Crop water use efficiency paradox evaluation method, device and computer program product

Abstract

The present invention discloses a crop water use efficiency paradox evaluation method, device, and computer program product, belonging to the field of agricultural irrigation technology. The method comprises: acquiring grid-scale resource and environmental data for a target region; processing the grid-scale resource and environmental data based on a trained machine learning model to obtain grid-scale crop blue water demand; calculating crop water productivity based on the grid-scale crop blue water demand; obtaining a crop water use efficiency paradox index based on the grid-scale crop blue water demand and crop water productivity; and analyzing the crop water use efficiency paradox status in the target region based on the crop water use efficiency paradox index. The device comprises a data acquisition module, a grid-scale data acquisition module, a first calculation module, a second calculation module, and a judgment module. The grid-scale crop water use efficiency paradox index can be obtained, enabling targeted water resource management in the target region and reducing waste of environmental resources, manpower, and financial resources.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and in particular to a method, device and computer program product for evaluating a 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 irrigated areas, with many beneficial effects. Nevertheless, the expansion of irrigated areas also results in enormous freshwater consumption, making water shortage a threat to sustainable agricultural development in many regions. Improving crop water use efficiency is generally considered one of the most effective ways to alleviate water shortages. However, a large body of evidence shows that the global agricultural system is facing a water-saving dilemma, primarily manifested in the contradiction between improving crop water use efficiency and increasingly severe water shortages. That is, improving crop water use efficiency does not necessarily lead to a reduction in total irrigation water use, leading to the water use efficiency paradox.

[0003] There are two main existing technologies to deal with the above-mentioned water use efficiency paradox:

[0004] First, based on the water resource accounting framework and the definition of the irrigation efficiency paradox, a method for determining the irrigation efficiency paradox was established at the field, irrigation district, and watershed scales to detect the irrigation efficiency paradox across spatial scales. Irrigation efficiency was calculated as the ratio of beneficial irrigation water (primarily crop evapotranspiration) to total irrigation water per unit land throughout the year. Water use was calculated by calculating crop evapotranspiration for both flooding and drip irrigation. The irrigation efficiency paradox is defined as a situation where agricultural water use actually increases when irrigation efficiency increases (for example, by switching from flooding to drip irrigation). This technology establishes a system for determining the irrigation efficiency paradox at different scales, including farmland, irrigation district, and watershed, providing a localized approach to alleviating agricultural water tensions.

[0005] Second, the AquaCrop method was used to quantify irrigation water demand, thereby calculating irrigation water productivity and water scarcity footprint. Hotspot analysis explored the relationship between efficiency and water scarcity, thereby assessing the reverse of water productivity in terms of crop yield and total water consumption. To identify hotspots, irrigation water productivity and water scarcity footprints at the grid and agro-economic zone scales were categorized as low, medium, and high, resulting in nine possible combinations of irrigation water productivity and water scarcity footprint. These combinations were mapped using a color-coded matrix, and the corresponding crop area for each color was calculated and expressed as a percentage of the total crop area. Hotspots were defined as areas with low overall water efficiency coefficients but high water use coefficients, indicating that crop production in water-scarce areas consumes a significant amount of irrigation water. This method reveals that improvements in overall crop water efficiency lead to increased irrigation demand and water scarcity.

[0006] However, current research methods for the crop water use efficiency paradox still have significant shortcomings in terms of quantitative assessment and spatial analysis. From a quantitative perspective, existing technologies can only assess the regional and spatial distribution of the crop water use efficiency paradox, but cannot quantitatively measure the strength of the paradox. There is a lack of quantitative indicators to describe the degree of the contradiction between improved crop water use efficiency and increased water use. As a result, paradox analysis cannot identify areas with severe water shortages, making it difficult to reflect the varying degrees of water stress between regions and develop differentiated water resource management plans.

[0007] Furthermore, the aforementioned paradox assessment techniques are often conducted at the scale of small watersheds or stations. While these fine-scale surveys can obtain accurate data through field measurements, they present significant challenges when assessing entire provinces or interprovincial watersheds. These methods are characterized by high costs and significant human and material resources. Currently, there is a lack of large-scale, spatially robust paradox assessment methods, making it difficult to comprehensively assess water scarcity across large regions. Furthermore, there is a lack of understanding of the spatiotemporal dynamics of crop water use efficiency paradoxes at both large and fine scales. Summary of the Invention

[0008] In order to solve the problems existing in the prior art, the present invention provides a method for evaluating the paradox of crop water use efficiency, which comprises:

[0009] Obtaining grid-scale resource and environmental data of the target area: processing the grid-scale resource and environmental data based on a trained machine learning model to obtain grid-scale crop blue water demand, wherein the training samples used in training the machine learning model include: site-scale resource and environmental data of the target area as independent variables and site-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 a 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 status of the target area based on the crop water use efficiency paradox index.

[0010] In another aspect, the present invention provides a device for evaluating the paradox of crop water use efficiency, comprising:

[0011] A data acquisition module is used to acquire grid-scale resource and environmental data of a target area; a grid-scale data acquisition module is used to process the grid-scale resource and environmental data based on a trained machine learning model to obtain grid-scale crop blue water demand, wherein the training samples used in training the machine learning model include: site-scale resource and environmental data of the target area as an independent variable and site-scale crop blue water demand of the target area as a dependent variable; a first calculation module is used to calculate crop water productivity based on the grid-scale crop blue water demand; a second calculation module is used to obtain a crop water use efficiency paradox index based on the grid-scale crop blue water demand and the crop water productivity; and a judgment module is used to analyze the crop water use efficiency paradox status of the target area based on the crop water use efficiency paradox index.

[0012] In another aspect of the present invention, an electronic device is provided, comprising: 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.

[0013] On the other hand, the present invention provides a computer-readable storage medium, which stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the above-mentioned crop water use efficiency paradox evaluation method.

[0014] In yet another aspect, the present invention provides a computer program product. When the computer program product is run on a computer, the computer executes the above method.

[0015] The technical solution provided by the embodiment of the present invention has the following beneficial effects:

[0016] By obtaining grid-scale resource and environmental data of the target area: the raster-scale resource and environmental data are processed based on the trained machine learning model to obtain the raster-scale crop blue water demand. The training samples used in the machine learning model training include: the site-scale resource and environmental 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 crop water productivity is calculated based on the raster-scale crop blue water demand; the crop water use efficiency paradox index is obtained based on the raster-scale crop blue water demand and crop water productivity; the crop water use efficiency paradox status of the target area is analyzed based on the crop water use efficiency paradox index, and the grid-scale crop water use efficiency paradox index can be obtained, so as to carry out targeted water resource management in the target area and reduce the waste of environmental resources and human and financial resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the crop water use efficiency paradox evaluation method provided in Example 1 of the present invention;

[0018] Figure 2 Schematic diagram of the structure of the crop water use efficiency paradox evaluation device provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] 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", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0021] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0022] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if monitoring (stated condition or event)" may be interpreted as "when determining" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0023] The embodiments of the present application provide a crop water use efficiency paradox evaluation method, device, and computer program product. Compared with the existing technology, they have the advantages of low cost and high efficiency, and can reflect the spatiotemporal dynamic laws of the crop water use efficiency paradox.

[0024] To achieve the above technical effects, the general ideas of this application are as follows:

[0025] A method for evaluating crop water use efficiency paradox, the method comprising the steps of:

[0026] S101: Acquire grid-scale resource and environmental data of the target area;

[0027] S102: Processing the grid-scale resource and environmental data based on the trained machine learning model to obtain the grid-scale crop blue water demand. The training samples used in training the machine learning model include: the site-scale resource and environmental data of the target area as an independent variable and the site-scale crop blue water demand of the target area as a dependent variable.

[0028] S103: Calculate crop water productivity based on the blue water demand of crops at the grid scale;

[0029] S104: derive the crop water use efficiency paradox index based on the grid-scale crop blue water demand and crop water productivity;

[0030] S105: Analyze the crop water use efficiency paradox status in the target area based on the crop water use efficiency paradox index.

[0031] See also Figure 1 , an embodiment of the present invention provides a method for evaluating the paradox of crop water use efficiency, which comprises the following steps:

[0032] Step S101: Obtain grid-scale resource and environmental data of a target area.

[0033] The target region can be, for example, a provincial administrative region or a trans-provincial river basin, and this embodiment does not limit this. Resource and environmental data includes, but is not limited to, annual average temperature, annual precipitation, annual evapotranspiration, digital elevation model (DEM) data, soil type, soil texture (e.g., sand, silt, clay), and soil effective moisture content. Site-scale resource and environmental data can be acquired using existing techniques, and this method does not limit this.

[0034] Step S102: Processing grid-scale resource and environmental data based on the trained machine learning model to obtain grid-scale crop blue water requirements.

[0035] The training samples used in training the machine learning model include: site-scale resource and environmental data of the target area as the independent variable and site-scale crop blue water demand of the target area as the dependent variable.

[0036] The blue water requirements of crops at the site level in the target area are calculated as follows:

[0037] First, it is necessary to calculate the daily reference evapotranspiration for each meteorological station in the target area. This method uses the Penman-Monteith (PM) formula modified by the Food and Agriculture Organization of the United Nations (FAO) to calculate the daily reference evapotranspiration. This calculation method is currently the only standard method recommended for calculating evapotranspiration. The calculation can be performed using time steps such as days, ten days, and months, among which the calculation accuracy is higher when the time step is day. Therefore, the present invention uses the day as the time step. The specific calculation formula is as follows:

[0038]

[0039] Where, is the daily reference evapotranspiration; is the slope of the temperature curve related to the saturated water vapor pressure (KPa / ℃); is the net radiation of the plant surface (MJ / m2·d); G is the heat flux of the soil (MJ / m2·d), which is usually taken as 0; is the commonly used quantity of humidity (KPa / ℃); is the average temperature of the air (℃); is the wind speed at 2 m above the ground (m / s); is the saturated water vapor pressure (Kpa); The actual observed water vapor pressure difference (KPa). In meteorological station monitoring, the anemometer is usually set at a height of 10m above the ground. Therefore, this paper uses the logarithmic wind speed profile relationship to convert the daily wind speed observed at each meteorological station into the wind speed value at 2m above the ground. The calculation formula is as follows:

[0040]

[0041] Where, is the height (m), For height Wind speed at (m / s).

[0042] Then, based on the above daily reference evapotranspiration, the daily potential evapotranspiration of crops is calculated in combination with crop type and crop growth and development stage. , the calculation formula is as follows:

[0043]

[0044] Where, For crops In the Daily potential evapotranspiration, in mm; For crops In the The crop coefficient of the day, is the daily reference evapotranspiration, and the formula can be used to calculate the The reference evapotranspiration of the same crop in different growth and development stages has different crop coefficients. Therefore, this method uses the segmented single value average method to calculate the crop coefficient This method uses the crop coefficient of the whole growth period The changes in growth are divided into three standard values ​​for the four stages of early growth, rapid growth, mid-growth and late growth: 、 and .constant and Corresponding to the early growth stage and the middle growth stage respectively; in the rapid growth stage, The fixed daily growth rate is Increase to At the end of growth, The fixed daily reduction rate is Reduce to In one embodiment, in the winter in northern my country, due to the freezing of the surface soil and the dormancy of crops, the crop coefficient is very small. Therefore, for winter wheat and winter rapeseed in northern my country, the crop coefficient for the 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 2m / s, sufficient water supply, good management, normal growth and large-scale high yield. However, due to the limitations of air humidity, wind speed and operational factors, the standard Therefore, this method is based on the standard crop coefficients of each crop growth stage and the actual climate and management conditions observed at each meteorological station. The specific calculation formula is as follows:

[0045]

[0046] Where, For crops Standardized crop coefficients at each growth stage, is the average minimum relative humidity at each growth stage, For crops The average height of each growth stage, in meters. That is, for the crop i on day t, the crop coefficient First, determine the growth stage of crop i on day t, and then determine the standard crop coefficient of crop i at that growth stage (for example, if crop i is in the early growth stage, then the standard crop coefficient of crop i is The value is value), and then according to the above correction formula we get , to obtain Crop coefficient The value of .

[0047] Finally, the site-scale crop blue water demand is calculated based on the daily crop potential evapotranspiration. First, the daily crop actual evapotranspiration is calculated as follows:

[0048]

[0049] Where, For crops In the Actual evapotranspiration per day, in mm; For crops In the The water stress coefficient of the day (dimensionless) is calculated as follows:

[0050]

[0051] Where, For crops In the The actual water content of the soil where the sky is located; is the maximum effective soil water content, which can be calculated by multiplying the effective soil water content by the crop rooting depth; Under no water stress conditions day crops The maximum available soil water content that can be absorbed from the soil in the root zone The ratio is calculated as follows:

[0052]

[0053] Where, For crops The effective depletion fraction; According to the principle of soil water balance, the calculation formula is as follows:

[0054]

[0055] Where, For crops In the The actual water content of the soil where the sky is located; The value can be 1 (day); For the The effective precipitation of the day can be calculated using CROPWAT (an application developed by the Food and Agriculture Organization of the United Nations for calculating crop water requirements and formulating irrigation plans); For crop i in the Daily irrigation water volume; is the actual evapotranspiration of crop i on day t, For crop i in the The daily runoff volume is calculated as follows:

[0056]

[0057] Where, is a parameter related to crop management conditions. In one embodiment, the value is 3 for irrigated crops and 2 for rainfed crops.

[0058] Through the above steps, the actual daily evapotranspiration of various crops under water stress can be calculated Potential evapotranspiration of crops without water stress and The difference is the irrigation water requirement, i.e., the blue water demand. Finally, the blue water demand for each crop during its entire growth period is calculated by summing up the daily blue water demand during the growth period of different crops, i.e., the site-scale crop blue water demand. The site-scale crop blue water demand is calculated using the following formula:

[0059]

[0060] Where, For crops Blue water demand per unit area during the growing season, i.e. site-scale crop blue water demand; is the total number of days in the crop growth period. For each crop, the site-scale blue water demand corresponding to that crop can be calculated using this formula.

[0061] Through the above steps, the blue water demand of crops in the region based on the weather station scale can be obtained.

[0062] Machine learning models are used to perform spatial predictions across spatial scales, yielding grid-scale crop blue water requirements. This method prioritizes the random forest model, an ensemble algorithm that combines multiple weak classifiers and then uses voting or averaging to achieve high accuracy and generalization. It's important to note that different crops have different blue water requirements, so each crop requires a corresponding machine learning model for predicting grid-scale blue water requirements.

[0063] The input data in this method is raster-scale resource and environmental data. Different resource and environmental data will lead to different crop water requirements. For example, high temperature, low precipitation, and large evaporation will increase crop water requirements; sandy soil has weak water holding capacity and rapid evaporation, resulting in large crop water requirements; dark brown soil absorbs a lot of heat and has a large evaporation rate, while yellow-white soil has strong reflectivity and relatively less evaporation.

[0064] Before using a machine learning model, it must be trained to obtain a fully trained model. This specifically involves constructing a dataset, which includes multiple training subsets. Each training subset corresponds to a crop and includes multiple training samples. The training data input is site-scale resource and environmental data. Data acquisition methods can be conventional, and this method is not limited to this. The output is site-scale crop blue water requirements, calculated through the aforementioned steps. The dataset is then used to train the machine learning model, obtaining a fully trained model. In one embodiment, a training subset is randomly divided into 10 equal-sized training subsets, seven of which are used for training. The remaining three subsets are used for model performance validation 100 times. Model performance is evaluated using metrics such as the regression coefficient of determination (R²), root mean square error (RMSE), and normalized root mean square error (NRMSE).

[0065] Through the above training process, a trained machine learning model is obtained. Since the model has spatial prediction capabilities, the blue water demand of crops at the raster scale can be obtained by inputting raster-scale resource and environmental data into the model.

[0066] Step S103: Calculate the crop water productivity based on the grid-scale crop blue water demand.

[0067] First, we need to calculate crop water productivity. In the water balance framework proposed by the International Water Management Institute (IWMI), crop water productivity is used as the primary indicator for evaluating crop water use efficiency. It is defined as the amount of irrigation water consumed by crops under specific crop varieties and cultivation conditions. On this basis, to reflect the comprehensive water use efficiency of various regions in a comparable manner, this method also converts crop yield (kg) into calorific value (kcal) based on the food supply calorie method. The specific calculation method is as follows:

[0068] Where, Grid cells middling crops Total blue water footprint; Grid cells middling crops blue water demand; For crops of irrigated area; 10 is the conversion factor, (kcal m -3 ) is the grid unit In one embodiment, the crop water productivity expressed in terms of heat is The time unit is year; is the number of crop species; Grid cells middling crops output; For crops edible proportion; For crops The caloric value per 100 grams can be obtained from the food balance sheets of the Food and Agriculture Organization of the United Nations (FAO).

[0069] The crop water productivity can be obtained through the above calculation steps .

[0070] Step S104: obtaining a crop water use efficiency paradox index based on the grid-scale crop blue water demand and crop water productivity.

[0071] First, the water shortage index needs to be calculated based on the blue water demand of crops at the grid scale. , the water shortage index is calculated according to the following formula:

[0072]

[0073] Where, Grid cells The water shortage index, in one embodiment, The time unit is years. Grid cells Total amount of blue water available for agriculture (km 3 yr -1 , cubic kilometers per year). Grid cells The available amount of natural water resources is obtained. In one embodiment, the provincial annual natural water resources (including surface water and groundwater) data are obtained according to the China Water Resources Bulletin, and are downscaled into monthly raster data based on the China Natural Runoff Dataset 1.0 (CNRD v1.0) with a spatial resolution of 0.25 degrees, as the available amount of natural water resources. Grid cells The present invention adopts the variable monthly flow method (VMF) to calculate the minimum blue water demand of environmental ecological flow, and retains 60%, 45% and 30% of the monthly average natural water resources as the minimum blue water demand of environmental ecological flow according to the dry month, normal month and high water month respectively. Grid cells Non-agricultural irrigation water demand (including municipal, industrial, animal husbandry, primary energy extraction, and power generation) is calculated. The above raster data were resampled to a 1 km resolution. The water stress index was ultimately categorized into four levels: low (corresponding to values ​​of 0-1), moderate (corresponding to values ​​of 1-1.5), significant (corresponding to values ​​of 1.5-2), and severe (corresponding to values ​​>2).

[0074] Finally, the crop water use efficiency paradox index (PI) is calculated based on the crop water productivity and water stress index. PI is the ratio of the change in the water stress index (WSI) relative to the baseline period to the change in the crop water productivity (CWPC) relative to the baseline period. The baseline period can be determined as needed. In one embodiment, the crop water use efficiency paradox for 2001-2010 (2000s) and 2011-2019 (2010s) is calculated using data from 1991-2000 (1990s) as the baseline. The 1991-2000 (1990s) data serves as the baseline period. The formula for calculating the crop water use efficiency paradox index is as follows:

[0075]

[0076] Where, Grid cells In the period The crop water use efficiency paradox index. and Grid cells In the period and base period The average water shortage index is the average water shortage index in the period The annual average value and water stress index in the base period The annual average value of and Grid cells In the period and base period The average crop water productivity is the crop water productivity in the period The annual average and crop water productivity in the base period The annual average of crop water productivity is calculated as the calories per unit of water use; the base period is the period Previous period and base period The water stress index is calculated in the same way as the crop water productivity. Taking 2001-2010 as an example, the grid unit During this period The calculation process of the average water shortage index is as follows: first calculate the grid cell The water stress index for each year was then summed and averaged.

[0077] Step S105: analyzing the crop water use efficiency paradox status in the target area according to the crop water use efficiency paradox index.

[0078] The judgment condition for the occurrence of crop water use efficiency paradox is: Greater than 1 and used for calculation Both the numerator and denominator in the formula are greater than 1. Since both the water stress index and crop water productivity have increased compared to the baseline period, and the rate of increase in the water stress index is higher than the rate of increase in crop water productivity, the improvement in crop water productivity has not reduced crop water use and reduced the risk of agricultural water stress as expected, thus resulting in a crop water use efficiency paradox. The larger the value, the higher the rate of increase of the water shortage index compared to the rate of increase of crop water productivity, and the stronger the intensity of the crop water use efficiency paradox.

[0079] For the target area, the target area is usually divided into multiple grids and the regional crop water use efficiency paradox index is calculated according to the following formula:

[0080]

[0081] in, is the grid cell number of the target area, CWPC and WSL are the crop water productivity and water stress index of the target area, respectively, both in years; For target areas during the period The crop water use efficiency paradox index is calculated. When the index meets the judgment conditions of the crop water use efficiency paradox, it means that the crop water use efficiency paradox has occurred in the target area. The larger the value, 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.

[0082] The embodiment of the present invention evaluates the rate of change of each indicator compared to the baseline period by integrating the changes in crop water productivity and agricultural water shortage index over a long period of time, thereby reflecting the crop water use efficiency paradox. Compared with the existing technology, it has the advantages of low cost and high efficiency, and can reflect the spatiotemporal dynamic laws of the crop water use efficiency paradox. Since this method is carried out on a grid scale, the results obtained can fully reflect the crop water use efficiency paradox on a regional scale, and can more conveniently develop targeted and specific planning measures, manage and adjust from the grid unit, thereby effectively alleviating the crop water use efficiency paradox problem and reducing unnecessary waste of manpower and financial resources.

[0083] In another example of this method, 15 major crops in my country from 1991 to 2019 were studied: wheat (winter wheat and spring wheat), maize (spring maize and summer maize), rice (early rice, late rice, and single-season rice), soybeans, peanuts, potatoes, cotton, sugarcane, sugar beets, and rapeseed (spring rapeseed and winter rapeseed). The sown area of ​​these crops accounted for over 77% of my country's total harvested area, and their total yield exceeded 72% of the country's total crop yield. The 1991–2005 statistical data were spatially allocated for the sown area and total yield of crops in China's major cropping systems based on the Spatial Production Allocation Model (SPAM) 2000 dataset, while the 2006–2019 agricultural statistical data were spatially allocated based on the SPAM 2010 data.

[0084] The above data samples analyzed by this method show that in the past three decades in my country, the crop water use efficiency paradox has been very obvious nationwide and in the Northeast, Northwest, North China, Central China, South China and East China. In these regions, WSI and CWPC have grown in synergy. This method also calculates the crop water use efficiency paradox index. (The base period is 1991-2000 (1990s)). A value greater than 1 indicates that the WSI growth rate exceeds the CWPC growth rate. The paradox is 1.02, and 42.93% of the regions in China have this paradox, and more than half of the regions Greater than 1.

[0085] See also Figure 2 An embodiment of the present invention provides a device for evaluating the paradox of crop water use efficiency, which includes: a data acquisition module 201, a grid-scale data acquisition module 202, a first calculation module 203, a second calculation module 204, and a judgment module 205.

[0086] Among them, the data acquisition module 201 is used to obtain grid-scale resource and environmental data of the target area; the raster-scale data acquisition module 202 is used to process the raster-scale resource and environmental data based on the trained machine learning model to obtain raster-scale crop blue water demand. The training samples used in the machine learning model training include: the site-scale resource and environmental 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 raster-scale crop blue water demand; the second calculation module 204 is used to obtain the crop water use efficiency paradox index based on the raster-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 based on the crop water use efficiency paradox index.

[0087] Optionally, the grid-scale data obtaining module 202 is specifically used to: calculate daily reference evapotranspiration; calculate daily crop potential evapotranspiration based on the daily reference evapotranspiration; and calculate site-scale crop blue water demand based on the daily crop potential evapotranspiration.

[0088] Optionally, the grid-scale data obtaining module 202 includes: a daily reference evapotranspiration calculation unit, which is specifically used to calculate the daily reference evapotranspiration according to the following formula: , where is the daily reference evapotranspiration; is the slope of the temperature curve related to the saturated water vapor pressure; is the net radiation of the plant surface; G is the heat flux of the soil; It is the commonly used amount of dryness and humidity; is the average temperature of the air; is the wind speed 2m above the ground; is the saturated water vapor pressure; It is the actual observation of water vapor pressure difference.

[0089] Optionally, the first calculation unit includes: a daily crop potential evapotranspiration calculation unit, which is specifically used to calculate the daily crop potential evapotranspiration according to the following formula: , where For crops In the Daily potential evapotranspiration, in mm; For crops In the Crop coefficient of the day.

[0090] 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.

[0091] 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.

[0092] 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 100g of crop caloric value.

[0093] Optionally, the second calculation module 204 is specifically configured to calculate a water shortage index by calculating the blue water demand of the crops at the grid scale. The water shortage index calculation formula is as follows: , where Grid cells water scarcity index. Grid cells of the total blue water available for agriculture; Grid cells the availability of natural water resources; Grid cells Minimum blue water demand for environmental ecological flow; Grid cells The non-agricultural irrigation water demand is calculated based on the crop water productivity and water shortage index. The crop water use efficiency paradox index calculation formula is as follows: , where Grid cells In the period The Crop Water Use Efficiency Paradox Index; and Grid cells In the period and base period The average water shortage index is the average water shortage index in the period The annual average value and water stress index in the base period The annual average value of and Grid cells In the period and base period The average crop water productivity is the crop water productivity in the period The annual average and crop water productivity in the base period The annual average of crop water productivity is calculated as the calories per unit of water use; the base period is the period The previous time period.

[0094] Optionally, the judgment module 205 is specifically configured to: determine the occurrence of crop water use efficiency paradox when: Greater than 1 and used for calculation Both the numerator and denominator in the formula are greater than 1. Since both the water stress index and crop water productivity have increased compared to the baseline period, and the rate of increase in the water stress index is higher than the rate of increase in crop water productivity, the improvement in crop water productivity has not reduced crop water use and reduced the risk of agricultural water stress as expected, thus resulting in a crop water use efficiency paradox. The larger the value, the higher the rate of increase of the water shortage index compared to the rate of increase of crop water productivity, and the stronger the intensity of the crop water use efficiency paradox.

[0095] For the target area, the target area is usually divided into multiple grids and the regional crop water use efficiency paradox index is calculated according to the following formula:

[0096]

[0097] in, is the grid cell number of the target area, CWPC and WSL are the crop water productivity and water stress index of the target area, respectively, both in years; For target areas during the period The crop water use efficiency paradox index is calculated. When the index meets the judgment conditions of the crop water use efficiency paradox, it means that the crop water use efficiency paradox has occurred in the target area. The larger the value, 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.

[0098] It should be noted that the crop water use efficiency paradox evaluation device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate the crop water use efficiency paradox evaluation. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be 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 embodiment and the crop water use efficiency paradox evaluation method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0099] An embodiment of the present invention provides an electronic device comprising: a memory and a processor. The processor is connected to the memory and configured to execute the above-described crop water use efficiency paradox evaluation method based on instructions stored in the memory. There may be one or more processors, and the processor may be single-core or multi-core. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and includes at least one memory chip. The memory may be an example of a computer-readable medium as described below.

[0100] An embodiment of the present invention provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the aforementioned crop water use efficiency paradox evaluation method. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented using any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media 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 cassettes, magnetic 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.

[0101] It is understood from common technical knowledge that the present invention may be implemented by other embodiments that do not depart from its spirit or essential features. Therefore, the embodiments disclosed above are, in all respects, merely illustrative and not exclusive. All modifications within the scope of the present invention or equivalent to the scope of the present invention are intended to be encompassed by the present invention.

Claims

1. A method for evaluating the paradox of crop water use efficiency, characterized in that: The method comprises: Obtain grid-scale resource and environmental data for the target area; Processing the grid-scale resource and environmental data based on the trained machine learning model to obtain grid-scale crop blue water requirements, wherein the training samples used in training the machine learning model include: site-scale resource and environmental data of the target area as an independent variable and site-scale crop blue water requirements of the target area as a dependent variable; The crop water productivity is calculated based on the blue water demand of the crop at the grid scale; Obtaining a crop water use efficiency paradox index according to the grid-scale crop blue water demand and the crop water productivity; Analyzing the crop water use efficiency paradox status in the target area according to the crop water use efficiency paradox index; The site-scale crop blue water demand is obtained by the following steps: Calculate the daily reference evapotranspiration; Calculating the daily crop potential evapotranspiration based on the daily reference evapotranspiration; Calculate the blue water demand of the crops at the site scale based on the daily potential evapotranspiration of the crops; The calculation of daily reference evapotranspiration includes: The daily reference evapotranspiration was calculated according to the following formula: Where, is the daily reference evapotranspiration; is the slope of the temperature curve related to the saturated water vapor pressure; is the net radiation of the plant surface; G is the heat flux of the soil; It is the commonly used amount of dryness and humidity; is the average temperature of the air; is the wind speed 2m above the ground; is the saturated water vapor pressure; It is the actual observed water vapor pressure difference; The daily crop potential evapotranspiration is calculated based on the daily reference evapotranspiration, including: The daily crop potential evapotranspiration was calculated according to the following formula: Where, For crops In the Daily potential evapotranspiration, in mm; For crops In the day's crop coefficient; The step of calculating the site-scale crop blue water demand based on the daily crop potential evapotranspiration includes: The actual evapotranspiration of the crop was calculated according to the following formula: Where, For crops In the Actual evapotranspiration of the day; For crops In the Water stress coefficient of the day; The blue water demand of crops at the site scale is calculated according to the following formula: Where, For crops 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; Before the grid-scale resource and environmental data are processed based on the trained machine learning model to obtain the grid-scale crop blue water demand, the method further includes: constructing a data set, the data set including a plurality of training subsets, each of the training subsets corresponding to a crop, and the training subsets including a plurality of training samples; Using the data set to train the machine learning model to obtain a trained machine learning model; 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 demand of the corresponding crop; The step of calculating the crop water productivity based on the grid-scale crop blue water demand includes: Crop water productivity is calculated according to the following formula: Where, Grid cells middling crops Total blue water footprint; 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; The method of obtaining the crop water use efficiency paradox index according to the grid-scale crop blue water demand and the crop water productivity includes: The water shortage index is calculated by calculating the blue water demand of the crops at the grid scale. The water shortage index calculation formula is as follows: Where, Grid cells the water stress index; Grid cells of the total blue water available for agriculture; Grid cells the availability of natural water resources; Grid cells Minimum blue water demand for environmental ecological flow; Grid cells Non-agricultural irrigation water demand; The crop water use efficiency paradox index is calculated based on the crop water productivity and the water shortage index. The calculation formula of the crop water use efficiency paradox index is as follows: Where, Grid cells In the period The crop water use efficiency paradox index; and Grid cells In the period and base period The average water shortage index is the average water shortage index in the period The annual average value of the water shortage index in the base period The annual average value of and Grid cells In the period and base period The average crop water productivity is the average crop water productivity of the crop in the period The annual average and crop water productivity of the reference period The annual average of the crop water productivity is calculated as the calories produced per unit of water use; the base period is the period The previous time period.

2. An evaluation device for implementing the crop water use efficiency paradox evaluation method according to claim 1, characterized in that: The device comprises: Data acquisition module, used to obtain grid-scale resource and environmental data of the target area; a grid-scale data acquisition module, configured to process the grid-scale resource and environmental data based on a trained machine learning model to obtain grid-scale crop blue water requirements, wherein the training samples used in training the machine learning model include: site-scale resource and environmental data of the target region as an independent variable and site-scale crop blue water requirements of the target region as a dependent variable; A first calculation module is used to calculate the crop water productivity according to the grid-scale crop blue water demand; A second calculation module is used to obtain a crop water use efficiency paradox index based on the grid-scale crop blue water demand and the crop water productivity; The judgment module is used to analyze the crop water use efficiency paradox status in the target area according to the crop water use efficiency paradox index.

3. A computer program product, characterized in that When the computer program product is run on a computer, the method according to claim 1 is executed by the computer.

Images