A water resource shortage risk prediction method, device and electronic equipment

Abstract

The application provides a water resource shortage risk prediction method and device and electronic equipment, and relates to the technical field of water conservancy. The method comprises the following steps: acquiring a historical runoff sequence of a target river basin; determining a threshold runoff according to the historical runoff sequence; fitting the historical runoff sequence by using a generalized additivity GAMLSS model to determine a probability distribution function; and determining a first calculation result according to the probability distribution function, wherein the first calculation result represents a predicted value of the number of years from a calculation year to the first time when the runoff is lower than the threshold runoff. The embodiment of the application can predict the predicted value of the year of water resource shortage, thereby improving the evaluation effect of the water resource shortage risk.

Description

Technical Field

[0001] This invention relates to the field of water conservancy technology, and in particular to a method, apparatus and electronic equipment for predicting water shortage risks. Background Technology

[0002] In recent years, water resources have shown a significant decline trend. Human activities, such as increased social water use and changes in the underlying surface, are the main reasons for the reduction in river runoff. For watersheds experiencing significant changes in the underlying surface and loss of hydrological sequence consistency, calculating and assessing the risk of water shortage under dynamic scenarios is crucial for ensuring future watershed water security.

[0003] In existing technologies, firstly, the Manner-Kendall (MK) mutation test method can be used to analyze trends and diagnose variations in watershed runoff sequences to reveal the evolution patterns of watershed runoff. Secondly, runoff evolution attribution analysis can be performed based on watershed hydrothermal equilibrium and hydrological model simulation. Thirdly, non-consistent hydrological frequency analysis and engineering hydrological design value calculation can be performed based on variable parameter probability distribution models. Many studies introduce covariates (such as time or rainfall) combined with regression models (such as the GAMLSS model) to characterize the non-consistency of hydrological sequences. However, most techniques only focus on numerical calculations and analyses of floods and runoff, lacking calculations for water scarcity risks.

[0004] It is evident that existing technologies have a poor effect on assessing water shortage risks. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for predicting water shortage risks, in order to solve the problem of poor water shortage risk assessment in the prior art.

[0006] According to a first aspect of the present invention, a method for predicting water shortage risk is provided, comprising:

[0007] Obtain historical runoff sequences for the target watershed;

[0008] The threshold runoff volume is determined based on the historical runoff sequence;

[0009] The probability distribution function was determined by fitting the historical runoff sequence using the generalized additivity GAMLSS model.

[0010] A first calculation result is determined based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff first falls below the threshold runoff.

[0011] According to a second aspect of the present invention, a water shortage risk prediction device is provided, comprising:

[0012] The acquisition module is used to obtain historical runoff sequences of the target watershed;

[0013] The first determining module is used to determine the threshold runoff volume based on the historical runoff sequence;

[0014] The second determining module is used to fit the historical runoff sequence using the generalized additivity GAMLSS model to determine the probability distribution function;

[0015] The third determining module is used to determine a first calculation result based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff volume first falls below the threshold runoff volume.

[0016] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to execute the water shortage risk prediction method provided by the present invention.

[0020] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the water shortage risk prediction method provided by the present invention.

[0021] In this embodiment of the invention, the historical runoff sequence of the target watershed is first obtained, and the threshold runoff volume corresponding to the target watershed is determined based on the historical runoff sequence. Then, the generalized additivity GAMLSS model is used to fit the historical runoff sequence to obtain the model with the best fit and the corresponding probability distribution function. Finally, the probability distribution function is used to predict the number of years from the calculation year to the first time the runoff volume is lower than the threshold runoff volume, thereby quantitatively assessing the risk of water shortage in the watershed due to extreme drought within a specified period, and improving the assessment effect of water shortage risk.

[0022] It should be understood that the description in this section is not intended to represent key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a water shortage risk prediction method provided in an embodiment of the present invention;

[0025] Figure 2 This is one of the structural schematic diagrams of a water shortage risk prediction device provided in an embodiment of the present invention;

[0026] Figure 3 This is a second schematic diagram of the structure of a water shortage risk prediction device provided in an embodiment of the present invention;

[0027] Figure 4 This is a block diagram of an electronic device for implementing the water shortage risk prediction method of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] In the embodiments of this invention, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0030] Please see Figure 1 , Figure 1 This is a flowchart illustrating a water shortage risk prediction method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, it includes the following steps:

[0031] Step S101: Obtain the historical runoff sequence of the target watershed.

[0032] The aforementioned historical runoff sequence may be determined based on the user's selection of the target watershed, and the aforementioned historical runoff sequence may include multiple sets of data.

[0033] Furthermore, each runoff sequence may include total runoff data corresponding to the target watershed.

[0034] Step S102: Determine the threshold runoff volume based on the historical runoff sequence.

[0035] The above steps can be understood as using the historical runoff sequence to calculate the cumulative frequency corresponding to each average flow, and then standardizing it to obtain the standardized runoff index relative to each average flow, and then determining the threshold runoff based on the standardized runoff index.

[0036] In addition, the above-mentioned threshold runoff can be divided into different levels of runoff based on the water shortage situation. In this case, it is necessary to determine the threshold runoff under different water shortage levels.

[0037] Step S103: Fit the historical runoff sequence using the generalized additivity GAMLSS model to determine the probability distribution function.

[0038] In the above steps, the probability distribution corresponding to the runoff sequence can be determined first, thereby obtaining the probability density function of the runoff sequence. The runoff probability density function represents the possible runoff values ​​of the river in different time periods. Since the river runoff is affected by the ecological environment around the river, the runoff probability density function is set to include time-varying variables. The time-varying variables represent the changes in the river's location, scale, and shape over time, so that the runoff is related to time.

[0039] It should be noted that the probability density function of runoff is the density function of a non-stationary probability distribution, which can be a normal distribution, a log-normal distribution, a Gumbel distribution, a gamma distribution, or a Weibull distribution.

[0040] Each probability distribution in the probability distribution set contains a location parameter and a scale parameter.

[0041] The probability distribution function of runoff represents the distribution of river runoff over different time periods. Since river runoff is affected by the ecological environment around the river, the runoff distribution function is also set to include time-varying variables. These time-varying variables represent the changes in the river's location, scale, and shape over time, thus establishing a relationship between the distribution of runoff and time.

[0042] Using the GAMLSS model, the Akaike Information Criterion GAIC value corresponding to each probability distribution type can be obtained. The probability distribution type with the smallest GAIC value and the parameters are selected as the optimal model corresponding to the runoff series. The above probability distribution function is set by the determined optimal model.

[0043] Step S104: Determine a first calculation result based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff volume first falls below the threshold runoff volume.

[0044] In this step, the probability of the annual runoff falling below the threshold runoff can be calculated based on the probability distribution function, starting from the initial year. This probability is used as the first probability value. The probability of the first runoff falling below the threshold runoff can be determined based on the first probability value, which is used as the second probability value. The expected number of years from the initial year to the first occurrence of the runoff falling below the threshold runoff is determined based on the second probability value. That is, the first calculation result can also be interpreted as the predicted number of years from the calculation year to the first occurrence of the runoff falling below the threshold runoff.

[0045] It should be noted that the above steps S101 to S104 can be performed by electronic devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, mainframe computers and other suitable computers, etc., and the embodiments of the present invention do not limit this.

[0046] In this embodiment of the invention, the historical runoff sequence of the target watershed is first obtained, and the threshold runoff volume corresponding to the target watershed is determined based on the historical runoff sequence. Then, the generalized additivity GAMLSS model is used to fit the historical runoff sequence to obtain the model with the best fit and the corresponding probability distribution function. Finally, the probability distribution function is used to predict the number of years from the calculation year to the first time the runoff volume is lower than the threshold runoff volume, thereby quantitatively assessing the risk of water shortage in the watershed due to extreme drought within a specified period, and improving the assessment effect of water shortage risk.

[0047] As an optional implementation, the threshold runoff includes at least one of the following: moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff.

[0048] In this embodiment of the invention, the threshold runoff can be divided into moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff. By classifying different levels of drought conditions, the first calculation result can include predicted values ​​corresponding to these three drought levels, thereby improving the prediction effect of water shortage risk. The predicted values ​​can become more accurate based on the actual severity of the drought.

[0049] As an optional implementation, determining the threshold runoff volume based on the historical runoff sequence includes:

[0050] Based on the historical runoff sequence, the scale parameter and shape parameter of the corresponding gamma Γ distribution are determined using the maximum likelihood estimation method, and the historical runoff sequence follows the Γ distribution;

[0051] Obtain the standardized runoff index, and determine the first parameter based on the standardized runoff index;

[0052] The threshold runoff volume is determined based on the first parameter and the inverse function of the Γ distribution.

[0053] In this embodiment of the invention, the scale parameter and shape parameter corresponding to the Γ distribution are determined by solving the Γ distribution using the maximum likelihood estimation method. It should be understood that the historical runoff sequence needs to follow the Γ distribution. Then, the standardized runoff index is obtained. The standardized runoff index can be determined according to the drought conditions. For example, when the threshold runoff includes moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff, the standardized runoff index can be selected as -2.0, -1.5, and -1.0. Subsequently, the first parameter is obtained by solving the standardized runoff index and other parameters. Finally, the threshold runoff is obtained by solving the first parameter and the inverse function of the Γ distribution.

[0054] The inverse function corresponding to the Γ distribution also includes scale parameters and shape parameters, so the scale parameters and shape parameters determined by the maximum likelihood estimation method need to be substituted into the solution.

[0055] As an optional implementation, the first parameter is calculated using the following formula:

[0056]

[0057] Where Z represents the standardized runoff index, c0, c1, c2, d1, d2 and d3 represent the sub-parameters in the parameter group, and y represents the first parameter;

[0058] The threshold runoff volume is calculated using the following formula:

[0059]

[0060] Where W represents the second parameter, e represents the natural constant, y represents the first parameter, and the inverse function of Γ is... β represents the scale parameter, and γ represents the shape parameter.

[0061] In this embodiment of the invention, Z is the aforementioned standardized runoff index. When drought levels are categorized as moderate drought, severe drought, and extreme drought, Z can also be selected with three different values ​​to correspond to the three drought levels. For example, Z can be -2.0, -1.5, and -1.0. Furthermore, c0, c1, c2, d1, d2, and d3 represent sub-parameters in the parameter group. In some optional implementations... Thus, the first parameter y can be obtained by solving for it.

[0062] After obtaining the first parameter y, the second parameter W can be directly solved, because the inverse function of Γ is... Therefore, the threshold runoff can be calculated based on the second parameter W, the scale parameter β, and the shape parameter γ. Q When drought levels are categorized into moderate drought, severe drought, and extreme drought, the threshold runoff for moderate drought is obtained. Severe drought threshold runoff Drought threshold runoff .

[0063] As an optional implementation, the step of fitting the historical runoff sequence using the GAMLSS model to determine the probability distribution function includes:

[0064] Obtain a set of probability distributions, including: normal distribution, log-normal distribution, Gumbel distribution, gamma distribution, and Weibull distribution;

[0065] Based on the historical runoff sequence and the probability distribution set, a probability density function is determined, wherein the probability density function is obtained through... express, and Represents a constant variable, time. For covariates;

[0066] The Akaike Information Criterion GAIC value is determined based on the type of the probability distribution set.

[0067] The GAIC value is calculated using the following formula:

[0068] Where # represents the penalty factor, df This represents the total degrees of freedom in the GAMLSS model. Represents the log-likelihood function;

[0069] The probability distribution type with the smallest GAIC value is selected as the target probability distribution type, and the probability distribution function is determined. , and Represents a constant variable, time. It is a covariate.

[0070] In this embodiment of the invention, multiple probability distributions including position parameters and scale parameters are obtained, and a probability distribution set is established, for example: using express S Given a set of different candidate probability distributions, for a given candidate probability distribution... The probability density function of the above historical runoff sequence can be expressed as: The aforementioned historical runoff sequence can also be expressed as In this model, the two parameters in the probability density function can be set as either constant variables or time variables with time t as a covariate. Furthermore, time t as a covariate includes both the first and second powers of time t. Finally, by comparing the GAIC values ​​corresponding to different probability distribution types and parameter settings, the probability distribution type and parameters with the smallest GAIC value are selected as the optimal model. Through this embodiment of the invention, a best-fitting probability distribution type can be selected from multiple probability distributions, and a matching probability distribution function can be obtained. This improves computational accuracy and lays the foundation for predicting water shortage risks in subsequent embodiments, thereby enhancing the effectiveness of prediction and assessment.

[0071] It should be noted that the probability density function of the optimal model can be used... This means that the probability distribution function can be expressed as... express.

[0072] As an optional implementation, determining the first calculation result based on the probability distribution function includes:

[0073] The first information is determined based on the probability distribution function, whereby the first information represents the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation.

[0074] The second information is determined based on the first information, and the second information represents the probability that the runoff volume will be lower than the threshold runoff volume for the first time from the start of the calculation year to the h-th year;

[0075] The first calculation result is determined based on the second information.

[0076] In this embodiment of the invention, the probability of runoff falling below the aforementioned threshold runoff volume each year from the starting year is calculated using a determined probability distribution function, thus determining the aforementioned first information. Then, the probability of the runoff volume falling below the threshold for the first time from the starting year is obtained using the first information, thus determining the aforementioned second information. After obtaining the second information, a predicted value for a drought event is determined based on the probability of the runoff volume falling below the threshold for the first time from the starting year. The predicted value represents the expected number of years from the starting year to the first occurrence of a drought event. A drought event can be understood as runoff volume falling below the aforementioned threshold runoff volume. Through this embodiment of the invention, the expected number of years from the calculation year to the first occurrence of a drought event can be obtained, thereby improving the assessment effect of water resource shortage risk.

[0077] It should be noted that after obtaining the first calculation result, the user can determine the time of the drought event based on the number of years represented by the first calculation result and the starting year of the calculation. For example, if the starting year of the calculation is 1990 and the predicted value represented by the first calculation result is 8, then the final determination of the time of the drought event through the embodiment of the present invention is 1998.

[0078] As an optional implementation, the first information is calculated using the following formula:

[0079]

[0080] in, This represents the first piece of information, where t represents time. Indicates the threshold runoff volume. Indicates constant variables;

[0081] The second information is calculated using the following formula:

[0082]

[0083] in, This indicates the second piece of information, where h represents the year when calculations cease. This indicates the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation.

[0084] The first calculation result is calculated using the following formula:

[0085]

[0086] in, This represents the first calculation result, and h represents the year when the calculation stopped. This represents the probability that, starting from the year of calculation, the runoff will be lower than the threshold runoff for the first time in year h.

[0087] It should be noted that if there exists a certain time T, satisfying... ,but Conversely, .

[0088] In this embodiment of the invention, when the threshold runoff includes moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff, the first information also includes the annual occurrence probability corresponding to the three cases, which can be used... , , express.

[0089] Similarly, when the aforementioned threshold runoff includes moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff, the aforementioned second information also includes the probability of the first occurrence for each of the three scenarios. This second information can be used... The expression indicates that k represents the drought level, including moderate drought, severe drought, and extreme drought.

[0090] Of course, when the above threshold runoff includes moderate drought threshold runoff, severe drought threshold runoff and extreme drought threshold runoff, it can also be applied to the above first calculation result. For example, the above first calculation result represents the expected number of years from the starting year when a certain level of drought event first occurs.

[0091] As an optional implementation, after determining the first calculation result based on the probability distribution function, the method further includes:

[0092] A second calculation result is determined based on the second information, and the second calculation result represents the probability that the runoff volume is lower than the threshold runoff volume within a preset time period.

[0093] In this embodiment of the invention, the second calculation result can represent the probability that the runoff is lower than the threshold runoff within a preset time period, which can be understood as the risk of water shortage within the preset time period. The second information represents the probability that the runoff will first fall below the threshold runoff from the start of the calculation year to the h-th year. Therefore, the second calculation result can be represented as the sum of the probabilities of a drought event occurring each year from the start of the calculation year to the n-th year, where h ≤ n. Through this embodiment of the invention, the risk of water shortage can be assessed and predicted from another perspective, further improving the assessment effect.

[0094] It should be noted that users can refer to both the first calculation result and the second calculation result to assess the risk of water shortage. The first calculation result can help users determine the specific year, while the second calculation result can represent the probability of a dry season event occurring within a preset time period. This can also be understood as determining the average time interval from the starting year until the next year with a specific level of dry season under changing conditions, thereby quantitatively assessing the risk of river water shortage caused by extreme dry season within a specified period.

[0095] As an optional implementation, the second calculation result is calculated using the following formula:

[0096]

[0097] in, This represents the second calculation result, where n represents the number of years included in the preset time period. This represents the probability that, from the start of the calculation year until the h-th year, the runoff volume will first fall below the threshold runoff volume. The probability that the annual runoff is lower than the threshold runoff from the start of the calculation year.

[0098] When the above-mentioned threshold runoff includes moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff, the second calculation result can also be calculated using the following formula:

[0099]

[0100] Here, k represents the level of water shortage risk, such as moderate drought, severe drought, and extreme drought.

[0101] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a water shortage risk prediction device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the water shortage risk prediction device 200 includes:

[0102] Module 201 is used to acquire historical runoff sequences of the target watershed;

[0103] The first determining module 202 is used to determine the threshold runoff volume based on the historical runoff sequence;

[0104] The second determining module 203 is used to fit the historical runoff sequence using the generalized additivity GAMLSS model to determine the probability distribution function;

[0105] The third determining module 204 is used to determine a first calculation result based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff volume first falls below the threshold runoff volume.

[0106] As an optional implementation, the threshold runoff includes at least one of the following: moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff.

[0107] Optionally, the first determining module includes:

[0108] The first determining unit is used to determine the scale parameter and shape parameter of the corresponding gamma Γ distribution based on the historical runoff sequence using the maximum likelihood estimation method, wherein the historical runoff sequence follows the Γ distribution;

[0109] The second determining unit is used to obtain the standardized runoff index and determine the first parameter based on the standardized runoff index;

[0110] The third determining unit is used to determine the threshold runoff volume based on the first parameter and the inverse function of the Γ distribution.

[0111] As an optional implementation, the first parameter is calculated using the following formula:

[0112]

[0113] Where Z represents the standard runoff index, c0, c1, c2, d1, d2 and d3 represent the sub-parameters in the parameter group, and y represents the first parameter;

[0114] The threshold runoff volume is calculated using the following formula:

[0115]

[0116] Where W represents the second parameter, e represents the natural constant, y represents the first parameter, and the inverse function of Γ is... β represents the scale parameter, and γ represents the shape parameter.

[0117] As an optional implementation, the second determining module includes:

[0118] The first acquisition unit is used to acquire a probability distribution set, which includes: normal distribution, log-normal distribution, Gumbel distribution, gamma distribution, and Weibull distribution;

[0119] The fourth determining unit is configured to determine a probability density function based on the historical runoff sequence and the probability distribution set, wherein the probability density function is determined by... express, and Represents a constant variable, time. For covariates;

[0120] The fifth determining unit is used to determine the Akaike Information Criterion GAIC value based on the type of the probability distribution set;

[0121] The GAIC value is calculated using the following formula:

[0122] Where # represents the penalty factor, df This represents the total degrees of freedom in the GAMLSS model. Represents the log-likelihood function;

[0123] The sixth determining unit is used to select the probability distribution type with the smallest GAIC value as the target probability distribution type and to determine the probability distribution function. , and Represents a constant variable, time. Let j be a covariate, and j represent the sequence.

[0124] As an optional implementation, the third determining module includes:

[0125] The seventh determining unit is used to determine first information based on the probability distribution function, wherein the first information represents the probability that the annual runoff is lower than the threshold runoff starting from the year of calculation;

[0126] The eighth determining unit is used to determine the second information based on the first information, wherein the second information represents the probability that the runoff volume is lower than the threshold runoff volume for the first time from the start of the calculation year to the h-th year;

[0127] The ninth determining unit determines the first calculation result based on the second information.

[0128] As an optional implementation, the first information is calculated using the following formula:

[0129]

[0130] in, This represents the first piece of information, where t represents time. Indicates the threshold runoff volume. Indicates constant variables;

[0131] The second information is calculated using the following formula:

[0132]

[0133] in, This indicates the second piece of information, where h represents the year when calculations cease. This indicates the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation.

[0134] The first calculation result is calculated using the following formula:

[0135]

[0136] in, This represents the first calculation result, and h represents the year when the calculation stopped. This represents the probability that, starting from the year of calculation, the runoff will be lower than the threshold runoff for the first time in year h.

[0137] As an optional implementation, please refer to Figure 3 The water shortage risk prediction device 200 also includes:

[0138] The fourth determining module 205 is used to determine a second calculation result based on the second information, wherein the second calculation result represents the probability that the runoff volume is lower than the threshold runoff volume within a preset time period.

[0139] As an optional implementation, the second calculation result is calculated using the following formula:

[0140]

[0141] in, This represents the second calculation result, where n represents the number of years included in the preset time period. This represents the probability that, from the start of the calculation year until the h-th year, the runoff volume will first fall below the threshold runoff volume. The probability that the annual runoff is lower than the threshold runoff from the start of the calculation year.

[0142] According to embodiments of the present invention, the present invention also provides an electronic device and a readable storage medium.

[0143] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0144] like Figure 4As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0145] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0146] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as water scarcity risk prediction methods.

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0152] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0153] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0154] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting water shortage risk, characterized in that, include: Obtain historical runoff sequences for the target watershed; The threshold runoff volume is determined based on the historical runoff sequence; The probability distribution function was determined by fitting the historical runoff sequence using the generalized additivity GAMLSS model. A first calculation result is determined based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff volume first falls below the threshold runoff volume. By fitting the historical runoff sequence using the GAMLSS model, the probability distribution function is determined, including: Obtain a set of probability distributions, including: normal distribution, log-normal distribution, Gumbel distribution, gamma distribution, and Weibull distribution; Based on the historical runoff sequence and the probability distribution set, a probability density function is determined, wherein the probability density function is obtained through... express, and Represents a constant variable, time. For covariates; The Akaike Information Criterion GAIC value is determined based on the type of the probability distribution set. The GAIC value is calculated using the following formula: ； Where # represents the penalty factor, df This represents the total degrees of freedom in the GAMLSS model. Let j represent the log-likelihood function, j represent the sequence, and n represent the number of years included in the preset time period. The probability distribution type with the smallest GAIC value is selected as the target probability distribution type, and the probability distribution function is determined. , and Represents a constant variable, time. For covariates; Determining the first calculation result based on the probability distribution function includes: The first information is determined based on the probability distribution function, whereby the first information represents the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation. The second information is determined based on the first information, and the second information represents the probability that the runoff volume will be lower than the threshold runoff volume for the first time from the start of the calculation year to the h-th year; The first calculation result is determined based on the second information; The first information is calculated using the following formula: ； in, This represents the first piece of information, where t represents time. Indicates the threshold runoff volume. Indicates constant variables; The second information is calculated using the following formula: ； in, This indicates the second piece of information, where h represents the year when calculations cease. This represents the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation; the first calculation result is calculated using the following formula: ； in, This represents the first calculation result, and h represents the year when the calculation stopped. This represents the probability that, from the start of the calculation year until the h-th year, the first runoff volume will be lower than the threshold runoff volume. If there exists a time T such that... ,but =T, otherwise, .

2. The water shortage risk prediction method according to claim 1, characterized in that, The threshold runoff includes at least one of the following: moderate drought threshold runoff, severe drought threshold runoff, and extreme drought threshold runoff.

3. The water shortage risk prediction method according to claim 1, characterized in that, Determining the threshold runoff volume based on the historical runoff sequence includes: Based on the historical runoff sequence, the scale parameter and shape parameter of the corresponding gamma Γ distribution are determined using the maximum likelihood estimation method, and the historical runoff sequence follows the Γ distribution; Obtain the standardized runoff index, and determine the first parameter based on the standardized runoff index; The threshold runoff volume is determined based on the first parameter and the inverse function of the Γ distribution.

4. The water shortage risk prediction method according to claim 3, characterized in that, The first parameter is calculated using the following formula: ； Where Z represents the standard runoff index, c0, c1, c2, d1, d2 and d3 represent the sub-parameters in the parameter group, and y represents the first parameter; The threshold runoff volume is calculated using the following formula: ； Where W represents the second parameter, e represents the natural constant, y represents the first parameter, and the inverse function of Γ is... β represents the scale parameter, and γ represents the shape parameter.

5. The water shortage risk prediction method according to claim 1, characterized in that, After determining the first calculation result based on the probability distribution function, the method further includes: A second calculation result is determined based on the second information, and the second calculation result represents the probability that the runoff volume is lower than the threshold runoff volume within a preset time period.

6. The water shortage risk prediction method according to claim 5, characterized in that, The second calculation result is calculated using the following formula: ； in, This represents the second calculation result, where n represents the number of years included in the preset time period. This represents the probability that, from the start of the calculation year until the h-th year, the runoff volume will first fall below the threshold runoff volume. The probability that the annual runoff is lower than the threshold runoff from the start of the calculation year.

7. A water shortage risk prediction device, characterized in that, include: The acquisition module is used to obtain historical runoff sequences of the target watershed; The first determining module is used to determine the threshold runoff volume based on the historical runoff sequence; The second determining module is used to fit the historical runoff sequence using the generalized additivity GAMLSS model to determine the probability distribution function; The third determining module is used to determine a first calculation result based on the probability distribution function. The first calculation result represents the predicted number of years from the start of the calculation year until the runoff volume first falls below the threshold runoff volume. The second determining module includes: The first acquisition unit is used to acquire a probability distribution set, which includes: normal distribution, log-normal distribution, Gumbel distribution, gamma distribution, and Weibull distribution; The fourth determining unit is used to determine the probability density function based on the historical runoff sequence and the probability distribution set, wherein the probability density function is determined by... express, and Represents a constant variable, time. For covariates; The fifth determining unit is used to determine the Akaike Information Criterion GAIC value based on the type of the probability distribution set; The GAIC value is calculated using the following formula: ； Where # represents the penalty factor, df This represents the total degrees of freedom in the GAMLSS model. Let j represent the log-likelihood function, j represent the sequence, and n represent the number of years included in the preset time period. The sixth determining unit is used to select the probability distribution type with the smallest GAIC value as the target probability distribution type and to determine the probability distribution function. , and Represents a constant variable, time. For covariates; The third determining module includes: The seventh determining unit is used to determine first information based on the probability distribution function, wherein the first information represents the probability that the annual runoff is lower than the threshold runoff starting from the year of calculation; The eighth determining unit is used to determine the second information based on the first information, wherein the second information represents the probability that the runoff volume is lower than the threshold runoff volume for the first time from the start of the calculation year to the h-th year; The ninth determining unit is used to determine the first calculation result based on the second information; The first information is calculated using the following formula: ； in, This represents the first piece of information, where t represents time. Indicates the threshold runoff volume. Indicates constant variables; The second information is calculated using the following formula: ； in, This indicates the second piece of information, where h represents the year when calculations cease. This indicates the probability that the annual runoff will be lower than the threshold runoff starting from the year of calculation. The first calculation result is calculated using the following formula: ； in, This represents the first calculation result, and h represents the year when the calculation stopped. This represents the probability that, from the start of the calculation year until the h-th year, the first runoff volume will be lower than the threshold runoff volume. If there exists a time T such that... ,but =T, otherwise, .

Images