CN116522446B

CN116522446B - Method for defining main channel of estuary bay tidal current sediment

Info

Publication number: CN116522446B
Application number: CN202310489181.8A
Authority: CN
Inventors: 刘培; 黄鹏飞; 傅学诚; 魏乾坤; 许劼婧; 刘志成
Original assignee: Pearl River Hydraulic Research Institute of PRWRC
Current assignee: Pearl River Hydraulic Research Institute of PRWRC
Priority date: 2023-04-28
Filing date: 2023-04-28
Publication date: 2023-12-05
Anticipated expiration: 2043-04-28
Also published as: CN116522446A

Abstract

The invention relates to the technical field of estuary bay tide sediment simulation, in particular to a method for defining a main channel of estuary bay tide sediment. The method comprises the following steps: acquiring estuary bay hydrological data and modeling according to the estuary bay hydrological data, so as to construct a primary estuary bay two-dimensional sediment mathematical model; acquiring historical hydrologic data and performing depth calculation by utilizing the historical hydrologic data, so as to construct a estuary and bay model evaluation classifier; evaluating and correcting the two-dimensional sediment mathematical model of the estuary bay by using an estuary bay model evaluation classifier so as to generate a secondary two-dimensional sediment mathematical model of the estuary bay; and selecting the section according to the two-dimensional sediment mathematical model of the secondary estuary bay so as to obtain selected section data, and acquiring section data according to the selected section data so as to obtain estuary bay section hydrological data. The invention can improve the accuracy and reliability of the demarcation result by establishing the primary and secondary mathematical models and utilizing the historical hydrologic data for evaluation and correction.

Description

Method for defining main channel of estuary bay tidal current sediment

Technical Field

The invention relates to the technical field of estuary bay tide sediment simulation, in particular to a method for defining a main channel of estuary bay tide sediment.

Background

The main tide channel is the main channel for sailing of ships in estuary and bay, and generally has a wider water area and a deeper water depth. Knowing and maintaining the main tide channel helps to ensure safe sailing of the vessel and reduces the risk of stranding and collision accidents of the vessel. Artificial intelligence (Artificial Intelligence, AI for short) refers to technology and applications that allow robots to have mental intelligence like robots. Artificial intelligence includes a number of fields that utilize large amounts of data and algorithms to help computers simulate human mental activities and achieve autonomous decisions and actions. The future artificial intelligence has very broad prospects. With the continuous development of technology and the continuous expansion of application scenes, the artificial intelligence is widely applied in various fields. How to combine artificial intelligence with main channel division of tidal current sediment in estuary and bay becomes a problem.

Disclosure of Invention

The application provides a method for defining a main channel of tidal current sediment in a estuary bay to solve at least one of the above technical problems.

The application provides a method for defining a main tidal current sediment channel of a estuary bay, which comprises the following steps:

step S1: acquiring estuary bay hydrological data and modeling according to the estuary bay hydrological data, so as to construct a primary estuary bay two-dimensional sediment mathematical model;

Step S2: acquiring historical hydrologic data and performing depth calculation by utilizing the historical hydrologic data, so as to construct a estuary and bay model evaluation classifier;

step S3: evaluating and correcting the two-dimensional sediment mathematical model of the estuary bay by using an estuary bay model evaluation classifier so as to generate a secondary two-dimensional sediment mathematical model of the estuary bay;

step S4: selecting sections according to a two-dimensional sediment mathematical model of the estuary bay through the preset section quantity, so as to obtain selected section data, and acquiring section data according to the selected section data, so as to obtain estuary bay section hydrologic data, wherein the estuary bay section hydrologic data comprise section along-path single-width flow velocity data, section water depth data and section sand content data;

step S5: calculating hydrological data of the cross section of the estuary bay so as to obtain single wide flow data of the cross section along the process and single wide flow sand data of the cross section along the process;

step S6: calculating the mean value according to the section along single wide flow data and the section along single wide flow sand volume data to obtain section single wide flow mean value data and section single wide flow sand volume mean value data, calculating the difference value according to estuary bay section hydrological data, section single wide flow mean value data and section single wide flow sand volume mean value data, and selecting the difference value to obtain larger single wide flow zone bit data and larger single wide flow sand volume zone bit data;

Step S7: and respectively carrying out sideline connection on the large single-wide flow position data and the large single-wide sand flow position data and carrying out region division on a preset electronic map, thereby obtaining a estuary bay tide main channel and a estuary bay sand conveying main channel.

According to the invention, a two-dimensional sediment mathematical model is utilized to model and simulate and analyze the water flow and sediment migration process in the estuary bay, so that the simulation precision and reliability are improved, the demarcation result is more accurate, the accuracy of the primary mathematical model is evaluated and corrected by collecting historical hydrologic data, utilizing a depth calculation method and the like, the reliability and accuracy of the demarcation result are improved, the calculation of single wide flow and single wide sediment quantity is carried out by acquiring estuary bay section hydrologic data, the comprehensive analysis and research of water flow and sediment transportation are realized, the section data is subjected to mean value calculation and difference value selection, the regional data of larger single wide flow and single wide sediment quantity are obtained, and the regional division is carried out on an electronic map, so that more visual and clear channel position and shape information is provided.

Preferably, step S1 is specifically:

step S11: acquiring estuary bay hydrographic data, wherein the estuary bay hydrographic data comprises estuary bay topographic data, estuary bay runoff data and estuary bay meteorological data;

Step S12: calculating according to estuary bay topography data, estuary bay topography data and estuary bay hydrologic data through an estuary bay hydrologic complexity formula, so as to obtain estuary bay hydrologic complexity;

the estuary bay hydrologic complexity formula is specifically:

；

for the hydrologic complexity of estuary bay +.>For estuary bay area data, < > for>For estuary bay river bank bending index data, +.>For the circumference of estuary bay>For average section flow of estuary bay>For average depth of estuary bay->Depth variation for estuary bay hydrological data, +.>For the average distance corresponding to the depth variation of the estuary bay hydrological data, ++>Is the influence coefficient of the depth variation degree of estuary bay, and is +.>For the influence coefficient of the average steering, +.>For the average steering variation on the central line of estuary bay, < ->Is the influence coefficient of the gradient change of the river bed, < ->Is the gradient change of the river bed on the central line of the estuary bay>Is a correction term for the hydrologic complexity of estuary bay.

Step S13: matching and selecting according to the hydrologic complexity of the estuary bay through a preset grid rule, so as to obtain an estuary bay grid division mode;

step S14: performing grid division on estuary bay hydrological data by using an estuary bay grid division mode so as to obtain an estuary bay grid model;

Step S15: the state variable definition is carried out on the estuary bay meshing model by utilizing estuary bay water depth data, estuary bay flow speed data, estuary bay flow direction data and estuary bay sediment concentration data in the estuary bay hydrologic data, so that an estuary bay state model is obtained;

step S16: carrying out hydrodynamic force calculation according to a estuary bay state model by a time compensation method so as to obtain an estuary bay applicable hydrodynamic equation, wherein the hydrodynamic force calculation is to solve a flow equation by using a Behceman formula and a jacobian iterative method;

step S17: and performing sediment transfer calculation according to the suitable hydrodynamic equation of the estuary bay and sediment characteristic data in the estuary bay hydrological data, so as to obtain sediment transfer process data, and constructing a primary estuary bay two-dimensional sediment mathematical model.

According to the method, various types of hydrologic data of estuary bay topography, runoff and weather are obtained, so that data preparation work is carried out for subsequent multidimensional deep data processing, calculation is carried out through the estuary bay topography, topography and hydrologic complexity, reference opinion is provided for selection of a subsequent estuary bay grid mode, the problem that calculation load is overlarge due to the fact that too fine grid mode is selected under the condition of too small complexity is avoided, or potential analysis deficiency is caused by the fact that the estuary bay with large complexity is divided by adopting a simple grid mode, errors of data results are reduced, the estuary bay hydrologic data are divided and defined by adopting a grid model, the water flow and sediment migration process in the estuary bay can be better described and analyzed, simulation precision and reliability are improved, a time compensation method can be used for effectively reducing time step, the calculation precision and reliability of a hydrodynamic equation are improved, compared with other conventional numerical calculation methods, the time compensation method can be used for reducing calculation time step size and calculating cost.

The invention utilizes a estuary bay hydrologic complexity formula which fully considers estuary bay area dataData of bending index of river bank of estuary bay +.>Perimeter of estuary bay->Average section flow rate of estuary bay->Average depth of estuary bay->Depth variation of estuary bay hydrological data +.>Average distance +.>Influence coefficient of degree of variation of estuary bay depth +.>Influence coefficient of average steering->Average steering variation on estuary bay centerline +.>Influence coefficient of the gradient of the river bed +.>River bed gradient change amount on central line of estuary bay +.>And the interaction relationship with each other to form a functional relationship +.>Estuary area data->The scale of the estuary bay is measured, the influence degree of the estuary bay hydrologic process is provided with indication operation, and the estuary bay river bank bending index data is +.>Reflecting the bending degree of the river bank of the estuary bay, correlating with the flow direction and speed distribution of the water flow, being helpful for evaluating the flow state characteristics in the hydrologic process, the perimeter of the estuary bay ∈ ->Representing the external dimension of the estuary bay, relating to the exchange capacity of the estuary bay and the complexity of the hydrologic process, the average section flow rate of the estuary bay +. >Reflecting the flow condition of the water flow in the estuary, and having important significance for the hydrologic process and water resource management of the estuary, and the average depth of the estuary>The depth characteristics of the estuary bay are measured, and the depth characteristics are closely related to the hydrologic process and the ecological environment of the estuary bay, and the depth variation of the estuary bay hydrologic data is +.>Representing the change of the depth of the estuary bay, the average distance corresponding to the depth change of the estuary bay hydrological data ∈>The spatial distribution of the internal depth change of the estuary is reflected, and the influence coefficient is used for adjusting the weight of each influence factor in a calculation formula in relation to the stability of the hydrologic process and the sensitivity of the internal hydrologic change of the estuary, so that the formula has more effective generalization capability, and the average steering change amount on the central line of the estuary is equal to that of the estuary>The average steering change on the central line of the estuary bay is represented to reflect the flow direction change condition of the water flow in the estuary bay, and the gradient change amount of the river bed on the central line of the estuary bay is +.>The change condition of the gradient of the river bed on the central line of the estuary bay is measured, and is related to the internal water flow speed of the estuary bay and the erosion and deposition process of the river bed, and the change condition is regulated through the correction term of the hydrologic complexity of the estuary bay, so that mathematical support with more reference value is provided.

Preferably, the historical hydrologic data includes estuary bay hydrologic image data and estuary bay historical hydrologic data, and the step S2 obtains the historical hydrologic data and uses the historical hydrologic data to perform depth calculation, so as to construct an estuary bay model evaluation classifier specifically includes:

step S21: performing time sequence extraction according to the estuary bay hydrological image data so as to obtain estuary bay hydrological time sequence image data;

step S22: sequentially extracting ripple characteristics from the hydrological time sequence image data of the estuary bay so as to obtain ripple characteristic data;

step S23: performing error correlation according to ripple feature data of the hydrological time sequence image data and ripple feature data of the corresponding next hydrological time sequence image data, so as to obtain correlated ripple feature data;

step S24: calculating according to the associated ripple characteristic data through an associated ripple calculation formula, so as to obtain historical flow rate data;

the associated ripple calculation formula specifically comprises:

；

for historical flow data>For data total number data->Is->Weight coefficient of each associated ripple feature data, +.>Is->Individual associated ripple characteristic data,/>Is->Weight coefficient of each associated ripple feature data, +. >Is->Individual associated ripple characteristic data,/>To generate adjustment coefficients based on the associated ripple and estuary bay water depth data->For periodic items +.>For the phase coefficient +.>For average error adjustment term, +.>Error adjustment term for central ripple generated from ripple characteristic data +.>A correction term for the historical flow rate data;

step S25: performing gridding according to the historical hydrologic data and the historical flow rate data, so as to obtain gridded hydrologic data;

step S26: extracting features according to the gridded hydrological data, so as to obtain locally associated hydrological feature data;

step S27: and carrying out depth modeling on the locally-associated hydrologic characteristic data so as to construct an estuary bay model evaluation classifier.

According to the invention, by acquiring the estuary bay hydrological image data and the estuary bay historical hydrological data, more comprehensive and detailed historical hydrological data support can be provided, by utilizing the historical hydrological data to carry out depth calculation, feature extraction and depth modeling, an estuary bay model evaluation classifier can be constructed, accurate prediction and simulation of estuary bay water flow are realized, by means of ripple feature extraction and error association processing, the precision and reliability of historical flow velocity data can be effectively improved, more accurate basis is provided for estuary bay simulation and prediction, by means of carrying out feature extraction and local association processing on meshed hydrological data, local associated hydrological feature data can be established, change rules and trends of an estuary bay hydrological environment can be better described, by means of fusing the hydrological image data and the historical hydrological data, fusion and utilization of multi-source data can be realized, the application value and effect of the historical hydrological data are improved, and the estuary bay model evaluation classifier can be based on the constructed estuary model evaluation classifier, and the estuary water flow prediction and simulation can be carried out, and the calculation model can be calculated and calculated quickly, and the calculation cost is greatly saved.

The present invention utilizes an associated ripple calculation formula that provides historical flow rate dataData total data for showing historical change of water flow rate in estuary bay +.>Representing the number of data points involved in the calculation, th ∈>Weight coefficient of the individual associated ripple feature data +.>First->Weight coefficient of the individual associated ripple feature data +.>Weight coefficients respectively representing the (i+1) -th associated ripple feature data and the (i) -th associated ripple feature data for adjusting the associated ripple feature dataThe degree of contribution of the symptom data in the calculation formula, the first->Personal associated ripple characteristic data->First->Personal associated ripple characteristic data->Data representing the characteristics of the relevant waves in the estuary bay, has an indication function for analyzing the change of the water flow velocity and the fluctuation characteristics in the estuary bay, and generates an adjustment coefficient +_based on the relevant waves and the estuary bay water depth data>According to the adjustment coefficient generated by the associated ripple and the estuary bay water depth data, the adjustment coefficient is used for correcting the result of a calculation formula, potential relation exists between potential flow velocity and water depth represented by the ripple, and the flow velocity of estuary bay water flow and the period term can be reflected to a certain extent by calculating the depth of the ripple under different weather conditions >The periodic characteristic of the change of the water flow speed is shown, which is helpful for revealing the periodic rule in the hydrologic process of the estuary and the bay, and the phase coefficient +.>The phase characteristic of the water flow speed change is shown, so that the phase relation in the water hydrologic process of the estuary bay can be known, and the average error adjustment term is +.>For correcting the average error of the calculation formula, the error adjustment term of the central ripple generated according to the ripple characteristic data, for correcting the influence of the ripple characteristic data in the calculation formula, the historical flow velocity numberCorrection term->And correcting to improve the accuracy and stability of the prediction result.

Preferably, the step of depth modeling is specifically:

step S271: dividing according to the locally associated hydrologic feature data so as to obtain training hydrologic feature data and test hydrologic feature data;

step S272: constructing a hydrologic cycle neural network model, and performing iterative training on the hydrologic cycle neural network model by utilizing training hydrologic characteristic data, so as to construct a primary estuary bay model evaluation classifier;

step S273: and performing iterative error fitting on the primary estuary model evaluation classifier by using the test hydrologic characteristic data, so as to obtain the estuary model evaluation classifier.

According to the invention, the data set is divided into the training hydrologic characteristic data and the test hydrologic characteristic data according to the local association hydrologic characteristic data, so that the model can be trained and tested on different data subsets, the generalization capability of the model is improved, the modeling is carried out on the time characteristics by using a hydrologic cycle neural network model (RNN), the dependency relationship of hydrologic characteristics in a time sequence can be effectively captured, the prediction and classification accuracy of the model on the estuary bay hydrologic process is improved, model parameters can be continuously optimized in the training process by iteratively training the hydrologic cycle neural network model, the fitting degree of the model on the training hydrologic characteristic data is improved, the iterative error fitting is carried out on a primary estuary model evaluation classifier by using the test hydrologic characteristic data, the model parameters can be further optimized, the error of the model on the test data is reduced, the prediction and classification accuracy of the model is improved, and the effective support based on depth calculation is provided by combining a deep learning algorithm with estuary flow sediment numerical prediction.

Preferably, the iterative error is calculated by optimizing a hydrologic characteristic data loss calculation formula, wherein the optimized hydrologic characteristic data loss calculation formula is specifically:

；

Predicting data loss values for hydrologic features, +.>Data quantity +.>Is->Weight coefficient of individual hydrologic feature prediction data, < ->Is->Weather condition fitting value corresponding to the individual hydrologic characteristic prediction data,/->Is->The individual hydrologic characteristics of the prediction data,is->Weight coefficient of individual hydrologic characteristic actual data, < ->Is->Personal hydrologic characteristic actual data,/->For the hydrologic data error adjustment term, +.>For scaling factor +.>Loss of error term for hydrographic feature data, +.>Adjusting coefficients for regularization coefficients,/->Is->Predictive adjustment item->Is->Actual adjustment item->And predicting a correction term of the data loss value for the hydrologic characteristic.

The invention utilizes an optimized hydrologic characteristic data loss calculation formula, and the first formulaWeather condition fitting value corresponding to individual hydrologic characteristic prediction data +.>By incorporating weather condition factors into the loss calculation, the adaptation of the model to environmental changes is improved, scaling factor +.>The relative importance of each item in the loss function is adjusted to help balance the fitting degree and generalization capability of the model, and the hydrologic characteristic data loss error item +.>Measuring the difference between the predicted result and the actual data, contributing to the prediction capability of the quantization model, and adjusting the coefficient by the regularization coefficient +. >For adjusting the weight of the gap between the predicted adjustment term and the actual adjustment term in the loss function. This helps to prevent model overfitting, improve generalization ability of the model, +.>Weight coefficient of personal hydrologic characteristic prediction data +.>First->Weight coefficient of personal hydrologic characteristic actual data +.>Respectively->Weight coefficients of the predicted data and the actual data of the individual hydrologic features, which represent the importance of the individual hydrologic features in the loss calculation, th ∈>Individual predictive adjustment items->First->Individual actual adjustment items->Representing the adjustment between the predicted result and the actual data, the accuracy of the model predicted result can be further improved by optimizing these adjustment terms, and the correction term of the predicted data loss value by the hydrologic feature +.>And carrying out loss correction to optimize loss calculation.

Preferably, step S4 is specifically:

selecting sections according to a two-dimensional sediment mathematical model of the estuary bay through the preset section number, so as to obtain selected section data;

and controlling the remote sensing equipment to acquire section data according to the selected section data, thereby acquiring the hydrographic data of the section of the estuary and the bay.

According to the invention, the remote sensing equipment is used for acquiring data of specific sections, so that the acquisition of detailed hydrological data of an actual estuary bay is facilitated, the accuracy of the data is improved, and the density of section selection can be changed by presetting different section numbers according to the requirement, so that the requirements of different research purposes and actual application scenes are flexibly met.

Preferably, step S5 is specifically:

calculating according to the water text data of the section of the estuary and the single-wide flow calculation formula, so as to obtain the single-wide flow data of the section along the journey;

calculating according to the water text data of the section of the estuary bay by a single wide quicksand calculation formula, so as to obtain the single wide quicksand quantity data of the section along the journey;

the single-wide flow calculation formula specifically comprises:

；

for the data of the section along-the-way single wide flow rate, +.>For the data of the cross section along the single wide flow rate, +.>Is the section water depth data;

the single wide quicksand calculation formula specifically comprises:

；

for the data of the single wide sand flow of the section along the way, < + >>For the data of the section along-the-way single wide flow rate, +.>Is section sand content data.

According to the invention, the single wide flow data and the single wide flow data of the section along the process are calculated according to the hydrographic data of the section of the estuary and the single wide flow calculation formula, so that the hydrodynamic process and the sediment transport process of the estuary and the estuary can be effectively analyzed.

Preferably, step S6 is specifically:

step S61: respectively carrying out average value calculation on the section along-process single-width flow data and the section along-process single-width sand flow data so as to obtain section single-width flow average value data and section single-width sand flow average value data;

Step S62: sequentially comparing the section along-process single-width flow data corresponding to the estuary bay section hydrological data with section single-width flow average data;

step S63: when the cross section along-process single-wide flow data corresponding to the estuary bay cross section hydrological data is determined to be larger than the cross section single-wide flow mean value data, determining the corresponding estuary bay cross section hydrological data as larger single-wide flow zone location data;

step S64: sequentially comparing the single-width flow sand data of the section along the process corresponding to the hydrographic data of the section of the estuary bay with the single-width flow sand mean value data of the section;

step S65: when the corresponding section along-process single-width quicksand data of the estuary bay section hydrological data is determined to be larger than the section single-width quicksand mean value data, the corresponding estuary bay section hydrological data is determined to be the larger single-width quicksand volume location data.

The invention can rapidly determine the larger single-wide flow position and the larger single-wide sand flow position by calculating the mean value data and comparing the mean value data with the actual data, thereby improving the data analysis efficiency, being beneficial to intuitively displaying the characteristics of sediment distribution and water flow change in the estuary bay,

preferably, step S7 is specifically:

Step S71: longitudinally connecting a left boundary and a right boundary of the large single wide flow zone bit data on a preset electronic map respectively, so as to obtain a left line of the main tide channel and a right line of the main tide channel;

step S72: dividing the left side line of the main tidal current channel and the right side line of the main tidal current channel on a preset electronic map so as to generate a main tidal current channel of the estuary and the bay;

step S73: longitudinally connecting a left boundary and a right boundary of larger single-width quicksand region position data on a preset electronic map respectively, so as to obtain a left line of a sand conveying main channel and a right line of the sand conveying main channel;

step S74: dividing the left line of the main sand conveying channel and the right line of the main sand conveying channel on a preset electronic map so as to generate the main sand conveying channel of the estuary and the bay.

According to the invention, the boundaries of the main tidal current channel and the main sand conveying channel can be defined by connecting the left and right boundaries of the large single wide flow position data and the large single wide sand flow position data, and the main tidal current channel and the main sand conveying channel are divided on the electronic map, so that the characteristics of water flow and sediment distribution in the estuary are visually displayed, and the main tidal current channel and the main sand conveying channel can be identified to better utilize water resources and land resources of the estuary, improve the resource utilization efficiency and promote the sustainable development of the estuary.

Preferably, the steps following step S7 include the steps of:

step S701: constructing a prediction model according to the estuary bay tide main channel and the estuary bay sand transporting main channel, so as to obtain an estuary bay siltation model;

step S702: carrying out prediction calculation according to the estuary bay siltation model so as to obtain estuary bay river bed siltation data;

step S703: and carrying out intelligent decision according to the estuary bay riverbed siltation data so as to generate estuary bay main channel cleaning data.

According to the application, the estuary bay siltation model can be obtained by constructing the prediction model based on the estuary bay tide main channel and the sand conveying main channel, so that the siltation condition of the estuary bay riverbed is predicted, intelligent decision is made according to the estuary bay riverbed siltation data, the estuary bay main channel cleaning data is generated, the estuary bay treatment work is guided, the estuary bay main channel cleaning data can be generated rapidly based on the estuary bay siltation model and the intelligent decision, the time and the cost of the manual decision are reduced, and the decision efficiency is improved.

The method has the beneficial effects that the primary estuary bay two-dimensional sediment mathematical model and the estuary bay model evaluation classifier are constructed by utilizing the hydrologic data and the historical hydrologic data, the models are further corrected to generate the secondary estuary bay two-dimensional sediment mathematical model, the accuracy of demarcating the estuary bay tidal current sediment main channel is improved, and the method can more reliably determine the larger single-wide flow area position data and the larger single-wide flow sand area position data by carrying out detailed calculation and analysis on the estuary bay section hydrologic data, so that the demarcation of the estuary bay tidal current main channel and the sand conveying main channel is facilitated. The method provided by the application can be used for determining the main channel of estuary bay tide sediment relatively quickly, reduces the cost and time of manual judgment, and can be applied to demarcating the main channel of estuary bay tide sediment to other estuary bays and water areas, thereby having relatively strong universality.

Drawings

Other features, objects and advantages of the application will become more apparent upon reading of the detailed description of a non-limiting implementation, made with reference to the accompanying drawings in which:

FIG. 1 is a flow chart showing the steps of a main channel dividing method for tidal sediment in estuaries and backbones according to an embodiment;

FIG. 2 is a flow chart showing the steps of a method for generating a two-dimensional mathematical model of the primary estuary bay according to an embodiment;

FIG. 3 is a flow chart showing the steps of a estuary model evaluation classifier construction method according to one embodiment;

FIG. 4 shows a flow chart of the steps of a depth modeling method of an embodiment;

FIG. 5 is a flow chart illustrating the steps of a method for acquiring greater single wide flow/sand location data in accordance with one embodiment;

FIG. 6 is a flow chart showing the steps of a method for generating a estuary and bay sand conveying main channel according to an embodiment;

FIG. 7 is a flow chart showing the steps of a method for generating estuary and bay main channel cleaning data according to an embodiment.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to fall within the scope of the present application.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

The invention provides a method for defining a main tidal current sediment channel of a estuary bay. The main channel defining method for tidal current sediment in estuary includes the following steps:

step 1: establishing a two-dimensional tidal flow sediment mathematical model of the estuary bay, and selecting a typical hydrologic combination to calculate a tidal flow sediment field;

step 2: selecting a plurality of sections 1, 2 and 3 … n from the top of the gulf to the mouth of the gulf, and counting the single wide flow velocity V (m/S), the water depth H (m) and the sand content S (kg/m) of each section along the way at the time of emergency and the time of rising and falling;

step 3: calculating single wide flow and single wide sand conveying amount of each section along the process, wherein the single wide flow is the product Q=V.H (m 3/S) of the flow velocity and the water depth, and the single wide sand conveying amount is the product W=Q.S (kg/S) of the single wide flow and the sand content;

step 4: calculating the average single-width flow rate and the average single-width sand conveying amount of the sections, and finding out the areas Ql1-Qr1, ql2-Qr2 and … Qln-Qrn where the single-width sand conveying amount of each section is larger than the average single-width flow rate of the sections, and the areas Wl1-Wr1, wl2-Wr2 and … Wln-Wrn where the single-width sand conveying amount is larger than the average sand conveying amount of the sections;

step 5: from the top of the gulf to the mouth of the gulf, each section Ql1 and Ql2 … Qln is longitudinally connected to form a left line of a main tide channel, each section Qr1 and Qr2 … Qrn is connected to form a right line of the main tide channel, and a region between the left line and the right line is the main tide channel; the left side line of each section Wl1 and Wl2 … Wln is longitudinally connected with the sand conveying main channel, the right side line of each section Wr1 and Wr2 … Wrn is connected with the sand conveying main channel, and the region between the left side line and the right side line is the sand conveying main channel.

Referring to fig. 1 to 7, the present application provides a method for defining a main channel of tidal current sediment in a estuary bay, comprising the following steps:

specifically, a mathematical modeling method, such as finite element analysis, finite difference method, or other numerical modeling technique, is used to construct a mathematical model of the primary estuary bay two-dimensional sediment.

specifically, these historical hydrologic data are deeply computed, for example, using deep learning techniques, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), and are divided into training and test sets, so that the neural networks are trained using the training sets, and the trained models are validated and evaluated using the test sets. The trained neural network can be used as an estuary model evaluation classifier for evaluating and correcting a primary estuary two-dimensional sediment mathematical model constructed before.

specifically, for example, when the intermediate data difference is too large, if the water flow velocity error is too large, weighted summation is performed, and data information of sediment accumulation and river bed scouring degree is adjusted.

specifically, for example, a two-dimensional silt mathematical model of the secondary estuary bay is used for section selection, thereby obtaining 6 pieces of selected section data. And then, acquiring section data by using the selected section data to obtain the water content data of the section of the estuary bay, wherein the water content data comprise the single wide flow rate data of the section along the journey, the water depth data of the section and the sand content data of the section.

Specifically, for example, the data of the water content of the cross section of the estuary bay is used for calculation, so that the data of the single wide flow rate of the cross section along the way and the data of the single wide flow sand of the cross section along the way are obtained. Wherein the profile along-the-path single-width flow data represents the volume of water flow through a profile in a unit time along a particular profile direction; the profile along-the-path single-width quicksand volume data represents the volume of suspended particulate matter passing through the profile under the same conditions.

Specifically, for example, average calculation is performed according to the section along-process single-width flow data and the section along-process single-width flow sand volume data, so as to obtain section single-width flow average data and section single-width flow sand volume average data. And then, calculating the difference value according to the estuary bay section hydrological data, the section single wide flow average value data and the section single wide flow sand amount average value data, and selecting the positive value to obtain the larger single wide flow position data and the larger single wide flow sand amount position data. And carrying out boundary connection on the large single-wide flow position data and the large single-wide sand flow position data, and carrying out region division on a preset electronic map to finally obtain a tidal current main channel and a sand conveying main channel of the estuary.

Specifically, for example, the main channel is defined and comprises a section, the same section comprises Hong Ji and dead season, the section specifically comprises single wide flow and distance from the west shore, the tide rising line, the tide falling line and the tide falling mean value are divided into tide main channels in sequence, the section sand conveying channel comprises sand conveying quality in unit time and distance from the west shore, the section sand conveying channel comprises sand conveying quality in unit time and sand conveying quality mean value in unit time, and the sand conveying main channels are divided into sections in sequence.

Preferably, step S1 is specifically:

specifically, for example, the topography data of the estuary bay is obtained by using technologies such as high-precision satellite images, laser radar scanning and the like, and further processed and analyzed by utilizing a Digital Elevation Model (DEM), so that the topography data of the estuary bay is obtained, and the topography data of the estuary bay including coastline, beach, sand dunes, river channels and the like are obtained by means of on-site exploration, remote sensing technology, aerodynamic simulation and the like. Meanwhile, methods such as sediment analysis and ancient environment reconstruction can be combined, and the evolution history and the environment background of the estuary and the bay can be further known. The hydro-meteorological site of the estuary bay river basin is monitored and recorded, and estuary bay runoff data including indexes such as annual precipitation, runoff quantity and evapotranspiration quantity are obtained. Meanwhile, the runoff process can be predicted and analyzed by means of numerical simulation, remote sensing technology and the like. Meteorological data of the estuary bay including indexes such as temperature, precipitation, wind direction, wind speed and the like are obtained through monitoring and recording of meteorological sites around the estuary bay. Meanwhile, the meteorological elements can be predicted and analyzed by means of numerical simulation, remote sensing technology and the like.

specifically, for example, the topographic data of the estuary bay is analyzed, and the indexes such as the size of the estuary bay and the gradient of the river bed are calculated. And analyzing the geomorphic data of the estuary bay, and calculating indexes such as river intersection quantity, sand distribution and the like. And analyzing the hydrologic data of the estuary bay, and calculating indexes such as tidal range, runoff quantity, sand conveying quantity and the like. Substituting each index obtained through calculation into a estuary bay hydrologic complexity formula to calculate the estuary bay hydrologic complexity.

Specifically, for example, a suitable estuary bay hydrologic complexity calculation formula may be used for calculation, such as perimeter area/water depth, or the rest calculates estuary bay hydrologic complexity.

The estuary bay hydrologic complexity formula is specifically:

；

for the hydrologic complexity of estuary bay +.>For estuary bay area data, < > for>For estuary bay river bank bending index data, +.>For the circumference of estuary bay>For average section flow of estuary bay>For average depth of estuary bay->Depth variation for estuary bay hydrological data, +. >For the average distance corresponding to the depth variation of the estuary bay hydrological data, ++>Is the influence coefficient of the depth variation degree of estuary bay, and is +.>For the influence coefficient of the average steering, +.>For the average steering variation on the central line of estuary bay, < ->Is the influence coefficient of the gradient change of the river bed, < ->Is the gradient change of the river bed on the central line of the estuary bay>Is a correction term for the hydrologic complexity of estuary bay.

specifically, for example, a suitable meshing method is selected according to the hydrologic complexity of the estuary bay. For example, if the estuary bay hydrologic complexity is high, a finer meshing, such as a hexagonal meshing method, is selected; if the estuary bay hydrologic complexity is low, a coarser grid division, such as a triangle or quadrilateral division method, is selected.

specifically, for example, the estuary bay is divided into a plurality of grid cells by using a selected grid division manner. The size of each grid cell depends on the selected grid division.

specifically, for example, estuary bay water depth data, flow rate data, flow direction data, and sediment concentration data are used to define state variables for each grid cell, thereby constructing an estuary bay state model.

specifically, the hydrodynamic calculation is performed, for example, by a time compensation method. In the process, a Behcet formula and a jacobian iterative method are applied to solve a flow equation, so that a hydrodynamic equation suitable for estuary and bay is obtained.

Specifically, for example, sediment transfer calculation is performed according to a suitable hydrodynamic equation of the estuary bay and sediment characteristic data (for example, particle size distribution, sediment concentration, etc.) in the hydrographic data of the estuary bay, so as to obtain sediment transfer process data. To construct a mathematical model of the two-dimensional sediment of the primary estuary bay.

specifically, for example, by performing time series extraction on remote sensing images or satellite images of the estuary bay, estuary bay hydrographic image data of a series of continuous time points can be acquired.

specifically, for example, for each hydrographic time series image data, ripple features are extracted by an image processing technique (e.g., edge detection, texture analysis, etc.). These features may include the shape, size, orientation, etc. of the corrugations.

Specifically, for example, to calculate historical flow rate data, a ripple feature match between adjacent time series images is found. This can be achieved by calculating the error correlation between the ripple feature data at different points in time. For example, the similarity between ripple features is measured using metrics such as euclidean distance, cosine similarity, and the like.

specifically, for example, the associated ripple calculation formula provided by the application is adopted for calculation.

Specifically, the historical flow rate data is calculated using an associated ripple calculation formula, for example, from the associated ripple feature data. For example, assuming that a ripple feature match is found for two adjacent moments, their spatial displacement and time interval are calculated. Then, by dividing by the time interval, historical flow rate data is obtained. Or the other calculation formulas for calculating the flow rate data through the associated ripple can be adopted.

The associated ripple calculation formula specifically comprises:

；

for historical flow data>For data total number data->Is->Weight coefficient of each associated ripple feature data, +.>Is- >Individual associated ripple characteristic data,/>Is->Weight coefficient of each associated ripple feature data, +.>Is->Individual associated ripple characteristic data,/>To generate adjustment coefficients based on the associated ripple and estuary bay water depth data->For periodic items +.>For the phase coefficient +.>For average error adjustment term, +.>Error adjustment term for central ripple generated from ripple characteristic data +.>A correction term for the historical flow rate data;

specifically, the historical hydrologic data and the historical flow rate data are spatially gridded using, for example, a grid interpolation method (e.g., kriging interpolation, inverse distance weighted interpolation, etc.).

specifically, feature extraction, such as extracting locally associated hydrologic features, is performed, for example, for the gridded hydrologic data. Specifically, the characteristics of correlation, adjacency, and stream directionality between each grid cell are calculated.

Specifically, for example, a estuary model evaluation classifier may be constructed based on locally associated hydrographic feature data. This may be accomplished by modeling the locally associated hydrographic feature data using deep learning methods, such as Convolutional Neural Networks (CNNs), recurrent Neural Networks (RNNs), and the like. By training the deep learning models, the classifier can be used for identifying and evaluating the performance of the two-dimensional sediment mathematical model of the estuary and the bay.

The present invention utilizes an associated ripple calculation formula that provides historical flow rate dataData total data for showing historical change of water flow rate in estuary bay +.>Representing the number of data points involved in the calculation, th ∈>Weight coefficient of the individual associated ripple feature data +.>First->Associated ripple feature dataWeight coefficient +.>The (i+1) th associated ripple feature data and the (i) th associated ripple feature data are respectively represented by weight coefficients for adjusting the contribution degree of each associated ripple feature data in a calculation formula, the (i)>Personal associated ripple characteristic data->First->Personal associated ripple characteristic data->Data representing the characteristics of the relevant waves in the estuary bay, has an indication function for analyzing the change of the water flow velocity and the fluctuation characteristics in the estuary bay, and generates an adjustment coefficient +_based on the relevant waves and the estuary bay water depth data>According to the adjustment coefficient generated by the associated ripple and the estuary bay water depth data, the adjustment coefficient is used for correcting the result of a calculation formula, potential relation exists between potential flow velocity and water depth represented by the ripple, and the flow velocity of estuary bay water flow and the period term can be reflected to a certain extent by calculating the depth of the ripple under different weather conditions >The periodic characteristic of the change of the water flow speed is shown, which is helpful for revealing the periodic rule in the hydrologic process of the estuary and the bay, and the phase coefficient +.>The phase characteristic of the water flow speed change is shown, so that the phase relation in the water hydrologic process of the estuary bay can be known, and the average error adjustment term is +.>For correcting the average error of the calculation formula, the error adjustment term of the central ripple generated according to the ripple characteristic data, for correcting the influence of the ripple characteristic data in the calculation formula, the correction term of the historical flow rate data ∈ ->And correcting to improve the accuracy and stability of the prediction result.

Preferably, the step of depth modeling is specifically:

in particular, the locally associated hydrographic feature data is divided into training and testing sets, for example, by random sampling, hierarchical sampling methods.

Specifically, for example, a cyclic neural network (RNN) model, such as a long and short term memory network (LSTM) or a gated cyclic unit (GRU), may be constructed for processing time series data, and iteratively training the RNN model using training hydrologic feature data to find optimal network parameters.

Specifically, an iterative error fit is performed on the primary estuary model evaluation classifier, for example, using test hydrographic feature data. This can be achieved by calculating the prediction error of the classifier on the test set and optimizing based on the error. For example, the model parameters are updated using a gradient descent method, an Adam optimizer method.

；

The invention utilizes an optimized hydrologic characteristic data loss calculation formula, and the first formulaWeather condition fitting value corresponding to individual hydrologic characteristic prediction data +.>By incorporating weather condition factors into the loss calculation, the adaptation of the model to environmental changes is improved, scaling factor +.>The relative importance of each item in the loss function is adjusted to help balance the fitting degree and generalization capability of the model, and the hydrologic characteristic data loss error item +. >Measuring the difference between the predicted result and the actual data, contributing to the prediction capability of the quantization model, and adjusting the coefficient by the regularization coefficient +.>For adjusting the weight of the gap between the predicted adjustment term and the actual adjustment term in the loss function. This helps to prevent model overfitting, improve generalization ability of the model, +.>Weight coefficient of personal hydrologic characteristic prediction data +.>First->Weight coefficient of personal hydrologic characteristic actual data +.>Respectively->Weight coefficients of the predicted data and the actual data of the individual hydrologic features, which represent the importance of the individual hydrologic features in the loss calculation, th ∈>Individual predictive adjustment items->First->Individual actual adjustment items->Representing the adjustment between the predicted result and the actual data, the accuracy of the model predicted result can be further improved by optimizing these adjustment terms, and the correction term of the predicted data loss value by the hydrologic feature +.>And carrying out loss correction to optimize loss calculation.

Preferably, step S4 is specifically:

specifically, for example, according to a two-dimensional sediment mathematical model of the estuary bay, a method such as an average distribution method and a maximum gradient method is used for selecting a preset number of sections.

More importantly, for example, the number of selected sections is acquired, hydrologic gradient calculation is performed according to the estuary bay hydrologic data, so that an estuary bay gradient data set is obtained, the number of sections is selected according to the number of sections of the estuary bay gradient data set, so that a maximum gradient value section set is obtained, the maximum gradient value section set is sequentially subjected to relative distance inspection, relatively smaller maximum gradient value sections in the maximum gradient value section set smaller than a preset relative distance are deleted, and the next smallest maximum gradient value section is selected from the rest estuary bay gradient data sets and added to the maximum gradient value section set.

Specifically, the selected section is monitored, for example, using a remote sensing device, such as an unmanned aerial vehicle, satellite remote sensing system, or the like. And acquiring hydrological data of the section of the estuary bay, such as single wide flow velocity data of the section along the journey, section water depth data and section sand content data through remote sensing image analysis.

Preferably, step S5 is specifically:

specifically, for example, a single-wide flow calculation formula q=v×h is used, where Q is a single-wide flow, V is a section along-flow velocity, and H is a section water depth.

specifically, for example, a single wide quicksand calculation formula qs=q×c is used, where Qs is the section along-the-path single wide quicksand amount, Q is the single wide flow amount, and C is the section sand content.

The single-wide flow calculation formula specifically comprises:

；

the single wide quicksand calculation formula specifically comprises:

；

Preferably, step S6 is specifically:

specifically, for example, the single wide flow rate and the single wide flow sand amount data of n sections are counted, added and divided by n to obtain the section single wide flow rate average value data and the section single wide flow sand amount average value data.

specifically, for example, the single-width flow data of each section is checked one by one, and compared with the section single-width flow mean data.

specifically, for example, if the single-wide flow data of a certain section is larger than the single-wide flow mean data of the section, the section is recorded as the larger single-wide flow zone bit data.

specifically, for example, single-width quicksand volume data of each section is checked one by one, and compared with section single-width quicksand volume average data.

Specifically, for example, if the single wide quicksand volume data of a certain section is larger than the single wide quicksand volume mean value data of the section, the section is recorded as the larger single wide quicksand volume zone bit data.

preferably, step S7 is specifically:

Specifically, for example, GIS software or map visualization tools are used to longitudinally connect the left and right boundaries of the larger single-width traffic zone location data to generate the left and right edges of the main tidal current channel.

specifically, for example, the left side line and the right side line of the main tide channel on the electronic map are used to mark the area between them as the main tide channel of the estuary and the bay.

specifically, for example, GIS software or map visualization tools are used to longitudinally connect the left and right boundaries of the larger single-width quicksand region location data to generate left and right lines of the sand conveyance main channel.

Specifically, for example, the left and right lines of the main sand conveying channel on the electronic map are used to mark the area between them as the main sand conveying channel of the estuary and the bay.

Preferably, the steps following step S7 include the steps of:

specifically, for example, a machine learning algorithm (such as a support vector machine, a decision tree, a random forest, etc.) or a deep learning method (such as a convolutional neural network, a cyclic neural network, etc.) is used to construct a prediction model for simulating the siltation process of the estuary bay by combining the data of the estuary bay tide main channel and the estuary bay sand transporting main channel.

Specifically, for example, real-time or historical estuary bay hydrologic data is input into a siltation model, and a bed siltation condition is predicted, thereby generating estuary bay bed siltation data.

Specifically, for example, according to the estuary bay riverbed siltation data, a siltation area needing to be cleaned is identified, a basis is provided for maintenance of an estuary bay main channel, and meanwhile, a corresponding cleaning strategy and scheme are formulated, so that the estuary bay main channel cleaning data is finally generated.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The method for defining the main channel of tidal current sediment in the estuary bay is characterized by comprising the following steps of:

step S1, including:

the estuary bay hydrologic complexity formula is specifically:

；

for the hydrologic complexity of estuary bay +.>For estuary bay area data, < > for>For estuary bay river bank bending index data, +.>For the circumference of estuary bay>For average section flow of estuary bay>For average depth of estuary bay->Depth variation for estuary bay hydrological data, +.>For the average distance corresponding to the depth variation of the estuary bay hydrological data, ++>Is the influence coefficient of the depth variation degree of estuary bay, and is +.>For the influence coefficient of the average steering, +.>For the average steering variation on the central line of estuary bay, < ->Is the influence coefficient of the gradient change of the river bed, < ->Is the gradient change of the river bed on the central line of the estuary bay>A correction term for the hydrologic complexity of the estuary bay;

step S17: performing sediment transfer calculation according to a suitable hydrodynamic equation of the estuary bay and sediment characteristic data in the estuary bay hydrological data, so as to obtain sediment transfer process data, and constructing a primary estuary bay two-dimensional sediment mathematical model;

step S4: selecting a section according to a two-dimensional sediment mathematical model of the secondary estuary bay so as to obtain selected section data, and obtaining section data according to the selected section data so as to obtain estuary bay section hydrologic data, wherein the estuary bay section hydrologic data comprise section along-path single-width flow velocity data, section water depth data and section sand content data;

step S6, including:

respectively carrying out average value calculation on the section along-process single-width flow data and the section along-process single-width sand flow data so as to obtain section single-width flow average value data and section single-width sand flow average value data;

sequentially comparing the section along-process single-width flow data corresponding to the estuary bay section hydrological data with section single-width flow average data;

when the cross section along-process single-wide flow data corresponding to the estuary bay cross section hydrological data is determined to be larger than the cross section single-wide flow mean value data, determining the corresponding estuary bay cross section hydrological data as larger single-wide flow zone location data;

sequentially comparing the single-width flow sand data of the section along the process corresponding to the hydrographic data of the section of the estuary bay with the single-width flow sand mean value data of the section;

when the section along-process single-width quicksand data corresponding to the estuary section hydrological data is determined to be larger than the section single-width quicksand mean value data, determining the corresponding estuary section hydrological data as larger single-width quicksand volume position data;

step S7, including:

longitudinally connecting a left boundary and a right boundary of the large single wide flow zone bit data on a preset electronic map respectively, so as to obtain a left line of the main tide channel and a right line of the main tide channel;

Dividing the left side line of the main tidal current channel and the right side line of the main tidal current channel on a preset electronic map so as to generate a main tidal current channel of the estuary and the bay;

longitudinally connecting a left boundary and a right boundary of larger single-width quicksand region position data on a preset electronic map respectively, so as to obtain a left line of a sand conveying main channel and a right line of the sand conveying main channel;

dividing the left line of the main sand conveying channel and the right line of the main sand conveying channel on a preset electronic map so as to generate the main sand conveying channel of the estuary and the bay.

2. The method according to claim 1, wherein the historical hydrographic data includes estuary bay hydrographic image data and estuary bay historical hydrographic data, and the step S2 of obtaining the historical hydrographic data and performing depth calculation using the historical hydrographic data, thereby constructing an estuary bay model evaluation classifier is specifically:

performing time sequence extraction according to the estuary bay hydrological image data so as to obtain estuary bay hydrological time sequence image data;

sequentially extracting ripple characteristics from the hydrological time sequence image data of the estuary bay so as to obtain ripple characteristic data;

performing error correlation according to ripple feature data of the hydrological time sequence image data and ripple feature data of the corresponding next hydrological time sequence image data, so as to obtain correlated ripple feature data;

Calculating according to the associated ripple characteristic data through an associated ripple calculation formula, so as to obtain historical flow rate data;

the associated ripple calculation formula specifically comprises:

；

for historical flow data>For data total number data->Is->The weight coefficients of the associated ripple feature data,is->Individual associated ripple characteristic data,/>Is->Weight coefficient of each associated ripple feature data, +.>Is->Individual associated ripple characteristic data,/>To generate adjustment coefficients based on the associated ripple and estuary bay water depth data->For periodic items +.>For the phase coefficient +.>For average error adjustment term, +.>Error adjustment term for central ripple generated from ripple characteristic data +.>A correction term for the historical flow rate data;

performing gridding according to the historical hydrologic data and the historical flow rate data, so as to obtain gridded hydrologic data;

extracting features according to the gridded hydrological data, so as to obtain locally associated hydrological feature data;

and carrying out depth modeling on the locally-associated hydrologic characteristic data so as to construct an estuary bay model evaluation classifier.

3. The method according to claim 2, wherein the step of depth modeling is specifically:

Dividing according to the locally associated hydrologic feature data so as to obtain training hydrologic feature data and test hydrologic feature data;

constructing a hydrologic cycle neural network model, and performing iterative training on the hydrologic cycle neural network model by utilizing training hydrologic characteristic data, so as to construct a primary estuary bay model evaluation classifier;

and performing iterative error fitting on the primary estuary model evaluation classifier by using the test hydrologic characteristic data, so as to obtain the estuary model evaluation classifier.

4. A method according to claim 3, wherein the iterative error is calculated by optimizing a hydrologic characteristic data loss calculation formula, wherein the optimized hydrologic characteristic data loss calculation formula is specifically:

；

predicting data loss values for hydrologic features, +.>Data quantity +.>Is->Weight coefficient of individual hydrologic feature prediction data, < ->Is->Weather condition fitting value corresponding to the individual hydrologic characteristic prediction data,/->Is->Personal hydrologic characteristic prediction data,/->Is->Weight coefficient of individual hydrologic characteristic actual data, < ->Is->Personal hydrologic characteristic actual data,/->For the hydrologic data error adjustment term, +.>For scaling factor +. >Loss of error term for hydrographic feature data, +.>Adjusting coefficients for regularization coefficients,/->Is->Predictive adjustment item->Is->Actual adjustment item->And predicting a correction term of the data loss value for the hydrologic characteristic.

5. The method according to claim 1, wherein step S4 is specifically:

6. The method according to claim 1, wherein step S5 is specifically:

the single-wide flow calculation formula specifically comprises:

；

the single wide quicksand calculation formula specifically comprises:

；

for the data of the single wide sand flow of the section along the way, < + > >For the data of the section along-the-way single wide flow rate, +.>Is section sand content data.

7. The method according to claim 1, characterized in that the steps following step S7 comprise the steps of: