Flood forecasting method and system, computer and storage medium

Abstract

The invention provides a flood forecasting method and system, a computer and a storage medium, and the method comprises the following steps: constructing a Markov logic network of domain knowledge having influence on rainfall runoff, and mining a driving factor set of rainfall runoff change; according to the driving factor set, constructing a process-driven hydrological model based on a basin rainfall runoff relation change rule; establishing an ensemble flood forecasting model; and performing parameter optimization on the ensemble flood forecasting model based on a swarm intelligence algorithm. By mining direct driving factors and indirect driving factors, accurate analysis of driving factors of rainfall runoff changes is realized, a basin rainfall runoff relation change rule is disclosed, a process-driven hydrological model is guided and constructed based on the rainfall runoff relation change rule, and a process-driven hydrological model is established by means of a set correlation theory. Combining the process-driven hydrological model with other hydrological models to construct a refined ensemble flood forecasting model; based on a swarm intelligence algorithm, model parameters and weights are optimized, the flood forecasting precision is improved, and the forecast period is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of flood forecasting, and in particular to a flood forecasting method, system, computer and storage medium. Background Art

[0002] Prediction using hydrological models is a common method for flood forecasting. The current hydrological models mainly include process-driven models and data-driven models. Process-driven models have clear physical mechanisms, such as the Xinanjiang model, TOPMODEL, and Sacramento model. Data-driven models are mostly black box models, which aim to establish the optimal mathematical relationship between input and output data and have no clear physical mechanism. Common data-driven models include neural network models, regression analysis models, and gray system models.

[0003] Since hydrological models face difficulties such as initial value errors, model errors, chaotic characteristics, parameter uncertainty and spatial variation of the underlying surface, various hydrological models have certain limitations in flood forecasting practice, resulting in low forecast accuracy. Summary of the invention

[0004] In view of the deficiencies in the prior art, the object of the present invention is to provide a flood forecasting method, system, computer and storage medium, aiming to solve the technical problem of low forecasting accuracy in the prior art.

[0005] In order to achieve the above object, in a first aspect, the present invention provides a flood forecasting method, comprising the following steps: Constructing a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and constructing a Markov logic network based on the first-order predicate knowledge base and the Markov network, thereby mining a set of driving factors of rainfall runoff changes according to the Markov logic network; According to the set of driving factors, a process-driven hydrological model based on the changing law of rainfall-runoff relationship in the watershed is constructed; Establishing an ensemble flood forecasting model including several hydrological models and the process-driven hydrological model; The following optimization model is established based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecasting model with the absolute error and minimum of the actual observation value as the goal: ; ; ; In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

[0006] According to one aspect of the above technical solution, the step of mining a set of driving factors of rainfall runoff change according to the Markov logic network specifically includes: Mining the direct driving factors of rainfall-runoff changes based on the Markov logic network; Based on the Markov logic network, combined with the basin big data, basin characteristic factor library and the first-order predicate knowledge base, the indirect driving factors of rainfall runoff changes are mined; The mined indirect driving factors are represented by first-order predicates, stored in a first-order predicate knowledge base, and the Markov logic network is updated; The above steps of mining indirect driving factors are repeated until there are no new indirect driving factors, and finally a driving factor set including the direct driving factors and indirect driving factors is obtained.

[0007] According to one aspect of the above technical solution, the potential function corresponding to the joint probability distribution of the Markov network is: , ; In the formula, , is the set of c-dimensional driving factors, , is the state value taken by variable X, is the potential function of the g-th group, is the state value of all variables in the g-th group, Z is the normalization factor, and v is the number of groups.

[0008] According to one aspect of the above technical solution, the steps of mining the indirect driving factors of rainfall runoff changes specifically include: The Gibbs method is used to sample the basin big data and the basin characteristic factors in the basin characteristic factor library to explore the indirect driving factors of rainfall runoff changes.

[0009] According to one aspect of the above technical solution, the calculation expression of the process quantity is as follows: ; In the formula, Indicates The number of parameters contained in the procedure.

[0010] In a second aspect, the present application also provides a flood forecasting system, comprising: A mining module is used to construct a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and to construct a Markov logic network based on the first-order predicate knowledge base and the Markov network, so as to mine a set of driving factors of rainfall runoff changes according to the Markov logic network; A process-driven module, used for constructing a process-driven hydrological model based on the variation law of rainfall-runoff relationship in the basin according to the set of driving factors; An ensemble forecasting module, used to establish an ensemble flood forecasting model including a plurality of hydrological models and the process-driven hydrological model; The optimization module is used to establish the following optimization model based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecasting model with the absolute error and minimum of the actual observation value as the goal: ; ; ; In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

[0011] According to one aspect of the above technical solution, the mining module specifically includes: A direct driving factor unit, used for mining direct driving factors of rainfall-runoff changes according to the Markov logic network; An indirect driving factor unit is used to mine indirect driving factors of rainfall runoff changes based on the Markov logic network, combined with the basin big data, the basin characteristic factor library and the first-order predicate knowledge base; An updating unit, used for performing first-order predicate representation on the mined indirect driving factors, storing them in a first-order predicate knowledge base, and updating the Markov logic network; The driver set unit is used to repeat the above steps of mining indirect driver factors until there are no new indirect driver factors, and finally obtain a driver set including the direct driver factors and indirect driver factors.

[0012] According to one aspect of the above technical solution, the indirect driving factor unit is specifically used for: The Gibbs method is used to sample the basin big data and the basin characteristic factors in the basin characteristic factor library to explore the indirect driving factors of rainfall runoff changes.

[0013] In a third aspect, an embodiment of the present application provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a flood forecasting method as described in the first aspect is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements a flood forecasting method as described in the first aspect.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: through the domain knowledge of experts, a first-order predicate knowledge base is constructed, a Markov logic network is constructed, and direct driving factors are mined; the obtained Markov logic network is used to combine the basin big data, the basin characteristic factor library and the first-order predicate knowledge base to mine indirect driving factors, and the mined driving factors are represented by first-order predicates, stored in the first-order predicate knowledge base, and the Markov logic network is updated, and the second part is repeated until no new indirect driving factors are found, and the search process ends, and the final direct and indirect driving factors are represented by knowledge, so as to achieve accurate analysis of the driving factors of rainfall-runoff changes, reveal the changing law of the relationship between rainfall and runoff in the basin, guide and construct a process-driven hydrological model based on the changing law of the relationship between rainfall and runoff, and use the set correlation theory to combine the process-driven hydrological model with other hydrological models to construct a refined ensemble flood forecasting model; based on the swarm intelligence algorithm, the model parameters and weights are optimized to improve the accuracy of flood forecasting and extend the forecast period. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the flood forecasting method in the first embodiment of the present invention; Figure 2 It is a structural block diagram of a flood forecasting system in a second embodiment of the present invention; Figure 3 is a schematic diagram of the hardware structure of a computer in the third embodiment of the present application; The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0017] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0018] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0020] Embodiment 1 See also Figure 1 , which is a flood forecasting method in a first embodiment of the present invention, comprising the following steps: Step S100, constructing a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and constructing a Markov logic network based on the first-order predicate knowledge base and the Markov network, thereby mining a set of driving factors of rainfall runoff changes according to the Markov logic network.

[0021] Specifically, in this embodiment, the step of mining the set of driving factors of rainfall runoff change according to the Markov logic network specifically includes: Step S110, mining direct driving factors of rainfall runoff changes according to the Markov logic network.

[0022] Step S120, based on the Markov logic network, combined with the basin big data, the basin characteristic factor library and the first-order predicate knowledge base, the indirect driving factors of rainfall runoff changes are mined. Specifically, the basin characteristic factor library refers to multiple basin characteristic factors extracted from the basin big data, including hydrological multi-factors composed of runoff monitoring, radar rainfall measurement, DEM (digital elevation model) and soil vegetation, remote sensing images, etc. of similar basins, as well as basic information such as social economy, water resources scheduling plans, previous flood control and disaster relief plans, and basin geographical characteristics. The corresponding basin characteristic factors can be extracted from the basin big data through the feature extraction algorithm, thereby constructing a basin characteristic factor library.

[0023] Step S130 , performing first-order predicate representation on the mined indirect driving factors, storing them in a first-order predicate knowledge base, and updating the Markov logic network.

[0024] Step S140, repeating the above steps of mining indirect driving factors until there are no new indirect driving factors, and finally obtaining a driving factor set including the direct driving factors and the indirect driving factors.

[0025] In view of the big data of watershed, the statistical relationship learning method of Markov Logic Networks (MLNs) is introduced into big data analysis to analyze the changes in the relationship between rainfall and runoff in the watershed and its driving factors. Markov logic network is a statistical relationship learning method that combines relationship representation, likelihood reasoning and machine learning. It consists of two parts: first-order predicate and Markov network.

[0026] The driving factors are divided into two categories: direct driving factors and indirect driving factors, and are processed in two stages: in the first stage, a first-order predicate knowledge base is constructed through the domain knowledge of experts, a Markov logic network is constructed, and direct driving factors are mined; in the second stage, the obtained Markov logic network is used to combine the basin big data, the basin characteristic factor library and the first-order predicate knowledge base to mine indirect driving factors, and the mined driving factors are represented by first-order predicates, stored in the first-order predicate knowledge base, and the Markov logic network is updated. The second part is repeated until no new indirect driving factors are found, the search process ends, and the final direct and indirect driving factors are represented by knowledge.

[0027] For ease of understanding, considering the complexity of changes in the rainfall-runoff relationship, and in order to clearly describe the changes in the rainfall-runoff relationship in a watershed and the driving factors, this embodiment takes the geographical attributes of the watershed (including watershed area, river bifurcation ratio, river network density, watershed length, watershed slope, watershed elevation, watershed shape, etc.) as an example for description, and the influence of other attributes on the rainfall-runoff relationship can be generalized accordingly.

[0028] Phase 1: The domain knowledge of experts in fields such as hydrology mainly includes the geographical location of the basin (determining whether the basin is a humid basin, arid basin, or semi-humid and semi-arid basin, etc.), climate conditions, rock and soil properties, geological structure, topography and vegetation distribution, etc., and related hydrological models, such as the water volume and energy conservation in the water cycle. Based on the domain knowledge, a first-order predicate knowledge base is constructed. The first-order predicate knowledge base consists of several first-order predicate rules. The first-order predicate rules consist of four types of symbols, namely constants, variables, functions, and predicates. For example, suppose and represent the watershed area and watershed slope respectively. , and are predicates, indicating that the basin area is related to the change of rainfall-runoff relationship, the basin area is not related to the change of rainfall-runoff relationship, and the basin area and basin slope have a dual driving relationship on rainfall-runoff.

[0029] Construct a Markov logic network. A Markov logic network is Dimension variables The joint distribution model of and defined in A set of potential functions on Based on the basin characteristic factor library and the first-order predicate knowledge base, a random field of basin rainfall-runoff relationship changes affected by basin geographical attributes is constructed. .in, The basin geographical attributes that drive changes in rainfall-runoff relationships, such as basin area, river bifurcation ratio, river network density, basin length, basin slope, basin elevation, basin shape, etc. Driving factors and There is a mutual correlation between them, forming a connecting edge For example, there is a correlation between the basin area and the basin length, which constitutes an undirected graph .like If any two nodes in a subgraph are connected by an edge, the subgraph is called a complete subgraph, and the largest complete subgraph is called a clique, denoted by ,in , v is The number of clusters in the non-negative real function About the group The potential function of The potential function set is recorded as .

[0030] The joint probability distribution of a Markov network is determined by the potential function values ​​of all groups in the network: , ; In the formula, , is the set of c-dimensional driving factors, , is the state value taken by variable X, is the potential function of the g-th group, is the state value of all variables in the g-th group, Z is the normalization factor, , v is the number of groups.

[0031] Phase 2: Since the change of rainfall-runoff relationship in the basin involves various data such as meteorology, water conservancy, industry and agriculture, ecology, etc., more driving factors cannot be directly obtained through the domain knowledge of experts. Under the guidance of the first-order predicate knowledge base, with the help of the basin characteristic factor library, the Gibbs sampling technology is used to sample the basin big data, and the newly obtained indirect driving factors are represented as first-order predicate forms, stored in the first-order predicate knowledge base, and the Markov logic network is updated. Repeat the second phase until no new indirect driving factors are found, store the final direct and indirect driving factors in the influencing factor library, update the rainfall-runoff relationship changes, and the search process ends.

[0032] Regarding the optimization of the parameters of driving factors’ influence degree: From the potential function expression, we can know that represents the potential function state of the g-th group, represents the weight of the group, that is, the influence of each driving factor on the change of rainfall-runoff relationship in the basin. Parameter learning is an important research topic in the Markov logic network system. In the Markov network, Gibbs Sampling (GS) is used to sample the basin big data and basin characteristic factors.

[0033] Characterization of the changing law of rainfall-runoff relationship: The final step of mining the changing law of rainfall-runoff relationship is the knowledge representation of the changing law of rainfall-runoff relationship. Starting from the definition of Markov logic network, it is easy to get a graph structure: when the closed atoms represented by two nodes appear in the same closed rule, there is an edge between the two nodes. The background grid is an organizational form of the formal background, reflecting the implicit relationship between the formal background. This embodiment adopts a method based on the background grid to represent knowledge.

[0034] Step S200: constructing a process-driven hydrological model based on the variation law of rainfall-runoff relationship in the watershed according to the set of driving factors.

[0035] By obtaining the above-mentioned driving factor set, namely direct driving factors and indirect driving factors, the evolution mechanism of water cycle in the basin and the changing laws of rainfall-runoff relationship in the basin are revealed. These laws can guide the selection of process-driven models and the calibration of model parameters. The above-mentioned process-driven hydrological models are conventional hydrological models selected and guided based on the above-mentioned driving factor set, such as Xinanjiang model, TOPMODEL, Sacramento model, etc.

[0036] Step S300, establish an ensemble flood forecasting model including several hydrological models and the process driven hydrological model. The above hydrological model can be selected according to the basin attributes, etc. Taking a semi-humid basin as an example, the Xinanjiang model, TOPMODEL, Sacramento model, super-seepage runoff model, etc. can be selected.

[0037] Since hydrological models face difficulties such as initial value errors, model errors, chaotic characteristics, parameter uncertainties, and spatial variation of the underlying surface, there are certain limitations if a single hydrological model is used in flood forecasting practice.

[0038] The idea of ​​ensemble forecasting originated in the field of meteorology. It combines the results of different models to produce more stable and reliable forecast results. Common methods of ensemble forecasting include simple averaging, weighted averaging, and Bayesian model averaging. The processing process of simple averaging and weighted averaging is too simple, and the ensemble forecasting effect is not obvious; the learning process of Bayesian model averaging is complex, the parameter solution efficiency is low, and the parameter optimization results are significantly affected by redundant samples. To solve the above problems, this scheme obtains the changing law of the relationship between rainfall and runoff in the basin, selects multiple hydrological models suitable for the basin to be studied, and constructs a refined ensemble flood forecasting model with the help of ensemble correlation theory; the swarm intelligence algorithm optimizes the model parameters and weights to improve the accuracy of flood forecasts and extend the forecast period, as follows: Step S400, establish the following optimization model based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecast model with the absolute error and minimum of the actual observation value as the goal: ; ; ; In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

[0039] The above optimization problem is a typical constrained optimization problem. Traditional methods for solving constrained optimization problems, such as Lagrange multiplier method, penalty function method, Bayesian method and neural network method, often take too long or fail to achieve the required accuracy when solving this problem. Introducing swarm intelligence algorithm into the solution of this constrained optimization problem can optimize the weights in the flood forecasting model and the quality of the model parameter calibration, thereby improving the accuracy of flood forecasting and extending the forecast period.

[0040] In summary, the flood forecasting method in the above embodiment of the present invention constructs a first-order predicate knowledge base and a Markov logic network through the domain knowledge of experts to mine direct driving factors; uses the obtained Markov logic network, combines the basin big data, the basin characteristic factor library and the first-order predicate knowledge base to mine indirect driving factors, and represents the mined driving factors with first-order predicates, stores them in the first-order predicate knowledge base, updates the Markov logic network, and repeats the second part until no new indirect driving factors are found, the search process ends, and the final direct and indirect driving factors are represented by knowledge to achieve accurate analysis of the driving factors of rainfall-runoff changes, reveal the changing law of the relationship between rainfall and runoff in the basin, guide and construct a process-driven hydrological model based on the changing law of the relationship between rainfall and runoff, and use the set correlation theory to combine the process-driven hydrological model with other hydrological models to construct a refined ensemble flood forecasting model; optimizes model parameters and weights based on swarm intelligence algorithms to improve flood forecast accuracy and extend the forecast period.

[0041] Embodiment 2 The second embodiment of the present application also provides a flood forecasting system, which is used to implement the embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the terms "module", "unit", "subunit" and the like can implement a combination of software and / or hardware of a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0042] like Figure 2 As shown, the system includes: a mining module 100, a process driving module 200, an ensemble forecasting module 300 and an optimization module 400; The mining module 100 is used to construct a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and to construct a Markov logic network based on the first-order predicate knowledge base and the Markov network, so as to mine a set of driving factors of rainfall runoff changes according to the Markov logic network; A process-driven module 200 is used to construct a process-driven hydrological model based on the change law of the rainfall-runoff relationship in the basin according to the set of driving factors; An ensemble forecasting module 300 is used to establish an ensemble flood forecasting model including a plurality of hydrological models and the process-driven hydrological model; The optimization module 400 is used to establish the following optimization model based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecasting model with the absolute error and minimum of the actual observation value as the goal: ; ; ; In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

[0043] Preferably, in this embodiment, the mining module 100 specifically includes: A direct driving factor unit, used for mining direct driving factors of rainfall-runoff changes according to the Markov logic network; An indirect driving factor unit is used to mine indirect driving factors of rainfall runoff changes based on the Markov logic network, combined with the basin big data, the basin characteristic factor library and the first-order predicate knowledge base; An updating unit, used for performing first-order predicate representation on the mined indirect driving factors, storing them in a first-order predicate knowledge base, and updating the Markov logic network; The driver set unit is used to repeat the above steps of mining indirect driver factors until there are no new indirect driver factors, and finally obtain a driver set including the direct driver factors and indirect driver factors.

[0044] Preferably, in this embodiment, the above-mentioned indirect driving factor unit is specifically used for: The Gibbs method is used to sample the basin big data and the basin characteristic factors in the basin characteristic factor library to explore the indirect driving factors of rainfall runoff changes.

[0045] It should be noted that each module can be a functional module or a program module, and can be implemented by software or hardware. For modules implemented by hardware, each module can be located in the same processor; or each module can be located in different processors in any combination.

[0046] Embodiment 3 The third embodiment of the present application provides a computer. It can be understood that the principles mentioned in the flood forecasting system in this embodiment correspond to the flood forecasting method in the first embodiment of the present application. For details of the relevant principles not described, please refer to the first embodiment and will not be elaborated here.

[0047] The computer may include a processor 81 and a memory 82 storing computer program commands.

[0048] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0049] Among them, the memory 82 may include a large-capacity memory for data or commands. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0050] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program commands executed by the processor 81 .

[0051] The processor 81 implements any one of the flood forecasting methods in the above embodiments by reading and executing the computer program commands stored in the memory 82 .

[0052] In some embodiments, the computer may further include a communication interface 83 and a bus 80. Figure 3 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0053] The communication interface 83 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication interface 83 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0054] The bus 80 includes hardware, software or both, and couples the components of the computer to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0055] Embodiment 4 In combination with the flood forecasting method in the above embodiments, the fourth embodiment of the present application provides a readable storage medium having computer program commands stored thereon; when the computer program commands are executed by a processor, any one of the flood forecasting methods in the above embodiments is implemented.

[0056] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A flood forecasting method, characterized in that: The following steps are involved: Constructing a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and constructing a Markov logic network based on the first-order predicate knowledge base and the Markov network, thereby mining a set of driving factors of rainfall runoff changes according to the Markov logic network; According to the set of driving factors, a process-driven hydrological model based on the changing law of rainfall-runoff relationship in the watershed is constructed; Establishing an ensemble flood forecasting model including several hydrological models and the process-driven hydrological model; The following optimization model is established based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecasting model with the absolute error and minimum of the actual observation value as the goal: ； ； ； In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

2. The flood forecasting method according to claim 1, characterized in that: The steps of mining the set of driving factors of rainfall runoff change according to the Markov logic network specifically include: Mining the direct driving factors of rainfall-runoff changes based on the Markov logic network; Based on the Markov logic network, combined with the basin big data, basin characteristic factor library and the first-order predicate knowledge base, the indirect driving factors of rainfall runoff changes are mined; The mined indirect driving factors are represented by first-order predicates, stored in a first-order predicate knowledge base, and the Markov logic network is updated; The above steps of mining indirect driving factors are repeated until there are no new indirect driving factors, and finally a driving factor set including the direct driving factors and indirect driving factors is obtained.

3. The flood forecasting method according to claim 2, characterized in that: The potential function corresponding to the joint probability distribution of the Markov network is: ， ； In the formula, , is the set of c-dimensional driving factors, , is the state value taken by variable X, is the potential function of the g-th group, is the state value of all variables in the g-th group, Z is the normalization factor, and v is the number of groups.

4. The flood forecasting method according to claim 3, characterized in that: The steps to explore the indirect drivers of rainfall-runoff changes include: The Gibbs method is used to sample the basin big data and the basin characteristic factors in the basin characteristic factor library to explore the indirect driving factors of rainfall runoff changes.

5. The flood forecasting method according to claim 1, characterized in that: The calculation expression of the process quantity is as follows: ； In the formula, Indicates The number of parameters contained in the procedure.

6. A flood forecasting system, characterized in that: include: A mining module is used to construct a first-order predicate knowledge base of domain knowledge that affects rainfall runoff, and to construct a Markov logic network based on the first-order predicate knowledge base and the Markov network, so as to mine a set of driving factors of rainfall runoff changes according to the Markov logic network; A process-driven module, used for constructing a process-driven hydrological model based on the variation law of rainfall-runoff relationship in the basin according to the set of driving factors; An ensemble forecasting module, used to establish an ensemble flood forecasting model including a plurality of hydrological models and the process-driven hydrological model; The optimization module is used to establish the following optimization model based on the swarm intelligence algorithm to optimize the parameters of the ensemble flood forecasting model with the absolute error and minimum of the actual observation value as the goal: ； ； ； In the formula, is the rth actual observation value output by the model, L is the number of actual observation values, is the weight of the i-th hydrological model in the ensemble flood forecasting model, is the weight of the sth process in the ith model, n is the number of hydrological models in the ensemble flood forecasting model, Represents the number of processes in the ith model.

7. The flood forecasting system according to claim 6, characterized in that: The mining module specifically includes: A direct driving factor unit, used for mining direct driving factors of rainfall-runoff changes according to the Markov logic network; An indirect driving factor unit is used to mine indirect driving factors of rainfall runoff changes based on the Markov logic network, combined with the basin big data, the basin characteristic factor library and the first-order predicate knowledge base; An updating unit, used for performing first-order predicate representation on the mined indirect driving factors, storing them in a first-order predicate knowledge base, and updating the Markov logic network; The driver set unit is used to repeat the above steps of mining indirect driver factors until there are no new indirect driver factors, and finally obtain a driver set including the direct driver factors and indirect driver factors.

8. The flood forecasting system according to claim 7, characterized in that: The indirect driving factor unit is specifically used for: The Gibbs method is used to sample the basin big data and the basin characteristic factors in the basin characteristic factor library to explore the indirect driving factors of rainfall runoff changes.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the flood forecasting method according to any one of claims 1 to 5 is implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the flood forecasting method as described in any one of claims 1 to 5 is implemented.

Images