Water consumption prediction method and system

Abstract

The invention provides an available water consumption prediction method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the fitting based on the available water consumption of a target drainage basin in a first time period, and obtaining a hook-shaped response function representing the relation between the predicted value of the available water consumption of the target drainage basin and the near-earth temperature; based on the air temperature data of the target drainage basin output by the plurality of global climate modes and the hook-type response function, determining the initial predicted value of the available water amount of the target drainage basin corresponding to each global climate mode in the second time period; constructing an emergence constraint model according to the air temperature change trend of each global climate mode in the third time period and the corresponding initial predicted value of the available water amount; and substituting the temperature change trend of the target drainage basin in the fourth time period into the emergence constraint model to obtain a water consumption predicted value of the target drainage basin in the second time period. According to the method, the available water amount of the target drainage basin in the future period is predicted by fitting the hook type response function and combining the emergence constraint method.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an available water volume prediction method and system. Background Art

[0002] Since the Industrial Revolution, the emission of greenhouse gases such as carbon dioxide in the atmosphere has increased, the energy balance and material circulation process of the earth's land and atmosphere have changed, the global temperature has continued to rise, coral reefs and tropical rainforests have died out on a large scale, extreme disasters such as rainstorms and floods have occurred frequently, and the imbalance and inequality of the social and economic system and the ecological environment have become increasingly severe. In order to cope with the negative impact of the warming rate, it is crucial to strengthen scientific research on the response mechanism of water resources to climate change.

[0003] In recent years, domestic and foreign scholars have estimated the available water on land through various meteorological and hydrological variables such as precipitation, evapotranspiration, runoff, and terrestrial water storage, and found that the available water on land in most parts of the world has a significant downward trend, but some studies have also found that the available water on land in some parts of the world has shown an upward trend. Existing studies use different meteorological and hydrological variables to represent the available water on land, resulting in large differences in research results, making it difficult to form a unified scientific conclusion.

[0004] Existing studies generally assess the evolution trends of global and regional terrestrial water availability in the past and present, but rarely predict the evolution of terrestrial water availability under future climate change scenarios. Therefore, it is difficult to scientifically support integrated water resources management and sustainable social and economic development. Summary of the invention

[0005] The present invention provides a method and system for predicting available water volume, which are used to solve the defect in the prior art that there is a lack of a method for the evolution of available water volume on land under future climate change scenarios, and to realize a method for predicting available water volume in a future river basin.

[0006] The present invention provides a method for predicting available water volume, comprising: Based on the available water volume of the target basin in the first time period, a hook-shaped response function is obtained to characterize the relationship between the predicted value of available water volume of the target basin and the near-ground temperature; Based on the temperature data of the target watershed output by multiple global climate models and the hook-type response function, determine a preliminary prediction value of available water volume in the target watershed corresponding to each global climate model in the second time period; constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; Substituting the temperature change trend of the target watershed in the fourth time period into the emergence constraint model to obtain the predicted value of available water volume of the target watershed in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

[0007] According to a method for predicting available water volume provided by the present invention, before the step of fitting the available water volume of the target basin in the first time period to obtain a hook-shaped response function characterizing the relationship between the predicted value of the available water volume in the target basin and the near-ground temperature, the method further includes: Based on the terrestrial water storage data of each grid point in the target basin in the first time period, a basin average terrestrial water storage series of the target basin is obtained; The ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed is used as the watershed runoff depth series; The sum of the average terrestrial water storage series of the basin and the runoff depth series of the basin is determined as the target basin available water volume in the first time period.

[0008] According to a method for predicting available water volume provided by the present invention, before the step of obtaining a basin average terrestrial water reserve series of the target basin based on the terrestrial water reserve data of each grid point in the target basin in the first time period, the method further includes: Based on a number of gravity satellite data of each grid point in the target watershed in the first time period, the terrestrial water storage data of each grid point in the target watershed in the first time period are inverted.

[0009] According to a method for predicting available water volume provided by the present invention, before the step of obtaining a basin average terrestrial water reserve series of the target basin based on the terrestrial water reserve data of each grid point in the target basin in the first time period, the method further includes: In the case where a plurality of gravity satellite data at each grid point in the target watershed in the first time period are missing, a random forest model is constructed and trained, wherein the random forest model characterizes the relationship between each driving factor and terrestrial water storage in the target watershed; The random forest model is used to reconstruct the complete terrestrial water storage data of each grid point in the target basin in the first time period.

[0010] According to a method for predicting available water volume provided by the present invention, before the step of using the ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed as the watershed runoff depth series, the method further includes: Constructing a plurality of artificial intelligence models, wherein the artificial intelligence models are used to output monthly runoff data for a first time period based on input monthly runoff data for a partial time period; Determine the artificial intelligence model with the highest Nash efficiency coefficient as the optimal model; The monthly runoff series of the target watershed in the first time period is determined based on the optimal model.

[0011] According to a method for predicting available water volume provided by the present invention, the step of determining a preliminary predicted value of available water volume of a target basin corresponding to each global climate model in a second time period specifically comprises: Calculate the first multi-year average temperature of the target watershed in the third time period; Calculate the second multi-year average temperature of the target basin in the third time period corresponding to each global climate model; Calculate the third multi-year average temperature of the target watershed in the second time period; Calculate the sum of the first multi-year basin average temperature and the third multi-year basin average temperature, subtract the third multi-year basin average temperature, project the obtained value into the hook-type response function, and determine the preliminary predicted value of available water in the target basin in the second time period.

[0012] The present invention also provides an available water quantity prediction device, comprising: A fitting module, for fitting the available water volume of the target watershed in the first time period to obtain a hook-shaped response function representing the relationship between the predicted value of the available water volume of the target watershed and the near-ground temperature; A determination module, for determining a preliminary prediction value of available water volume in the target basin corresponding to each global climate model in the second time period based on the temperature data of the target basin output by multiple global climate models and the hook-type response function; A construction module, for constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; A prediction module, used for substituting the temperature change trend of the target basin in the fourth time period into the emergence constraint model to obtain a predicted value of available water volume of the target basin in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the available water volume prediction methods described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the available water prediction method as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the available water prediction method as described above is implemented.

[0016] The available water prediction method and system provided by the present invention predict the available water volume of the target basin in the future by fitting the Hook response function and combining the emergence constraint method, providing an important and highly operational reference basis for global and regional water and drought disaster risk assessment and early warning under the climate change scenario, and providing engineering reference value for responding to future climate disasters, scientifically formulating emission reduction strategies and comprehensive management of water resources in the basin. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is one of the flow diagrams of the available water volume prediction method provided by the present invention; Figure 2 It is one of the schematic diagrams of the Hook response function fitted in the available water prediction method provided by the present invention; Figure 3 is a schematic diagram of a sliding window in the available water volume prediction method provided by the present invention; Figure 4 This is the second schematic diagram of the Hook response function fitted in the available water prediction method provided by the present invention; Figure 5 It is a structural schematic diagram of the available water volume prediction device provided by the present invention; Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Combine the following Figures 1 to 4 The method for predicting available water volume of the present invention is introduced as follows: Figure 1 As shown, including: Step 101, based on the available water volume of the target basin in the first time period, a hook-shaped response function is obtained to characterize the relationship between the predicted value of the available water volume of the target basin and the near-ground temperature; The target basin is the basin for which the available water volume in the future period needs to be predicted.

[0021] The first time period represents the historical period in which the relevant hydrological and meteorological data of the target basin can be obtained. Therefore, it is possible to obtain various data related to the water volume of the target basin in the first time period and determine the available water volume of the target basin in the first time period. WA , which is the amount of water available in the target basin during historical periods.

[0022] Since the data of the target basin in the first time period is used to fit the hook response function, it is preferred to set a longer first time period. In this embodiment, the first time period is a complete time period from 1950 to 2022.

[0023] Furthermore, the average monthly temperature of the target basin in the first time period is obtained.

[0024] On this basis, the Binning scaling function can better characterize the nonlinear relationship between variables and has been widely used in recent years to analyze the response characteristics of extreme precipitation and runoff to global warming. WA , the average monthly temperature of the basin, and construct the Hook response function based on the box element scaling function.

[0025] Specifically, taking the average monthly temperature of the basin as the sorting criterion, the combined series of monthly temperature-basin available water volume in the first time period are divided into 12 boxes with the same sample capacity. The median of the daily temperature is taken to represent the box temperature, and the average value of the available water volume in the basin in each temperature box is used to represent the available water volume, finally obtaining 12 sets of temperature-available water volume series.

[0026] Through research, it is found that precipitation and runoff generally present a Hook structure of "rising first and then falling" trajectory with the near-ground temperature. Therefore, the local weighted sliding regression smoothing method is used to fit 12 sets of temperature-available water series to draw the Hook structure of temperature-available water in the target basin, such as Figure 2 shown.

[0027] Among them, the temperature at the inflection point of the Hook structure is called the peak temperature, that is, Figure 2 T pp .

[0028] It can be understood that the fitted Hook response function represents the relationship between the predicted value of available water volume of the target basin and the near-ground temperature. On this basis, by obtaining the near-ground temperature of the target basin in the future period, the available water volume in the corresponding future period can be determined based on the Hook response function.

[0029] Step 102, based on the temperature data of the target basin output by multiple global climate models and the hook-type response function, determine a preliminary prediction value of available water volume in the target basin corresponding to each global climate model in the second time period; To this end, the temperature data of the target basin in the future period are obtained as the near-surface temperature based on multiple global climate models.

[0030] The second time period represents the future period to be predicted.

[0031] Optionally, in this embodiment, 35 global climate models are selected to obtain the available water volume of the target basin in the second time period under the 35 global climate models as a preliminary prediction value of the available water volume.

[0032] Step 103, constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; Furthermore, emergent constraints are a method used to reduce the uncertainty of climate model predictions. Based on the relationship between observed data and model simulations, it constrains the prediction of future climate change by identifying the statistical relationship between certain observable variables in the model ensemble and future climate responses.

[0033] Therefore, based on the preliminary prediction value of available water volume, an emergence constraint model is constructed to obtain more accurate available water volume prediction results.

[0034] Optionally, first calculate the annual average temperature trend of each global climate model in the third time period, denoted as .

[0035] The third time period also represents a historical time period. Optionally, the third time period may intersect, partially overlap, or completely overlap with the first time period.

[0036] It can be understood that the third time period is a historical time period in which the output data of the global climate model can be obtained, and in this embodiment, specifically, it is from 1985 to 2014.

[0037] Furthermore, the data of 35 global climate models were integrated to obtain 35 sets of historical annual average temperature trends and preliminary prediction values ​​of available water in the future period WA fut1 The emergence constraint model constructed by the pairing combination is as follows: ; In the formula, a and b Represents the parameters of the emergence constraint model.

[0038] Through the above method, the emergence constraint model with parameters can be obtained. On this basis, the least squares method is used to solve the parameters of the emergence constraint model with parameters. a and b .

[0039] Step 104, substituting the temperature change trend of the target watershed in the fourth time period into the emergence constraint model to obtain a predicted value of available water volume of the target watershed in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

[0040] Furthermore, based on the reanalysis data of the ERA5-Land dataset, the temperature change trend in the third time period is deduced, and the trend term is substituted into the constructed emergence constraint model, as follows: ; In the formula, The forecast result of the change of available water volume in the basin in the future period after correction is expressed, that is, the final forecast value of available water volume in the target basin in the second time period; It represents the temperature trend of the target basin in the fourth time period, which is obtained based on the ERA5-Land dataset (the fifth generation of land surface reanalysis dataset of the European Centre for Medium-Range Weather Forecasts).

[0041] Among them, the fourth time period also represents the historical period, that is, the forecast results of available water volume in the future period are corrected through the temperature change trend in the historical period.

[0042] Optionally, in this implementation manner, the fourth time period is the same as the third time period, and is set to 1985 to 2014.

[0043] The present invention fits the Hook response function and combines the emergence constraint method to predict the available water volume of the target basin in the future, providing an important and highly operational reference for global and regional water and drought disaster risk assessment and early warning under the climate change scenario, and providing engineering reference value for responding to future climate disasters, scientifically formulating emission reduction strategies and comprehensive management of water resources in the basin.

[0044] In the available water forecasting method of the present invention, before the step of fitting the available water volume of the target basin in the first time period to obtain a hook-shaped response function characterizing the relationship between the predicted value of the available water volume in the target basin and the near-ground temperature, the method further includes: Based on the terrestrial water storage data of each grid point in the target basin in the first time period, a basin average terrestrial water storage series of the target basin is obtained; The ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed is used as the watershed runoff depth series; The sum of the average terrestrial water storage series of the basin and the runoff depth series of the basin is determined as the target basin available water volume in the first time period.

[0045] The target basin is gridded, and based on the collected hydrological and meteorological data of the target basin in the first time period, the terrestrial water storage data of each grid point in the target basin in the first time period are obtained. The Thiessen polygon method is used to obtain the average terrestrial water storage series of the target basin in the first time period based on the grid point data. TWS .

[0046] Furthermore, based on the pre-collected hydrological and meteorological data of the target basin in the first time period, the monthly runoff series of the target basin in the first time period is obtained. Q .

[0047] Divide the monthly runoff of the watershed by the watershed area A , and obtain the basin runoff depth series.

[0048] Then calculate the cumulative value of the basin average terrestrial water storage series and the basin monthly runoff depth series to obtain the target basin available water volume in the first time period: ; In the formula, WA is the available water volume in the target basin, Q For the lunar runoff, A is the basin area, TWS It is a series of land water storage.

[0049] In the available water prediction method of the present invention, before the step of obtaining the basin average terrestrial water reserve series of the target basin based on the terrestrial water reserve data of each grid point in the target basin in the first time period, the method further includes: Based on a number of gravity satellite data of each grid point in the target watershed in the first time period, the terrestrial water storage data of each grid point in the target watershed in the first time period are inverted.

[0050] A number of gravity satellite data of each grid point in the target watershed in the first time period are collected, and the terrestrial water storage data of each grid point in the target watershed in the first time period are inverted.

[0051] Among them, the Potsdam Geoscience Center in Germany, the Jet Propulsion Laboratory (JPL) of the California Institute of Technology, the Center for Space Research at University of Texas, Austin (CSR), and NASA's Goddard Space Flight Center (GSFC) are responsible for data interpretation and publish global gravity field output data on a monthly scale as gravity satellite data.

[0052] Optionally, one or more gravity satellite data are selected to invert the terrestrial water storage data.

[0053] In this implementation, the latest sixth-generation (RL06) products released by JPL, CSR, and GSFC are used simultaneously. These three data sources have different spatial resolutions and all provide mascon (mass dense) monthly-scale equivalent water heights (excluding the average field from 2004 to 2009) based on the solution of the concentrated mass block gravity field. Finally, a long sequence of TWSA (Terrestrial Water Storage Anomaly) data sets are output.

[0054] In order to consider the uncertainties that may be caused by different data products, three sets of GRACE / GRACE-FO (Gravity Recovery And Climate Experiment / GRACE Follow-On, gravity satellite and its successor satellite) gravity satellite datasets were interpolated to a 0.25°×0.25° spatial grid, and the average of each product was taken in each time step to finally obtain the monthly data of land water storage from 2002 to 2022.

[0055] In the method for predicting available water volume of the present invention, before the step of obtaining the average terrestrial water reserve series of the target river basin based on the terrestrial water reserve data of each grid point in the target river basin in the first time period, the method further includes: In the case where a plurality of gravity satellite data at each grid point in the target watershed in the first time period are missing, a random forest model is constructed and trained, wherein the random forest model characterizes the relationship between each driving factor and terrestrial water storage in the target watershed; The random forest model is used to reconstruct the complete terrestrial water storage data of each grid point in the target basin in the first time period.

[0056] It is understandable that if the first time period is set to 2002 to 2022, the terrestrial water storage data of the target basin in the first time period can be directly inverted through gravity satellite data.

[0057] However, in this implementation, the first time period is set from 1950 to 2022, that is, the gravity satellite data of each grid point in the target basin in the first time period are missing. Therefore, by constructing a random forest model, the complete terrestrial water storage data in the first time period is reconstructed.

[0058] Specifically, the relative humidity of each grid point in the target basin is first determined based on the Clausius-Clapeyron thermodynamic equation. RH .

[0059] The Clausius-Clapeyron thermodynamic equation is defined as follows: ; In the formula, For the temperature T The saturated vapor pressure at T 0 is the first integral constant, which is 273.16K; is the second integral constant, which is 611Pa; is the latent heat of vaporization constant, take ; is the water vapor gas constant, take ; T is the air temperature, which is the input variable of the Clausius-Clapeyron thermodynamic equation.

[0060] The meteorological and hydrological data of each grid point in the target basin are collected in advance to obtain meteorological and hydrological observation samples. The 2-meter air temperature and dew point temperature in the meteorological and hydrological observation samples of each grid point in the target basin are substituted into the Clausius-Clapeyron thermodynamic equation as input variables to calculate the relative humidity of each grid point ( RH ), specifically: ,in, T dew is the dew point temperature, T 2m The air temperature is 2m.

[0061] Furthermore, the specific humidity q is the ratio of water vapor mass to total air mass mass, using ERA5 ground pressure p And dew point temperature, the formula is as follows: ; On this basis, if Figure 3As shown in the figure, for each grid point in the target watershed, 5×5 is set as the spatial sliding window threshold, and the data in the grid points involved in the spatial range are selected as the input of the random forest model. This method can improve the robustness of the machine learning model.

[0062] The random forest model was used to construct a relationship model between the driving factors in the above spatial range and the GRACE gravity satellite land water storage data.

[0063] Among them, the driving factors are data from 2002 to 2022, including: Category 1: variables obtained or derived from ERA5-Land, including temperature, relative humidity, snowfall, precipitation, runoff depth, shortwave radiation and longwave radiation; Category 2: ENSO (El Nino Southern Oscillation) index, including NINO 1+2 area sea surface temperature anomaly index, NINO 3 area sea surface temperature anomaly index, NINO 3.4 area sea surface temperature anomaly index, NINO 4 area sea surface temperature anomaly index; The third category: the average series of global climate model output data, including monthly average temperature, monthly relative humidity, monthly precipitation, monthly snowfall, monthly runoff depth, monthly average specific humidity, monthly shortwave radiation intensity and monthly longwave radiation. Among them, the average series of global climate model output data refers to the average value of the output results of 35 global climate models, that is, each variable has a set of output series.

[0064] For each grid point, a lag of 2 months is considered, that is, for each month, the driving factors of that month and the previous 1-2 months are selected as the input of the random forest model. The driving factors and GRACE gravity satellite data from 2002 to 2022 are used to construct a random forest model to simulate terrestrial water storage, which is expressed as: ; In the formula, represents the terrestrial water storage simulated by the random forest model at time t, represents the input variable at time t, represents the input variable at time t-1, represents the input variable at time t-2; F Represents a random forest model.

[0065] Furthermore, the gradient descent method is used to calibrate the random forest model of each grid point to obtain the parameters, and then the random forest model driven by the long series data set since 1950 is used to reconstruct the long series terrestrial water storage data set since 1950. That is, based on the terrestrial water storage data from 2002 to 2022, the terrestrial water storage data of the target basin in the first time period are reconstructed.

[0066] In the method for predicting available water volume of the present invention, before the step of using the ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed as the watershed runoff depth series, the method further includes: Constructing a plurality of artificial intelligence models, wherein the artificial intelligence models are used to output monthly runoff data for a first time period based on input monthly runoff data for a partial time period; Determine the artificial intelligence model with the highest Nash efficiency coefficient as the optimal model; The monthly runoff series of the target watershed in the first time period is determined based on the optimal model.

[0067] Furthermore, since it is also difficult to obtain the basin monthly runoff data for the complete first time period, the basin monthly runoff series for the first time period is determined based on the basin monthly runoff data for the partial time period that can be obtained in combination with the artificial intelligence model.

[0068] Specifically, the Thiessen polygon method is first used to derive the basin-averaged monthly series of ERA5-Land and global climate model output data. The main idea is to transform the grid data set into a basin-averaged data set.

[0069] Secondly, multiple artificial intelligence models are used to construct a monthly runoff simulation model. In this implementation, five artificial intelligence models, including artificial neural network, support vector machine, long short-term memory model, random forest and Gaussian linear regression model, are selected.

[0070] The driving factors of each AI model fall into two categories: The first category, variables obtained or derived from ERA5-Land, include temperature, relative humidity, snowfall, precipitation, runoff depth, shortwave radiation, and longwave radiation; The second category is the average series of global climate model output data, including monthly mean temperature, monthly relative humidity, monthly precipitation, monthly snowfall, monthly runoff depth, monthly mean specific humidity, monthly shortwave radiation intensity and monthly longwave radiation.

[0071] Optionally, based on the driving factors and the runoff observation data of the basin hydrological station, five artificial intelligence models are constructed, and a 7-month lag is considered to simulate the monthly runoff series since the establishment of the hydrological station, which is expressed as: ; In the formula, represents the monthly runoff simulated by the kth machine learning model at time t, represents the input variable at time t, represents the input variable at time t-1, represents the input variable at time t-2, represents the input variable at time t-7; F k Indicates k artificial intelligence models, k =1,2,…,5.

[0072] The gradient descent method was used to calibrate the five artificial intelligence models to obtain the optimal parameters, and then the Nash efficiency coefficient (NSE) of the monthly runoff simulated by each artificial intelligence model and the observed monthly runoff was calculated: ; In the formula, To simulate the runoff sequence; and are the measured runoff series and its mean, respectively; NT is the length of the runoff series. The closer NSE is to 1, the better the simulation effect is.

[0073] The NSEs of five artificial intelligence models were calculated respectively, and the artificial intelligence model with the highest NSE was selected to reconstruct the long series of monthly runoff. The optimal artificial intelligence model calibrated by the long series data set since 1950 was used to reconstruct the long series of monthly runoff data set since 1950.

[0074] That is, based on the short-term data that can be obtained, the monthly runoff series of the target basin in the first time period is reconstructed.

[0075] In the method for predicting available water volume of the present invention, the step of determining a preliminary predicted value of available water volume of the target basin corresponding to each global climate model in the second time period specifically includes: Calculate the first multi-year average temperature of the target watershed in the third time period; Calculate the second multi-year average temperature of the target basin in the third time period corresponding to each global climate model; Calculate the third multi-year average temperature of the target watershed in the second time period; Calculate the sum of the first multi-year basin average temperature and the third multi-year basin average temperature, subtract the third multi-year basin average temperature, project the obtained value into the hook-type response function, and determine the preliminary predicted value of available water in the target basin in the second time period.

[0076] Specifically, the Thiessen polygon is used to calculate the first multi-year average temperature of the target basin in the third time period, denoted as T obs ; Then, for each global climate model, the second multi-year basin average temperature of the target basin in the third time period is calculated using Thiessen polygons, denoted as T his .

[0077] On this basis, Thiessen polygons are used to calculate the third multi-year average temperature of the target basin in the second time period, that is, in the future period, denoted as T fut .

[0078] like Figure 4 As shown, T obs Projected onto the fitted Hook response function, the available water volume of the corresponding target basin in the third time period is obtained, which is recorded as WA obs .

[0079] Then, for each global climate model, we further obtain T obs + (T fut -T his ), the available water volume of the corresponding basin in the Hook response function is used as the initial prediction value WA of the available water volume of the target basin in the second time period fut1 .

[0080] Through the above method, the preliminary predicted values ​​of available water volume in the target basin in the second time period under 35 global climate models can be determined one by one.

[0081] It should be noted that the method of collecting and collating some of the data above is as follows: The target basin is determined, and for each grid point in the target basin, monthly meteorological and hydrological observation data from 1950 to 2022 are collected from the fifth-generation atmospheric reanalysis dataset (ERA5-Land) of the European Centre for Medium-Range Weather Forecasts, including 2m air temperature, air pressure, dew point temperature, snowfall, precipitation, runoff depth, shortwave radiation and longwave radiation.

[0082] The time series of four ENSO (El Nino Southern Oscillation) indices from 1950 to the present are further obtained, including the NINO 1+2 region sea surface temperature anomaly index, the NINO 3 region sea surface temperature anomaly index, the NINO 3.4 region sea surface temperature anomaly index, and the NINO 4 region sea surface temperature anomaly index.

[0083] The monthly average temperature, monthly relative humidity, monthly precipitation, monthly snowfall, monthly runoff depth, monthly average specific humidity, monthly shortwave radiation intensity and monthly longwave radiation of each global climate model in the historical period (1950-2014) are further obtained; for the future period (2015-2100), the monthly average temperature data of each global climate model under the shared socioeconomic pathway of SSP585 are obtained, and the monthly relative humidity, monthly precipitation, monthly snowfall, monthly runoff depth, monthly average specific humidity, monthly shortwave radiation intensity and monthly longwave radiation of the future period 2015-2022 are further obtained.

[0084] Collect monthly runoff data from the hydrological stations at the outlet sections of the target basins; and interpolate the ERA5-Land and global climate model output data to a 0.25°×0.25° spatial grid.

[0085] The available water volume prediction system provided by the present invention is described below. The available water volume prediction system described below and the available water volume prediction method described above can be referenced to each other.

[0086] like Figure 5 As shown, the available water volume prediction system includes a fitting module 501, a determination module 502, a construction module 503 and a prediction module 504: A fitting module, for fitting the available water volume of the target watershed in the first time period to obtain a hook-shaped response function representing the relationship between the predicted value of the available water volume of the target watershed and the near-ground temperature; The target basin is the basin for which the available water volume in the future period needs to be predicted.

[0087] The first time period represents the historical period in which the relevant hydrological and meteorological data of the target basin can be obtained. Therefore, it is possible to obtain various data related to the water volume of the target basin in the first time period and determine the available water volume of the target basin in the first time period. WA , which is the amount of water available in the target basin during historical periods.

[0088] Since the data of the target basin in the first time period is used to fit the Hook response function, it is preferred to set a longer first time period. In this embodiment, the first time period is a complete time period from 1950 to 2022.

[0089] Furthermore, the average monthly temperature of the target basin in the first time period is obtained.

[0090] On this basis, the Binning scaling function can better characterize the nonlinear relationship between variables and has been widely used in recent years to analyze the response characteristics of extreme precipitation and runoff to global warming. WA, the average monthly temperature of the basin, and construct a hook-type response function based on the box element scaling function.

[0091] Specifically, taking the average monthly temperature of the basin as the sorting criterion, the combined series of monthly temperature-basin available water volume in the first time period are divided into 12 boxes with the same sample capacity. The median of the daily temperature is taken to represent the box temperature, and the average value of the available water volume in the basin in each temperature box is used to represent the available water volume, finally obtaining 12 sets of temperature-available water volume series.

[0092] Through research, it is found that precipitation and runoff generally present a Hook structure of "rising first and then falling" trajectory with the near-ground temperature. Therefore, the local weighted sliding regression smoothing method is used to fit 12 sets of temperature-available water series to draw the Hook structure of temperature-available water in the target basin, such as Figure 2 shown.

[0093] Among them, the temperature at the inflection point of the Hook structure is called the peak temperature, that is, Figure 2 T pp .

[0094] It can be understood that the fitted Hook response function represents the relationship between the predicted value of available water volume of the target basin and the near-ground temperature. On this basis, by obtaining the near-ground temperature of the target basin in the future period, the available water volume in the corresponding future period can be determined based on the Hook response function.

[0095] A determination module, configured to determine a preliminary predicted value of available water volume in the target basin corresponding to each global climate model in the second time period based on the temperature data of the target basin output by multiple global climate models and the Hook response function; To this end, the temperature data of the target basin in the future period are obtained as the near-surface temperature based on multiple global climate models.

[0096] The second time period represents the future period to be predicted.

[0097] Optionally, in this embodiment, 35 global climate models are selected to obtain the available water volume of the target basin in the second time period under the 35 global climate models as a preliminary prediction value of the available water volume.

[0098] A construction module, for constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; Furthermore, emergent constraints are a method used to reduce the uncertainty of climate model predictions. Based on the relationship between observed data and model simulations, it constrains the prediction of future climate change by identifying the statistical relationship between certain observable variables in the model ensemble and future climate responses.

[0099] Therefore, based on the preliminary prediction value of available water volume, an emergence constraint model is constructed to obtain more accurate available water volume prediction results.

[0100] Optionally, first calculate the annual average temperature trend of each global climate model in the third time period, denoted as .

[0101] The third time period also represents a historical time period. It is understandable that the third time period is a historical time period in which the output data of the global climate model can be obtained, specifically from 1985 to 2014 in this embodiment.

[0102] Furthermore, the data of 35 global climate models were integrated to obtain 35 sets of historical annual average temperature change trends and future WA fut1 The emergence constraint model constructed by the pairing combination is as follows: ; In the formula, a and b Represents the parameters of the emergence constraint model.

[0103] Through the above method, the emergence constraint model with parameters can be obtained. On this basis, the least squares method is used to solve the parameters of the emergence constraint model with parameters. a and b .

[0104] A prediction module, used for substituting the temperature change trend of the target basin in the fourth time period into the emergence constraint model to obtain a predicted value of available water volume of the target basin in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

[0105] Furthermore, based on the reanalysis data of the ERA5-Land dataset, the temperature change trend in the third time period is deduced, and the trend term is substituted into the constructed emergence constraint model, as follows: ; In the formula, The forecast result of the change of available water volume in the basin in the future period after correction is expressed, that is, the final forecast value of available water volume in the target basin in the second time period; It represents the temperature change trend of the target basin in the fourth time period, which is obtained based on the ERA5-Land dataset.

[0106] Among them, the fourth time period also represents the historical period, that is, the forecast results of available water volume in the future period are corrected through the temperature change trend in the historical period.

[0107] Optionally, in this implementation manner, the fourth time period is the same as the third time period, and is set to 1985 to 2014.

[0108] The present invention fits the Hook response function and combines the emergence constraint method to predict the available water volume of the target basin in the future, providing an important and highly operational reference for global and regional water and drought disaster risk assessment and early warning under the climate change scenario, and providing engineering reference value for responding to future climate disasters, scientifically formulating emission reduction strategies and comprehensive management of water resources in the basin.

[0109] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor (processor) 610, a communication interface (Communications Interface) 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the logic instructions in the memory 630 to execute the available water prediction method, which includes: fitting the available water in the target basin in the first time period to obtain a hook-type response function that characterizes the relationship between the predicted value of available water in the target basin and the near-ground temperature; determining the preliminary predicted value of available water in the target basin corresponding to each global climate model in the second time period based on the temperature data of the target basin output by multiple global climate models and the hook-type response function; constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary predicted value of available water; substituting the temperature change trend of the target basin in the fourth time period into the emergence constraint model to obtain the predicted value of available water in the target basin in the second time period; wherein the first time period, the third time period and the fourth time period are all earlier than the second time period.

[0110] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0111] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the available water prediction method provided by the above-mentioned methods, which includes: fitting the available water volume of the target river basin in the first time period to obtain a hook-type response function that characterizes the relationship between the predicted value of available water volume in the target river basin and the near-ground temperature; determining the preliminary predicted value of available water volume in the target river basin corresponding to each global climate model in the second time period based on the temperature data of the target river basin output by multiple global climate models and the hook-type response function; constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary predicted value of available water; substituting the temperature change trend of the target river basin in the fourth time period into the emergence constraint model to obtain the predicted value of available water volume in the target river basin in the second time period; wherein, the first time period, the third time period and the fourth time period are all earlier than the second time period.

[0112] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the available water prediction method provided by the above-mentioned methods, the method comprising: fitting the available water volume of the target river basin in the first time period to obtain a hook-type response function that characterizes the relationship between the predicted value of available water volume in the target river basin and the near-ground temperature; determining the preliminary predicted value of available water volume in the target river basin corresponding to each global climate model in the second time period based on the temperature data of the target river basin output by multiple global climate models and the hook-type response function; constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary predicted value of available water volume; substituting the temperature change trend of the target river basin in the fourth time period into the emergence constraint model to obtain the predicted value of available water volume in the target river basin in the second time period; wherein, the first time period, the third time period and the fourth time period are all earlier than the second time period.

[0113] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting available water volume, characterized in that: include: Based on the available water volume of the target basin in the first time period, a hook-shaped response function is obtained to characterize the relationship between the predicted value of available water volume of the target basin and the near-ground temperature; Based on the temperature data of the target watershed output by multiple global climate models and the hook-type response function, determine a preliminary prediction value of available water volume in the target watershed corresponding to each global climate model in the second time period; constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; Substituting the temperature change trend of the target watershed in the fourth time period into the emergence constraint model to obtain the predicted value of available water volume of the target watershed in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

2. The method for predicting available water volume according to claim 1, characterized in that: Before the step of fitting the available water volume of the target basin in the first time period to obtain a hook-shaped response function characterizing the relationship between the predicted value of the available water volume of the target basin and the near-ground temperature, the method further includes: Based on the terrestrial water storage data of each grid point in the target basin in the first time period, a basin average terrestrial water storage series of the target basin is obtained; The ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed is used as the watershed runoff depth series; The sum of the average terrestrial water storage series of the basin and the runoff depth series of the basin is determined as the target basin available water volume in the first time period.

3. The method for predicting available water volume according to claim 2, characterized in that: Before the step of obtaining the average terrestrial water reserve series of the target river basin based on the terrestrial water reserve data of each grid point in the target river basin in the first time period, the step further includes: Based on a number of gravity satellite data of each grid point in the target watershed in the first time period, the terrestrial water storage data of each grid point in the target watershed in the first time period are inverted.

4. The method for predicting available water volume according to claim 3, characterized in that: Before the step of obtaining the average terrestrial water reserve series of the target river basin based on the terrestrial water reserve data of each grid point in the target river basin in the first time period, the step further includes: In the case where a plurality of gravity satellite data at each grid point in the target watershed in the first time period are missing, a random forest model is constructed and trained, wherein the random forest model characterizes the relationship between each driving factor and terrestrial water storage in the target watershed; The random forest model is used to reconstruct the complete terrestrial water storage data of each grid point in the target basin in the first time period.

5. The method for predicting available water volume according to claim 2, characterized in that: Before the step of using the ratio of the monthly runoff series of the target watershed in the first time period to the watershed area of ​​the target watershed as the watershed runoff depth series, the step further includes: Constructing a plurality of artificial intelligence models, wherein the artificial intelligence models are used to output monthly runoff data for a first time period based on input monthly runoff data for a partial time period; Determine the artificial intelligence model with the highest Nash efficiency coefficient as the optimal model; The monthly runoff series of the target watershed in the first time period is determined based on the optimal model.

6. The method for predicting available water volume according to any one of claims 1 to 5, characterized in that: The step of determining a preliminary predicted value of available water volume in the target basin corresponding to each global climate model in the second time period specifically includes: Calculate the first multi-year average temperature of the target watershed in the third time period; Calculate the second multi-year average temperature of the target basin in the third time period corresponding to each global climate model; Calculate the third multi-year average temperature of the target watershed in the second time period; Calculate the sum of the first multi-year basin average temperature and the third multi-year basin average temperature, subtract the third multi-year basin average temperature, project the obtained value into the hook-type response function, and determine the preliminary predicted value of available water in the target basin in the second time period.

7. An available water forecasting system, characterized in that: include: A fitting module, for fitting the available water volume of the target watershed in the first time period to obtain a hook-shaped response function representing the relationship between the predicted value of the available water volume of the target watershed and the near-ground temperature; A determination module, for determining a preliminary prediction value of available water volume in the target basin corresponding to each global climate model in the second time period based on the temperature data of the target basin output by multiple global climate models and the hook-type response function; A construction module, for constructing an emergence constraint model according to the temperature change trend of each global climate model in the third time period and the corresponding preliminary prediction value of available water; A prediction module, used for substituting the temperature change trend of the target basin in the fourth time period into the emergence constraint model to obtain a predicted value of available water volume of the target basin in the second time period; The first time period, the third time period and the fourth time period are all earlier than the second time period.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the available water prediction method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the available water prediction method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting available water volume according to any one of claims 1 to 6 is implemented.

Images