CN110990761B - Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium - Google Patents
Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110990761B CN110990761B CN201911336959.1A CN201911336959A CN110990761B CN 110990761 B CN110990761 B CN 110990761B CN 201911336959 A CN201911336959 A CN 201911336959A CN 110990761 B CN110990761 B CN 110990761B
- Authority
- CN
- China
- Prior art keywords
- sequence
- sequence set
- parameter
- error value
- numbered
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to a hydrological model parameter calibration method, a hydrological model parameter calibration device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring serial numbers which are randomly and initially generated according to the hyper-parameter sequences of the hydrological model, constructing a sequence set, acquiring the hyper-parameter value of each serial number sequence in the sequence set and the real input parameter of the hydrological model, acquiring the predicted flow output by the hydrological model, acquiring an error value corresponding to each serial number sequence according to the error value between the predicted flow and the real output flow, reconstructing the sequence set according to the error value corresponding to each serial number sequence, and reconstructing the reconstructed sequence set as the sequence set until the latest minimum error value meets the preset condition; and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model. In the whole process, the parameters of the hydrologic model are automatically calibrated, and the calibrating process is based on a strict data processing process, so that the precision and high efficiency of parameter calibrating are ensured.
Description
Technical Field
The application relates to the technical field of hydrology and water conservancy, in particular to a hydrology model parameter calibration method, a hydrology model parameter calibration device, computer equipment and a storage medium.
Background
Hydrology refers to various phenomena such as water changes and movements in nature. The present general reference is to an edge discipline for researching the space-time distribution and change rule of water in nature. Hydrology belongs to the earth science, and research is about the science of the occurrence, circulation, content, distribution, physicochemical properties, influence of water on the earth's surface, in the soil, under rock and in the atmosphere, and the relationship with all living things.
In order to efficiently and accurately conduct hydrologic research, numerous hydrologic models, such as a Xinanjiang model, a Zhang Cunyi model, a topmodel model and the like, are proposed in the prior art, and although efficiency and accuracy of hydrologic research can be improved based on the hydrologic models, parameter calibration of the hydrologic models is a difficult problem.
The traditional hydrologic parameter calibration is generally carried out by adopting a manual error testing mode, and the manual error testing method is a parameter calibration method for manually adjusting parameters by comparing the fitting degree of an analog value and an actual measurement value.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an automatic and accurate hydrological model parameter calibration method, apparatus, computer device, and storage medium.
A method of hydrologic model parameter calibration, the method comprising:
acquiring a serial number sequence which is randomly and initially generated according to a hyperparametric sequence of a hydrological model, and constructing a sequence set;
acquiring a hyper-parameter value, a real input parameter and a real output flow of a hydrological model of each numbered sequence in the sequence set, inputting the hyper-parameter value and the real input parameter into the hydrological model, and acquiring a predicted flow output by the hydrological model;
obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording a minimum error value and a corresponding minimum error serial number;
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and re-using the reconstructed sequence set as the sequence set, and returning to the step of acquiring the super-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
And restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model.
In one embodiment, the obtaining the number sequence generated randomly and initially according to the hyperparametric sequence of the hydrological model, and constructing the sequence set includes:
acquiring the hyper-parameter quantity, the hyper-parameter range and the parameter calibration precision of the hydrologic model;
generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision;
randomly generating 2 according to the super-parameter sequence n A number sequence, a constituent sequenceAnd (3) collecting, wherein n is the parameter calibration precision.
In one embodiment, reconstructing the sequence set according to the error value corresponding to each numbered sequence includes:
screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set;
randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial positions respectively for the two number sequences of a single pair of combinations, and mutually exchanging the number values subsequent to the starting points in the two number sequences to obtain an exchange sequence set;
reconstructing a sequence set according to the exchange sequence set.
In one embodiment, reconstructing the sequence set from the exchange sequence set includes:
performing de-duplication treatment on the exchange sequence set to obtain a de-duplicated exchange sequence set;
and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the deduplication exchange sequence set to obtain a reconstructed sequence set, wherein the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
In one embodiment, the filtering the number sequences according to the error values corresponding to each number sequence, and obtaining the filtered sequence set includes:
acquiring the weight of the error value corresponding to each numbered sequence;
and according to the weight, randomly selecting a numbered sequence by adopting a roulette algorithm to obtain a screening sequence set.
In one embodiment, reconstructing a sequence set according to the error value corresponding to each numbered sequence, and reconstructing the reconstructed sequence set as the sequence set, and returning to the step of obtaining the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition includes:
Reconstructing a sequence set according to the error value corresponding to each numbered sequence, and reconstructing the reconstructed sequence set as the sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
In one embodiment, the obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and before recording the minimum error value and the corresponding minimum error serial number, further includes:
acquiring a preset error function;
and calculating an error value between the predicted flow and the real output flow through the preset error function.
A hydrological model parameter calibration apparatus, the apparatus comprising:
the sequence set construction module is used for acquiring a serial number sequence which is randomly and initially generated according to the hyper-parameter sequence of the hydrological model and constructing a sequence set;
the calculation module is used for acquiring the hyper-parameter value of each numbered sequence in the sequence set, the real input parameter and the real output flow of the hydrological model, inputting the hyper-parameter value and the real input parameter into the hydrological model, and acquiring the predicted flow output by the hydrological model;
The recording module is used for obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording a minimum error value and a corresponding minimum error serial number;
the cyclic updating module is used for reconstructing a sequence set according to the error value corresponding to each numbered sequence, reconstructing the reconstructed sequence set as the sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
and the calibration module is used for reducing the latest minimum error number sequence into a calibration parameter value to obtain the calibration parameter of the hydrologic model.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method as described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method as described above.
The hydrological model parameter calibration method, the hydrological model parameter calibration device, the computer equipment and the storage medium acquire serial numbers generated randomly and initially according to the hydrological model hyper-parameter sequences, construct a sequence set, acquire the hyper-parameter value of each serial number sequence in the sequence set, the real input parameters and the real output flow of the hydrological model, input the hyper-parameter value and the real input parameters into the hydrological model, acquire the predicted flow output by the hydrological model, acquire the error value corresponding to each serial number sequence according to the error value between the predicted flow and the real output flow, reconstruct the sequence set according to the error value corresponding to each serial number sequence, reconstruct the reconstructed sequence set as the sequence set, and return to the step of acquiring the hyper-parameter value of each serial number sequence in the sequence set until the latest minimum error value meets the preset condition; and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model. In the whole process, the parameters of the hydrologic model are automatically calibrated, and the calibrating process is based on a strict data processing process, so that the precision and high efficiency of parameter calibrating are ensured.
Drawings
FIG. 1 is an application environment diagram of a hydrologic model parameter calibration method in one embodiment;
FIG. 2 is a flow chart of a method for calibrating parameters of a hydrological model according to an embodiment;
FIG. 3 is a flow chart of a method for calibrating parameters of a hydrological model according to another embodiment;
FIG. 4 is a block diagram of a device for calibrating parameters of a hydrological model according to one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The hydrological model parameter calibration method provided by the application can be applied to an application environment shown in figure 1. The user operates the terminal 102 and sends out a hydrological model parameter calibration operation instruction, the terminal 102 executes the hydrological model parameter calibration method of the application, which specifically obtains serial numbers which are randomly and initially generated according to the hydrological model hyper-parameter sequences, constructs a serial number set, obtains the hyper-parameter value of each serial number sequence in the serial number set, the real input parameters and the real output flow of the hydrological model, inputs the hyper-parameter value and the real input parameters into the hydrological model, obtains the predicted flow output by the hydrological model, obtains the error value corresponding to each serial number sequence according to the error value between the predicted flow and the real output flow, reconstructs the serial number set according to the error value corresponding to each serial number sequence, and returns the reconstructed serial number set to the step of obtaining the hyper-parameter value of each serial number sequence in the serial number set until the latest minimum error value meets the preset condition; and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model. Optionally, the terminal 102 may also store the parameter-scaled hydrologic model for further hydrologic data processing. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, among others.
In one embodiment, as shown in fig. 2, a hydrological model parameter calibration method is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps:
s100: and acquiring a serial number sequence which is randomly and initially generated according to the hyper-parameter sequence of the hydrologic model, and constructing a sequence set.
For each hydrological model, the corresponding super-parameter number and super-parameter range are fixed, generally, when the parameter rate timing of which hydrological model is needed at the time is clear, the super-parameter number and the super-parameter range can be directly determined, a super-parameter sequence can be generated in advance based on the super-parameter number and the super-parameter range, and then the super-parameter sequence is randomly initialized to obtain a number sequence, and all the number sequences are collected to obtain a sequence set.
S200: the method comprises the steps of obtaining hyper-parameter values of each numbered sequence in a sequence set, real input parameters and real output flow of a hydrological model, inputting the hyper-parameter values and the real input parameters into the hydrological model, and obtaining predicted flow output by the hydrological model.
Obtaining the hyper-parameter value of each serial number sequence and the real input parameter and the real output flow of the hydrological model, substituting the real input parameter and the hyper-parameter value into the hydrological model, and obtaining the predicted flow output by the hydrological model, namely carrying out primary flow prediction processing by the hydrological model with the hyper-parameter value introduced, and obtaining the predicted flow of the hydrological model aiming at the input real input parameter. Specifically, the hyper-parameter value of each numbered sequence can be calculated according to the calculation range of each hyper-parameter and the parameter calibration precision. For example, the parameter calibration precision n=2, there are 3 super parameters, the value ranges of the super parameters are respectively 1-2, 2-3 and 3-4, the number sequences of the super parameters are respectively 10, 11 and 00, and the corresponding super parameter values are 1.67, 3 and 3. Further, based on the case that 22=4 hyper-parameter values corresponding to the hyper-parameters with the parameter calibration precision of 2 are available, the corresponding number sequences thereof may be 00, 01, 10 and 11, respectively, and taking the first hyper-parameter as an example, it may take 4 values in the range of 1-2, and 1-2 is divided into 4 values in total by adopting the mode of equally-spaced averaging, and the corresponding number sequence is 10, and therefore, the hyper-parameter value of the number sequence 10 is 1.67. Substituting the super parameter value and the real input parameter into the hydrologic model, and carrying out flow prediction according to the hydrologic model substituted by the super parameter value to obtain the predicted flow output by the hydrologic model. Assuming that a hydrologic model is y=a (x1+x2) +b+c, X1 and X2 are true input parameters of the hydrologic model, a, b and c are three excess values determined above, y is a flow prediction value of the hydrologic model, a, b and c have 4 values in the range of values, and assuming that x1=1 and x2=2 and the true flow value is 7, 4 values corresponding to a, b and c need to be randomly selected so that the final y is as close to 7 as possible. It should be noted that the above is only used to simplify the schematic step S200, and the equation actually corresponding to the hydrological model is far more complex than the above.
S300: and obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording the minimum error value and the corresponding minimum error serial number.
Calculating error values between the predicted flow and the real flow, determining the error value corresponding to each serial number, namely determining the error value corresponding to each super parameter, and recording the minimum error value and the corresponding minimum error serial number. Specifically, a preset error function may be obtained first, and the predicted flow and the actual flow may be introduced into the error function to obtain an error value.
S400: reconstructing a sequence set according to the error value corresponding to each numbered sequence, and resetting the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition.
The preset condition is a preset cycle stop condition, and specifically may be that the number of returns reaches a certain number (preset number), or the minimum error values obtained by continuous certain number of cycles are equal. Step S400 is specifically a cyclic step, in which the numbered sequences corresponding to the larger error value are removed according to the error value corresponding to each numbered sequence, the sequence set is reconstructed, the reconstructed sequence set is used as the sequence set again, and the step of obtaining the super-parameter value of each numbered sequence in the sequence set is returned until the latest minimum error value meets the preset condition. Assuming that each numbered sequence in the currently obtained sequence set is 01, 10, 11 and 00 respectively, removing 01 with larger error value according to the corresponding error value, reconstructing the sequence set into 10, 11 and 00, and returning to the step of obtaining the super parameter value of each numbered sequence in the sequence set to obtain a new minimum error value until the latest minimum error value is equal to the last corresponding minimum error, or the number of times of returning is larger than the preset number of times, such as 10 times, or the number of times of returning is equal to the last corresponding minimum error value (namely, the minimum error value is not updated), and stopping.
S500: and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model.
And restoring the latest minimum error number sequence corresponding to the latest minimum error value into a rating parameter value to obtain a rating parameter of the hydrologic model, and finishing parameter rating of the hydrologic model.
According to the hydrological model parameter calibration method, the serial number sequences which are randomly and initially generated according to the hydrological model hyper-parameter sequences are obtained, a sequence set is constructed, hyper-parameter values of each serial number sequence in the sequence set, real input parameters and real output flow of the hydrological model are obtained, the hyper-parameter values and the real input parameters are input into the hydrological model, predicted flow output by the hydrological model is obtained, an error value corresponding to each serial number sequence is obtained according to the error value between the predicted flow and the real output flow, the sequence set is reconstructed according to the error value corresponding to each serial number sequence, the reconstructed sequence set is reused as the sequence set, and the hyper-parameter values of each serial number sequence in the sequence set are returned until the latest minimum error value meets the preset condition; and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model. In the whole process, the parameters of the hydrologic model are automatically calibrated, and the calibrating process is based on a strict data processing process, so that the precision and high efficiency of parameter calibrating are ensured.
As shown in fig. 3, in one embodiment, step S100 includes:
s120: acquiring the hyper-parameter quantity, the hyper-parameter range and the parameter calibration precision of the hydrologic model;
s140: generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision;
s160: random initial generation of 2 based on hyper-parameter sequences n And numbering sequences to form a sequence set, wherein n is the parameter calibration precision.
The number of the hyper-parameters and the hyper-parameter range corresponding to the hydrologic model are both fixed in advance, the hyper-parameter number and the hyper-parameter range of each hydrologic model can be definitely regulated when the hydrologic model is generated, the parameter calibration precision refers to the calibration precision requirement of the hydrologic model, specifically, the data quantity which is input to a terminal by a user and needs to be processed by different calibration precision is different, generally, the higher the calibration precision is, the higher the data quantity which needs to be processed is, and the higher the precision of the hydrologic data predicted by the hydrologic model after the final parameter calibration is, and vice versa. The precision influences the span of the super parameter value, and 2 can be selected from the spans n The super parameter values are numbered in order from small to large and counted in binary. For example, if the value of one superparameter is 2-3 and the precision is 2, there are 2, 2.33, 2.67 and 3 superparameters, the numbers are 00, 01, 10 and 11 respectively, and the number of digits of the number is n. The precision is typically 4 (to 10%) or 7 (to 1%), and when the precision is 4, it corresponds to 16 parts of data, the precision is at least 10%, and when the precision is 7, it corresponds to 128 parts of data, the precision is at least 1%. For example, with an accuracy of 2, the hydrological model has 3 superparameters, each corresponding to 2 n The number of super parameter values is 4, the super parameter sequence is 01110, the number of the first super parameter is 01, the second number is 11, and the third number is 10, the number of bits of the super parameter sequence can be seen as m x n, wherein m is the number of super parameters.
In one embodiment, reconstructing the sequence set from the error value corresponding to each numbered sequence includes: screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set; randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial positions respectively for the two number sequences of the single pair combination, and mutually exchanging the number values of the starting points in the two number sequences to obtain an exchange sequence set; reconstructing the sequence set according to the exchange sequence set.
According to the error value screening number sequences corresponding to each number sequence, the number sequence with smaller error value can be preferentially selected to reconstruct a screening sequence set, so that the hydrologic model with the calibrated post parameters can accurately predict hydrologic data. For example, the screening sequence sets {010101, 101111, 111000} with smaller error values are randomly screened, the number sequences are combined two by two, non-initial start points are randomly selected for the combination of 010101 and 101111, for example, the 4 th bit is selected as the start point to exchange the 4 th bit subsequent number value 101 in 010101 with the 4 th bit subsequent number value 111 in 101111, thus obtaining 010111 and 101101, and for other two combinations, similar processing procedures are adopted, which are not repeated herein, so as to obtain an exchange sequence set, and the exchange sequence set is taken as the basis, thus reconstructing the sequence set.
In one embodiment, reconstructing the set of sequences from the set of exchange sequences comprises: performing de-duplication treatment on the exchange sequence set to obtain a de-duplicated exchange sequence set; and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the duplicate-removed exchange sequence set to obtain a reconstructed sequence set, wherein the number of the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
After the exchange processing in the previous step, there may be repeated number sequences in the exchange sequence set, so that the exchange sequence set needs to be subjected to de-duplication processing, the repeated number sequences are removed, the number sequences contained in the de-duplication exchange sequence set are reduced, and supplementation is needed, so that the number of subsets (number sequences) contained in the sequence set in each cycle is constant, the supplementation number sequences are randomly generated, and the generated supplementation number sequences are supplemented to the re-exchange sequence set to obtain a reconstructed sequence set. Specifically, the random generation refers to that the complementary number sequence is randomly generated based on the same mode of the initially generated number sequence, namely, the complementary number sequence is also related to the hyper-parameters, the hyper-parameter values and the calibration accuracy of the hydrologic model, and the specific corresponding relation refers to the corresponding relation between the number sequence and the hyper-parameters, the hyper-parameter values and the calibration accuracy of the hydrologic model.
In one embodiment, filtering the number sequences according to the error value corresponding to each number sequence, and obtaining the filtered sequence set includes:
acquiring the weight of the error value corresponding to each numbered sequence; and randomly selecting a numbered sequence by adopting a roulette algorithm according to the weight to obtain a screening sequence set.
The weight of the error value may be the difference between the maximum error value and the error value corresponding to the current numbered sequence, and the closer the error value and the maximum error are, the smaller the weight corresponding thereto, and vice versa. It can be appreciated that after the above processing, based on the weights, the numbered sequences with smaller error values can be filtered out to form a filtered sequence set. For example, if the error is 0.1,0.2,0.3, the weight=maximum error-error, the error value weights corresponding to the three numbered sequences are 0.2,0.1,0, the total weight is 0.3, a random number of 0-0.3 is taken, the sequence 1 is taken in 0-0.2, the sequence 2 is taken in 0.2-0.3, the worst sequence with the weight of 0 is not taken, and finally the numbered sequence with smaller error value is obtained, thus forming a screening sequence set.
In one embodiment, reconstructing the sequence set according to the error value corresponding to each numbered sequence, and reconstructing the reconstructed sequence set as the sequence set, and returning to the step of obtaining the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition comprises:
Reconstructing a sequence set according to the error value corresponding to each numbered sequence, and resetting the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
And if the minimum error values obtained in the preset times are not updated, i.e. the minimum error values obtained in the preset times are the same, for example, the minimum error values obtained in 10 return cycles are all 0.1, stopping the cycle, recording the latest minimum error sequence, and restoring the minimum error sequence to the calibration parameter value to calibrate the parameters of the hydrologic model.
In one embodiment, according to the error value between the predicted flow and the real output flow, an error value corresponding to each serial number is obtained, and before the minimum error value and the corresponding minimum error serial number are recorded, the method further includes:
acquiring a preset error function; and calculating an error value between the predicted flow and the real output flow through a preset error function.
The preset error function is a function preset for error calculation, the error specifically comprises an absolute error, a relative error and a coefficient of a determination system, namely three error function formulas respectively correspond to the three error function formulas, the three error function formulas are general hydrologic general formulas, and specific setting/selection can be according to the needs of actual scenes or user preference.
In order to explain the technical scheme and the effect of the hydrological model parameter calibration method in more detail, the steps included in the whole scheme will be described by adopting specific examples. In one application example, the hydrological model parameter calibration method of the application comprises the following steps:
1. the range of the super parameters is set, generally, the number and the range of the super parameters of each model are fixed, and the number of the super parameters is recorded as m.
2. An error function is set, wherein the error function is used for comparing the difference between a predicted value and a true value, and generally has three error function formulas of absolute error, relative error and coefficient determination, the formulas are general hydrologic general formulas, and the setting is carried out according to the preference of a user.
3. Setting the rated precision n, wherein the precision influences the span of the super parameter value, and 2 is selected from the spans n The super parameter values are numbered in order from small to large and counted in binary. For example, if the value of one superparameter is 2-3 and the precision is 2, there are 2, 2.33, 2.67 and 3 superparameters, the numbers are 00, 01, 10 and 11 respectively, and the number of digits of the number is n. The typical precision is 4 (to 10%) or 7 (to 1%).
4. Input data of the hydrologic model such as rainfall and evaporation are set, and real output data such as flow are set. Specifically, the input data is also real data, that is, the input data is understood to be the real data of the hydrologic model input in the actual application and the real hydrologic data of the hydrologic model test object obtained by other methods, taking the output hydrologic data as the flow as an example, where the input data is the real data of the hydrologic model, such as the real rainfall, evaporation and the like, corresponding to a certain river area.
5. The super-parametric sequence is formed in a fixed super-parametric order. For example, the precision is 2, and there are three superparameters in total, then the total superparameter sequence is 01110, representing the first superparameter number 01, the second number 11, and the third number 10. The number of bits of the total sequence can be seen as m x n.
6. Random initialization generation 2 n The sequences are numbered and the total number of sequences is noted as N.
7. And calculating the hyper-parameter value of each serial number sequence, substituting the hyper-parameter value into the hydrologic model, calculating the predicted flow of the hydrologic model, and substituting the real flow and the predicted flow into an error function to obtain an error value. Finally, each serial number corresponds to an error value, and the serial number of the lowest error value and the corresponding error value are separately recorded.
8. The number sequences are randomly selected by adopting a roulette algorithm according to the probability of the error value. The procedure is a simple one, for example three sequences, error 0.1,0.2,0.3, weight = max error-error 0.2,0.1,0, sum 0.3, take a random number of 0-0.3, take sequence 1 in 0-0.2, take sequence 2 in 0.2-0.3, the worst sequence with weight 0 is not taken, the procedure is repeated N times, a new set of repeated sequences is generated.
9. In the new sequence, the starting points are randomly selected in pairs, and the values below the starting points are swapped (the starting point cannot be the first point, otherwise it is equivalent to no swap). For example, two sequences 010101 and 101111, are exchanged from the fourth point, yielding 01011 1 and 101101.
10. The exchanged sequences are de-duplicated and new sequence supplements are randomly generated to maintain a total of N.
11. Jump to step 7, calculate the error value, which is a loop. And comparing the lowest error value recorded separately, and stopping the cycle when the lowest error value is not updated in 10 cycles.
12. And restoring the latest lowest error number sequence when the circulation is stopped to be a rating parameter value, namely, finding out the required automatic rating parameter.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or steps.
As shown in fig. 4, a hydrological model parameter calibration device, the device includes:
the sequence set construction module 100 is used for acquiring a serial number sequence which is randomly and initially generated according to the hyper-parameter sequence of the hydrological model and constructing a sequence set;
the calculation module 200 is configured to obtain a hyper-parameter value of each numbered sequence in the sequence set, and a real input parameter and a real output flow of the hydrologic model, input the hyper-parameter value and the real input parameter to the hydrologic model, and obtain a predicted flow output by the hydrologic model;
The recording module 300 is configured to obtain an error value corresponding to each serial number according to an error value between the predicted flow and the real output flow, and record a minimum error value and a corresponding minimum error serial number;
the cyclic updating module 400 is configured to reconstruct a sequence set according to the error value corresponding to each numbered sequence, and re-use the reconstructed sequence set as a sequence set, and return to the step of obtaining the super-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
and the calibration module 500 is used for reducing the latest minimum error number sequence into calibration parameter values to obtain calibration parameters of the hydrologic model.
The hydrological model parameter calibration device acquires serial numbers which are randomly and initially generated according to the hydrological model hyper-parameter sequences, constructs a sequence set, acquires hyper-parameter values of each serial number sequence in the sequence set, real input parameters and real output flow of the hydrological model, inputs the hyper-parameter values and the real input parameters into the hydrological model, acquires predicted flow output by the hydrological model, acquires error values corresponding to each serial number sequence according to the error values between the predicted flow and the real output flow, reconstructs the sequence set according to the error values corresponding to each serial number sequence, and takes the reconstructed sequence set as the sequence set again, and returns to the step of acquiring the hyper-parameter values of each serial number sequence in the sequence set until the latest minimum error value meets preset conditions; and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model. In the whole process, the parameters of the hydrologic model are automatically calibrated, and the calibrating process is based on a strict data processing process, so that the precision and high efficiency of parameter calibrating are ensured.
In one embodiment, the sequence set construction module 100 is further configured to obtain the number of superparameters, the superparameter range, and the parameter calibration accuracy of the hydrologic model; generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision; random initial generation of 2 based on hyper-parameter sequences n And numbering sequences to form a sequence set, wherein n is the parameter calibration precision.
In one embodiment, the cyclic update module 400 is further configured to screen the number sequences according to the error value corresponding to each number sequence, to obtain a screening sequence set; randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial positions respectively for the two number sequences of the single pair combination, and mutually exchanging the number values of the starting points in the two number sequences to obtain an exchange sequence set; reconstructing the sequence set according to the exchange sequence set.
In one embodiment, the cyclic update module 400 is further configured to perform deduplication processing on the exchange sequence set to obtain a deduplicated exchange sequence set; and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the duplicate-removed exchange sequence set to obtain a reconstructed sequence set, wherein the number of the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
In one embodiment, the cyclic update module 400 is further configured to obtain a weight of the error value corresponding to each number sequence; and randomly selecting a numbered sequence by adopting a roulette algorithm according to the weight to obtain a screening sequence set.
In one embodiment, the cyclic updating module 400 is further configured to reconstruct the sequence set according to the error value corresponding to each numbered sequence, and re-use the reconstructed sequence set as the sequence set, and return to the step of obtaining the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
In one embodiment, the hydrological model parameter calibration device further includes an error value calculation module, configured to obtain a preset error function; and calculating an error value between the predicted flow and the real output flow through a preset error function.
For specific limitations of the hydrological model parameter calibration device, reference may be made to the above limitation of the hydrological model parameter calibration method, and no further description is given here. The various modules in the above-described hydrological model parameter rate apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing data such as hydrologic model input, real hydrologic model output and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a hydrological model parameter calibration method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring a serial number sequence which is randomly and initially generated according to a hyperparametric sequence of a hydrological model, and constructing a sequence set;
acquiring a hyper-parameter value of each numbered sequence in the sequence set, a real input parameter and a real output flow of the hydrological model, and inputting the hyper-parameter value and the real input parameter into the hydrological model to acquire a predicted flow output by the hydrological model;
obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording the minimum error value and the corresponding minimum error serial number;
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and re-using the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring the hyper-parameter quantity, the hyper-parameter range and the parameter calibration precision of the hydrologic model; generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision; random initial generation of 2 based on hyper-parameter sequences n And numbering sequences to form a sequence set, wherein n is the parameter calibration precision.
In one embodiment, the processor when executing the computer program further performs the steps of:
screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set; randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial positions respectively for the two number sequences of the single pair combination, and mutually exchanging the number values of the starting points in the two number sequences to obtain an exchange sequence set; reconstructing the sequence set according to the exchange sequence set.
In one embodiment, the processor when executing the computer program further performs the steps of:
performing de-duplication treatment on the exchange sequence set to obtain a de-duplicated exchange sequence set; and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the duplicate-removed exchange sequence set to obtain a reconstructed sequence set, wherein the number of the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring the weight of the error value corresponding to each numbered sequence; and randomly selecting a numbered sequence by adopting a roulette algorithm according to the weight to obtain a screening sequence set.
In one embodiment, the processor when executing the computer program further performs the steps of:
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and resetting the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring a preset error function; and calculating an error value between the predicted flow and the real output flow through a preset error function.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a serial number sequence which is randomly and initially generated according to a hyperparametric sequence of a hydrological model, and constructing a sequence set;
Acquiring a hyper-parameter value of each numbered sequence in the sequence set, a real input parameter and a real output flow of the hydrological model, and inputting the hyper-parameter value and the real input parameter into the hydrological model to acquire a predicted flow output by the hydrological model;
obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording the minimum error value and the corresponding minimum error serial number;
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and re-using the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
and restoring the latest minimum error number sequence to a rating parameter value to obtain the rating parameter of the hydrologic model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the hyper-parameter quantity, the hyper-parameter range and the parameter calibration precision of the hydrologic model; generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision; random initial generation of 2 based on hyper-parameter sequences n And numbering sequences to form a sequence set, wherein n is the parameter calibration precision.
In one embodiment, the computer program when executed by the processor further performs the steps of:
screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set; randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial positions respectively for the two number sequences of the single pair combination, and mutually exchanging the number values of the starting points in the two number sequences to obtain an exchange sequence set; reconstructing the sequence set according to the exchange sequence set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing de-duplication treatment on the exchange sequence set to obtain a de-duplicated exchange sequence set; and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the duplicate-removed exchange sequence set to obtain a reconstructed sequence set, wherein the number of the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the weight of the error value corresponding to each numbered sequence; and randomly selecting a numbered sequence by adopting a roulette algorithm according to the weight to obtain a screening sequence set.
In one embodiment, the computer program when executed by the processor further performs the steps of:
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and resetting the reconstructed sequence set as a sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a preset error function; and calculating an error value between the predicted flow and the real output flow through a preset error function.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method of hydrologic model parameter calibration, the method comprising:
acquiring a serial number sequence which is randomly and initially generated according to a hyperparametric sequence of a hydrological model, and constructing a sequence set; the hyper-parameter sequence of the hydrologic model is pre-generated based on the number of hyper-parameters and the hyper-parameter range of the hydrologic model;
acquiring a hyper-parameter value, a real input parameter and a real output flow of a hydrological model of each numbered sequence in the sequence set, inputting the hyper-parameter value and the real input parameter into the hydrological model, and acquiring a predicted flow output by the hydrological model;
Obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording a minimum error value and a corresponding minimum error serial number;
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and re-using the reconstructed sequence set as the sequence set, and returning to the step of acquiring the super-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition;
restoring the latest minimum error number sequence to a rating parameter value to obtain a rating parameter of the hydrologic model;
reconstructing the sequence set according to the error value corresponding to each numbered sequence comprises:
screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set;
randomly combining the numbered sequences in the screening sequence set, and mutually exchanging the numbered values of the numbered sequences in each combination to obtain an exchange sequence set;
reconstructing a sequence set according to the exchange sequence set.
2. The method of claim 1, wherein the obtaining a sequence set from a sequence of numbers that is randomly and initially generated from a hyperparametric sequence of a hydrological model, the sequence set comprising:
Acquiring the hyper-parameter quantity, the hyper-parameter range and the parameter calibration precision of the hydrologic model;
generating a super-parameter sequence according to the super-parameter number, the super-parameter range and the parameter calibration precision;
randomly generating 2 according to the super-parameter sequence n And numbering sequences to form a sequence set, wherein n is the parameter calibration precision.
3. The method of claim 1, wherein randomly combining the numbered sequences in the set of screening sequences, the numbered values of the numbered sequences in each combination being interchanged, the obtaining the set of interchanged sequences comprising:
and randomly combining the number sequences in the screening sequence set in pairs, randomly selecting starting points of non-initial bits respectively for the two number sequences of a single pair of combinations, and mutually exchanging the number values subsequent to the starting points in the two number sequences to obtain an exchange sequence set.
4. The method of claim 1, wherein reconstructing the set of sequences from the set of exchange sequences comprises:
performing de-duplication treatment on the exchange sequence set to obtain a de-duplicated exchange sequence set;
and randomly generating a supplementary number sequence, and supplementing the supplementary number sequence to the deduplication exchange sequence set to obtain a reconstructed sequence set, wherein the reconstructed sequence set is equal to the number of subsets contained in the sequence set.
5. The method of claim 1, wherein the filtering the number sequences according to the error value corresponding to each number sequence to obtain a filtered sequence set includes:
acquiring the weight of the error value corresponding to each numbered sequence;
and according to the weight, randomly selecting a numbered sequence by adopting a roulette algorithm to obtain a screening sequence set.
6. The method according to claim 1, wherein reconstructing a sequence set according to the error value corresponding to each numbered sequence, and reconstructing the reconstructed sequence set as the sequence set, and returning to the step of obtaining the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition comprises:
reconstructing a sequence set according to the error value corresponding to each numbered sequence, and reconstructing the reconstructed sequence set as the sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the minimum error value obtained in the preset times is returned to be not updated.
7. The method according to claim 1, wherein the obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and before recording the minimum error value and the corresponding minimum error serial number, further comprises:
Acquiring a preset error function;
and calculating an error value between the predicted flow and the real output flow through the preset error function.
8. A hydrological model parameter calibration apparatus, the apparatus comprising:
the sequence set construction module is used for acquiring a serial number sequence which is randomly and initially generated according to the hyper-parameter sequence of the hydrological model and constructing a sequence set; the hyper-parameter sequence of the hydrologic model is pre-generated based on the number of hyper-parameters and the hyper-parameter range of the hydrologic model;
the calculation module is used for acquiring the hyper-parameter value of each numbered sequence in the sequence set, the real input parameter and the real output flow of the hydrological model, inputting the hyper-parameter value and the real input parameter into the hydrological model, and acquiring the predicted flow output by the hydrological model;
the recording module is used for obtaining an error value corresponding to each serial number according to the error value between the predicted flow and the real output flow, and recording a minimum error value and a corresponding minimum error serial number;
the cyclic updating module is used for reconstructing a sequence set according to the error value corresponding to each numbered sequence, reconstructing the reconstructed sequence set as the sequence set, and returning to the step of acquiring the hyper-parameter value of each numbered sequence in the sequence set until the latest minimum error value meets the preset condition; reconstructing the sequence set according to the error value corresponding to each numbered sequence comprises: screening the numbered sequences according to the error value corresponding to each numbered sequence to obtain a screened sequence set; randomly combining the numbered sequences in the screening sequence set, and mutually exchanging the numbered values of the numbered sequences in each combination to obtain an exchange sequence set; reconstructing a sequence set according to the exchange sequence set;
And the calibration module is used for reducing the latest minimum error number sequence into a calibration parameter value to obtain the calibration parameter of the hydrologic model.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911336959.1A CN110990761B (en) | 2019-12-23 | 2019-12-23 | Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911336959.1A CN110990761B (en) | 2019-12-23 | 2019-12-23 | Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110990761A CN110990761A (en) | 2020-04-10 |
| CN110990761B true CN110990761B (en) | 2023-09-08 |
Family
ID=70074660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911336959.1A Active CN110990761B (en) | 2019-12-23 | 2019-12-23 | Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110990761B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389469A (en) * | 2015-11-09 | 2016-03-09 | 中山大学 | Automatic calibration method of storm water management model parameters |
| CN106682355A (en) * | 2017-01-12 | 2017-05-17 | 中国水利水电科学研究院 | Hydrological model parameter calibration method based on PSO (particle swarm optimization)-GA (genetic algorithm) mixed algorithm |
| CN109034507A (en) * | 2018-10-11 | 2018-12-18 | 华自科技股份有限公司 | Hydropower station amount prediction technique and device, computer equipment and storage medium |
| CN109740113A (en) * | 2018-12-03 | 2019-05-10 | 东软集团股份有限公司 | Hyper parameter threshold range determines method, apparatus, storage medium and electronic equipment |
| CN109993372A (en) * | 2019-04-12 | 2019-07-09 | 淮河水利委员会水文局(信息中心) | One kind being based on the probabilistic flood probability forecasting procedure of multi-source |
-
2019
- 2019-12-23 CN CN201911336959.1A patent/CN110990761B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389469A (en) * | 2015-11-09 | 2016-03-09 | 中山大学 | Automatic calibration method of storm water management model parameters |
| CN106682355A (en) * | 2017-01-12 | 2017-05-17 | 中国水利水电科学研究院 | Hydrological model parameter calibration method based on PSO (particle swarm optimization)-GA (genetic algorithm) mixed algorithm |
| CN109034507A (en) * | 2018-10-11 | 2018-12-18 | 华自科技股份有限公司 | Hydropower station amount prediction technique and device, computer equipment and storage medium |
| CN109740113A (en) * | 2018-12-03 | 2019-05-10 | 东软集团股份有限公司 | Hyper parameter threshold range determines method, apparatus, storage medium and electronic equipment |
| CN109993372A (en) * | 2019-04-12 | 2019-07-09 | 淮河水利委员会水文局(信息中心) | One kind being based on the probabilistic flood probability forecasting procedure of multi-source |
Non-Patent Citations (1)
| Title |
|---|
| Dmitri Kavetski 等.Parameter Estimation and Predictive Uncertainty Quantification in Hydrological Modelling.《Handbook of Hydrometeorological Ensemble Forecasting》.2018,1-42. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110990761A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017202259B2 (en) | Methods and systems for reservoir history matching for improved estimation of reservoir performance | |
| TWI444844B (en) | Simulation parameter correction technique | |
| Zhang et al. | Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change | |
| Pešta et al. | Conditional least squares and copulae in claims reserving for a single line of business | |
| CN116167289B (en) | Power grid operation scene generation method and device, computer equipment and storage medium | |
| CN117454668B (en) | Method, device, equipment and medium for predicting failure probability of parts | |
| KR20140111822A (en) | Error correction method for global climate model using non-stationary quantile mapping | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN110990761B (en) | Hydrological model parameter calibration method, hydrological model parameter calibration device, computer equipment and storage medium | |
| CN110852475B (en) | Extreme gradient lifting algorithm-based vegetation index prediction method, system and equipment | |
| CN104090932B (en) | A kind of content recommendation method and device | |
| CN111401569A (en) | Hyper-parameter optimization method and device and electronic equipment | |
| Levnajić | Derivative-variable correlation reveals the structure of dynamical networks | |
| Giribone et al. | Option pricing via radial basis functions: Performance comparison with traditional numerical integration scheme and parameters choice for a reliable pricing | |
| CN115859783A (en) | Multi-fidelity network construction method and device for nuclear reactor simulation test | |
| CN113987803B (en) | Frequency control method, device, equipment and storage medium based on model correction | |
| CN114417549A (en) | Digital twin target field data processing system based on supercomputer | |
| CN111125918A (en) | Complex product reliability evaluation method based on similar life model and similar life | |
| Mazy et al. | A Formally Correct and Algorithmically Efficient LULC Change Model-building Environment. | |
| Mazy et al. | A formally and algorithmically efficient LULC change model-building environment | |
| CN117937477B (en) | Method and device for predicting reactive power boundary value of generator set and computer equipment | |
| CN104570757B (en) | Method and device for operating an integrated control assembly | |
| CN116629348B (en) | Intelligent workshop data acquisition and analysis method and device and computer equipment | |
| KR102491128B1 (en) | Electronic device that supports to determine whether a water meter is faulty through the creation of an ai-based failure determination model and the operating method thereof | |
| EP4386625A1 (en) | Training an autoencoder to obtain a generative model |
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 |