CN115600822B - Method and system for distributing initial water right of river basin across provinces - Google Patents
Method and system for distributing initial water right of river basin across provinces Download PDFInfo
- Publication number
- CN115600822B CN115600822B CN202211497042.1A CN202211497042A CN115600822B CN 115600822 B CN115600822 B CN 115600822B CN 202211497042 A CN202211497042 A CN 202211497042A CN 115600822 B CN115600822 B CN 115600822B
- Authority
- CN
- China
- Prior art keywords
- index
- evaluation index
- initial water
- value
- river basin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000011156 evaluation Methods 0.000 claims abstract description 87
- 238000009826 distribution Methods 0.000 claims abstract description 40
- 238000011161 development Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 18
- 238000012216 screening Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 230000035772 mutation Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000009191 jumping Effects 0.000 claims description 6
- CNYFJCCVJNARLE-UHFFFAOYSA-L calcium;2-sulfanylacetic acid;2-sulfidoacetate Chemical compound [Ca+2].[O-]C(=O)CS.[O-]C(=O)CS CNYFJCCVJNARLE-UHFFFAOYSA-L 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 239000010842 industrial wastewater Substances 0.000 claims description 3
- 239000008235 industrial water Substances 0.000 claims description 3
- 238000003973 irrigation Methods 0.000 claims description 3
- 230000002262 irrigation Effects 0.000 claims description 3
- 239000003621 irrigation water Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000010206 sensitivity analysis Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 4
- 150000001875 compounds Chemical class 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 101100001672 Emericella variicolor andG gene Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Geometry (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for distributing initial water right of a river basin across provinces, wherein the method comprises the following steps: reading water resource survey data of river basin crossing provinces, and obtaining and analyzing a representative hydrological series capable of reflecting withering changes and current underlying surface conditions; acquiring basic data of river basin across provinces, wherein the basic data comprises water resource development and utilization data, economic and social data and ecological environment data; obtaining an evaluation index of an evaluation index system for constructing initial water resource distribution across provinces, rivers and watersheds, and reducing the evaluation index; and constructing an SMAA-VIKOR initial water weight distribution model, solving, and obtaining the initial water weight distribution proportion of each provincial administrative region. The invention can improve the water resource distribution precision and fairness across provincial river basins.
Description
Technical Field
The invention relates to a water resource optimal configuration and scheduling technology. In particular to a method and a system for distributing initial water right of a river basin across provinces.
Background
With the development of economy and the improvement of ecological environment protection consciousness, the water resource bottleneck problem in the development process of China is more and more prominent. The clear water resource right plays a good role in solving the public tragedy of water resource utilization, restraining water resource overload and improving the water resource utilization benefit. In order to better serve the economic development, the strictest water resource management system is carried out from the strictest fine-tube good water resource, and the initial water resource allocation system is perfected, which is currently important work content.
The initial water right distribution of the river basin across provinces is an important subject at present, which relates to benefit distribution among provinces and factors such as nature, society, economy and the like, so the initial water right distribution is a decision process with multiple regions, multiple targets, multiple attributes and multiple layers, more parameters and constraint conditions, strong subjectivity of weight setting, relatively complex calculation and no better solution at present.
Therefore, new technical solutions need to be studied.
Disclosure of Invention
The invention aims to: on one hand, the method for distributing the initial water right of the river basin across the province is provided, so that the problems in the prior art are solved. In another aspect, a system for implementing the above method is provided.
The technical scheme is as follows: the method for distributing the initial water right of the river basin across the province comprises the following steps:
step S1, reading water resource survey data of a river basin across provinces, obtaining and analyzing a representative hydrological series capable of reflecting the withering change and the current underlying surface condition;
s2, collecting basic data of river basin crossing provinces, wherein the basic data comprises water resource development and utilization data, economic and social data and ecological environment data; obtaining an evaluation index of an evaluation index system for constructing initial water resource distribution of a river basin crossing provinces, and reducing the evaluation index;
and S3, constructing an SMAA-VIKOR initial water weight distribution model, solving, and obtaining the initial water weight distribution proportion of each provincial administrative region.
According to an aspect of the present application, the process of obtaining and analyzing in step S1, which can reflect the change of kurtosis and the representative hydrological series under the current underlying surface condition, is further:
s11, acquiring a natural runoff time sequence in the hydrological series, and fitting by adopting a linear equation to judge the trend condition of the natural runoff series;
and S12, judging whether the natural runoff time sequence has the jumping phenomenon, and checking the exact time of the element mean change of the time sequence by a statistical method to determine the exact time of the natural runoff having the jumping phenomenon.
According to an aspect of the present application, in step S11, the process of fitting by using the linear equation specifically includes:
x t '≈a 0 +a 1 t；a 1 indicating natural runoffxThe tendency of (a) to be in a tendency,a 0 is a constant value of the regression equation,x t 'as an estimate of natural runoff, natural runoffxAnd timetThe degree of closeness of linear correlation between them is defined by correlation coefficientrRepresenting;
in the formula (I), the compound is shown in the specification,x b is as followsbThe natural runoff volume of the year is,x m is the mean value of the time series of the runoff volume,t m =（n+1）/2，nthe length of the series of natural runoff flows,rthe value is positive, which indicates that the natural runoff quantity in the natural runoff time series is calculatednThere is a trend of linear increase in the year.
According to an aspect of the present application, in the step S12, the step of determining whether there is a jump phenomenon in the time series of natural runoff is further performed by:
step S12a forkArray composed of time series of natural runoffx（x 1 ，x 2 ，…x i ，…x j ，…x k ) Constructing rank sequenceS k ，S k =r 1 +r 2 +…，+r i ，…+r k (ii) a When x is i ＞x j When r is i (= 1) when x i =x j When r is i (= 0) when x i ＜x j When r is i =﹣1，
Step S12b, judging max I at time tS k I is equal to the predetermined value, if so, the momenttThe time of the mutation point;
step S12c, calculating the probability P of the catastrophe point,P=2exp[﹣6k t 2 /（n 3 +n 2 ）](ii) a When in usePAt < 0.5, the detected mutation points are statistically significant. n has the same meaning as above.
According to one aspect of the application, the evaluation index system comprises a target layer, a criterion layer and an index layer, wherein the target layer is the total amount of watershed water resources, and the criterion layer comprises a fair principle, an efficient principle and a sustainable principle; the indexes related to the fairness principle comprise current water consumption, population number, total GDP amount, basin area and irrigation area; indexes related to the high-efficiency principle comprise GDP per capita, GDP water consumption of ten thousand yuan, increased industrial value water consumption of ten thousand yuan, effective utilization coefficient of farmland irrigation water and industrial water reuse rate; the indexes related to the sustainable principle comprise forest coverage rate, population growth rate, GDP growth rate, urbanization rate, inferior V-class water discharge proportion, industrial wastewater discharge standard rate and water quality standard rate of a water functional area.
According to an aspect of the present application, in the step S2, the process of reducing the evaluation index specifically includes:
s21, constructing an XGBOST model, collecting a plurality of evaluation indexes as the input of the XGBOST model, taking the comprehensive evaluation index value as the output of the XGBOST model, and training the model;
s22, extracting the relative importance degree information of each evaluation index from the connection weight of the trained XGBOST model, and screening the evaluation indexes;
s23, carrying out sensitivity analysis on each evaluation index by adopting a trained XGBOST model, and quantitatively calculating the relative contribution rate of the change of each evaluation index to the change of a decision result;
s24, constructing a comprehensive judgment criterion for screening the evaluation indexes based on the relative importance degree information and the relative contribution rate of the evaluation indexes, and screening the evaluation indexes based on the comprehensive judgment criterion;
the process of constructing the comprehensive judgment criterion for screening the evaluation indexes comprises the steps of calculating products of relative importance degree information and relative contribution rate one by one aiming at each evaluation index to obtain a first comprehensive evaluation index; then, calculating the average value of the first comprehensive evaluation index, using each evaluation index and the average value as a quotient, then calculating the decimal logarithm value of the quotient, and judging whether the decimal logarithm value of the evaluation index meets the threshold value one by one.
According to one aspect of the application, the process of training the XGBOOST model is:
step S21a, generating a scheduling scheme set meeting constraint conditions, and calculating a positive ideal point when all index values reach the optimum and a negative ideal point when all index values reach the worst to obtain upper and lower limit states of the scheme;
s21b, generating input items of the XGB OST model training samples by adopting a random simulation method, randomly generating a preset number of random numbers which are subjected to uniform distribution, and carrying out discretization calculation on index values between positive ideal points and negative ideal points to generate a preset number of training sample input items;
and S21c, calculating Euclidean distances and pasting schedules of the samples from the positive ideal points and the negative ideal points, and normalizing the pasting degree.
According to an aspect of the application, the step S3 is further:
s31, constructing a decision matrix of the alternative scheme and standardizing to obtain a standardized decision matrix;
s32, determining the distribution of a feasible weight space, sampling based on a probability density function of the feasible weight space, and randomly generating feasible weights;
s33, constructing a VIKOR model and calculating to obtain the ranking of each alternative scheme;
s34, ranking of the alternative schemes obtained in the storage calculation process, and calculating a sorting acceptability index, a global acceptability index and a central weight vector; and obtaining the initial water weight distribution proportion of each provincial administrative district.
According to another aspect of the present application, there is provided an initial water right distribution system across river basins of the province, comprising:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the processor, and the instructions are used for being executed by the processor to implement the method for distributing the initial water right across the river basin in the province according to any technical scheme.
Has the beneficial effects that: by means of dimension reduction and optimization of an evaluation index system and construction of an SMAA-VIKOR initial water weight distribution model, the problem that weight setting subjectivity is strong in the prior art is solved, and water resource distribution accuracy and fairness of the river basin of the cross-province can be improved.
Drawings
FIG. 1 is a flow chart of the overall implementation process of the present invention.
FIG. 2 is a flow chart of a representative hydrological series obtained and analyzed in accordance with the present invention to reflect the changes in fullness and dryness and current underlying surface conditions.
FIG. 3 is a flowchart for reducing the evaluation index according to the present invention.
FIG. 4 is a flow diagram of the present invention for training the XGBOST model.
Fig. 5 is a detailed process diagram of step S3 of the present invention.
Detailed Description
In order to solve the problems in the prior art, the applicant researches the existing documents, in the existing patents and papers, the definition and selection of indexes are not uniform, different indexes are given in different documents, the subjectivity is high, and the fairness of the water diversion result is often questioned. The skilled person also has made some research, for example, the TOPSIS model is used to determine the water division ratio, but the fairness of the water division ratio obtained by this method has yet to be studied in depth.
For complex evaluation indexes, complex nonlinear relations exist among the evaluation indexes, how to reduce the dimension of an evaluation index system is achieved, meanwhile, relatively accurate nonlinear mapping between input vectors and output data is achieved, and the method is an important basis for construction of the evaluation index system and construction of index weights. For this reason, the applicant has conducted research and has given the following technical solutions.
As shown in fig. 1, the method for distributing the initial water right across the river basin of the province comprises the following steps:
s1, reading water resource survey data of river basin crossing provinces, obtaining and analyzing a representative hydrological series capable of reflecting withering changes and current underlying surface conditions. And after the initial water weight distribution proportion is obtained subsequently, regulating and controlling parameters of the representative hydrological sequence are regulated according to the proportion, so that the distribution of water resources is realized. In some embodiments, the water resource allocation can be realized by adjusting the runoff of the areas in the year of year, year.
S2, collecting basic data of river basin crossing provinces, wherein the basic data comprises water resource development and utilization data, economic and social data and ecological environment data; obtaining an evaluation index of an evaluation index system for constructing initial water resource distribution of a river basin crossing provinces, and reducing the evaluation index;
and S3, constructing an SMAA-VIKOR initial water weight distribution model, and solving to obtain the initial water weight distribution proportion of each provincial administrative region.
In this example, the research basin was first investigated, and then the basic data was collected, from which a representative hydrological series was obtained. Then, a series of indexes are collected as alternative items of the evaluation indexes, the indexes are combed and dimension reduction is carried out through the establishment of an index evaluation system, appropriate evaluation indexes are selected from the indexes, and an evaluation index system is established. And finally, constructing an initial water weight distribution model, taking the data as one of input data, and solving the model to obtain initial water weight distribution proportion data. Specific implementations are described in detail below.
In another embodiment of the present application, as shown in fig. 2, the process of obtaining and analyzing the representative hydrological series capable of reflecting the rich variation and the current underlying surface condition in step S1 is further:
s11, acquiring a natural runoff time sequence in the hydrological series, and fitting by adopting a linear equation to judge the trend condition of the natural runoff series; the process of fitting by adopting the linear equation is specifically as follows:
x t '≈a 0 +a 1 t；a 1 indicating natural runoffxThe tendency of (a) to be in a tendency,a 1 if > 0, x tends to increase with the increase of time t, otherwise, x tends to decrease,a 1 also referred to as the tendency value,a 0 is a constant of the regression to be,x t 'is a natural runoff estimate.
Natural runoff volumexAnd timetThe degree of closeness of linear correlation between them is defined by correlation coefficientrRepresenting;
in the formula (I), the compound is shown in the specification,x b is a firstbThe natural runoff volume of the year is,x m is the mean value of the time series of the runoff volume,t m =（n+1）/2，nthe length of the series of the natural runoff is long,rthe value is positive, which indicates that the natural runoff quantity in the natural runoff time series is calculatednThere is a linear increasing trend in the year.rWhen the value is negative, the natural runoff quantity in the natural runoff time series is calculatednThere is a linear decreasing trend in the year.rWhen =0, the regression coefficient is 0, which indicates the natural runoffxIs time independent.rThe larger the absolute value of (a) is, the smaller the linear correlation is, whereas the larger the absolute value of (b) is, the more closely the linear correlation is.
Obtaining confidence level by inquiring coefficient checking tableαWhen is coming into contact withrIs less thanγ 0.05 When the utility model is used, the water is discharged,the linear change trend of the natural runoff sequence is not obvious; when the absolute value of r is inγ 0.05 Andγ 0.01 when the absolute value of r is larger than the absolute value of r, the linear change trend of the natural runoff volume sequence is obviousγ 0.01 When the natural runoff quantity sequence is linear, the linear change trend of the natural runoff quantity sequence is considered to be particularly remarkable.
And S12, judging whether the natural runoff time sequence has the jumping phenomenon, and checking the exact time of the element mean change of the time sequence by a statistical method to determine the exact time of the natural runoff having the jumping phenomenon.
In step S12, the step of determining whether a jump phenomenon exists in the time series of natural runoff further includes:
step S12a forkArray composed of time series of natural runoffx（x 1 ，x 2 ，…x i ，…x j ，…x k ) Constructing rank sequenceS k ，S k =r 1 +r 2 +…，+r i ，…+r k (ii) a When the temperature is higher than the set temperaturex i ＞x j When the temperature of the water is higher than the set temperature,r i =1, whenx i =x j When the temperature of the water is higher than the set temperature,r i =0, whenx i ＜x j When the utility model is used, the water is discharged,r i =﹣1，
step S12b, judging intTime, max |)S k I is equal to the predetermined value, if so, the momenttThe time of the mutation point;
step S12c, calculating the probability of the mutation point momentP，P=2exp[﹣6k t 2 /（n 3 +n 2 ）](ii) a When in usePThe detected mutation points are statistically significant at less than 0.5.
Specifically, after the treatment, the following evaluation index system was obtained. The evaluation index system comprises a target layer, a criterion layer and an index layer, wherein the target layer is the total amount of watershed water resources, and the criterion layer comprises a fairness principle, an efficient principle and a sustainable principle; the indexes related to the fairness principle comprise current water consumption, population quantity, total GDP amount, drainage basin area and irrigation area; indexes related to the high-efficiency principle comprise average human GDP, average human water consumption, ten thousand yuan GDP water consumption, ten thousand yuan industrial added value water consumption, farmland irrigation water effective utilization coefficient and industrial water repetition rate; the indexes related to the sustainable principle comprise forest coverage rate, population growth rate, GDP growth rate, urbanization rate, inferior V-class water discharge proportion, industrial wastewater discharge standard rate and water quality standard rate of a water functional area.
In this embodiment, the fairness principle mainly considers the current water usage, population distribution, natural conditions, productivity distribution, and the like in different areas, and it is necessary to achieve fairness and reasonableness in the initial water right distribution. The efficient principle mainly considers that water resources are both natural resources and economic resources, and the economic benefit of the water resources needs to be considered in the initial water right distribution. The sustainable principle mainly considers that water resources are an important support for the sustainable development of the economic society, and in the initial water right distribution, the principle of harmonious development of the water resources and the economic society is followed, and the bearing capacity of the development and utilization of the water resources in the drainage basin cannot be exceeded. Based on the evaluation index system of the embodiment, a corresponding weight matrix is constructed.
Specifically, the reduction process of the evaluation index is relatively complicated, and will be described below. In the method, an idea of deleting indexes one by one is adopted, and an index system dimension reduction method based on the XGB model is provided around five aspects of comprehensive discrimination criteria of XGB model training sample generation, XGB model topological structure design, index importance identification, index sensitivity identification and index screening.
As shown in fig. 3 and 4, in another embodiment of the present application, in the step S2, the process of reducing the evaluation index specifically includes:
and S21, constructing the XGBOST model, collecting a plurality of evaluation indexes as the input of the XGBOST model, taking the comprehensive evaluation index value as the output of the XGBOST model, and training the model.
The process of training the XGBOOST model is:
and S21a, generating a scheduling scheme set meeting constraint conditions, and calculating a positive ideal point when all index values reach the optimum and a negative ideal point when all index values reach the worst to obtain upper and lower limit states of the scheme.
And S21b, generating input items of the XGB OST model training samples by adopting a random simulation method, randomly generating a preset number of random numbers which are uniformly distributed, and performing discretization calculation on index values between the positive ideal points and the negative ideal points to generate a preset number of training sample input items.
And S21c, calculating Euclidean distances and pasting degrees of the samples from the positive ideal points and the negative ideal points, and normalizing the pasting degrees.
In this step, the approach degree is a comprehensive evaluation index reflecting the quality of the water right allocation scheme. The value range of the pasting progress is [0,1 ]]The relative distance of the training sample from the positive and negative ideal points is reflected. The larger the penetration degree is, the farther the sample is from the negative ideal point is shown, and the closer the sample is to the positive ideal point, the better the sample is; otherwise, the worse. The index value normalized by each training sample is used as the XGBOST model input, the closeness coefficient is used as the XGBOST model output, and the finally generated XGBOST model training sample set can be expressed as follows: {x id ，c t I1t=1,2，…，D；d=1,2,…，n｝。
And S22, extracting the relative importance degree information of each evaluation index from the trained XGBOST model connection weight value, and screening the evaluation indexes.
Let the input vector of the input layer be (x 1 ，x 2 ，…，x d ，…，x n ） T The output vector of the intermediate layer isy 1 ，y 2 ，…， y d ，…，y n ） T 。zIs the actual output value of the XGboost model. Input layer sectionDotdAnd intermediate level nodessThe connection weight value between them is recorded asw ds Intermediate layer nodesAnd the connection weight between the nodes of the output layer is recorded as w s ，θ s Andθthreshold values for the intermediate layer and the output layer, respectively.
XGBOOST model connection weightw ds And w s The information quantity of a certain index value introduced into the XGB OST model is reflected, and the contribution degree of the index to the output of the XGB OST model is determined. Thus, define the firstdRelative importance of individual indicatorsR d Comprises the following steps:
R d the larger the value of (A) is, the more remarkable the effect of the index on the flood control scheduling multi-attribute decision is shown, and the more important the position in the original index system is.
And S23, carrying out sensitivity analysis on each evaluation index by adopting the trained XGBOST model, and quantitatively calculating the relative contribution rate of the change of each evaluation index to the change of the decision result.
Using each index value of a sample as an input vector (b:)x 1 ，x 2 ，…，x j ，…，x n ） T The output value of the XGBoost model is recorded asz’. For the firstjAn index valuex j Setting 9 different change scenes under the condition of keeping other indexes unchanged, namelyx j * =x j ×（1+∆x j ），∆x j =0, ± 5%, ± 10%, 15%, + -20%, by (C)x 1 ，x 2 ，…，x j ，…，x n ） T Predicting the relative change of the actual output value of the XGboost model as the input of the XGboost model, and analyzing the XGboost model according to the relative changeSensitivity of the actual output values to the respective indices.
In order to quantitatively analyze the sensitivity of each index, the method comprises∆x j Output value of XGBoost model when = +/-20%zHas an absolute change amount of∆z j = I |)z-z m I, calculating the relative variation:∆z j * =∆z j /z，
further calculate thejVariation of each index to output value of XGboost modelzRelative rate of contribution of changeG j ：
G j =∆z j * /(∆z 1 * +∆z 2 * +…，+∆z j * )×100%。
And S24, constructing a comprehensive judgment criterion for screening the evaluation indexes based on the relative importance degree information and the relative contribution rate of the evaluation indexes, and screening the evaluation indexes based on the comprehensive judgment criterion.
The process of constructing the comprehensive judgment criterion for screening the evaluation indexes comprises the steps of calculating the product of relative importance degree information and relative contribution rate one by one aiming at each evaluation index to obtain a first comprehensive evaluation index; then, calculating the average value of the first comprehensive evaluation index, using each evaluation index and the average value as a quotient, then calculating the decimal logarithm value of the quotient, and judging whether the decimal logarithm value of the evaluation index meets the threshold value one by one.
The relative importance and the relative contribution rate quantitatively represent the relative importance and sensitivity information of each index, and can provide reference basis for a decision maker to screen the indexes. However, in the actual index screening process, there is still a large subjective randomness and ambiguity as to which indexes are finally deleted and retained. In order to more effectively combine the relative importance and the relative contribution rate information to carry out index screening, a comprehensive index which can simultaneously consider the sizes of the two is definedF j ：
F j =R j ×G j ；
In the formula (I), the compound is shown in the specification,R j andG j are respectively the firstjThe relative importance and the relative contribution rate of each index have a value range of [0, 1%]The above formula can make the multiplication operationF j Has better numerical discrimination.
When it comes tojRelative importance and relative contribution rate of each indexR j 、G j When the value is simultaneously taken as a large value,F j the value is also larger; when it comes tojRelative importance and relative contribution rate of each indexR j 、G j One being larger and the other being smaller,F j the value is moderate; when it comes tojRelative importance and relative contribution rate of each indexR j 、G j At the same time, when the value is smaller,F j the value is small. Therefore, according to each indexF j The order of deletion of the indexes is determined by the value size, i.e.F j Smaller metrics should be considered for deletion first. When a certain index is reachedF j Value ratio overall indexF j When the average value of (a) is smaller by more than one order of magnitude, it is considered that the relative importance and the relative contribution rate of the index are significantly lower than the average level of the overall index, and the index can be deleted. In order to quantitatively describe the discrimination process, a comprehensive discrimination index is further definedP j ：P j =lg(F j / F j ’ ) In the formula:F j ’ is a whole indexF j Average value of (a).
Comprehensive judgment indexP j Reflects the comprehensive indexF j Is taken fromF j ’ A difference in magnitude. If it isP j ＞0Indicating the indexF j Is greater than the average level; if it isP j ＜0Indicating the indexF j Is less than the average level; in particular whenP j ＜﹣1Indicating the indexF j Is taken fromF j ’ Which differ by more than an order of magnitude, significantly below the average level, can be deleted. Therefore, this application will be describedP j ≤﹣1And as a threshold value of the index screening, the index screening is changed from a subjective analysis and judgment process to a quantitative calculation process.
Applicants have found that the weights used in the calculation of the existing VIKOR model are relatively fixed and subjective as designed by experts. The difference of the weight values directly influences the subsequent output results, so that the distribution of the initial water right is not objective and accurate, and the following solution is provided for the purpose.
As shown in fig. 5, in another embodiment of the present application, the step S3 further includes:
s31, constructing a decision matrix of the alternative scheme and standardizing to obtain a standardized decision matrix;
s32, determining the distribution of a feasible weight space by adopting an SMAA method, sampling based on a probability density function of the feasible weight space, and randomly generating feasible weights;
s33, constructing a VIKOR model and calculating to obtain the ranking of each alternative scheme;
s34, storing the ranking of the alternative schemes obtained in the calculation process, and calculating a sorting acceptability index, a global acceptability index and a central weight vector; and obtaining the initial water weight distribution proportion of each provincial administrative district.
In this example, the weights are randomly generated by SMAA, and then the VIKOR model is repeatedly called to calculate, giving the ranking of alternatives. The problem that in the prior art, the given weight value needs to be marked by an expert, so that the subjectivity of the weight and the result is high is solved.
In a further embodiment, step S32 is described in detail.
For theMAn initial water right distribution schemeA=｛A m I1m=1,2,…，MAndNan attributeC=｛C n - < 1,2 > \ 8230;,N｝，A m it is shown that the m-th scheme,C n denotes the firstnAn attribute; the weight of an attribute may be expressed asw n 。W=｛w n = n =1,2, \ 8230;,N｝。0≤w n less than or equal to 1, evaluation index matrixX=[x mn ] M×N . The problem of initial water weight distribution belongs to a random multi-attribute decision problem, and uncertainty of the problem is derived from two aspects of index evaluation values and index weights. In general, the uncertainty of the index evaluation value comes from the uncertainty of the random optimization result. The index weight reflects information of two aspects of importance degree of the index and subjective preference of a decision maker, and the information is also an uncertainty source of the index weight. The uncertainty of the index evaluation value and the index weight can be described by using corresponding probability density functions. Therefore, the index evaluation value of the above expression can be used as a obedient probability density functionf X （ζ) Random variable of (2)ζ mn To describe.ζ mn An index evaluation value of an nth attribute of an mth schema.
In the existing decision making process, experts may not completely master each index information, reasonable weight information cannot be given when weights are given, and the index weight values are considered to obey any type of distribution in a designated interval.
Probability density function of known index evaluationf X （ζ) And index weight probability density functionf W （w) Further, SMAA-2 obtains the comprehensive utility of each scheme by weighted summation of utility values of each attribute through the following linear utility functionu m =u（x m ，w) Then pass its weighted valueu m Calculate the best of each solutionSorting the inferior, selecting the equilibrium scheme meeting the decision requirement,
。
in the formula, a random variable may be usedζ mn Instead of constantsx mn Uncertainty of the reaction index value, can be found in the above formulax mn Is transformed intoζ mn . The scheme ranking function is rank (ζ m ，w）
In the formula, scheme ranking function rank (b) ((b))ζ m ，w) The value range is [1 ],M]，ρ[true]andρ[false]respectively 1 and 0.
Further, defining ranking propensity weightsW m r （ζ) For any w ∈W m r （ζ) SMAA-2 protocolA m A sequence of r (r =1,2, \ 8230; is obtained,M) Is defined as a ranking tendency weightW m r （ζ) Specifically, the formula is shown as follows:W m r （ζ）=｛w∈W m r （ζ）：rank（ζ m ，w）=r｝。
rank acceptability indicatorb m r Which is the expected value of the rank-biased weight and is a double integral over the attribute value space and the weight vector space, representing an alternativex m Rank the firstrAcceptability of a name may also be considered an alternativex m Rank of firstrProbability of a name:b m r =∫ X f（ζ）∫ Wmr（ζ） f W （w）dwdζ。
global acceptability degreeb m h It is an alternative toA m Obtain all ranksb m r Describes overall acceptable levels of the solution as a whole:
in the formula, indexa m h Is in the range of [0,1 ]]，a r Representing alternatives for two-level weightingA m A certain ordering ofrFor the indexa m h Contribution degree of (1), common second-order weight with linear weighta r = m-r)/(m-1), reciprocal weighta r =1/r and center of gravity weight, wherein weightrThe smaller the corresponding secondary weight, the greater the importance of the acceptability when ranked further up.
In a further embodiment, the overall implementation flow of the SMAA-VIKOR initial water right assignment is as follows:
(1) And constructing an initial evaluation matrix. And calculating index values of water resource development and utilization, economic society, ecological environment and the like of different provinces of the drainage basin according to the drainage basin to which the initial water right is to be distributed. Suppose that the problem requiring decision is made ofMIndividual provinceA=｛A m I i Im=1,2,…，MAndNan indexC=｛C n I =1,2, \8230, a,Nconstructed of whereinA m Denotes the firstmThe number of the provinces is one,C n indicates the nth index. Then the initial evaluation matrix of the different provinces isX=[x mn ] M×N （x mn Is the nth index value of the mth province, m is the number of provinces, and n is the number of indexes).
(2) The initial evaluation matrix is normalized. Due to fairness principle in decision processIndexes of the efficient principle and the sustainable principle relate to different types of indexes of water resource development and utilization, economy and society and the like, the different dimensions and magnitude levels of the indexes can cause no comparability of different index data, and a vector standardization formula is used for determining a matrixX=[x mn ] M×N Standardizing to obtain decision matrix after standardization of different provincesR=[r mn ] M×N （r mn The nth normalized index value for the mth province),
(3) Determining a positive ideal point R of the basin to be divided into initial water weights + =[r 1 + ,r 2 + ,……，r N + ]And negative ideal point R - =[r 1 - ,r 2 - ,……，r N - ]。
(4) Computing alternativesmGroup benefit ofS m And individual regretR m ；
(5) Computing alternativesmOverall benefit of (1)Q m ，
(6) Ordering alternatives
For alternative schemesiGroup benefit ofS i And regret degree of the subjectR i And combined benefitsQ i Sorting is carried out, and the smaller the numerical value is, the better the numerical value is;
the first condition is as follows: acceptability advantage Q (A ') -Q (A') > DQ, wherein the protocolA"Is Q i Rank the second in ascending order, andDQ = 1/(m-1)，mis the number of scenarios;
and (2) carrying out a second condition: acceptable stability of decision
Scheme(s)A'Must satisfy the group-based benefitSOr regret of the individualRSorting is also the first scheme of sorting;
if one of the two conditions is not met, obtaining a compromise solution;
if the condition two is not satisfied, the schemeA'And schemesA"Are all compromise solutions;
if condition one is not satisfied, the ordering of the schemes isA', A", A M ,In which the schemeA M The determination of Q (A ') -Q (A') < DQ is maximizedMThe value is obtained.
According to another aspect of the present application, there is provided an initial water right distribution system across provincial river watersheds, including:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein the content of the first and second substances,
the memory stores instructions executable by the processor, and the instructions are used for being executed by the processor to implement the method for distributing the initial water right across the river basin of the province in any embodiment. In the present embodiment, the processor, the memory, and the like are prior art, and those skilled in the art can implement the technical solution of the present application according to the prior knowledge and the content disclosed in the present application, solve the technical problems presented in the present application, and obtain corresponding technical effects.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the details of the embodiments, and various equivalent modifications can be made within the technical spirit of the present invention, and the scope of the present invention is also within the scope of the present invention.
Claims (7)
1. The method for distributing the initial water right of the river basin across the province is characterized by comprising the following steps of:
s1, reading water resource survey data of a river basin crossing provinces, obtaining and analyzing a representative hydrological series capable of reflecting withering changes and current underlying surface conditions;
s2, collecting basic data of river basin crossing provinces, wherein the basic data comprises water resource development and utilization data, economic and social data and ecological environment data; obtaining an evaluation index of an evaluation index system for constructing initial water resource distribution across provinces, rivers and watersheds, and reducing the evaluation index;
in step S2, the process of reducing the evaluation index specifically includes:
s21, constructing an XGBOOST model, collecting a plurality of evaluation indexes as the input of the XGBOOST model, taking the comprehensive evaluation index value as the output of the XGBOOST model, and training the model;
s22, extracting the relative importance degree information of each evaluation index from the connection weight of the trained XGBOOST model, and screening the evaluation indexes;
s23, carrying out sensitivity analysis on each evaluation index by adopting a trained XGBOST model, and quantitatively calculating the relative contribution rate of the change of each evaluation index to the change of a decision result;
s24, constructing a comprehensive judgment criterion for screening the evaluation indexes based on the relative importance degree information and the relative contribution rate of the evaluation indexes, and screening the evaluation indexes based on the comprehensive judgment criterion;
the process of constructing the comprehensive judgment criterion for screening the evaluation indexes comprises the steps of calculating the product of relative importance degree information and relative contribution rate one by one aiming at each evaluation index to obtain a first comprehensive evaluation index; then calculating the average value of the first comprehensive evaluation index, using each evaluation index and the average value as a quotient, then calculating the decimal logarithm value of the quotient, and judging whether the decimal logarithm value of the evaluation index accords with a threshold value one by one;
s3, constructing an SMAA-VIKOR initial water weight distribution model, and solving to obtain an initial water weight distribution proportion of each provincial administrative region;
the step S3 further comprises:
s31, constructing a decision matrix of the alternative scheme and standardizing to obtain a standardized decision matrix;
s32, determining the distribution of a feasible weight space by adopting an SMAA method, sampling based on a probability density function of the feasible weight space, and randomly generating feasible weights;
s33, constructing a VIKOR model and calculating to obtain the ranking of each alternative scheme;
s34, storing the ranking of the alternative schemes obtained in the calculation process, and calculating a sorting acceptability index, a global acceptability index and a central weight vector; and obtaining the initial water weight distribution proportion of each provincial administrative district.
2. The method for assigning the initial water right across the river basin of the province of claim 1, wherein the step S1 of obtaining and analyzing the representative hydrological series capable of reflecting the withering change and the current underlying surface condition further comprises the following steps:
s11, acquiring a natural runoff time sequence in the hydrological series, and fitting by adopting a linear equation to judge the trend condition of the natural runoff series;
and S12, judging whether the natural runoff time sequence has the jumping phenomenon, and determining the exact time of the natural runoff with the jumping phenomenon by testing the exact time of the change of the mean value of the elements of the time sequence through a statistical method.
3. The method of claim 2, wherein the initial water right is distributed across the river basin of the province,
in step S11, the process of fitting by using the linear equation specifically includes:
x t '≈a 0 +a 1 t；a 1 shows the trend tendency of the natural runoff x, a 0 Is a regression constant, x t ' is an estimated value of the natural runoff, and the closeness degree of the linear correlation between the natural runoff x and the time t is represented by a correlation coefficient r;
in the formula, x b Natural runoff of year b, x m Is the mean of the time series of the runoff m The series length of the natural runoff is not less than (n + 1)/2,n, and the r value is positive, which represents the natural runoff in the time series of the natural runoffThe volume has a tendency to increase linearly over the calculated n years.
4. The method for distributing initial water right across provincial river basin according to claim 3, wherein in the step S12, the step of judging whether the natural runoff time sequence has a jump phenomenon further comprises the following steps:
step S12a, array x (x) composed of time series for k natural runoff quantities 1 ，x 2 ，…x i ，…x j ，…x k ) Construction of rank sequence S k ，S k =r 1 +r 2 +…，+r i ，…+r k (ii) a When x is i ＞x j When r is i (= 1) when x i =x j When r is i (= 0) when x i ＜x j When r is i =﹣1，
Step S12b, judging max I S at the time t k Whether I is equal to a preset value or not, if yes, the moment t is a mutation point moment;
step S12c, calculating probability P of the mutation point time, wherein P =2exp [ -6 k t 2 /（n 3 +n 2 ）](ii) a When P is less than or equal to 0.5, the detected mutation point is statistically significant.
5. The method for distributing the initial water right of the river basin across the provinces as claimed in claim 1, wherein the evaluation index system comprises a target layer, a criterion layer and an index layer, wherein the target layer is the total amount of water resources of the river basin, and the criterion layer comprises a fairness principle, an efficient principle and a sustainability principle; the indexes related to the fairness principle comprise current water consumption, population quantity, total GDP amount, drainage basin area and irrigation area; indexes related to the high-efficiency principle comprise GDP per capita, GDP water consumption of ten thousand yuan, increased industrial value water consumption of ten thousand yuan, effective utilization coefficient of farmland irrigation water and industrial water reuse rate; the indexes related to the sustainable principle comprise forest coverage rate, population growth rate, GDP growth rate, urbanization rate, inferior V-type water discharge proportion, industrial wastewater discharge standard-reaching rate and water quality standard-reaching rate of a water functional area.
6. The method for distributing the initial water right across the river basin of the province of claim 5, wherein the process of training the XGB OST model is as follows:
step S21a, generating a scheduling scheme set meeting constraint conditions, and calculating a positive ideal point when all index values reach the optimum and a negative ideal point when all index values reach the worst to obtain upper and lower limit states of the scheme;
s21b, generating input items of the XGB OST model training samples by adopting a random simulation method, randomly generating a preset number of random numbers which are uniformly distributed, and performing discretization calculation on index values between positive ideal points and negative ideal points to generate a preset number of training sample input items;
and S21c, calculating Euclidean distances and pasting degrees of the samples from the positive ideal points and the negative ideal points, and normalizing the pasting degrees.
7. The utility model provides a stride initial water right distribution system in province's river basin which characterized in that includes:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein the content of the first and second substances,
the memory stores instructions executable by the processor for implementing the method of initial water right assignment across a river basin of the province according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497042.1A CN115600822B (en) | 2022-11-28 | 2022-11-28 | Method and system for distributing initial water right of river basin across provinces |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497042.1A CN115600822B (en) | 2022-11-28 | 2022-11-28 | Method and system for distributing initial water right of river basin across provinces |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600822A CN115600822A (en) | 2023-01-13 |
| CN115600822B true CN115600822B (en) | 2023-02-28 |
Family
ID=84853719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211497042.1A Active CN115600822B (en) | 2022-11-28 | 2022-11-28 | Method and system for distributing initial water right of river basin across provinces |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600822B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305006A (en) * | 2018-02-02 | 2018-07-20 | 浙江省水利河口研究院 | Reservoir usufruct of water resource amount primary distribution method based on the constraint of water supply fraction |
| CN109886473A (en) * | 2019-01-24 | 2019-06-14 | 河海大学 | A kind of basin scene water system Multiobjective Optimal Operation method considering downstream ecology |
| CN111401782A (en) * | 2020-04-03 | 2020-07-10 | 水利部交通运输部国家能源局南京水利科学研究院 | Method for scheduling, managing and evaluating index system of river water quantity across provinces and rivers |
| CN114819178A (en) * | 2022-02-23 | 2022-07-29 | 中国国家铁路集团有限公司 | Railway construction progress index prediction and online updating method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AR109623A1 (en) * | 2018-02-16 | 2019-01-09 | Pescarmona Enrique Menotti | PROCESS AND SYSTEM OF ANALYSIS AND HYDROLOGICAL MANAGEMENT FOR BASINS |
-
2022
- 2022-11-28 CN CN202211497042.1A patent/CN115600822B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305006A (en) * | 2018-02-02 | 2018-07-20 | 浙江省水利河口研究院 | Reservoir usufruct of water resource amount primary distribution method based on the constraint of water supply fraction |
| CN109886473A (en) * | 2019-01-24 | 2019-06-14 | 河海大学 | A kind of basin scene water system Multiobjective Optimal Operation method considering downstream ecology |
| CN111401782A (en) * | 2020-04-03 | 2020-07-10 | 水利部交通运输部国家能源局南京水利科学研究院 | Method for scheduling, managing and evaluating index system of river water quantity across provinces and rivers |
| CN114819178A (en) * | 2022-02-23 | 2022-07-29 | 中国国家铁路集团有限公司 | Railway construction progress index prediction and online updating method |
Non-Patent Citations (1)
| Title |
|---|
| 大凌河流域初始水权分配实践评价;吴丹等;《水利水电科技进展》(第05期);39-44 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600822A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113379109B (en) | Runoff forecasting method based on prediction model self-adaption | |
| Coulibaly et al. | Downscaling precipitation and temperature with temporal neural networks | |
| Merz et al. | Flood frequency regionalisation—spatial proximity vs. catchment attributes | |
| CN116070971A (en) | Orderly flow regulation and control method and system for river and lake water system | |
| Pizzoli et al. | How to best classify rural and urban | |
| CN109472403B (en) | Medium-and-long-term runoff forecasting method integrating empirical mode decomposition and remote correlation | |
| CN110276700A (en) | Water resource optimal allocation method, apparatus, equipment and storage medium | |
| CN108647425B (en) | K-means high flow or low flow time forecasting procedure based on particle group optimizing | |
| Tigkas et al. | Comparative study of evolutionary algorithms for the automatic calibration of the Medbasin-D conceptual hydrological model | |
| CN109377014A (en) | Basin water resources Optimal Configuration Method | |
| CN112633645B (en) | Social and economic benefit accounting method for water resource mining and efficient utilization effects of river source arid region | |
| Kolekar et al. | Prediction of municipal solid waste generation for developing countries in temporal scale: A fuzzy inference system approach | |
| CN108830417A (en) | A kind of residential energy consumption prediction technique and system based on ARMA and regression analysis | |
| Dehghani et al. | Application of novel hybrid artificial intelligence algorithms to groundwater simulation | |
| Xiao et al. | A novel sub-models selection algorithm based on max-relevance and min-redundancy neighborhood mutual information | |
| Oyebode | Evolutionary modelling of municipal water demand with multiple feature selection techniques | |
| CN110782131A (en) | Performance evaluation method for water cooperation organization of farmers | |
| CN113592278A (en) | SBM water environment bearing capacity evaluation method considering unexpected output | |
| CN106682414A (en) | Method and device for establishing timing sequence prediction model | |
| Muronda et al. | Uncertainty analysis of reservoir operation based on stochastic optimization approach using the generalized likelihood uncertainty estimation method | |
| CN115600822B (en) | Method and system for distributing initial water right of river basin across provinces | |
| CN110188922A (en) | A kind of long-term Runoff Forecast method in the RBF neural based on runoff mechanism | |
| Coppola Jr et al. | Fuzzy rule-based methodology for estimating monthly groundwater recharge in a temperate watershed | |
| Szabó et al. | Parametric Postprocessing of Dual-Resolution Precipitation Forecasts | |
| Zahraie et al. | SST clustering for winter precipitation prediction in southeast of Iran: Comparison between modified K-means and genetic algorithm-based clustering methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |