Method for forecasting water consumption demand based on farmland crop growth parameters

Abstract

The invention discloses a method for forecasting water consumption demand based on farmland crop growth parameters, which comprises the following steps of: 1, acquiring historical monitoring data of a farmland to be measured and preprocessing the historical monitoring data, 2, constructing a farmland crop water consumption demand forecasting model which sequentially comprises a leaf area index calculation module, a yield calculation module and an evapotranspiration calculation module; 3, training the model constructed in the step 2 by adopting a loss function according to the actually monitored leaf area index, the actually monitored yield and the actually monitored water consumption, and adjusting model parameters based on a training result to obtain a farmland crop water consumption forecasting model; 4, real-time monitoring data of the farmland to be measured are obtained, the farmland crop water consumption demand forecasting model trained and adjusted in the step 3 is input, and future short-term water consumption demand of the farmland crops is obtained, short-term forecasting of actual water consumption demand of the crops is achieved, adjustment of model parameters is simplified, and higher space-time resolution is achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method for predicting water consumption based on crop growth parameters. Background Art

[0002] The Python library for calculating actual crop evapotranspiration based on a single-source surface energy balance model is a short-term crop water consumption forecast model based on remote sensing data and hydrological parameters. By inputting remote sensing, meteorological and other data, based on the principle of surface energy balance, it automatically outputs biomass, evapotranspiration and other data in the Python environment to directly obtain the actual crop water consumption, crop coefficient and other process parameters. Combined with future meteorological data, the Penman formula is used to predict the actual crop water consumption in the future.

[0003] The SEBAL, SEBS, METRIC single-source models and the TSEB dual-source model are often used as methods to calculate the actual water consumption of crops. However, the current methods have high requirements for images in remote sensing evapotranspiration, are often limited by the temporal and spatial resolution of satellite data, and involve a large amount of data, resulting in intensive calculations. This limits the calculation of the actual water consumption of crops in terms of workload and inversion accuracy. Summary of the invention

[0004] One of the embodiments of this specification provides a method for predicting water consumption based on crop growth parameters. The method for predicting water consumption based on crop growth parameters includes:

[0005] Step 1: Obtain historical monitoring data of the farmland to be tested for preprocessing, wherein the historical monitoring data includes historical crop information, historical remote sensing data, and historical meteorological data;

[0006] Step 2: construct a farmland crop water consumption forecasting model, which is a single-source surface energy balance model developed in a Python environment, and includes a leaf area index calculation module, a yield calculation module, and an evapotranspiration calculation module in sequence;

[0007] Leaf area index calculation module: used to calculate the leaf area index of the farmland to be tested based on the number of plants and the leaf area of ​​a single plant;

[0008] Yield calculation module: used to use the meteorological data and crop information of the farmland to be tested, and then calculate the yield of the farmland to be tested based on photosynthesis efficiency, area index and biomass production efficiency;

[0009] Evapotranspiration calculation module: used to calculate the evapotranspiration of the tested farmland crops according to the surface energy balance principle;

[0010] Step 3: According to the actually monitored leaf area index, the actually monitored yield and the actually monitored water consumption, the model constructed in step 2 is trained using the loss function, and the model parameters are adjusted based on the training results to obtain a model for predicting the water consumption of farmland crops;

[0011] Step 4: Obtain real-time monitoring data of the farmland to be tested, and input the farmland crop water consumption forecasting model trained and adjusted in step 3 to obtain the future short-term water consumption of farmland crops.

[0012] One of the embodiments of the present specification provides a device, characterized in that it includes at least one memory and at least one processor; the memory is used to store computer-executable instructions; the processor is used to run the computer-executable instructions, and the computer-executable instructions can be run to implement any method for predicting water consumption based on farmland crop growth parameters.

[0013] One of the embodiments of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for predicting water consumption based on farmland crop growth parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0015] Figure 1 It is an exemplary flow chart of a method for predicting water consumption based on farmland crop growth parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0020] Figure 1 1 is an exemplary flow chart of a method for predicting water consumption based on crop growth parameters in some embodiments of this specification. Figure 1 As shown, the method of the present invention comprises the following steps:

[0021] Step 1: Obtain the historical monitoring data of the farmland to be tested for preprocessing. The historical monitoring data includes historical crop information, historical remote sensing data, and historical meteorological data.

[0022] In some embodiments, historical crop information includes plant number, total area of ​​plants per unit area of ​​the tested farmland, historical yield and leaf area index of the tested farmland, etc. Historical remote sensing data includes solar radiation data, remote sensing image data, etc. Historical meteorological data includes temperature, relative humidity, sunshine hours, wind speed, precipitation, etc.

[0023] In some embodiments, the remote sensing data is specifically: using the "polygon" tool in the https: / / earthexplorer.usgs.gov website to select the desired Landsat image area, and adding the desired image type to the order, and then downloading the image in the batch download application based on the order number.

[0024] In some embodiments, the DEM is specifically: the required image is obtained by selecting SRTM 1Arc-Second Global, and a shape file is created in QGIS, the area covered by multiple DEM images is "merged" and "cropped", the merged DEM layer is set as the input file, the study area layer is set as the mask layer, and the corresponding relationship of the projection is ensured. Finally, the cropped DEM image is saved in the input folder containing the Landsat image.

[0025] Step 2: Construct a farmland crop water consumption forecasting model, which is a single-source surface energy balance model developed in a Python environment, and includes a leaf area index calculation module, a yield calculation module, and an evapotranspiration calculation module in sequence.

[0026] Among them, the leaf area index calculation module is used to calculate the leaf area index of the farmland to be tested based on the number of plants and the leaf area of ​​a single plant.

[0027] Specifically, the calculation formula based on the number of plants and the leaf area of ​​a single plant is as follows:

[0028] LAI=(N×A) / S,

[0029] Among them, N is the number of plants in the farmland to be tested (plants / ha); A is the leaf area of ​​a single plant of the crop in the farmland to be tested (m2); S is the total area of ​​plants per unit area of ​​the farmland to be tested (m2).

[0030] Yield calculation module: It is used to use the meteorological data and crop information of the farmland to be tested, and then calculate the yield of the farmland to be tested based on the photosynthesis efficiency, area index and biomass production efficiency.

[0031] Specifically, the climate, soil, plant and other parameters are used for calculation in the model, and the required yield parameters are obtained by dividing the product of photosynthesis efficiency, leaf area index and biomass production efficiency by the sum of respiration rate and unit 1.

[0032] Evapotranspiration calculation module: used to calculate the evapotranspiration of the tested farmland crops based on the surface energy balance principle.

[0033] Specifically, the Python library for calculating actual crop evapotranspiration based on a single-source surface energy balance model is an algorithm version of a single-source surface energy balance model developed in the Python environment. It not only uses various data such as remote sensing and meteorology as input parameters to invert actual water consumption, but also provides more information about crop growth, including LAI, yield, etc., together with actual water consumption as output parameters of the model. The calculation principle for inverting actual crop water consumption is based on the total surface energy balance equation, and the calculation formula is as follows:

[0034] λET=R n -GH,

[0035] Where: λET is the latent heat flux (W / m 2 ); λ is the latent heat of vaporization of water; Rn is the net radiation flux of the surface (W / m 2 ); G is soil heat flux (W / m 2 ); H is the sensible heat flux (W / m 2 ).

[0036] Step 1: First calculate the net radiation flux Rn (W / m2), which is the main energy source for surface energy, momentum and water transport and exchange. The calculation formula is as follows:

[0037] Rn=(1-α)R S ↓+ε0R L ↓-ε0σT 4 s,

[0038] Where: R S ↓ Solar shortwave radiation reaching the surface (W / m 2 ), i.e., incident shortwave radiation; R L ↓The solar long-wave radiation reaching the surface, that is, the incident long-wave radiation (W / m 2 ). α is the surface albedo (-). ε0 is the surface emissivity obtained by the semi-empirical relationship between NDVI and leaf area index (LAI), which can be retrieved from the red and near-infrared bands. σ is the Stephen Boltzmann constant, which is 5.67*10 -8 (W / m 2 ·K 4 ), TS is the surface temperature (combined radiation temperature of soil and vegetation) (K).

[0039] Step 2: Calculate the soil heat flux G Based on the single-source land surface energy balance model, the Python library calculates the actual crop evapotranspiration using the empirical equation developed by Bastiaanssen to calculate the soil heat flux G as R n part of

[0040] G=T s,datum (0.0038+0.007 α )(1-0.98NDVI 4 )×Rn,

[0041] Where: T s,datum is the surface temperature (T) corrected based on the slope and angle of the digital elevation map (DEM) of the study area. S ).

[0042] Step 3: Calculate the sensible heat flux H. The sensible heat flux is also called the sensible heat flux, which refers to the heat exchange in the form of turbulence between the atmosphere and the underlying surface caused by temperature changes. The calculation formula is as follows:

[0043]

[0044] Where: ρ is the air density (kg / m 3 );C p is the specific heat capacity of air at constant pressure (J / kg·K); dT is the temperature difference between Z1 and Z2 above the ground, usually 0.1m and 2m; r ahis the aerodynamic impedance for heat transfer (s / m). The coefficients "a" and "b" are determined iteratively for cold and hot pixels, so they are specific for each image.

[0045] The calculation of each instantaneous parameter is as follows: Based on the instantaneous Rn, H and G at the satellite transit time, the instantaneous evaporation fraction (EF i ), and converted to daily evaporation fraction (EF 24 ), which is used to reduce the afternoon ET a Error caused by addition:

[0046]

[0047] EF 24 =Ω×EF i

[0048] R 24 is the average net radiation of the day (W / m 2 ), which can be calculated as:

[0049] Rn24=[(1-α)×Ra-110]×τ sw ,

[0050] Among them, R a is the daily extraterrestrial solar radiation (W / m 2 ). sw is the atmospheric transmittance.

[0051] The final actual crop evapotranspiration is calculated according to the FAO Penman-Monteith Penman formula method recommended by the Food and Agriculture Organization of the United Nations. The basic principle is:

[0052]

[0053] ET a =K c ×ET0

[0054] Where: ET0 is potential evapotranspiration (mm); K c is the crop coefficient; R n is the net radiation of the crop surface (W / m2); G is the soil heat flux (W / m2); γ is the psychrometric constant (kPa / ℃); T is the daily average temperature (℃); u2 is the wind speed at a height of 2 meters (m / s); Δ is the slope of the saturated water vapor pressure curve (kPa / ℃); e s is the saturated water vapor pressure (kPa); e a is the actual water vapor pressure (kPa).

[0055] Step 3: According to the actually monitored leaf area index, the actually monitored yield and the actually monitored water consumption, the loss function is used to train the model constructed in step 2, and the model parameters are adjusted based on the training results to obtain a model for predicting the water consumption of farmland crops.

[0056] In some embodiments, the K derived from the model is c Linear interpolation is performed to obtain K in the area between satellite stations c The ET0 obtained by the meteorological station between two adjacent satellites is used to obtain the daily ET obtained by the satellite. a Interpolation is performed to obtain the time series inversion ET for the entire simulation period a ; Using ArcGIS to calculate the ET inversion based on remote sensing in the test area a The average value of the model is taken as the ET a , the ET obtained by the field surface renewal system a As a monitoring ET for the entire test area a ; Using the root mean square error (RMSE), Nash-Sutcliffe characteristic (NSE) and correlation coefficient (R 2 ) statistical goodness of fit indexes for the ET of remote sensing inversion time series a , yield and LAI were compared with the monitoring values.

[0057] Step 4: Obtain real-time monitoring data of the farmland to be tested, and input the farmland crop water consumption forecasting model trained and adjusted in step 3 to obtain the future short-term water consumption of farmland crops.

[0058] In some embodiments, the crop history K is obtained by using the output of a python library based on a single-source land surface energy balance model to calculate the actual crop evapotranspiration. c , where K c The default value remains unchanged in the short term, using the current K c As the future short-term K c The estimated value is then used to calculate the future ET0 using future meteorological data, and the actual water consumption ET of future short-term crops is obtained according to the Penman formula. a .

[0059] The beneficial effects of the present invention are:

[0060] (1) The present invention uses an algorithm of a single-source surface energy balance model developed in a Python environment to simulate changes in soil moisture content and potential evapotranspiration, simplify model parameter adjustment, provide a process for automatically adjusting model parameters, reduce the possibility of errors caused by manual adjustment of model parameters, and support multiple data sources to improve the generalization ability of inversion results, so as to achieve higher spatiotemporal resolution, better compatibility, and more model parameters to provide more accurate and reliable inversion results.

[0061] (2) The present invention combines the crop coefficient inverted by the Python library that calculates the actual evapotranspiration of crops based on the single-source surface energy balance model with future meteorological data, and proposes the assumption that the crop coefficient Kc remains unchanged. Based on the Penman formula, on the basis of inverting farmland process parameters including yield and leaf area index to assist agricultural production, the short-term forecast of the actual water consumption of crops is achieved, providing important data support for the intelligent irrigation system to guide future field irrigation and thus improve irrigation efficiency, and helping farmers and irrigation agencies optimize irrigation plans to improve crop production efficiency. Accurate irrigation systems not only avoid excessive or insufficient irrigation to reduce water waste, but also improve agricultural disaster prevention and mitigation capabilities.

[0062] The present invention also provides another embodiment, taking two walnut orchards in the Central Valley of California as the farmland to be tested, and a short-term forecasting method for the actual water consumption required by walnut saplings based on remote sensing and future meteorology. The specific steps of the short-term forecasting method for the actual water consumption required by walnut saplings are as follows:

[0063] Ground monitoring: Field surface renewal monitoring systems were installed at two walnut orchards in the Central Valley of California, 1 m above the crop canopy on May 1 and 5, 2017.

[0064] Remote sensing evapotranspiration model establishment:

[0065] The model calculation is based on the principle of surface energy balance. The latent heat flux is calculated by estimating the net radiation flux, soil heat flux and sensible heat flux, and the instantaneous ET is derived, which is finally converted into daily evapotranspiration to obtain the inverted ETa. The Python library model for calculating the actual evapotranspiration of crops based on the single-source surface energy balance model can be found on the website https: / / pysebal-doc.readthedocs.io / en / install / run.html for specific operation operations.

[0066] Input parameter processing: When clear sky conditions permit, satellite remote sensing data can be obtained from specific websites according to the source of remote sensing data, such as Landsat from https: / / earthexplorer.usgs.gov; DEM data can be obtained from specific websites according to the study area, such as SRTM; relative humidity, wind speed, solar radiation and temperature data can be obtained from the nearest automatic weather station. If there is no nearest real-time monitoring weather station, open source data can be used, such as the China National Meteorological Station Network.

[0067] Specifically, soil and crop information comes from the USDA NRCS Web Soil Survey (WSS) and data provided by growers;

[0068] Specifically, daily and hourly meteorological data including solar radiation, wind speed, relative humidity, and air temperature were obtained from the CIMIS website (https: / / cimis.water.ca.gov / ).

[0069] Specifically, satellite remote sensing data were obtained from the Earth Resources Observation and Science Center of the United States Geological Survey (http: / / eros.usgs.gov / ), including a total of 83 clear-sky Landsat 8 and TRIS images from the walnut growing season from 2017 to 2020.

[0070] Specifically, the DEM data include DEM maps with a spatial resolution of 30 meters. The surface temperature is corrected according to the altitude and slope obtained from the 1Arc-Second data in SRTM and “cropped” in QGIS.

[0071] Model evaluation: Root mean square error (RMSE), Nash-Sutcliffe characteristic (NSE) and correlation coefficient (R 2 )Statistical goodness of fit index for ET of remote sensing inversion time series a and measured ET a Make a comparison.

[0072] Specifically, between two adjacent satellite passes, the ET0 obtained from the nearest CIMIS weather station (No. 222) and the linearly interpolated K c Figure pair inversion ET a Interpolate to obtain the time series inversion ET for the entire simulation period a ; Using ArcGIS to calculate the ET inversion based on remote sensing in the test area a The average value of the model is taken as the ET a , the ET obtained by the field surface renewal system a As the measured ET of the entire test area a ; Using the root mean square error (RMSE), Nash-Sutcliffe characteristic (NSE) and correlation coefficient (R 2 )Statistical goodness of fit index for ET of remote sensing inversion time series a and measured ET a Make a comparison.

[0073] Short-term crop water consumption forecast: The crop historical K is obtained by using the output of the Python library based on the single-source surface energy balance model to calculate the actual crop evapotranspiration. c , where K c The default value remains unchanged in the short term, using the current K c As the future short-term K cThe estimated value is then used to calculate the future ET0 using future meteorological data, and the actual water consumption ET of future short-term crops is obtained according to the Penman formula. a .

[0074] One of the embodiments of the present invention provides a device, including at least one memory and at least one processor; the memory is used to store computer-executable instructions; the processor is used to run the computer-executable instructions, and the computer-executable instructions are run to implement any method for predicting water consumption based on farmland crop growth parameters.

[0075] One of the embodiments of the present invention provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for predicting water consumption based on farmland crop growth parameters.

[0076] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0077] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0078] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0079] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0080] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0081] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0082] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for predicting water consumption based on crop growth parameters, characterized in that: include: Step 1: Obtain historical monitoring data of the farmland to be tested for preprocessing, wherein the historical monitoring data includes historical crop information, historical remote sensing data, and historical meteorological data; Step 2: Construct a farmland crop water consumption forecasting model, which includes a leaf area index calculation module, a yield calculation module, and an evapotranspiration calculation module; Leaf area index calculation module: used to calculate the leaf area index of the farmland to be tested based on the number of plants and the leaf area of ​​a single plant; Yield calculation module: used to use the meteorological data and crop information of the farmland to be tested, and then calculate the yield of the farmland to be tested based on photosynthesis efficiency, leaf area index and biomass production efficiency; Evapotranspiration calculation module: used to calculate the evapotranspiration of the tested farmland crops according to the surface energy balance principle; Step 3: According to the actually monitored leaf area index, the actually monitored yield and the actually monitored water consumption, the model constructed in step 2 is trained using the loss function, and the model parameters are adjusted based on the training results to obtain a model for predicting the water consumption of farmland crops; Step 4: Obtain real-time monitoring data of the farmland to be tested, and input the farmland crop water consumption forecasting model trained and adjusted in step 3 to obtain the future short-term water consumption of farmland crops.

2. The method for predicting water consumption based on crop growth parameters according to claim 1, characterized in that: The leaf area index calculation includes: The calculation formula based on the number of plants and the leaf area of ​​a single plant is as follows: LAI=(N×A) / S Among them, N is the number of plants in the farmland to be tested (plants / ha); A is the leaf area of ​​a single plant of the crop in the farmland to be tested (m2); S is the total area of ​​plants per unit area of ​​the farmland to be tested (m2).

3. The method for predicting water consumption based on crop growth parameters according to claim 1, characterized in that: The calculation of evapotranspiration includes: Based on the principle of surface energy balance, the latent heat flux is calculated by estimating the net radiation flux, soil heat flux and sensible heat flux, and the instantaneous evapotranspiration is derived.

4. A device, characterized in that: comprising at least one memory and at least one processor; The memory is used to store computer executable instructions; The processor is used to run the computer executable instructions, and the computer executable instructions can be used to implement any method of predicting water consumption based on farmland crop growth parameters as described in any one of claims 1 to 3.

5. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for predicting water consumption based on farmland crop growth parameters as described in any one of claims 1 to 3.

Images