Crop water utilization efficiency paradox evaluation method and device and computer program product

Abstract

The invention discloses a crop water utilization efficiency paradox evaluation method and device and a computer program product, and belongs to the technical field of agricultural irrigation. The method comprises the following steps: acquiring grid scale resource environment data of a target region; processing the grid scale resource environment data based on the trained machine learning model to obtain a grid scale crop blue water demand; calculating the crop water productivity according to the grid scale crop blue water demand; obtaining a crop water utilization efficiency paradox index according to the grid scale crop blue water demand and the crop water productivity; and analyzing the crop water utilization efficiency paradox condition of the target region according to the crop water utilization efficiency paradox index. The device comprises a data acquisition module, a grid scale data obtaining module, a first calculation module, a second calculation module and a judgment module. The grid-scale crop water utilization efficiency paradox index can be obtained, water resource management is performed on a target area in a targeted manner, and waste of environmental resources and manpower and financial resources is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and particularly relates to a method, a device and a computer program product for evaluating the crop water use efficiency paradox. Background Art

[0002] Given the importance of irrigated agriculture in increasing crop yields, countries around the world often seek to enhance food security by expanding the irrigated area, and have achieved many beneficial effects. Nevertheless, the expansion of the irrigated area has also brought about a huge freshwater consumption, thus making water resource shortage a threat to the sustainable development of agriculture in many regions. Improving crop water use efficiency is generally considered to be one of the most effective ways to alleviate the water shortage problem. However, a large amount of evidence shows that the global agricultural system is facing a water-saving dilemma, mainly manifested as the contradiction between improving crop water use efficiency and the increasingly serious water resource shortage, that is, the improvement of crop water use efficiency does not necessarily lead to a reduction in the total amount of irrigation water used, which results in the occurrence of the water use efficiency paradox.

[0003] Currently, there are mainly the following two existing technologies to address the above situation of the water use efficiency paradox: First, at the field, irrigation district and basin scales, based on the water resource accounting framework and the definition of the irrigation efficiency paradox, a judgment method for the irrigation efficiency paradox is established to detect the irrigation efficiency paradox across spatial scales. The irrigation efficiency is calculated as the ratio of the beneficial irrigation water (mainly crop evapotranspiration) to the total irrigation water for the annual crop evapotranspiration per unit land. The water consumption is obtained by calculating the crop evapotranspiration of two irrigation methods, flood irrigation and drip irrigation. The paradox of irrigation efficiency is defined as the situation where the agricultural water consumption increases instead when the irrigation efficiency increases (such as changing from flood irrigation to drip irrigation). This technology establishes a judgment system for the irrigation efficiency paradox at different scales of farmland, irrigation districts and basins, providing a localized method for alleviating the tense relationship of agricultural water use.

[0004] Second, the AquaCrop method is used to quantify the irrigation water requirement, and then the irrigation water productivity and the water shortage footprint are calculated. Through hotspot analysis, the relationship between high and low efficiency and high and low water shortage is explored to evaluate the opposite situation of the water resource productivity research of crop yield and total water consumption. To determine the hotspot areas, the irrigation water productivity and the water shortage footprint at the grid and agricultural economic zone scales are divided into three levels: low, medium and high. Therefore, there can be nine combinations of irrigation water productivity and the water shortage footprint. These combinations are mapped using a color-coded matrix, and the corresponding crop area determined by each color is calculated and expressed as a percentage of the total crop area. The hotspot area is defined as the area with a relatively low comprehensive water volume coefficient but a relatively high water use volume coefficient, which means that the crop production in the water shortage area consumes a large amount of irrigation water. This method reveals the phenomenon that the increase in the total efficiency of crop water use leads to an increase in irrigation demand and water resource shortage.

[0005] However, the current research methods for the crop water use efficiency paradox still have obvious deficiencies in quantitative evaluation and spatial analysis. In terms of quantitative indicators, the existing technologies can only evaluate the regions and spatial distribution information where the crop water use efficiency paradox appears, and cannot quantitatively measure the strength of the crop water use efficiency paradox. There is a lack of quantitative indicators to describe the strength of the contradiction that the water consumption increases while the crop water use efficiency improves. As a result, the judgment and analysis of the paradox cannot identify the regions with serious water resource shortage, and it is difficult to reflect the differential degree of water stress among regions, thus making it impossible to formulate differentiated water resource management plans.

[0006] In addition, the paradox judgment of the above technologies is often carried out at the small watershed scale or station scale. Although accurate data can be obtained through on-site measurement in these fine-scale investigations, when it is necessary to evaluate an entire province or a cross-provincial river basin, this method faces huge challenges and has obvious disadvantages such as high cost and consuming a large amount of manpower and material resources. Currently, there is a lack of a large-scale spatialized paradox phenomenon evaluation method, which cannot comprehensively evaluate the water resource shortage situation in large-scale regions, and there is a lack of understanding of the spatio-temporal dynamic laws of the crop water use efficiency paradox at large scales and fine scales. Summary of the Invention

[0007] To solve the problems existing in the prior art, on the one hand, the present invention provides a method for evaluating the crop water use efficiency paradox, which includes: Obtaining grid-scale resource and environment data of the target area: processing the grid-scale resource and environment data based on a trained machine learning model to obtain grid-scale crop blue water demand. The training samples used during the training of the machine learning model include: the station-scale resource and environment data of the target area as independent variables and the station-scale crop blue water demand of the target area as dependent variables; calculating crop water productivity based on the grid-scale crop blue water demand; obtaining the crop water use efficiency paradox index based on the grid-scale crop blue water demand and the crop water productivity; and analyzing the water use efficiency paradox situation of the target area according to the crop water use efficiency paradox index.

[0008] On the other hand, the present invention provides a device for evaluating the crop water use efficiency paradox, which includes: A data acquisition module for acquiring raster-scale resource and environment data of a target area; a raster-scale data generation module for processing the raster-scale resource and environment data based on a trained machine learning model to obtain raster-scale crop blue water requirements, wherein the training samples used in training the machine learning model include: site-scale resource and environment data of the target area as independent variables and site-scale crop blue water requirements of the target area as dependent variables; a first calculation module for calculating crop water productivity based on the raster-scale crop blue water requirements; a second calculation module for obtaining a crop water use efficiency paradox index based on the raster-scale crop blue water requirements and the crop water productivity; and a judgment module for analyzing the crop water use efficiency paradox situation of the target area according to the crop water use efficiency paradox index.

[0009] In another aspect of the present invention, there is provided an electronic device, which includes: a processor and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned crop water use efficiency paradox evaluation method.

[0010] In still another aspect of the present invention, there is provided a computer-readable storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, the code set or the instruction set is loaded and executed by a processor to implement the above-mentioned crop water use efficiency paradox evaluation method.

[0011] In still another aspect of the present invention, there is provided a computer program product, which causes the computer to execute the above-mentioned method when the computer program product runs on the computer.

[0012] The beneficial effects brought by the technical solution provided by the embodiments of the present invention are as follows: By acquiring raster-scale resource and environment data of the target area, processing the raster-scale resource and environment data based on a trained machine learning model to obtain raster-scale crop blue water requirements, wherein the training samples used in training the machine learning model include: site-scale resource and environment data of the target area as independent variables and site-scale crop blue water requirements of the target area as dependent variables; calculating crop water productivity based on the raster-scale crop blue water requirements; obtaining a crop water use efficiency paradox index based on the raster-scale crop blue water requirements and the crop water productivity; and analyzing the crop water use efficiency paradox situation of the target area according to the crop water use efficiency paradox index, a grid-scale crop water use efficiency paradox index can be obtained, so as to manage water resources in the target area in a targeted manner and reduce the waste of environmental resources and human, financial and material resources. Description of the Drawings

[0013] Figure 1It is the flowchart of the crop water use efficiency paradox evaluation method provided by the first embodiment of the present invention; Figure 2 It is the schematic structural diagram of the crop water use efficiency paradox evaluation device provided by the second embodiment of the present invention. Detailed implementation manners

[0014] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0015] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0016] It should be understood that the term "and / or" used herein is only a description of the associated relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0017] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if it is monitored (stated condition or event)" can be interpreted as "when it is determined" or "in response to determining" or "when (stated condition or event) is detected" or "in response to detecting (stated condition or event)".

[0018] The embodiments of the present application provide a crop water use efficiency paradox evaluation method, device and computer program product, which have the advantages of low cost and high efficiency compared with the prior art, and can reflect the spatio-temporal dynamic laws of the crop water use efficiency paradox.

[0019] To achieve the above technical effects, the general idea of the present application is as follows: A crop water use efficiency paradox evaluation method, the method includes steps: S101: Obtain the grid-scale resource and environment data of the target area; S102: Process the raster-scale resource and environment data based on the trained machine learning model to obtain the raster-scale crop blue water demand. The training samples used during the training of the machine learning model include: the site-scale resource and environment data of the target area as the independent variable and the site-scale crop blue water demand of the target area as the dependent variable; S103: Calculate the crop water productivity based on the raster-scale crop blue water demand; S104: Obtain the crop water use efficiency paradox index based on the raster-scale crop blue water demand and the crop water productivity; S105: Analyze the crop water use efficiency paradox situation in the target area according to the crop water use efficiency paradox index.

[0020] See Figure 1 , an embodiment of the present invention provides a method for evaluating the crop water use efficiency paradox, which includes the following steps: Step S101: Obtain the raster-scale resource and environment data of the target area.

[0021] The target area can be, for example, a provincial administrative region or an inter-provincial river basin, and this embodiment does not limit this. The resource and environment data includes but is not limited to the annual average temperature, annual precipitation, annual evapotranspiration, digital elevation model (DEM, Digital Elevation Model) data, soil type, soil texture (such as sand particles, silt particles, clay particles), and soil available water content. The acquisition method of the site-scale resource and environment data can be the prior art, and this method does not limit this.

[0022] Step S102: Process the raster-scale resource and environment data based on the trained machine learning model to obtain the raster-scale crop blue water demand.

[0023] The training samples used during the training of the machine learning model include: the site-scale resource and environment data of the target area as the independent variable and the site-scale crop blue water demand of the target area as the dependent variable.

[0024] The calculation method of the site-scale crop blue water demand in the target area is as follows: First, it is necessary to calculate the daily reference evapotranspiration for each meteorological station in the target area , and this method uses the Penman-Monteith (P-M) formula modified by the Food and Agriculture Organization (FAO) of the United Nations to calculate the daily reference evapotranspiration . This calculation method is the only currently recommended standard method for calculating evapotranspiration. The calculation can be performed with time steps such as daily, dekadal, and monthly, and the calculation accuracy is higher with a daily time step. Therefore, the present invention uses a daily time step. The specific calculation formula is as follows: Wherein, is the daily reference evapotranspiration; is the slope related to the temperature curve and saturation water vapor pressure (KPa / ℃); is the net radiation amount on the plant surface layer (MJ / m2·d); G is the soil heat flux (MJ / m2·d), usually taken as 0; is the common amount of dryness and humidity (KPa / ℃); is the average temperature of the air (℃); is the wind speed at 2 m above the ground (m / s); is the saturation water vapor pressure (Kpa); is the actual observed water vapor pressure difference (Kpa). In the monitoring of meteorological stations, the installation height of the anemometer is usually 10 m above the ground. Therefore, in this paper, the logarithmic wind speed profile relationship is used to convert the daily wind speed observed at each meteorological station into the wind speed value at 2 m above the ground. The calculation formula is as follows: Wherein, is the height (m), is the wind speed at the height of (m / s).

[0025] Then, based on the above daily reference evapotranspiration, the daily crop potential evapotranspiration is calculated by combining the crop type and the crop growth and development stage. The calculation formula is as follows: Wherein, is the potential evapotranspiration of the crop on the th day, with the unit of mm; is the crop coefficient of the crop on the th day, is the daily reference evapotranspiration. Through this formula, the reference evapotranspiration on the th day can be calculated. Since the crop coefficient of the same crop varies in different growth and development stages, the piecewise single-value averaging method is adopted in this method to calculate the crop coefficient . This method divides the change of the crop coefficient during the whole growth period into three standard values in four stages: the initial growth stage, the rapid growth stage, the middle growth stage, and the late growth stage: , and . The constants and Correspond to the initial growth stage and the mid - growth stage respectively; during the rapid growth period, it increases from to at a fixed daily growth rate; at the end - growth stage, it decreases from to at a fixed daily reduction rate. In one of the embodiments, due to the environmental conditions of topsoil freezing and crop dormancy in winter in northern China, the crop coefficient is very small. Therefore, for winter wheat and winter rape in northern China, the crop coefficient during the over - wintering period needs to be added. The three standard crop coefficient values mentioned above represent the crop coefficients under the conditions of air humidity of about 45%, wind speed of about 2 m / s, sufficient water supply, good management, normal growth, and high - yield in large areas. However, due to limiting factors such as air humidity, wind speed, and operation factors, the standard values are not generally applicable in China. Therefore, based on the standard crop coefficients at each growth stage of the above - mentioned crops, this method corrects the of each meteorological station according to the actual climate and management conditions observed by each meteorological station. The specific calculation formula is as follows: In the formula, is the standard crop coefficient at each growth stage of crop , is the average value of the minimum relative humidity at each growth stage, is the average height of crop at each growth stage, with the unit of m. That is to say, for the crop coefficient of crop i on the t - th day, first determine the growth stage of crop i on the t - th day, and thus determine the standard crop coefficient of crop i at this growth stage (for example: if crop i is in the initial growth stage, then use the value of this crop as the value), and then obtain according to the above - mentioned correction formula, and use the obtained value as the value of crop coefficient .

[0026] Finally, calculate the crop blue - water demand at the station scale according to the daily crop potential evapotranspiration. First, calculate the daily actual evapotranspiration of the crop, and its calculation is as follows: In the formula, is the actual evapotranspiration of crop on the - th day, with the unit of mm; is the water stress coefficient (dimensionless) of crop on the - th day, and its calculation formula is as follows: In the formula, is the actual soil water content of the crop at the th day; is the maximum available soil water content, which can be calculated by multiplying the available soil water content by the rooting depth of the crop; is the maximum available soil water content that the crop can absorb from the soil in the root zone at the th day under non-water stress conditions, and its proportion is calculated as follows: In the formula, is the effective depletion fraction of the crop ; According to the principle of soil water balance, the calculation formula is as follows: In the formula, is the actual soil water content of the crop at the th day; can take the value of 1 (day); is the effective precipitation on the th day, which can be calculated according to CROPWAT (an application developed by the Food and Agriculture Organization of the United Nations for calculating crop water requirements and formulating irrigation plans); is the irrigation water volume of crop i on the th day; is the actual evapotranspiration of crop i on the tth day, is the runoff of crop i on the th day, and its calculation formula is as follows: In the formula, is a parameter related to crop management conditions. In one of the embodiments, the value for irrigated crops is 3, and the value for rainfed crops is 2.

[0027] Through the above steps, the actual evapotranspiration of various crops under water stress can be calculated . The difference between the potential evapotranspiration of the crop under non-water stress and is the irrigation water requirement, that is, the blue water demand. Finally, by accumulating the daily blue water demands during the growth period of different crops, the blue water demand for the entire growth period of each crop is obtained, that is, the blue water demand of crops at the station scale. The blue water demand of crops at the station scale is calculated according to the following formula: Wherein, is the blue water demand per unit area of the crop during the growth period, that is, the blue water demand of the crop at the station scale; is the total number of days in the crop growth period. For each crop, the blue water demand of the crop corresponding to the station scale can be calculated by using this formula.

[0028] Through the above steps, the blue water demand of the crops at the meteorological station scale in this area can be obtained.

[0029] Use a machine learning model to calculate at the spatial scale for spatial prediction to obtain the blue water demand of the crop at the grid scale. This method preferably uses a random forest model, which is an ensemble algorithm. By combining multiple weak classifiers, the final result is obtained through voting or taking the mean, so that the result of the overall model has high accuracy and generalization performance. It should be noted that for different crops, their blue water demands are different, so each crop corresponds to a machine learning model for predicting the blue water demand at the grid scale.

[0030] In this method, the input data is the grid-scale resource and environment data. Different resource and environment data will lead to different crop water demands. For example, when the temperature is high, the precipitation is low, and the evapotranspiration is large, the crop water demand will increase; the sandy soil has weak water holding capacity and fast evaporation, so the crop water demand is large; the black-brown soil absorbs more heat and has large evaporation, while the yellow-white soil has strong reflection and relatively less evaporation, etc.

[0031] Before using the machine learning model, the machine learning model needs to be trained to obtain a trained machine learning model. Specifically, it includes: constructing a data set, which includes multiple training subsets, each training subset corresponds to a crop, and includes multiple training samples. The input of the training data is: the resource and environment data at the station scale, and the data acquisition method can be the prior art, which is not limited in this method. The output is: the blue water demand of the crop at the station scale, which is calculated through the foregoing steps; then use the data set to train the machine learning model to obtain a trained machine learning model. In one embodiment, for a certain training subset, it is randomly divided into 10 training sub-subsets of equal size, and 7 of them are used for training. The remaining 3 sub-subsets are used for model performance verification, and the verification times are 100 times. At the same time, indicators such as the coefficient of determination (R2), root mean square error (RMSE), and normalized root mean square error (NRMSE) are used to evaluate the model performance.

[0032] Through the above training process, a trained machine learning model is obtained. Since the model has the ability of spatial prediction, by inputting the grid-scale resource and environment data into the model, the blue water demand of the crop at the grid scale can be obtained.

[0033] Step S103: Calculate the crop water productivity based on the grid-scale crop blue water requirement.

[0034] First, it is necessary to calculate the crop water productivity. In the water balance framework proposed by the International Water Management Institute (IWMI), the crop water productivity is the main indicator used to evaluate the crop water use efficiency, and it is defined as the irrigation water consumption of the crop under specific crop varieties and cultivation conditions. On this basis, in order to comparably reflect the comprehensive water use efficiency of each region, this method also converts the crop yield (kg) into calorific value (kcal) based on the food supply calorific value method. The specific calculation method is as follows: In the formula, is the total amount of blue water footprint of the crop in the grid cell ; is the blue water requirement of the crop in the grid cell ; is the irrigation area of the crop ; 10 is the conversion factor, (kcal m ) is the crop water productivity expressed in calorific value in the grid cell , and in one embodiment -3 the time unit is year; is the number of crop types; is the yield of the crop in the grid cell ; is the edible ratio of the crop ; is the calorific value per 100 grams of the crop , and its data can be obtained from the food balance sheet of the Food and Agriculture Organization of the United Nations (FAO).

[0035] The crop water productivity can be obtained through the above calculation steps .

[0036] Step S104: Obtain the crop water use efficiency paradox index based on the grid-scale crop blue water requirement and the crop water productivity.

[0037] First, it is necessary to calculate the water shortage index according to the grid-scale crop blue water requirement , and calculate the water shortage index according to the following formula: In the formula, is the water shortage index of the grid cell , and in one embodiment, Taking years as the time unit. is the grid cell total available blue water for agriculture (km 3 yr -1 , cubic kilometers per year). is the available amount of natural water resources for the grid cell In one embodiment, provincial annual natural water resource amounts (including surface water and groundwater) data are obtained according to the "China Water Resources Bulletin", and are downscaled to monthly grid data based on the China Natural Runoff Dataset Version 1.0 (CNRD v1.0) with a spatial resolution of 0.25 degrees as the available amount of natural water resources. is the minimum blue water demand for environmental ecological flow of the grid cell In the present invention, the variable monthly flow method (VMF) is used for calculation. According to dry months, normal months, and wet months, 60%, 45%, and 30% of the monthly average natural water resource amounts are respectively retained as the minimum blue water demand for environmental ecological flow. is the non-agricultural irrigation water demand of the grid cell (including sectors such as municipal, industrial production, animal husbandry, primary energy extraction, power generation, etc.). The above grid data are all resampled to a resolution of 1 km. Finally, the water shortage index is divided into four levels: low (corresponding value is 0 - 1), medium (corresponding value is 1 - 1.5), significant (corresponding value is 1.5 - 2), and severe (corresponding value > 2).

[0038] Finally, the crop water use efficiency paradox index PI is calculated based on the crop water productivity and the water shortage index. PI is the ratio of the change multiple of the water shortage index WSI relative to the reference period to the change multiple of the crop water productivity CWPC relative to the reference period. The reference period can be determined according to requirements. In one embodiment, data from 1991 - 2000 (1990s) are used as the baseline to calculate the crop water use efficiency paradox for 2001 - 2010 (2000s) and 2011 - 2019 (2010s). Then the data from 1991 - 2000 (1990s) are the reference period. The calculation formula for the crop water use efficiency paradox index is as follows: In the formula, is the crop water use efficiency paradox index of the grid cell in the period . and are respectively the average water shortage indices of the grid cell in the period and the reference period . The average water shortage index is the annual average of the water shortage index in the period and the water shortage index in the reference period Annual average value; and are respectively the in the period and the baseline period The average crop water productivity, and the average crop water productivity is the annual average value of the crop water productivity in the period and the annual average value of the crop water productivity in the baseline period The crop water productivity is calculated in calories per unit of water use; the baseline period is the time period before the period , and the period and the baseline period The water shortage index is calculated in the same way as the crop water productivity. Taking the period from 2001 to 2010 as an example, the calculation process of the average water shortage index of the grid cell in this period is as follows: First, calculate the water shortage index of the grid cell each year, and then sum and take the average.

[0039] Step S105: Analyze the crop water use efficiency paradox situation in the target area according to the crop water use efficiency paradox index.

[0040] The judgment condition for the occurrence of the crop water use efficiency paradox is: when is greater than 1 and both the numerator and denominator in the formula for calculating are greater than 1. Since both the water shortage index and the crop water productivity have increased compared to the baseline period, and the increase rate of the water shortage index is higher than that of the crop water productivity, that is, the increase in crop water productivity has not reduced the crop water use and agricultural water shortage risk as expected, so the crop water use efficiency paradox appears. The larger the

[0041] value, the higher the increase rate of the water shortage index compared to the increase rate of the crop water productivity, and the stronger the intensity of the crop water use efficiency paradox. Among them, is the number of grid cells in the target area, CWPC and WSL are respectively the crop water productivity and the water shortage index of the target area, both in years; is the crop water use efficiency paradox index of the target area in the period . When this index meets the judgment condition of the crop water use efficiency paradox, it means that the crop water use efficiency paradox appears in the target area; The larger the value is, the higher the increase rate of the water shortage index in the target area compared to the increase rate of crop water productivity, and the stronger the intensity of the crop water use efficiency paradox.

[0042] In the embodiments of the present invention, by comprehensively considering the changes in crop water productivity and agricultural water shortage index over a long time series, the change rates of various indicators compared to the baseline period are evaluated, thereby reflecting the situation of the crop water use efficiency paradox. Compared with the prior art, it has the advantages of low cost and high efficiency, and can reflect the spatio-temporal dynamic laws of the crop water use efficiency paradox. Since this method is carried out at the grid scale, the obtained results can comprehensively reflect the situation of the crop water use efficiency paradox at the regional scale, and can more conveniently carry out targeted and specific planning measures, manage and adjust from grid cells, thereby effectively alleviating the problem of the crop water use efficiency paradox and reducing unnecessary waste of manpower and financial resources.

[0043] In another embodiment of this method, 15 major crops in China from 1991 to 2019, such as wheat (winter wheat, spring wheat), corn (spring corn, summer corn), rice (early rice, late rice, single-season rice), soybean, peanut, potato, cotton, sugarcane, beet, and rapeseed (spring rapeseed, winter rapeseed), are used as the research objects. The sown areas of these crops exceed 77% of the total harvested area of crops in China, and the total output exceeds 72% of the total crop output. Among them, the statistical data from 1991 to 2005 are based on the 2000 crop yield spatial allocation (Spatial Production Allocation Model, SPAM 2000) dataset for spatial allocation of the sown areas and total yields of crops in major planting systems in China, while the agricultural statistical data from 2006 to 2019 are based on SPAM2010 data for spatial allocation.

[0044] The above data samples analyzed by this method show that in the past thirty years in China, the crop water use efficiency paradox is very obvious nationwide and in regions such as Northeast, Northwest, North China, Central China, South China, and East China. In these regions, WSI and CWPC increase synergistically. This method also calculates the crop water use efficiency paradox index (using 1991 - 2000 (1990s) as the baseline period). Greater than 1 indicates that the WSI growth rate exceeds the CWPC growth rate. The results show that the national average is 1.02, and this paradox exists in 42.93% of the regions in China, and in more than half of these regions is greater than 1.

[0045] See Figure 2, an embodiment of the present invention provides a device for evaluating the crop water use efficiency paradox, the device includes: a data acquisition module 201, a grid-scale data obtaining module 202, a first calculation module 203, a second calculation module 204, and a judgment module 205.

[0046] Among them, the data acquisition module 201 is used to acquire grid-scale resource and environment data of the target area; the grid-scale data obtaining module 202 is used to process the grid-scale resource and environment data based on the trained machine learning model to obtain the grid-scale crop blue water demand. The training samples used during the training of the machine learning model include: the site-scale resource and environment data of the target area as the independent variable and the site-scale crop blue water demand of the target area as the dependent variable; the first calculation module 203 is used to calculate the crop water productivity based on the grid-scale crop blue water demand; the second calculation module 204 is used to obtain the crop water use efficiency paradox index according to the grid-scale crop blue water demand and the crop water productivity; the judgment module 205 is used to analyze the water use efficiency paradox status of the target area according to the crop water use efficiency paradox index.

[0047] Optionally, the grid-scale data obtaining module 202 is specifically used for: calculating the daily reference evapotranspiration; calculating the daily crop potential evapotranspiration according to the daily reference evapotranspiration; calculating the site-scale crop blue water demand according to the daily crop potential evapotranspiration.

[0048] Optionally, the grid-scale data obtaining module 202 includes: a daily reference evapotranspiration calculation unit, which is specifically used for: calculating the daily reference evapotranspiration according to the following formula: , where is the daily reference evapotranspiration; is the slope related to the temperature curve and the saturation water vapor pressure; is the net radiation amount of the plant surface layer; G is the soil heat flux; is the common amount of dryness and humidity; is the average temperature of the air; is the wind speed at 2 m above the ground; is the saturation water vapor pressure; is the actual observed water vapor pressure difference.

[0049] Optionally, the first calculation unit includes: a daily crop potential evapotranspiration calculation unit, which is specifically used for: calculating the daily crop potential evapotranspiration according to the following formula: , where is the crop on the th day of potential evapotranspiration, with the unit of mm; is the crop on the th day of crop coefficient.

[0050] Optionally, the first calculation unit includes: a site-scale crop blue water demand calculation unit, which is specifically configured to calculate the actual evapotranspiration of the crop according to the following formula: , where For crops In the Actual evapotranspiration of the day; For crops In the The water stress coefficient of the day is calculated; the blue water demand of crops at the site scale is calculated according to the following formula: , where For crops The blue water demand per unit area during the growing season, i.e. the blue water demand of crops at the site scale, is the total number of days in the crop growth period.

[0051] Optionally, the grid-scale data acquisition module 202 is specifically used to: construct a data set, the data set includes multiple training subsets, each training subset corresponds to a crop, and the training subset includes multiple training samples; use the data set to train a machine learning model to obtain a trained machine learning model; wherein there are multiple machine learning models, each machine learning model corresponds to a crop, and the machine learning model is used to predict the grid-scale blue water demand of the corresponding crop.

[0052] Optionally, the first calculation module 203 is specifically configured to calculate the crop water productivity according to the following formula: , where Grid cells middling crops Total blue water footprint of Grid cells middling crops blue water demand; For crops of irrigated area; 10 is the conversion factor, Grid cells Crop water productivity expressed in kcal m -3 , is the number of crop species, Grid cells middling crops The output, For crops The edible ratio, For every 100 grams of crops caloric value.

[0053] Optionally, the second calculation module 204 is specifically configured to: calculate the water shortage index based on the grid-scale crop blue water demand, and the calculation formula of the water shortage index is as follows: , where is the water shortage index of the grid cell . is the total available blue water for agriculture of the grid cell ; is the available amount of natural water resources of the grid cell ; is the minimum blue water demand for environmental ecological flow of the grid cell ; is the non-agricultural irrigation water demand of the grid cell ; The crop water use efficiency paradox index is calculated based on the crop water productivity and the water shortage index, and the calculation formula of the crop water use efficiency paradox index is as follows: , where is the crop water use efficiency paradox index of the grid cell in the period ; and are the average water shortage indexes of the grid cell in the period and the reference period respectively. The average water shortage index is the annual average of the water shortage index in the period and the annual average of the water shortage index in the reference period ; and are the average crop water productivities of the grid cell in the period and the reference period respectively. The average crop water productivity is the annual average of the crop water productivity in the period and the annual average of the crop water productivity in the reference period . The crop water productivity is calculated in calories per unit water use; The reference period is the time period before the period .

[0054] Optionally, the judgment module 205 is specifically configured to: The judgment condition for the occurrence of the crop water use efficiency paradox is: when is greater than 1 and both the numerator and denominator in the formula for calculating are greater than 1. Since both the water shortage index and the crop water productivity have increased compared to the reference period, and the increase ratio of the water shortage index is higher than the increase ratio of the crop water productivity, that is, the increase in crop water productivity does not reduce crop water consumption and agricultural water shortage risk as expected, so the crop water use efficiency paradox appears. The larger the value is, the higher the increase rate of the water shortage index is compared with the increase rate of crop water productivity, and the stronger the intensity of the crop water use efficiency paradox is.

[0055] For the target area, usually the target area is divided into multiple grids, and the regional crop water use efficiency paradox index is calculated according to the following formula: Among them, is the number of grid cells in the target area, CWPC and WSL are the crop water productivity and water shortage index of the target area respectively, both in years; is the crop water use efficiency paradox index of the target area in the period When this index meets the judgment conditions of the crop water use efficiency paradox, it indicates that the crop water use efficiency paradox appears in the target area; The larger the value is, the higher the increase rate of the water shortage index of the target area is compared with the increase rate of crop water productivity, and the stronger the intensity of the crop water use efficiency paradox is.

[0056] It should be noted that: when evaluating the crop water use efficiency paradox by the crop water use efficiency paradox evaluation device provided in the above embodiments, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the crop water use efficiency paradox evaluation device provided in the above embodiments and the embodiments of the crop water use efficiency paradox evaluation method belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be repeated here.

[0057] An embodiment of the present invention provides an electronic device, which includes: a memory and a processor. The processor is connected to the memory and is configured to execute the above-mentioned crop water use efficiency paradox evaluation method based on the instructions stored in the memory. The number of processors can be one or more, and the processor can be a single-core or multi-core processor. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one storage chip. The memory can be an example of the following computer-readable medium. An embodiment of the present invention provides a computer-readable storage medium, on which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, the code set or the instruction set is loaded and executed by a processor to implement the above-mentioned method for evaluating the crop water use efficiency paradox. The computer-readable storage medium includes: permanent and non-permanent, removable and non-removable media can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of the computer's storage medium include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc-read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information accessible by a computing device.

[0058] As is known by technical common sense, the present invention can be implemented by other embodiments that do not depart from its spiritual essence or essential features. Therefore, the above-disclosed embodiments are illustrative in all aspects and not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are encompassed by the present invention.

Claims

1. A method for evaluating the paradox of crop water use efficiency, characterized in that, The method includes: Obtaining the grid-scale resource and environment data of the target area; Processing the grid-scale resource and environment data based on the trained machine learning model to obtain the grid-scale crop blue water requirement. The training samples used in training the machine learning model include the site-scale resource and environment data of the target area as independent variables and the site-scale crop blue water requirement of the target area as the dependent variable; Calculating the crop water productivity based on the grid-scale crop blue water requirement; Obtaining the crop water use efficiency paradox index based on the grid-scale crop blue water requirement and the crop water productivity; Analyzing the crop water use efficiency paradox situation of the target area according to the crop water use efficiency paradox index.

2. The method according to claim 1, characterized in that The site-scale crop blue water requirement is obtained through the following steps: Calculating the daily reference evapotranspiration; Calculating the daily crop potential evapotranspiration based on the daily reference evapotranspiration; Calculating the site-scale crop blue water requirement based on the daily crop potential evapotranspiration.

3. The method according to claim 2, wherein The calculating the daily reference evapotranspiration includes: Calculating the daily reference evapotranspiration according to the following formula: Wherein, is the daily reference evapotranspiration; is the slope related to the temperature curve and saturated water vapor pressure; is the net radiation flux at the plant surface; G is the soil heat flux; is the common quantity of dryness and humidity; is the average temperature of the air; is the wind speed at 2 m above the ground; is the saturated water vapor pressure; is the actual observed water vapor pressure difference.

4. The method according to claim 3, wherein The calculating the daily crop potential evapotranspiration based on the daily reference evapotranspiration includes: Calculating the daily crop potential evapotranspiration according to the following formula: In the formula, is the potential evapotranspiration of the crop on the th day, with the unit of mm; is the crop coefficient of the crop on the th day.

5. The method according to claim 4, characterized in that, The calculating the site-scale crop blue water requirement based on the daily crop potential evapotranspiration includes: Calculating the actual evapotranspiration of the crop according to the following formula: In the formula, is the actual evapotranspiration of the crop on the th day; is the water stress coefficient of the crop on the th day. Calculating the site-scale crop blue water requirement according to the following formula: In the formula, is the blue water requirement per unit area of the crop during the growth period, that is, the blue water requirement of the crop at the site scale; is the total number of days in the crop growth period.

6. The method according to claim 1, wherein Before processing the grid-scale resource and environment data based on the trained machine learning model to obtain the grid-scale crop blue water requirement, it further includes: constructing a data set, the data set includes multiple training subsets, each training subset corresponds to a crop, and the training subset includes multiple training samples; Training the machine learning model using the data set to obtain a trained machine learning model; Among them, there are multiple machine learning models, each machine learning model corresponds to a crop, and the machine learning model is used to predict the grid-scale crop blue water requirement of the corresponding crop.

7. The method according to claim 1, characterized in that, The calculating the crop water productivity based on the grid-scale crop blue water requirement includes: Calculate the crop water productivity according to the following formula: Where, Grid cells middling crops Total blue water footprint of Grid cells middling crops blue water demand; Grid cells middling crops of irrigated area; 10 is the conversion factor, Grid cells Crop water productivity expressed in kcal m -3 , is the number of crop species, Grid cells middling crops The output, For the crops The edible ratio, For every 100 grams of the crop caloric value.

8. The method according to claim 7, wherein The obtaining the crop water use efficiency paradox index based on the grid-scale crop blue water requirement and the crop water productivity includes: Calculating the water shortage index through the grid-scale crop blue water requirement, and the formula for the water shortage index is as follows: In the formula, is the water shortage index of the grid cell ; is the total available blue water for agriculture of the grid cell ; is the available amount of natural water resources of the grid cell ; is the minimum blue water demand for environmental ecological flow of the grid cell ; is the non-agricultural irrigation water demand of the grid cell . Calculating the crop water use efficiency paradox index based on the crop water productivity and the water shortage index, and the formula for the crop water use efficiency paradox index is as follows: Wherein, is the grid cell in the period of the crop water use efficiency paradox index; and are respectively the average water shortage indexes of the grid cell in the period and the base period The average water shortage index is the annual average value of the water shortage index in the period and the annual average value of the water shortage index in the base period ; and are respectively the average crop water productivities of the grid cell in the period and the base period The average crop water productivity is the annual average value of the crop water productivity in the period and the annual average value of the crop water productivity in the base period The crop water productivity is calculated in calories per unit water use; the base period is the time period before the period .

9. An evaluation device for the paradox of crop water use efficiency, characterized in that, The device includes: A data acquisition module for obtaining the grid-scale resource and environment data of the target area; A raster-scale data acquisition module, configured to process the raster-scale resource and environment data based on a machine learning model that has completed training, so as to obtain the raster-scale crop blue water requirement. The training samples used during the training of the machine learning model include: the site-scale resource and environment data of the target area as an independent variable and the site-scale crop blue water requirement of the target area as a dependent variable; A first calculation module, configured to calculate the crop water productivity based on the raster-scale crop blue water requirement; A second calculation module, configured to obtain the crop water use efficiency paradox index based on the raster-scale crop blue water requirement and the crop water productivity; A judgment module, configured to analyze the crop water use efficiency paradox status of the target area based on the crop water use efficiency paradox index.

10. A computer program product, characterized in that, When the computer program product runs on a computer, the method according to any one of claims 1-8 is executed by the computer.

Images