CN111898660A - Hydrological simulation method for averagely fusing multi-source data based on Bayesian mode - Google Patents

Hydrological simulation method for averagely fusing multi-source data based on Bayesian mode Download PDF

Info

Publication number
CN111898660A
CN111898660A CN202010691996.0A CN202010691996A CN111898660A CN 111898660 A CN111898660 A CN 111898660A CN 202010691996 A CN202010691996 A CN 202010691996A CN 111898660 A CN111898660 A CN 111898660A
Authority
CN
China
Prior art keywords
long
model
series
data
correction
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.)
Granted
Application number
CN202010691996.0A
Other languages
Chinese (zh)
Other versions
CN111898660B (en
Inventor
尹家波
郭生练
王俊
顾磊
田晶
邓乐乐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN202010691996.0A priority Critical patent/CN111898660B/en
Publication of CN111898660A publication Critical patent/CN111898660A/en
Application granted granted Critical
Publication of CN111898660B publication Critical patent/CN111898660B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/29Graphical models, e.g. Bayesian networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/049Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medical Informatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a hydrological simulation method for averagely fusing multi-source data based on a Bayesian mode, which comprises the steps of firstly collecting meteorological data, hydrological series, satellite inversion precipitation and analyzing an air temperature data set of ground stations in scarce data areas; then, a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping are adopted to respectively establish correction models of the ground observation data and the synchronous simulated meteorological data sets in different months; then, a seasonal Bayes mode averaging method is adopted, the weight of each deviation correction scene is optimized through a posterior probability density function, and a corrected long-series meteorological data set is obtained; and (4) calibrating a basin hydrological model and a long and short term memory neural network model according to the measured data, and finally inputting the corrected long series meteorological data set to realize runoff process simulation. The invention can realize long series runoff simulation in scarce data areas, and can provide important reference basis with strong operability for basin water resource management and planning.

Description

Hydrological simulation method for averagely fusing multi-source data based on Bayesian mode
Technical Field
The invention relates to the technical field of hydrological simulation, in particular to a hydrological simulation method based on Bayesian mode average fusion multi-source data.
Background
High-quality long-series precipitation and gas temperature data are important basic data for disaster early warning prevention and control, agricultural production management, ecological protection, basin hydrological simulation and hydraulic engineering planning and design. Traditional meteorological data mainly depend on site observation, but a meteorological site network is usually low in density and uneven in space arrangement, so that the time-space change characteristics of meteorological variables are difficult to accurately reflect, and the engineering application requirements such as high-precision hydrological simulation cannot be met.
In recent years, satellite telemetry and data inversion algorithms are rapidly developed, precipitation quantitative observation products based on satellite remote sensing inversion have wider coverage range and higher space-time resolution, the defect of insufficient arrangement of meteorological stations is effectively overcome, and new data reference is provided for data-free areas. Meanwhile, as human observation means and data assimilation technologies become mature day by day, students perform quality control on observation data from various sources (ground, ships, radiosonde, anemometry balloons, airplanes, satellites and the like), and propose a data assimilation technology for numerical weather forecast to reconstruct a long-term historical climate process, namely a so-called reanalysis data set, which assimilates the numerical weather forecast and a large amount of ground observation data and satellite remote sensing information, and has the advantages of high spatial and temporal resolution precision, long time span and the like.
The inventor of the present application finds that the method of the prior art has at least the following technical problems in the process of implementing the present invention:
the method is limited by the influences of remote sensing precision, inversion algorithm, numerical prediction mode, assimilation scheme and the like, satellite precipitation and reanalysis temperature data have large system deviation, and the method is difficult to be directly applied to watershed hydrological simulation. Scholars at home and abroad evaluate the applicability of the inversion data set in the fields of meteorology, agriculture, hydrology and the like in different climate areas, and a small amount of research is carried out to correct the system deviation of the precipitation temperature data set. However, different deviation correction methods have certain differences, which bring great uncertainty to the radial flow simulation, and the simulation effect of the existing method is poor.
Disclosure of Invention
The invention provides a hydrological simulation method based on Bayesian mode average fusion multi-source data, which is used for solving or at least partially solving the technical problem of poor hydrological simulation effect of the method in the prior art.
In order to solve the technical problem, the invention provides a hydrological simulation method for averagely fusing multi-source data based on a Bayesian mode, which comprises the following steps:
s1: collecting ground observation data of ground stations in a scarce data area, wherein the ground observation data comprises limited meteorological observation data, a hydrologic actual measurement series data set, a satellite inversion precipitation data set and a re-analysis gas temperature data set;
s2: respectively adopting a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping to establish deviation correction models of ground observation data and a synchronous simulated meteorological data set in different months, wherein each correction method corresponds to one deviation correction model, and each deviation correction model corresponds to one set of correction data set;
s3: carrying out post-evaluation on the three sets of correction data sets corresponding to the deviation correction model established in the step S2 by adopting a seasonal Bayesian mode averaging method to obtain a long-series meteorological data set;
s4: and (4) calibrating the pre-constructed watershed hydrological model and the long-short term memory neural network model, driving the calibrated watershed hydrological model and the long-short term memory neural network model by using the long-series meteorological data set obtained in S3, outputting the long-series runoff process, and taking the long-series runoff process as a hydrological simulation result.
In one embodiment, S2 specifically includes:
s2.1: correcting precipitation occurrence frequency, magnitude and air temperature simulation deviation month by adopting a daily deviation correction method based on quantile mapping to obtain a first correction data set corresponding to the deviation correction model;
s2.2: correcting the precipitation magnitude and the air temperature simulation deviation month by adopting a regression correction method to obtain a second correction data set corresponding to the deviation correction model;
s2.3: and correcting the precipitation magnitude and the air temperature simulation deviation month by adopting an equal rate correction method to obtain a third correction data set corresponding to the deviation correction model.
In one embodiment, S3 specifically includes:
s3.1: constructing a probability density function of a meteorological correction variable according to a Bayes total probability formula;
s3.2: determining corresponding weights according to the relative contribution of the deviation correction effect of each deviation correction model, thereby establishing a seasonal Bayesian mode average correction model;
s3.3: and inputting the long-series meteorological data sets into a seasonal Bayesian mode average model established in S3.2, and obtaining the corrected long-series meteorological data sets by a weighted average method of optimal weight.
In one embodiment, S4 specifically includes:
s4.1: constructing a basin hydrological model according to short series runoff observation data of scarce data areas and meteorological observation data of the same period, and calibrating parameters of the basin hydrological model;
s4.2: simulating to obtain a daily runoff process based on a calibrated watershed hydrological model;
s4.3: correcting the daily runoff process obtained by simulation by adopting a machine learning technology, and constructing a long-term and short-term memory neural network model;
s4.4: inputting the long series meteorological data set obtained in the S3 into a well-calibrated watershed hydrological model, outputting a daily runoff process, inputting the output daily runoff process into the long and short term memory neural network model, simulating the long series runoff process, and taking the simulated long series runoff process as a hydrological simulation result.
In one embodiment, S4.3 specifically includes:
determining the time delay influencing the daily actual measurement runoff by carrying out statistical analysis on the simulated daily runoff process and the actual measurement daily runoff process in the scarce data area; and correcting the daily runoff process simulated in the step S4.2 by adopting a long-short term memory neural network model, wherein the corrected simulated runoff series is represented as:
Qcor(t)=FLSTM[Qsim(t),Qsim(t-1),Qsim(t-2),…,Qsim(t-N)]
in the formula: qcor(t) represents the corrected runoff at time t, Qsim(t) simulated runoff of the hydrological model at time t, Qsim(t-1) representing simulated runoff of the hydrological model at the t-1 moment, and N representing the time lag determined by the long-term and short-term memory neural network model; FLSTM represents a long-short term memory neural network model.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
the hydrological simulation method based on Bayesian mode average fusion multi-source data provided by the invention fully exerts the advantages of satellite remote sensing observation data and ground meteorological station data, overcomes the defects of low observation space resolution and short ground observation station series of satellite inversion and re-analysis technologies, obtains long-series meteorological data through data fusion and deviation correction technologies, improves the hydrological simulation effect, and is scientific, reasonable and close to the engineering practice; in addition, important reference basis with strong operability can be provided for basin hydrological simulation and water resource planning in the practical application process; the method comprises the steps of simulating to obtain a daily runoff process by using a watershed hydrological model with only four parameters, considering that engineering measures such as dams, reservoirs, agricultural irrigation, water diversion, cross-watershed water transfer and the like often cause large errors of the watershed hydrological model, and further correcting simulated runoff by adopting a machine learning technology to obtain a long series runoff process.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a detailed flow diagram of the method of the present invention;
FIG. 2 is a schematic diagram of ground weather station observation, raster weather simulation data, and runoff data;
FIG. 3 is a graph of a posterior probability density function of precipitation in an isocratic correction mode.
Detailed Description
The invention provides a hydrological simulation method for averagely fusing multi-source data based on a Bayesian mode, and hydrological simulation is carried out on runoff of a scarce data area by adopting the method for averagely fusing the multi-source data based on the Bayesian mode, so that the hydrological simulation effect is improved.
In order to achieve the technical effects, the main inventive concept of the invention is as follows: firstly, collecting limited meteorological observation data, hydrological actual measurement series, satellite inversion precipitation and analysis of a temperature data set of a ground station in a scarce data area; then, a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping are adopted to respectively establish correction models of the ground observation data and the synchronous simulated meteorological data sets in different months; then, post-evaluating the three sets of correction data sets by adopting a seasonal Bayesian mode averaging method, and optimizing the weight of each deviation correction scene through a posterior probability density function to obtain a corrected long-series meteorological data set; and (4) calibrating a watershed hydrological model and a long-short term memory neural network model according to the measured data, and finally inputting the corrected long-series meteorological data set to realize runoff simulation of the scarce data area.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The hydrological simulation method based on Bayesian mode average fusion multi-source data comprises the steps of firstly collecting limited meteorological observation data, hydrological actual measurement series, satellite inversion precipitation and analyzing an air temperature data set of a ground station of a scarce data area; then, a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping are adopted to respectively establish correction models of three sets of ground observation data and a synchronous simulated meteorological data set in different months; then, a seasonal Bayesian mode averaging method is adopted to carry out post-evaluation on the three sets of correction data sets, and the weight of each deviation correction scheme is optimized through a posterior probability density function; and (3) calibrating a watershed hydrological model and a long-short term memory neural network model according to the measured data, and finally inputting the corrected long-series meteorological data set to realize runoff simulation of the scarce data area, wherein the specific flow is shown in figure 1.
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings, and the method of the invention specifically comprises the following steps:
s1: and collecting ground observation data of ground stations in the scarce data area, wherein the ground observation data comprises limited meteorological observation data, a hydrologic actual measurement series data set, a satellite inversion precipitation data set and a re-analysis gas temperature data set.
In specific implementation, the satellite inversion precipitation product adopted by the embodiment is an MSWEP-V2 data set, the product integrates a plurality of satellite inversion data sources, 76747 global ground station observation data and reanalysis data sources, and deviation correction is performed on the land precipitation process based on water balance by adopting actual measurement data of 13762 global runoff stations, so that the product is one of precipitation data sources with the highest international space-time precision.
Further, the re-analysis gas temperature data set adopted by the embodiment is a fifth generation re-analysis climate product ERA5 of the european mid-term weather forecast center; the horizontal resolution of the hourly analysis field of the data set is 31km, 137 layers are vertically layered, and the top layer reaches the height of 0.01 hPa; the ERA5 adopts a Cycle31r2 model version of a comprehensive forecasting system, based on spectral harmonic resolution T255, and interpolates simplified Gaussian grid (N128) data to grids with different resolutions of 0.25-2.5 degrees and the like by a bilinear interpolation technology, so that the data is one of global reanalysis data with the highest space-time resolution at present.
As shown in fig. 2, a schematic diagram of the ground station meteorological observation data, runoff data and grid simulation meteorological data is given, for the drainage basin of the embodiment, the ground observation meteorological data and runoff data series are short in length, so that long meteorological simulation data need to be collected, and the corrected long-series meteorological data set can be obtained through the deviation correction model, so that the drainage basin hydrological simulation can be realized through driving the hydrological model.
S2: and respectively adopting a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping to establish deviation correction models of the ground observation data and the synchronous simulated meteorological data sets in different months, wherein each correction method corresponds to one deviation correction model, and each deviation correction model corresponds to one set of correction data set.
In one embodiment, S2 specifically includes:
s2.1: correcting precipitation occurrence frequency, magnitude and air temperature simulation deviation month by adopting a daily deviation correction method based on quantile mapping to obtain a first correction data set corresponding to the deviation correction model;
specifically, a precipitation threshold value of each month in the simulation series is determined according to the occurrence frequency of actual measurement daily precipitation in different months, when the daily precipitation is higher than the precipitation threshold value, the rainfall is judged to be rainy, otherwise, the rainfall is rainy; then calculating the system deviation of the frequency distribution function of the measured daily rainfall (air temperature) and the historical period simulation series in each month, then calculating the correction coefficient corresponding to each quantile, and finally using the coefficient to correct the simulated long-series meteorological data:
Figure RE-GDA0002679399920000061
in the formula:
Figure RE-GDA0002679399920000062
and
Figure RE-GDA0002679399920000063
respectively the day precipitation and the gas temperature series of the mth month after correction; pG,mAnd TG,mRespectively correcting the day precipitation and the air temperature series of the mth month before the historical period; fobsP,mAnd FGP,m(FobsT,mAnd FGT,m) The cumulative distribution functions are measured and simulated series of the rainfall (air temperature) in the historical period.
S2.2: correcting the precipitation magnitude and the air temperature simulation deviation month by adopting a regression correction method to obtain a second correction data set corresponding to the deviation correction model;
specifically, a regression relationship (i.e., 12 regression correction models) is established for the measured daily rainfall (air temperature) and the satellite fusion daily rainfall (reanalyzed data set air temperature) at the meteorological site of each month as follows:
Pobs,m=aP,m+bP,m·PG,m+
Tobs,m=aT,m+bT,m·TG,m+ (2)
in the formula: pobs,mAnd Tobs,mMeasured daily precipitation and daily temperature, P, of the mth monthG,mAnd TG,mRespectively simulating precipitation and gas temperature series in the same period; a isP,mAnd bP,m(aT,mAnd bT,m) The regression coefficients of the precipitation (air temperature) series respectively represent model residuals.
S2.3: and correcting the precipitation magnitude and the air temperature simulation deviation month by adopting an equal rate correction method to obtain a third correction data set corresponding to the deviation correction model.
Specifically, the isocratic correction method assumes that the satellite inverted precipitation (or the re-analyzed gas temperature data) and the month deviation of the ground observation series have consistency in different periods, firstly calculates the correction factor of each month based on the ground observation information, and then applies the factor to the long series simulation data set of the same month. The method is easy to operate and good in effect, and is widely applied to the field of satellite inversion precipitation product correction in recent years. For each month of the meteorological site, calculating the deviation ratio (precipitation) or the absolute deviation (air temperature) of the month based on the observation data and the simulation series respectively, obtaining a corresponding correction factor, correcting the satellite precipitation by using the following formula, and analyzing the air temperature series again:
Figure RE-GDA0002679399920000064
in the formula: n represents the total number of observation days in the mth month of the site, and i represents the daily precipitation or air temperature series time sequence.
S3: and (4) performing post-evaluation on the three sets of correction data sets corresponding to the deviation correction model established in the step (S2) by adopting a seasonal Bayesian mode averaging method to obtain a long-series meteorological data set.
Wherein, S3 specifically includes:
s3.1: constructing a probability density function of a meteorological correction variable according to a Bayes total probability formula;
specifically, let S be a correcting variable, and R ═ D, O]Characterizing model input data (where D is the correction series for each method in the training period, and O is the measured series), and f ═ f1,f2,…,fK]For the output results of K different correction modes, the probability density function of S obtained by a Bayesian total probability formula is as follows:
Figure RE-GDA0002679399920000071
in the formula: p is a radical ofk(S|fkR) is the Kth correction pattern fkA probability density function of the correction value S given the data R; p (f)kIr) is the posterior probability density function of the kth correction pattern given the training data R.
As shown in fig. 3, a schematic diagram of a posterior probability density function of precipitation in an isocratic correction mode is given.
S3.2: determining corresponding weights according to the relative contribution of the deviation correction effect of each deviation correction model, thereby establishing a seasonal Bayesian mode average correction model;
specifically, firstly, carrying out normal conversion on a meteorological site observation series and a simulation series obtained by each correction method through a Box-Cox function, and then carrying out weighted average on estimation results of multiple modes based on a normal linear distribution hypothesis:
Figure RE-GDA0002679399920000072
in the formula:
Figure RE-GDA0002679399920000073
denotes the mean value fkVariance is
Figure RE-GDA0002679399920000074
Normal distribution of (2); e denotes the expected value of the function, wkIs the weight of the kth deviation correction pattern.
Further, in this embodiment, K is 3.
S3.3: and inputting the long-series meteorological data sets into a seasonal Bayesian mode average model established in S3.2, and obtaining the corrected long-series meteorological data sets by a weighted average method of optimal weight.
S4: and (4) calibrating the pre-constructed watershed hydrological model and the long-short term memory neural network model, driving the calibrated watershed hydrological model and the long-short term memory neural network model by using the long-series meteorological data set obtained in S3, outputting the long-series runoff process, and taking the long-series runoff process as a hydrological simulation result.
In one embodiment, S4 specifically includes:
s4.1: constructing a basin hydrological model according to short series runoff observation data of scarce data areas and meteorological observation data of the same period, and calibrating parameters of the basin hydrological model;
specifically, the watershed hydrological model is a GR4J hydrological model, which is a lumped conceptual hydrological model with only 4 parameters, and the model has the characteristics of simple structure, fewer parameters, high precision and the like, and has been widely used. Calibration is carried out.
S4.2: simulating to obtain a daily runoff process based on a calibrated watershed hydrological model;
specifically, the runoff series obtained from the simulation is represented as:
Qsim=FGR4J[Prep,Tmean,Latitude,BasinArea,ParameterX](6)
in the formula: qsim represents a simulated runoff series, Prep represents a rainfall series after downscaling, Tmean represents a daily average air temperature series after downscaling, Latitude represents a Latitude mean value of a watershed, BasinArea represents a watershed area, ParameterX represents model parameters obtained through calibration in step 4.1, and FGR4J represents a GR4J model.
S4.3: correcting the daily runoff process obtained by simulation by adopting a machine learning technology, and constructing a long-term and short-term memory neural network model;
wherein, S4.3 specifically includes:
determining the time delay influencing the daily actual measurement runoff by carrying out statistical analysis on the simulated daily runoff process and the actual measurement daily runoff process in the scarce data area; and correcting the daily runoff process simulated in the step S4.2 by adopting a long-short term memory neural network model, wherein the corrected simulated runoff series is represented as:
Qcor(t)=FLSTM[Qsim(t),Qsim(t-1),Qsim(t-2),…,Qsim(t-N)](7)
in the formula: qcor(t) represents the corrected runoff at time t, Qsim(t) simulated runoff of the hydrological model at time t, Qsim(t-1) representing simulated runoff of the hydrological model at the t-1 moment, and N representing the time lag determined by the long-term and short-term memory neural network model; FLSTM represents a long-short term memory neural network model.
Further, the LSTM model is trained using the minimum batch gradient descent method, which is a technique conventional in the art.
S4.4: inputting the long series meteorological data set obtained in the S3 into a well-calibrated watershed hydrological model, outputting a daily runoff process, inputting the output daily runoff process into the long and short term memory neural network model, simulating the long series runoff process, and taking the simulated long series runoff process as a hydrological simulation result.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.

Claims (5)

1. A hydrologic simulation method for averagely fusing multi-source data based on a Bayesian mode is characterized by comprising the following steps of:
s1: collecting ground observation data of ground stations in a scarce data area, wherein the ground observation data comprises limited meteorological observation data, a hydrologic actual measurement series data set, a satellite inversion precipitation data set and a re-analysis gas temperature data set;
s2: respectively adopting a daily deviation correction method, a regression correction method and an equal rate correction method based on quantile mapping to establish deviation correction models of ground observation data and a synchronous simulated meteorological data set in different months, wherein each correction method corresponds to one deviation correction model, and each deviation correction model corresponds to one set of correction data set;
s3: carrying out post-evaluation on the three sets of correction data sets corresponding to the deviation correction model established in the step S2 by adopting a seasonal Bayesian mode averaging method to obtain a long-series meteorological data set;
s4: and (4) calibrating the pre-constructed watershed hydrological model and the long-short term memory neural network model, driving the calibrated watershed hydrological model and the long-short term memory neural network model by using the long-series meteorological data set obtained in S3, outputting the long-series runoff process, and taking the long-series runoff process as a hydrological simulation result.
2. The hydrological simulation method of claim 1, wherein S2 specifically comprises:
s2.1: correcting precipitation occurrence frequency, magnitude and air temperature simulation deviation month by adopting a daily deviation correction method based on quantile mapping to obtain a first correction data set corresponding to the deviation correction model;
s2.2: correcting the precipitation magnitude and the air temperature simulation deviation month by adopting a regression correction method to obtain a second correction data set corresponding to the deviation correction model;
s2.3: and correcting the precipitation magnitude and the air temperature simulation deviation month by adopting an equal rate correction method to obtain a third correction data set corresponding to the deviation correction model.
3. The hydrological simulation method of claim 1, wherein S3 specifically comprises:
s3.1: constructing a probability density function of a meteorological correction variable according to a Bayes total probability formula;
s3.2: determining corresponding weights according to the relative contribution of the deviation correction effect of each deviation correction model, thereby establishing a seasonal Bayesian mode average correction model;
s3.3: and inputting the long-series meteorological data sets into a seasonal Bayesian mode average model established in S3.2, and obtaining the corrected long-series meteorological data sets by a weighted average method of optimal weight.
4. The hydrological simulation method of claim 1, wherein S4 specifically comprises:
s4.1: constructing a basin hydrological model according to short series runoff observation data of scarce data areas and meteorological observation data of the same period, and calibrating parameters of the basin hydrological model;
s4.2: simulating to obtain a daily runoff process based on a calibrated watershed hydrological model;
s4.3: correcting the daily runoff process obtained by simulation by adopting a machine learning technology, and constructing a long-term and short-term memory neural network model;
s4.4: inputting the long series meteorological data set obtained in the S3 into a well-calibrated watershed hydrological model, outputting a daily runoff process, inputting the output daily runoff process into the long and short term memory neural network model, simulating the long series runoff process, and taking the simulated long series runoff process as a hydrological simulation result.
5. The hydrological simulation method of claim 1, wherein S4.3 specifically comprises:
determining the time delay influencing the daily actual measurement runoff by carrying out statistical analysis on the simulated daily runoff process and the actual measurement daily runoff process in the scarce data area; and correcting the daily runoff process simulated in the step S4.2 by adopting a long-short term memory neural network model, wherein the corrected simulated runoff series is represented as:
Qcor(t)=FLSTM[Qsim(t),Qsim(t-1),Qsim(t-2),···,Qsim(t-N)]
in the formula: qcor(t) represents the corrected runoff at time t, Qsim(t) simulated runoff of the hydrological model at time t, Qsim(t-1) representing simulated runoff of the hydrological model at the t-1 moment, and N representing the time lag determined by the long-term and short-term memory neural network model; FLSTM represents a long-short term memory neural network model.
CN202010691996.0A 2020-07-17 2020-07-17 Hydrological simulation method for average fusion of multi-source data based on Bayesian mode Active CN111898660B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010691996.0A CN111898660B (en) 2020-07-17 2020-07-17 Hydrological simulation method for average fusion of multi-source data based on Bayesian mode

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010691996.0A CN111898660B (en) 2020-07-17 2020-07-17 Hydrological simulation method for average fusion of multi-source data based on Bayesian mode

Publications (2)

Publication Number Publication Date
CN111898660A true CN111898660A (en) 2020-11-06
CN111898660B CN111898660B (en) 2022-10-04

Family

ID=73190662

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010691996.0A Active CN111898660B (en) 2020-07-17 2020-07-17 Hydrological simulation method for average fusion of multi-source data based on Bayesian mode

Country Status (1)

Country Link
CN (1) CN111898660B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112464559A (en) * 2020-11-24 2021-03-09 山东交通学院 Data fusion method and system for fuel cell engine fault prediction
CN112612995A (en) * 2021-03-08 2021-04-06 武汉理工大学 Multi-source rainfall data fusion algorithm and device based on Bayesian regression
CN112700068A (en) * 2021-01-15 2021-04-23 武汉大学 Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN112766580A (en) * 2021-01-25 2021-05-07 武汉大学 Multi-source precipitation product fusion method based on dynamic heuristic algorithm
CN113158542A (en) * 2021-01-29 2021-07-23 武汉大学 Multivariable design flood estimation method suitable for data-lacking area
CN113254861A (en) * 2021-06-23 2021-08-13 中山大学 Method and device for calibrating hydrological model parameters in data-free area and terminal equipment
CN113986897A (en) * 2021-10-22 2022-01-28 武汉大学 Multi-source data fusion method and device based on hydrological robot
CN115062818A (en) * 2022-05-10 2022-09-16 中国长江三峡集团有限公司 Reservoir storage sediment probability forecasting method based on Bayesian mode averaging and machine learning
CN115617935A (en) * 2022-10-18 2023-01-17 中国水利水电科学研究院 Underground water reserve deviation downscaling method based on fusion model
CN117473458A (en) * 2023-06-25 2024-01-30 中国电力工程顾问集团西南电力设计院有限公司 Satellite radiation data ground correction method based on quantile mapping

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5539704A (en) * 1995-06-23 1996-07-23 Western Atlas International, Inc. Bayesian sequential Gaussian simulation of lithology with non-linear data
EP1744185A1 (en) * 2005-07-13 2007-01-17 CIMA-Università degli Studi di Genova Method for estimating a variable geophysical field particularly for forecasting atmospheric precipitation
CN105260607A (en) * 2015-10-20 2016-01-20 华中科技大学 Serial connection and parallel connection coupling multi-model hydrological forecasting method
CN106875060A (en) * 2017-02-20 2017-06-20 宁波市水利水电规划设计研究院 A kind of flood real-time correction method based on global algorithms of automatic optimization
CN109685334A (en) * 2018-12-10 2019-04-26 浙江大学 A kind of new hydrological model simulation evaluation method based on Multiscale Theory
CN110059745A (en) * 2019-04-17 2019-07-26 武汉大学 A kind of Basin Rainfall product correction method based on star merged and system
CN110442937A (en) * 2019-07-24 2019-11-12 武汉大学 A kind of valley water security management method merging satellite remote sensing and machine learning techniques

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5539704A (en) * 1995-06-23 1996-07-23 Western Atlas International, Inc. Bayesian sequential Gaussian simulation of lithology with non-linear data
EP1744185A1 (en) * 2005-07-13 2007-01-17 CIMA-Università degli Studi di Genova Method for estimating a variable geophysical field particularly for forecasting atmospheric precipitation
CN105260607A (en) * 2015-10-20 2016-01-20 华中科技大学 Serial connection and parallel connection coupling multi-model hydrological forecasting method
CN106875060A (en) * 2017-02-20 2017-06-20 宁波市水利水电规划设计研究院 A kind of flood real-time correction method based on global algorithms of automatic optimization
CN109685334A (en) * 2018-12-10 2019-04-26 浙江大学 A kind of new hydrological model simulation evaluation method based on Multiscale Theory
CN110059745A (en) * 2019-04-17 2019-07-26 武汉大学 A kind of Basin Rainfall product correction method based on star merged and system
CN110442937A (en) * 2019-07-24 2019-11-12 武汉大学 A kind of valley water security management method merging satellite remote sensing and machine learning techniques

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
NIKOLAOS MASTRANTONAS ETAL.: "Evaluating the Benefits of Merging Near-Real-Time Satellite Precipitation Products: A Case Study in the Kinu Basin Region, Japan", 《JOURNAL OF HYDROMETEOROLOGY》 *
刘章君等: "贝叶斯概率水文预报研究进展与展望", 《水利学报》 *
梁莉等: "基于贝叶斯原理的降水预报偏差订正及水文试验", 《万方数据库》 *
高瑞等: "天山西部山区VIC模型的应用", 《南水北调与水利科技》 *

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112464559A (en) * 2020-11-24 2021-03-09 山东交通学院 Data fusion method and system for fuel cell engine fault prediction
CN112700068B (en) * 2021-01-15 2022-04-29 武汉大学 Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN112700068A (en) * 2021-01-15 2021-04-23 武汉大学 Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN112766580B (en) * 2021-01-25 2022-04-29 武汉大学 Multi-source precipitation product fusion method based on dynamic heuristic algorithm
CN112766580A (en) * 2021-01-25 2021-05-07 武汉大学 Multi-source precipitation product fusion method based on dynamic heuristic algorithm
CN113158542A (en) * 2021-01-29 2021-07-23 武汉大学 Multivariable design flood estimation method suitable for data-lacking area
CN113158542B (en) * 2021-01-29 2022-10-04 武汉大学 Multivariable design flood estimation method suitable for data-lacking area
CN112612995A (en) * 2021-03-08 2021-04-06 武汉理工大学 Multi-source rainfall data fusion algorithm and device based on Bayesian regression
CN113254861A (en) * 2021-06-23 2021-08-13 中山大学 Method and device for calibrating hydrological model parameters in data-free area and terminal equipment
CN113254861B (en) * 2021-06-23 2021-09-24 中山大学 Method and device for calibrating hydrological model parameters in data-free area and terminal equipment
CN113986897A (en) * 2021-10-22 2022-01-28 武汉大学 Multi-source data fusion method and device based on hydrological robot
CN113986897B (en) * 2021-10-22 2024-09-27 武汉大学 Multi-source data fusion method and device based on hydrological robot
CN115062818A (en) * 2022-05-10 2022-09-16 中国长江三峡集团有限公司 Reservoir storage sediment probability forecasting method based on Bayesian mode averaging and machine learning
CN115617935A (en) * 2022-10-18 2023-01-17 中国水利水电科学研究院 Underground water reserve deviation downscaling method based on fusion model
CN117473458A (en) * 2023-06-25 2024-01-30 中国电力工程顾问集团西南电力设计院有限公司 Satellite radiation data ground correction method based on quantile mapping

Also Published As

Publication number Publication date
CN111898660B (en) 2022-10-04

Similar Documents

Publication Publication Date Title
CN111898660B (en) Hydrological simulation method for average fusion of multi-source data based on Bayesian mode
CN107316095B (en) Regional weather drought level prediction method coupled with multi-source data
CN110442937B (en) Drainage basin hydrological simulation method integrating satellite remote sensing and machine learning technology
CN115507822B (en) Flood risk prediction method driven by hydrologic cycle variation
CN111027175B (en) Method for evaluating social and economic influences of flood based on coupling model integrated simulation
CN101480143B (en) Method for predicating single yield of crops in irrigated area
CN114265836A (en) All-weather assimilation method and device of satellite microwave hygrothermograph based on cloud area temperature and humidity profile inversion
CN114019579B (en) High space-time resolution near-surface air temperature reconstruction method, system and equipment
CN112700068B (en) Reservoir dispatching rule optimization method based on machine learning fusion of multi-source remote sensing data
CN104134095A (en) Crop yield estimation method based on scale transformation and data assimilation
CN113158542B (en) Multivariable design flood estimation method suitable for data-lacking area
CN110909447B (en) High-precision short-term prediction method for ionization layer region
CN113553782B (en) Downscaling method for forecasting wind speed
CN107609713B (en) Land-air coupling real-time forecasting method through rainfall and runoff double-factor correction
CN114970377B (en) Method and system for field flood forecasting based on Xinanjiang and deep learning coupling model
CN116663719A (en) Flood risk prediction method, system and electronic equipment
CN112785035A (en) Medium-short term hydrological forecasting method and system integrating multivariate information
CN114861840A (en) Multi-source precipitation data fusion method
CN114461983B (en) Satellite precipitation product space downscaling method based on water balance principle
CN116245008A (en) Dynamic estimation method of drainage basin hydrologic model parameters based on digital twin
CN117172037B (en) Distributed hydrologic forecasting method, device, computer equipment and medium
CN117273200A (en) Runoff interval forecasting method based on convolution optimization algorithm and Pyraformer neural network
CN117493476A (en) Runoff backtracking simulation method and system integrating physical mechanism and artificial intelligence
CN117493475A (en) Method and system for reconstructing regional moon runoff based on missing data through machine learning
CN115641696B (en) Gridding flood forecast model construction and real-time correction method based on multi-source information

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