system based on the time sequence provided by the embodiment of the invention comprises: the system comprises a remote server, a data transmission gateway, a meteorological station in a preset range and a plurality of soil information acquisition nodes arranged in the preset range; and the remote server calculates and outputs a predicted value of the soil water content in the preset range within the future preset duration according to the soil related information acquired by the soil information acquisition nodes at the same time and the weather related information acquired by the weather station. The system has the advantages of high response speed, convenient arrangement, flexibility, reliability and high efficiency; the method can adaptively adjust the soil water content prediction related parameters according to the soil characteristics and the climatic conditions of different regions, and then carry out analysis processing according to the atmospheric environment data and the soil environment data to give a predicted value of the soil water content for guiding irrigation operation, thereby effectively improving the irrigation efficiency and reducing the water resource waste.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a block diagram of a soil moisture content prediction system based on time series according to an embodiment of the present invention;
FIG. 2 is a block diagram of a system for predicting soil water content based on time series according to an embodiment of the present invention;
fig. 3 is a structural block diagram of a soil information collecting node according to an embodiment of the present invention;
FIG. 4 is a block diagram of a weather station according to an embodiment of the present invention;
fig. 5 is a block diagram of a data transmission gateway according to an embodiment of the present invention;
fig. 6 is a schematic circuit diagram of a MOS transistor power control module according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating updating of parameters of a soil moisture content prediction model according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1-2, a system for predicting soil water content based on time series according to an embodiment of the present invention includes: the system comprises a remote server 1, a data transmission gateway 2, a meteorological station 3 in a preset range and a plurality of soil information acquisition nodes 4 arranged in the preset range; when the preset range is large, such as 1 hectare, a plurality of weather stations and a plurality of data transmission gateways can be arranged.
As shown in fig. 3, the soil information collection node 4 includes: the device comprises a first core processor, and a soil temperature and humidity EC value sensor, a soil PH value sensor, a soil water potential sensor, a first wireless communication module and a first power module which are connected with the first core processor. A plurality of soil information acquisition nodes are located the different positions in crop garden, are responsible for gathering the soil environment information in crop garden.
Referring to FIG. 4, the weather station includes: the second core processor, and the wind speed and wind quantity sensor, the rain gauge, the air temperature and humidity meter, the illumination meter, the second wireless communication module and the second power module which are connected with the second core processor. And as the related weather factors do not change greatly in the range of the park, the weather stations are arranged in a small amount.
For example, the data transmission gateway 2 sends the information acquisition instruction to the soil information collection node and the weather station at a frequency of once every 15 minutes. And the relevant soil relevant information and the weather relevant information are gathered to the data transmission gateway through the wireless communication module and uploaded to the remote server.
The remote server includes: the device comprises a data storage module, a data processing module and a prediction module; wherein: the data storage module is used for storing original data of soil related information and weather related information transmitted by the data gateway, time series data of the soil related information and the weather related information processed by the data processing module and a soil water content prediction value output by the prediction module; the data processing module is used for preprocessing the original data; the soil moisture content at the future moment can be predicted conveniently according to the time sequence. And the prediction module is used for predicting the soil water content within the future preset time according to the time sequence data processed by the data processing module. The prediction module is a deep neural network consisting of a certain number of full-connection layers and LSTM layers, the network structure has a memory characteristic, the correlation among data can be understood, the optimal soil water content at the future moment is predicted finally, and the change trend of the water content is presumed.
In the embodiment, the system has the advantages of high response speed, convenience in arrangement, flexibility, reliability and high efficiency; the method can adaptively adjust the soil water content prediction related parameters according to the soil characteristics and the climatic conditions of different regions, and then performs analysis processing according to atmospheric environment data and soil environment data, so that the soil water content at the future time can be well predicted, and further the change trend of the water content can be predicted, so that the method can be better combined with a garden irrigation system, and more conditions are created for garden irrigation decision making, so that irrigation operation is guided, the irrigation efficiency is effectively improved, and the waste of water resources is reduced. Meanwhile, a new method is provided for predicting the water content of the soil.
In one embodiment, referring to fig. 5, the data transmission gateway includes: the TF card, the GSM module and the third wireless communication module are connected with the third core processor; the TF card may be used to temporarily store data received by the third wireless communication module to prevent data loss due to dropped frames from the data storage module of the remote server.
The third wireless communication module is in wireless communication with the first wireless communication module and the second wireless communication module respectively; and the data transmission gateway sends the data to a remote server for sending related instructions and enabling the soil information acquisition node and the meteorological station to feed back the data.
The first wireless communication module of the soil information collection node and the second wireless communication module of the weather station may be: the UART-to-Zigbee module slave machine; the third wireless communication module of the data transmission gateway is: UART changes Zigbee module host computer. The module slave is connected to the module host in a direct connection and a bridge connection manner respectively.
The soil information acquisition node and the weather station module can realize Zigbee one-key networking, and slave machines of related modules can be added randomly within a data transmission distance range.
In one embodiment, the first power module of the soil information collection node and/or the second power module of the weather station includes: the voltage stabilizing module is connected with the rechargeable battery, wherein a power supply voltage stabilizing chip for building the voltage stabilizing circuit can be MP 1584; the peripheral circuit includes an anti-reverse connection circuit and the like.
The soil information acquisition node comprises a soil temperature and humidity (EC) value sensor of a soil information acquisition node, such as a three-in-one sensor of a type SMTE-3z and a soil EC in the market; for EC values in soil, i.e.: the method has the advantages of collecting the total salt content (conductivity) of the soil, simultaneously measuring the temperature and the moisture value in the soil, along with high measurement precision and good waterproof performance. Soil water potential sensors are for example: the TEROS21 soil water potential sensor (original MPS-6) is composed of a humidity sensor and a porous material with a known moisture release curve, wherein when the porous material and surrounding soil reach moisture balance, the humidity sensor measures the moisture content of the porous material, and converts the moisture content into water potential according to the moisture release curve.
The first core processor is, for example, a core processor using STM32F103C8T6, and its minimum system circuit is composed of a crystal oscillator circuit, a reset circuit, and itself. Its USART1 port is electrically connected with 485 level conversion circuit, and USATR3 port is electrically connected with first wireless communication module, and above-mentioned each sensor passes through 485 level conversion circuit and is connected with first core processor, and the communication is the Modbus communication protocol, can save the hardware resource of first core processor effectively.
Further, in the meteorological station, an air temperature and humidity meter can adopt an HTU21D temperature and humidity sensor; the illumination meter adopts a BH1750 illumination sensor, and the rain gauge is a rain barrel double-tipping-bucket rain gauge.
In one embodiment, the soil information collection node and/or the meteorological station further comprises an MOS tube power supply control module;
the first core processor is respectively in control connection with a soil temperature and humidity EC value sensor, a soil PH value sensor and a soil water potential sensor through an MOS tube power supply control module; and the second core processor is respectively connected with the wind speed and wind quantity sensor, the rain gauge, the air hygrothermograph and the illumination meter through the MOS tube power supply control module.
Referring to fig. 6, the circuit of the MOS transistor power supply control module takes an HTU21D air temperature and humidity sensor power supply control circuit as an example: the HTU21_ CON is a power supply control port, and the HTU21_ GND port is connected with a GND pin of the HTU21D sensor; when the control port is at a high level, the MOS tube (Q2, the model can be AO3400) is conducted, the GND pin of the sensor is connected with the GND of the circuit through the MOS tube, and the HTU21D air temperature and humidity sensor is electrified to work; on the contrary, when the control port is at a low level, the MOS tube is turned off, the GND pin of the sensor is suspended, and the HTU21D air temperature and humidity sensor is powered off. Namely: the power supply of the HTU21D air temperature and humidity sensor is independently controlled by a core processor through a circuit of an MOS tube power supply control module; the MOS tube power supply control module is in a turn-off state when the soil collection node and/or the meteorological station are in a dormant state, and electric energy is saved.
In one embodiment, the data processing module includes:
the removing submodule is used for removing abnormal data of soil related information and weather related information in the data acquisition process: due to the influences of sensor hardware faults, sensor initialization, weather factors and the like, abnormal data may be collected in the data acquisition process, and the existence of the data has a large influence on the predicted data. If the data transmission is complete and correct according to the check bit of the data segment, determining whether the sensor works normally; e.g. deleting data that the soil temperature is 30 degrees higher than the air temperature; according to the data fluctuation situation of the previous time and the later time, the data is judged to be mutation, or the data is continuously kept for a long time without change, and the like, and the data is deleted.
And the interpolation submodule is used for supplementing and interpolating the value of the removed data. Lagrange interpolation is carried out on data at a certain time lost in the transmission process or data at a certain time deleted due to data abnormity, and the interpolation method comprises the following steps:
n time points { x ] around the interpolation time are taken0,x1,x2…xn-1Corresponding sensor data of { y }0,y1,y2…yn-1Form a point set { (x)0,y0),(x1,y1),(x2,y2)…(xn-1,yn-1)}；
Set DnIs a set of corner marks for point (x, y), DnN polynomials p are plotted as {0,1,2 … n-1}j(x)，j∈DnAll have any k ∈ DnAll have pk(x),Bk＝{i|i≠k,i∈DnMake
pk(x) Is a polynomial of degree n-1 and satisfies
And p isk(xk)＝1；
Can obtain the product
The data is the needed interpolation data;
the expansion submodule is used for expanding data dimension and constructing new characteristic feedback soil information because measurement parameters are less and soil information is difficult to master comprehensively; the new characteristics include the amount of time variation in soil moisture, the amount of time variation in soil temperature, and the amount of time variation in soil water potential.
The numerical value standardization submodule is used for carrying out standardization processing on data, and a conversion formula is as follows:
wherein x is the original data of the soil-related information and the weather-related information,
is the mean of the raw data, σ is the standard deviation of the raw data, x*Is the converted data.
In one embodiment, the soil moisture content prediction model is added with an LSTM circulation network layer to enable the network to be in a network stateThe model has the capacity of accumulating and clearing memory information. The LSTM circulation network has internal "LSTM cell" circulation in addition to external RNN circulation. "LSTM cell" includes the input value xtState value CtExternal input door itAnd an output gate otForgetting door ftOutput value ht. Three door structure it、ot、ftThe number of the neurons is three in fact,
for the activation function of the neuron, W is the cyclic weight, b is the bias, and the calculation update formula is as follows:
it＝σ(Wi*[ht-1,xt]+bi)
ft＝σ(Wf*[ht-1,xt]+bf)
ot＝σ(Wo*[ht-1,xt]+bo)
ht＝ot*tanh(Ct)
the soil water content prediction model is obtained by training according to a data set collected by a conventional crop garden. Because the soil properties of different areas, such as viscosity, water retention, vegetation coverage and other conditions are different, the crop production conditions are also different, and the water change rule in the soil naturally has difference. Therefore, parameters of the soil water content prediction model need to be corrected, and when prediction errors meet requirements, updating of network parameters can be stopped.
Based on the same inventive concept, the embodiment of the invention also provides a soil water content prediction method based on the time series, and as the principle of the problem solved by the method is similar to that of a soil water content prediction system based on the time series, the implementation of the method can be referred to the implementation of the system, and repeated parts are not repeated.
The embodiment of the invention also provides a soil water content prediction method based on the time sequence, which comprises the following steps:
s100, a data transmission gateway sends acquisition instructions to soil information acquisition nodes and a meteorological station within a preset range at intervals of a preset period; after the soil information acquisition node and the meteorological station receive the corresponding instructions, the corresponding sensors are controlled to continuously acquire preset duration data and send the preset duration data to the data transmission gateway according to a preset format;
s200, the data transmission gateway adds the received soil related information and weather related information to a data segment of the current time and then sends the data segment to a remote server;
s300, the remote server preprocesses the received soil related information and the received weather related information, inputs the soil water content prediction model, and outputs the predicted value of the soil water content within the preset range within the preset time length in the future.
And the remote server combines the current environment data and the soil water content data predicted at the current moment in the past moment into one frame of data and stores the frame of data in the data storage module.
In this embodiment, the soil information collection node is responsible for collecting information such as soil humidity, temperature, EC value, PH value, soil water potential and the like; the weather station is responsible for collecting information such as air humiture, illumination, wind direction, wind speed, rainfall. And when the detection instruction is not received, the sensor is also in a dormant state, and the power supply of each sensor is disconnected by the controlled MOS tube power supply control module.
Referring to fig. 7, in step S100, the data transmission gateway sends an acquisition instruction to the soil information acquisition node and the weather station through the third wireless communication module every 15 minutes, for example; after the soil information acquisition module receives a corresponding instruction, the meteorological station turns on the power supply of each sensor; after the data of the sensor is stable, the data are continuously collected for 30 seconds, the maximum value and the minimum value can be removed by the first core processor and the second core processor, and the average value is sent to the data transmission gateway according to a certain data format. For example: soil01T25H37E05P65Po100E represents a first node of a Soil information acquisition node, the Soil temperature is 25 ℃, the Soil humidity is 37%, the Soil EC value is 0.5ms/cm, the Soil PH value is 6.5, and the Soil water potential is-100 kPa; air01T25H37L00010W5S40R20E represents a weather station I, the Air temperature is 25 ℃, the Air humidity is 37%, the illumination intensity is 10Lux, the wind direction is southwest (north is 0, calculation is clockwise), the wind speed is 40m/S, and the rainfall is 20 mm/min.
In steps S200 to S300, the data transmission gateway adds the time data to the received data, and then sends the data to the remote server through the GSM module. And after the data reaches the remote server, removing abnormal values, performing interpolation processing on the missing data, expanding data dimensionality and performing standardization processing on the data. And (4) putting the processed data into a soil water content prediction model, and finally obtaining the soil water content at the future moment. For example, one week or half month, as determined by the time series data entered.
Furthermore, each time the remote server receives the data, the current environment data and the soil water content data of the current time predicted in the past time are combined into one frame of data to be stored in the data storage module. For example, the predicted soil moisture content may be fed back to an irrigation system or a corresponding user interface to direct irrigation.
In one embodiment, further comprising: s400, comparing the predicted value with a future measured value to realize the correction of the soil water content prediction model parameter;
the specific correction steps are as follows:
s401: every preset period, such as 15 minutes; the data transmission gateway issues an acquisition command to the soil information acquisition node and the meteorological station; and the soil information acquisition node and the meteorological station transmit data to the data transmission gateway after the acquisition is finished, and then transmit the data to the remote server.
S402: the server compares the actual measured value and the predicted value of the soil water content every time the server receives data, stores an error to a data storage module, and uses the current data and historical data to form a time sequence to predict the soil water content at the future moment;
s403: and (3) sorting and classifying the data in the data storage module by taking one week or half a month as a time period, extracting the data with errors in the same direction between the predicted value and the actual measured value in continuous time, and extracting the continuous time data segments of the data together for updating the network parameters of the soil water content prediction model.
S404: because the prediction model in the soil water content prediction module has certain knowledge on the change rule of the water in the soil; the network parameters will remain in a stable state after a small number of updates.
S405: the prediction error is used as a basis for judging whether the network parameters are correct or not; if the error value is normally distributed with a mean value of 0 and a variance of 1.6, namely the prediction error is +/-5% (the error of the soil temperature and humidity EC value sensor on humidity measurement is 5%) within a certain time period, the stability of the soil water content prediction model can be judged, and the updating of network parameters is stopped.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A time series based soil moisture content prediction system, comprising: the system comprises a remote server, a data transmission gateway, a meteorological station in a preset range and a plurality of soil information acquisition nodes arranged in the preset range;
the soil information acquisition node sends the acquired soil related information to the remote server through the data transmission gateway; the soil-related information includes: temperature, humidity, EC and PH values;
the weather station sends the collected weather related information to the remote server through the data transmission gateway; the weather-related information includes: wind speed, wind volume, rainfall, air temperature and humidity and illumination data;
and the remote server calculates and outputs a predicted value of the soil water content in the preset range within the future preset duration according to the obtained soil related information and weather related information at the same time.
2. The system of claim 1, wherein the soil information collection node comprises: the device comprises a first core processor, and a soil temperature and humidity EC value sensor, a soil PH value sensor, a soil water potential sensor, a first wireless communication module and a first power module which are connected with the first core processor.
3. The system of claim 2, wherein the weather station comprises: the second core processor, and the wind speed and wind quantity sensor, the rain gauge, the air temperature and humidity meter, the illumination meter, the second wireless communication module and the second power module which are connected with the second core processor.
4. The system of claim 3, wherein said soil information collection node and/or said weather station further comprises a MOS tube power control module;
the first core processor is respectively in control connection with a soil temperature and humidity EC value sensor, a soil PH value sensor and a soil water potential sensor through an MOS tube power supply control module;
and the second core processor is respectively connected with the wind speed and wind quantity sensor, the rain gauge, the air hygrothermograph and the illumination meter through an MOS tube power supply control module.
5. The system of claim 3, wherein the data transfer gateway comprises: the TF card, the GSM module and the third wireless communication module are connected with the third core processor;
the third wireless communication module is in wireless communication with the first wireless communication module and the second wireless communication module respectively; and the data transmission gateway sends the data to the remote server.
6. The system of claim 4, wherein the remote server comprises: the device comprises a data storage module, a data processing module and a prediction module;
the data storage module is used for storing original data of soil related information and weather related information transmitted by the data gateway, time series data of the soil related information and the weather related information processed by the data processing module and a soil water content prediction value output by the prediction module;
the data processing module is used for preprocessing the original data;
and the prediction module is used for predicting the soil water content in the future preset time according to the time sequence data processed by the data processing module.
7. The system of claim 6, wherein the data processing module comprises:
the removing submodule is used for removing abnormal data of the soil related information and the weather related information;
the interpolation submodule is used for supplementing the value of the removed data and carrying out Lagrange interpolation; the interpolation method is as follows:
n time points { x ] around the interpolation time are taken0,x1,x2…xn-1Corresponding sensor data of { y }0,y1,y2…yn-1Form a point set { (x)0,y0),(x1,y1),(x2,y2)…(xn-1,yn-1)}；
Set DnIs a set of corner marks for point (x, y), DnN polynomials p are plotted as {0,1,2 … n-1}j(x)，j∈DnAll have any k ∈ DnAll have pk(x),Bk＝{i|i≠k,i∈DnMake
pk(x) Is a polynomial of degree n-1And satisfy
pk(xm) 0, and pk(xk)＝1；
To obtain
The required interpolation data is obtained;
the expansion submodule is used for expanding data dimensions and constructing new characteristic feedback soil information; the new characteristics comprise time variation of soil humidity, time variation of soil temperature and time variation of soil water potential;
the numerical value standardization submodule is used for carrying out standardization processing on data, and a conversion formula is as follows:
wherein x is the original data of the soil-related information and the weather-related information,
is the mean of the raw data, σ is the standard deviation of the raw data, x*Is the converted data.
8. The system of claim 6, wherein the prediction module is a time series based soil moisture content prediction model; the prediction model is a deep neural network composed of a preset number of fully-connected layers and LSTM layers.
9. A soil water content prediction method based on a time series is characterized by comprising the following steps:
s100, a data transmission gateway sends acquisition instructions to soil information acquisition nodes and a meteorological station within a preset range at intervals of a preset period; after the soil information acquisition node and the meteorological station receive the corresponding instructions, the corresponding sensors are controlled to continuously acquire preset duration data and send the preset duration data to the data transmission gateway according to a preset format;
s200, the data transmission gateway adds the received soil related information and weather related information to a data segment of the current time and then sends the data segment to a remote server;
s300, the remote server preprocesses the received soil related information and the received weather related information, inputs the soil water content prediction model, and outputs the predicted value of the soil water content within the preset range within the preset time length in the future.
10. The method of claim 9, further comprising:
and S400, comparing the predicted value with a future measured value to realize the correction of the soil water content prediction model parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010561600.0A CN111561972A (en) | 2020-06-18 | 2020-06-18 | Soil water content prediction system and method based on time sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010561600.0A CN111561972A (en) | 2020-06-18 | 2020-06-18 | Soil water content prediction system and method based on time sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111561972A true CN111561972A (en) | 2020-08-21 |
Family
ID=72073917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010561600.0A Pending CN111561972A (en) | 2020-06-18 | 2020-06-18 | Soil water content prediction system and method based on time sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111561972A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064013A (en) * | 2021-03-31 | 2021-07-02 | 广东电网有限责任公司 | Lightning arrester state monitoring method, device and system |
| CN113218808A (en) * | 2021-03-31 | 2021-08-06 | 安徽华梦检测科技有限公司 | Separation detection device for soil detection and use method thereof |
| CN113341106A (en) * | 2021-06-03 | 2021-09-03 | 广州大学 | Automatic dry depth probe and method for predicting and acquiring dry depth information |
| CN113435649A (en) * | 2021-06-29 | 2021-09-24 | 布瑞克农业大数据科技集团有限公司 | Global agricultural data sorting method, system, device and medium |
| CN113647314A (en) * | 2021-07-13 | 2021-11-16 | 深圳市见康水耕智慧农业有限公司 | Intervention method and system for soil planting |
| CN113673160A (en) * | 2021-08-23 | 2021-11-19 | 中国水利水电科学研究院 | Porous material optimized burying method for efficient utilization of crop moisture |
| CN114062656A (en) * | 2021-11-16 | 2022-02-18 | 河南省焦作地质勘察设计有限公司 | Geological disaster prediction method and system |
| CN114118634A (en) * | 2022-01-26 | 2022-03-01 | 深圳大学 | Soil moisture prediction method and device |
| CN115349432A (en) * | 2022-09-23 | 2022-11-18 | 中联智慧农业股份有限公司 | Intelligent irrigation method and system based on optical radiation and meteorological prediction |
| WO2022245312A1 (en) * | 2021-05-18 | 2022-11-24 | Hi̇t Bi̇li̇şi̇m Danişmanlik Turi̇zm Hi̇zmetleri̇ Sanayi̇ Ve Ti̇caret Li̇mi̇ted Şi̇rketi̇ | A method for estimating soil moisture and a system operating according to said method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104848901A (en) * | 2015-06-17 | 2015-08-19 | 贵州师范学院 | System for real-time monitoring and prediction of soil moisture content, and detection method for soil moisture content |
| US20170238484A1 (en) * | 2016-02-22 | 2017-08-24 | Ainesh Arumugam | Method and apparatus for smart irrigation controller |
| CN110050673A (en) * | 2019-04-30 | 2019-07-26 | 黄河水利委员会黄河水利科学研究院 | A kind of intelligent irrigation management system |
| CN110084367A (en) * | 2019-04-19 | 2019-08-02 | 安徽农业大学 | A kind of Forecast of Soil Moisture Content method based on LSTM deep learning model |
-
2020
- 2020-06-18 CN CN202010561600.0A patent/CN111561972A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104848901A (en) * | 2015-06-17 | 2015-08-19 | 贵州师范学院 | System for real-time monitoring and prediction of soil moisture content, and detection method for soil moisture content |
| US20170238484A1 (en) * | 2016-02-22 | 2017-08-24 | Ainesh Arumugam | Method and apparatus for smart irrigation controller |
| CN110084367A (en) * | 2019-04-19 | 2019-08-02 | 安徽农业大学 | A kind of Forecast of Soil Moisture Content method based on LSTM deep learning model |
| CN110050673A (en) * | 2019-04-30 | 2019-07-26 | 黄河水利委员会黄河水利科学研究院 | A kind of intelligent irrigation management system |
Non-Patent Citations (7)
| Title |
|---|
| 周海峰: "土壤墒情监测系统开发与预报模型研究", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
| 周海峰等: "辣椒不同深度土壤墒情预报的BP神经网络模型", 《内蒙古农业大学学报（自然科学版）》 * |
| 张天柱: "《温室工程规划、设计与建设》", 31 January 2010, 中国轻工业出版社 * |
| 李喆 等: "《基于物联网的时空连续多元信息获取布局技术研究》", 30 April 2017, 东南大学出版社 * |
| 毛欣宇: "《电动修复及其改进连用技术对重金属污染土壤的修复研究》", 31 December 2018, 河海大学出版社 * |
| 汪晓虹，周含策编: "《高等数学实验（第2版）学软件 做数学》", 29 February 2016, 北京：国防工业出版社 * |
| 赵茂泰: "《电子测量仪器设计》", 31 July 2010, 华中科技大学出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064013A (en) * | 2021-03-31 | 2021-07-02 | 广东电网有限责任公司 | Lightning arrester state monitoring method, device and system |
| CN113218808A (en) * | 2021-03-31 | 2021-08-06 | 安徽华梦检测科技有限公司 | Separation detection device for soil detection and use method thereof |
| WO2022245312A1 (en) * | 2021-05-18 | 2022-11-24 | Hi̇t Bi̇li̇şi̇m Danişmanlik Turi̇zm Hi̇zmetleri̇ Sanayi̇ Ve Ti̇caret Li̇mi̇ted Şi̇rketi̇ | A method for estimating soil moisture and a system operating according to said method |
| CN113341106A (en) * | 2021-06-03 | 2021-09-03 | 广州大学 | Automatic dry depth probe and method for predicting and acquiring dry depth information |
| CN113435649A (en) * | 2021-06-29 | 2021-09-24 | 布瑞克农业大数据科技集团有限公司 | Global agricultural data sorting method, system, device and medium |
| CN113647314A (en) * | 2021-07-13 | 2021-11-16 | 深圳市见康水耕智慧农业有限公司 | Intervention method and system for soil planting |
| CN113673160A (en) * | 2021-08-23 | 2021-11-19 | 中国水利水电科学研究院 | Porous material optimized burying method for efficient utilization of crop moisture |
| CN113673160B (en) * | 2021-08-23 | 2023-09-12 | 中国水利水电科学研究院 | Porous material optimized burying method for efficient utilization of crop moisture |
| CN114062656A (en) * | 2021-11-16 | 2022-02-18 | 河南省焦作地质勘察设计有限公司 | Geological disaster prediction method and system |
| CN114118634A (en) * | 2022-01-26 | 2022-03-01 | 深圳大学 | Soil moisture prediction method and device |
| CN115349432A (en) * | 2022-09-23 | 2022-11-18 | 中联智慧农业股份有限公司 | Intelligent irrigation method and system based on optical radiation and meteorological prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111561972A (en) | Soil water content prediction system and method based on time sequence | |
| Varman et al. | Deep learning and IoT for smart agriculture using WSN | |
| Kaewmard et al. | Sensor data collection and irrigation control on vegetable crop using smart phone and wireless sensor networks for smart farm | |
| CN104904569B (en) | A kind of intelligent irrigation regulator control system and method based on the estimation of dynamic water content | |
| CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| CN101953287B (en) | Multi-data based crop water demand detection system and method | |
| CN103701845A (en) | Cloud computing based monitoring and early warning control cloud service system and method for greenhouse cluster internet of things | |
| CN105843147A (en) | Smart agriculture monitoring and management system | |
| CN112400676B (en) | Intelligent irrigation system based on big data | |
| WO2019205528A1 (en) | Antenna data-based algorithm for predicting solar energy collection power of wireless sensor network node | |
| CN116545954B (en) | Communication gateway data transmission method and system based on internet of things | |
| CN106131770A (en) | A kind of data fusion method of the wireless sensor network for greenhouse | |
| CN104093186A (en) | Method for multi-hop wireless sensor network opportunistic routing and system thereof | |
| CN105183057A (en) | Grain bin temperature and humidity control system based on Zigbee technology | |
| CN111967665A (en) | Irrigation decision method and system based on neural network | |
| CN115530054A (en) | Irrigation control method and device, electronic equipment and storage medium | |
| CN116138145A (en) | Intelligent agricultural management system | |
| CN104807498A (en) | Farmland environment wireless monitoring system based on Zigbee and 3G technology | |
| Irianto | Design of smart farm irrigation monitoring system using IoT and LoRA | |
| CN206115670U (en) | System for automated analysis crop output influence factor | |
| Al Nahian et al. | IoT based soil monitoring and automatic irrigation system | |
| Wahl et al. | Development and power characterization of an iot network for agricultural imaging applications | |
| CN107396292B (en) | Soil humidity information acquisition system for precision agriculture | |
| Reddy et al. | Photovoltaic, internet-of-things-enabled intelligent agricultural surveillance system | |
| CN106605578A (en) | Intelligent irrigation system based on technologies of Internet of Things |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200821 |