WO2022032874A1 - Adversarial neural network-based hydrological parameter calibration method for data region - Google Patents

Adversarial neural network-based hydrological parameter calibration method for data region Download PDF

Info

Publication number
WO2022032874A1
WO2022032874A1 PCT/CN2020/123715 CN2020123715W WO2022032874A1 WO 2022032874 A1 WO2022032874 A1 WO 2022032874A1 CN 2020123715 W CN2020123715 W CN 2020123715W WO 2022032874 A1 WO2022032874 A1 WO 2022032874A1
Authority
WO
WIPO (PCT)
Prior art keywords
hydrological
parameters
neural network
data
adversarial neural
Prior art date
Application number
PCT/CN2020/123715
Other languages
French (fr)
Chinese (zh)
Inventor
李胜
张�荣
刘晟一
田彪
丁交亮
彭江江
刘继军
Original Assignee
贵州东方世纪科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 贵州东方世纪科技股份有限公司 filed Critical 贵州东方世纪科技股份有限公司
Publication of WO2022032874A1 publication Critical patent/WO2022032874A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the invention belongs to the hydrological parameter calibration technology, and in particular relates to a hydrological parameter calibration method based on an adversarial neural network in an area with data.
  • Hydrological models play an important role in the study of hydrological laws and in solving practical problems in production. With the rapid development of modern science and technology, information technology with computers and communications as the core is widely used in the fields of hydrology, water resources and hydraulic engineering. The research on hydrological models has developed rapidly, and is widely used in the study of basic hydrological laws, flood and drought disaster prevention, water resources evaluation and development and utilization, water environment and ecosystem protection, climate change and the analysis of the impact of human activities on water resources and water environment. and other fields. Therefore, it is of great scientific significance and application value to study how to improve the prediction accuracy of hydrological models.
  • the hydrological model needs to consider every link of the whole hydrological process of "precipitation - runoff - confluence", each link has many influencing factors, it is impossible to introduce every factor into the model arrived. Therefore, it is necessary to select these influencing factors to produce a certain prediction error.
  • the accuracy of the measured data and the size of the error are determined by the advanced and mature measurement technology, which affects the fitting degree of the model simulation, thereby affecting the prediction accuracy of the model.
  • These data include not only traditional hydrological (flow) meteorological (rainfall) data, but also factors such as geology, vegetation, soil and land use.
  • the parameters of the distributed hydrological model have clear physical meanings, and it is easy to estimate the variation range of the parameters, but it is difficult to determine the optimal value of the parameters.
  • the calibration of parameters is an important link to improve the prediction accuracy of hydrological models.
  • the parameter calibration of the hydrological model generally adopts the traditional trial-and-error method, that is, the parameter values of the hydrological model are continuously adjusted manually to meet the simulation accuracy requirements, but for the hydrological model without data
  • the calibration of model parameters, using this method has problems such as low calibration accuracy, which seriously affects the accuracy of hydrological forecasting.
  • the technical problem to be solved by the present invention is: to provide a method for calibrating hydrological parameters in areas with data based on an adversarial neural network, so as to solve the problem that the prior art adopts the traditional trial-and-error method for determining the parameters of the hydrological model of watersheds without data, that is, through The parameter values of the hydrological model are continuously adjusted manually to meet the requirements of simulation accuracy.
  • this method has problems such as low calibration accuracy, which seriously affects the accuracy of hydrological forecasting.
  • An adversarial neural network-based calibration method for hydrological parameters in areas with data which includes:
  • Step 1 Collect soil texture, vegetation coverage, land utilization, terrain data, runoff coefficient, total annual evaporation, gradient and slope data;
  • Step 2 Divide the calibration area into calculation units below 30 square kilometers;
  • Step 3 Determine the underlying surface and meteorological related factors of each parameter of each calculation unit according to the physical characteristics of the parameters of the hydrological model;
  • Step 4 The adversarial neural network GAN is used to automatically calibrate the hydrological parameters of the watershed with data.
  • the adversarial neural network GAN takes noise as the input, and optimizes the parameters through the hydrological model to obtain the optimal hydrological parameters for each unit.
  • the method for automatic calibration of hydrological parameters using the adversarial neural network GAN described in step 4 is:
  • Step 4.1 Generate samples with normally distributed noise as the input of the generator
  • Step 4.2 Input the generated sample set into the hydrological model for optimization to obtain the optimal parameters
  • Step 4.3 Input the optimal parameters output by the hydrological model and the samples generated by the generator to the discriminator to judge the true and false.
  • step 4.2 when the generated sample set is input into the hydrological model for optimization to obtain the optimal parameters, the deterministic coefficient is used as the optimization principle.
  • the invention divides the optimized area into countless independent computing units, and then uses the confrontation neural network GAN to automatically calibrate the hydrological parameters to realize the parameter calibration of the data area, so it can effectively solve the problem of the modern hydrological model due to its strong professionalism.
  • the resulting problem of difficulty in use can reduce a lot of tedious steps and work for professional manual parameter adjustment and calibration in practical applications.
  • the existing technology adopts the traditional trial and error method for the determination of the parameters of the hydrological model in the watershed with data, that is, the parameter values of the hydrological model are continuously adjusted manually to meet the simulation accuracy requirements.
  • Subjectivity, repetitive work, low efficiency and extremely high complexity which are not conducive to technical problems such as the application and promotion of hydrological models.
  • FIG. 1 is a schematic diagram of the automatic calibration process flow of the adversarial neural network GAN of the present invention for performing hydrological parameters on similar units.
  • An adversarial neural network-based calibration method for hydrological parameters in areas with data which includes:
  • Step 1 Collect soil texture, vegetation coverage, land utilization, terrain data, runoff coefficient, total annual evaporation, gradient and slope data;
  • Step 2 Divide the calibration area into calculation units below 30 square kilometers;
  • Step 3 Determine the underlying surface and meteorological related factors of each parameter of each calculation unit according to the physical characteristics of the parameters of the hydrological model;
  • Step 4 Use the adversarial neural network GAN to automatically calibrate the hydrological parameters of the watershed with data.
  • the adversarial neural network GAN takes noise as the input, and optimizes the parameters through the hydrological model to obtain the optimal hydrological parameters for each unit;
  • the method for automatic calibration of hydrological parameters using the adversarial neural network GAN described in step 4 is:
  • Step 4.1 Generate samples with normally distributed noise as the input of the generator
  • Step 4.2 Input the generated sample set into the hydrological model for optimization to obtain the optimal parameters
  • Step 4.3 Input the optimal parameters output by the hydrological model and the samples generated by the generator to the discriminator to judge the true and false.
  • step 4.2 when the generated sample set is input into the hydrological model for optimization to obtain the optimal parameters, the deterministic coefficient is used as the optimization principle.
  • GAN Generative Adversarial Networks
  • GAN The core idea of GAN comes from the Nash equilibrium of game theory. It sets the two parties involved as a generator and a discriminator. The purpose of the generator is to learn the real data distribution as much as possible, and the purpose of the discriminator is to discriminate as accurately as possible. Whether the input data comes from the real data or the generator; the two models need to be continuously optimized at the same time, each improving its own generating ability and discriminating ability, and the calculation is completed when the two reach a balance.
  • the certainty coefficient of the hydrological model can be seen to be improved from 0.78 in the initial stage to 0.86. It shows that the neural network can be used for the optimization of hydrological model parameters.
  • the deterministic coefficient is used as the optimization principle.
  • the learning ability of the deep learning network is quite strong.
  • the generated model can quickly converge to the range of the real sample. Since the real value also needs to be updated iteratively, it is extremely prone to overfitting problems, which directly lead to convergence. Slow or stuck in a local optimum.
  • the present invention solves these problems by using dormant local neurons, weight regularization, and adjustment of neuron data.
  • the core problem of the present invention is to find the optimal parameters of the data basin. Therefore, an optimal search strategy can be added to optimize the generated samples to improve the performance of the entire network.
  • the reason why the present invention adopts the adversarial neural network to derive the optimal parameters is that each iteration is generated by random changes in the best distribution space of the last time.

Abstract

An adversarial neural network-based hydrological parameter calibration method for a data region, comprising: collecting soil texture, vegetation coverage, a land utilization rate, topographic data, a runoff coefficient, total annual evaporation, and gradient and slope data; dividing a calibration region into computing units of less than 30 square kilometers; determining each underlying surface parameter of each computing unit and a meteorological related factor; and performing automatic calibration on hydrological parameters of a data watershed by using an adversarial neural network GAN to obtain an optimal hydrological parameter of each computing unit. The technical problems in the prior art such as the work is repetitive, the efficiency is low, the complexity is extremely high, and the application and popularization of a hydrologic model are not utilized are solved.

Description

一种基于对抗神经网络的有资料地区水文参数率定方法A method for calibration of hydrological parameters in areas with data based on adversarial neural network 技术领域technical field
本发明属于水文参数率定技术，尤其涉及一种基于对抗神经网络的有资料地区水文参数率定方法。The invention belongs to the hydrological parameter calibration technology, and in particular relates to a hydrological parameter calibration method based on an adversarial neural network in an area with data.
背景技术Background technique
水文模型在进行水文规律研究和解决生产实际问题中起着重要的作用，随着现代科学技术的飞速发展，以计算机和通信为核心的信息技术在水文水资源及水利工程科学领域的广泛应用，使水文模型的研究得到迅速发展，并广泛应用于水文基本规律研究、水旱灾害防治、水资源评价与开发利用、水环境和生态系统保护、气候变化及人类活动对水资源和水环境影响分析等领域。因此，研究如何提高水文模型的预测精度,具有重要的科学意义和应用价值。Hydrological models play an important role in the study of hydrological laws and in solving practical problems in production. With the rapid development of modern science and technology, information technology with computers and communications as the core is widely used in the fields of hydrology, water resources and hydraulic engineering. The research on hydrological models has developed rapidly, and is widely used in the study of basic hydrological laws, flood and drought disaster prevention, water resources evaluation and development and utilization, water environment and ecosystem protection, climate change and the analysis of the impact of human activities on water resources and water environment. and other fields. Therefore, it is of great scientific significance and application value to study how to improve the prediction accuracy of hydrological models.
任何模型均伴有误差和不确定性，模型建模工作中，误差源是大量的，其误差来源主要有以下几个方面：Any model is accompanied by errors and uncertainties. In the model modeling work, there are a large number of error sources, and the error sources mainly include the following aspects:
(1)被排除在外的因素引起的误差(1) Errors caused by excluded factors
在建模过程中，水文模型需要考虑“降水——产流——汇流”整个水文过程的每个环节，每个环节都有许多影响因子，把每个因子都引入到模型中是不可能做到的。所以要对这些影响因子有所选择产生一定的预测误差。In the modeling process, the hydrological model needs to consider every link of the whole hydrological process of "precipitation - runoff - confluence", each link has many influencing factors, it is impossible to introduce every factor into the model arrived. Therefore, it is necessary to select these influencing factors to produce a certain prediction error.
(2)实测历史记录资料的误差(2) The error of the measured historical record data
实测数据资料精度的高低、误差的大小决定于测量技术的先进和成熟程度，影响模型模拟的拟合度，从而影响模型的预测精度。这些资料不但包括传统的水文(流量)气象(降雨)资料，还包括地质、植被、土壤和土地利用等因素。The accuracy of the measured data and the size of the error are determined by the advanced and mature measurement technology, which affects the fitting degree of the model simulation, thereby affecting the prediction accuracy of the model. These data include not only traditional hydrological (flow) meteorological (rainfall) data, but also factors such as geology, vegetation, soil and land use.
(3)参数误差(3) Parameter error
分布式水文模型参数具有比较明确的物理意义，易于估计参数的变化范围，但是参数最优值难以确定。The parameters of the distributed hydrological model have clear physical meanings, and it is easy to estimate the variation range of the parameters, but it is difficult to determine the optimal value of the parameters.
(4)模型结构误差(4) Model structure error
在模型设计和建立过程中采用的不正确的计算方法，不合适的时间步长，不恰当的运行次序，不完整或有偏差的模型结构等都会引起模型预测误差。Incorrect calculation methods, inappropriate time steps, inappropriate running sequences, incomplete or biased model structures, etc. used in the model design and establishment process can all cause model prediction errors.
为了消除上述原因引起的模型预测误差，参数的率定是提高水文模型预测精度的一个重要环节，大部分的流域水文模型特别是中小流域的一些参数不能直接通过观测试验确定，它们的取值却与流域的下垫面特征有着一定的关系，但却不能与流域的下垫面特征建立起关系，所以对于流域水文模型来说参数的率定仍然是一个困难的问题。In order to eliminate the model prediction errors caused by the above reasons, the calibration of parameters is an important link to improve the prediction accuracy of hydrological models. Most of the watershed hydrological models, especially some parameters in small and medium-sized watersheds, cannot be directly determined through observation and experiments, and their values are not It has a certain relationship with the characteristics of the underlying surface of the watershed, but it cannot establish a relationship with the characteristics of the underlying surface of the watershed, so the calibration of parameters for the watershed hydrological model is still a difficult problem.
在现有技术中针对有资料流域具体应用时，水文模型的参数率定一般采用传统的试错法，即通过人工不断调整水文模型的参数值，以达到模拟精度要求，但是对于无资料的水文模型参数的率定，采用该方法就存在率定准确率低，严重影响水文预报精确度等问题。In the prior art for specific applications in watersheds with data, the parameter calibration of the hydrological model generally adopts the traditional trial-and-error method, that is, the parameter values of the hydrological model are continuously adjusted manually to meet the simulation accuracy requirements, but for the hydrological model without data The calibration of model parameters, using this method, has problems such as low calibration accuracy, which seriously affects the accuracy of hydrological forecasting.
发明内容SUMMARY OF THE INVENTION
本发明要解决的技术问题是：提供一种基于对抗神经网络的有资料地区水文参数率定方法，以解决以解决现有技术针对无资料流域水文模型参数确定采用传统的试错法，即通过人工不断调整水文模型的参数值，以达 到模拟精度要求，采用该方法存在率定准确率低，严重影响水文预报精确度等问题。The technical problem to be solved by the present invention is: to provide a method for calibrating hydrological parameters in areas with data based on an adversarial neural network, so as to solve the problem that the prior art adopts the traditional trial-and-error method for determining the parameters of the hydrological model of watersheds without data, that is, through The parameter values of the hydrological model are continuously adjusted manually to meet the requirements of simulation accuracy. However, this method has problems such as low calibration accuracy, which seriously affects the accuracy of hydrological forecasting.
本发明的技术方案是：The technical scheme of the present invention is:
一种基于对抗神经网络的有资料地区水文参数率定方法，它包括：An adversarial neural network-based calibration method for hydrological parameters in areas with data, which includes:
步骤1、采集土壤质地、植被覆盖度、土地利用率、地形数据、径流系数、年蒸发总量、比降和坡度数据；Step 1. Collect soil texture, vegetation coverage, land utilization, terrain data, runoff coefficient, total annual evaporation, gradient and slope data;
步骤2、将率定区域划分为30平方公里以下的计算单元；Step 2. Divide the calibration area into calculation units below 30 square kilometers;
步骤3、根据水文模型参数的物理特性，确定每一个计算单元每一个参数下垫面及气象相关因子；Step 3. Determine the underlying surface and meteorological related factors of each parameter of each calculation unit according to the physical characteristics of the parameters of the hydrological model;
步骤4、采用对抗神经网络GAN对有资料流域水文参数的自动率定，对抗神经网络GAN以噪声作为输入，通过水文模型进行参数优选，得到每个单元最优的水文参数。Step 4. The adversarial neural network GAN is used to automatically calibrate the hydrological parameters of the watershed with data. The adversarial neural network GAN takes noise as the input, and optimizes the parameters through the hydrological model to obtain the optimal hydrological parameters for each unit.
步骤3所述每一个参数下垫面及气象相关因子为：The underlying surface and weather-related factors of each parameter described in step 3 are:
Figure PCTCN2020123715-appb-000001
Figure PCTCN2020123715-appb-000001
Figure PCTCN2020123715-appb-000002
Figure PCTCN2020123715-appb-000002
步骤4所述采用对抗神经网络GAN进行水文参数的自动率定的方法为：The method for automatic calibration of hydrological parameters using the adversarial neural network GAN described in step 4 is:
步骤4.1、以正态分布的噪声作为生成器的输入生成样本；Step 4.1. Generate samples with normally distributed noise as the input of the generator;
步骤4.2、将生成的样本集输入到水文模型中进行优选得到最优参数；Step 4.2. Input the generated sample set into the hydrological model for optimization to obtain the optimal parameters;
步骤4.3、将水文模型输出的最优参数和生成器生成的样本输入到判别器的判别真假。Step 4.3: Input the optimal parameters output by the hydrological model and the samples generated by the generator to the discriminator to judge the true and false.
步骤4.2所述将生成的样本集输入到水文模型中进行优选得到最优参数时，是以确定性系数作为优选原则。In step 4.2, when the generated sample set is input into the hydrological model for optimization to obtain the optimal parameters, the deterministic coefficient is used as the optimization principle.
本发明有益效果：Beneficial effects of the present invention:
本发明将优化区域划分为无数个独立的计算单元，然后采用对抗神经网络GAN进行水文参数的自动率定，实现有资料地区的参数率定，因此可以有效的解决了现代水文模型由于专业性强导致的使用困难的问题，可以在实际应用中减少了大量的专业人工参数调整与率定的繁琐步骤和工作。为各类水文模型推广应用，解决了现有技术针对有资料流域水文模型参数确定采用传统的试错法，即通过人工不断调整水文模型的参数值，以达到模拟精度要求，采用该方法存在人为主观性，工作重复性、效率低和复杂度极高，不利用水文模型的应用推广等技术问题。The invention divides the optimized area into countless independent computing units, and then uses the confrontation neural network GAN to automatically calibrate the hydrological parameters to realize the parameter calibration of the data area, so it can effectively solve the problem of the modern hydrological model due to its strong professionalism. The resulting problem of difficulty in use can reduce a lot of tedious steps and work for professional manual parameter adjustment and calibration in practical applications. For the popularization and application of various hydrological models, it solves the problem that the existing technology adopts the traditional trial and error method for the determination of the parameters of the hydrological model in the watershed with data, that is, the parameter values of the hydrological model are continuously adjusted manually to meet the simulation accuracy requirements. Subjectivity, repetitive work, low efficiency and extremely high complexity, which are not conducive to technical problems such as the application and promotion of hydrological models.
附图说明：Description of drawings:
图1为本发明对抗神经网络GAN对相似单元进行水文参数的自动率定流程示意图。FIG. 1 is a schematic diagram of the automatic calibration process flow of the adversarial neural network GAN of the present invention for performing hydrological parameters on similar units.
具体实施方式detailed description
一种基于对抗神经网络的有资料地区水文参数率定方法，它包括：An adversarial neural network-based calibration method for hydrological parameters in areas with data, which includes:
步骤1、采集土壤质地、植被覆盖度、土地利用率、地形数据、径流系数、年蒸发总量、比降和坡度数据；Step 1. Collect soil texture, vegetation coverage, land utilization, terrain data, runoff coefficient, total annual evaporation, gradient and slope data;
步骤2、将率定区域划分为30平方公里以下的计算单元；Step 2. Divide the calibration area into calculation units below 30 square kilometers;
步骤3、根据水文模型参数的物理特性，确定每一个计算单元每一个参数下垫面及气象相关因子；Step 3. Determine the underlying surface and meteorological related factors of each parameter of each calculation unit according to the physical characteristics of the parameters of the hydrological model;
步骤4、采用对抗神经网络GAN对有资料流域水文参数的自动率定，对抗神经网络GAN以噪声作为输入，通过水文模型进行参数优选，得到每个单元最优的水文参数；Step 4. Use the adversarial neural network GAN to automatically calibrate the hydrological parameters of the watershed with data. The adversarial neural network GAN takes noise as the input, and optimizes the parameters through the hydrological model to obtain the optimal hydrological parameters for each unit;
步骤3所述每一个参数下垫面及气象相关因子为：The underlying surface and weather-related factors of each parameter described in step 3 are:
Figure PCTCN2020123715-appb-000003
Figure PCTCN2020123715-appb-000003
Figure PCTCN2020123715-appb-000004
Figure PCTCN2020123715-appb-000004
步骤4所述采用对抗神经网络GAN进行水文参数的自动率定的方法为：The method for automatic calibration of hydrological parameters using the adversarial neural network GAN described in step 4 is:
步骤4.1、以正态分布的噪声作为生成器的输入生成样本；Step 4.1. Generate samples with normally distributed noise as the input of the generator;
步骤4.2、将生成的样本集输入到水文模型中进行优选得到最优参数；Step 4.2. Input the generated sample set into the hydrological model for optimization to obtain the optimal parameters;
步骤4.3、将水文模型输出的最优参数和生成器生成的样本输入到判别器的判别真假。Step 4.3: Input the optimal parameters output by the hydrological model and the samples generated by the generator to the discriminator to judge the true and false.
步骤4.2所述将生成的样本集输入到水文模型中进行优选得到最优参数时，是以确定性系数作为优选原则。In step 4.2, when the generated sample set is input into the hydrological model for optimization to obtain the optimal parameters, the deterministic coefficient is used as the optimization principle.
对抗式生成网络(Generative Adversarial Networks,GAN)是生成 模型的一个子类，可以对现有数据样本的潜在分布进行估计，构建出可以符合数据分布的模型，并生成新的数据样本，并且模型具有一定的自学习能力，可以应用在半监督学习中。Generative Adversarial Networks (GAN) is a subclass of generative models, which can estimate the potential distribution of existing data samples, build a model that can conform to the data distribution, and generate new data samples, and the model has A certain self-learning ability can be applied in semi-supervised learning.
GAN的核心思想来源于博弈论的纳什均衡，它设定的参与双方分别为一个生成器和一个判别器，生成器的目的是尽量去学习真实的数据分布，而判别器的目的是尽量正确判别输入数据是来自真实数据还是来自生成器；两个模型需要同时不断优化，各自提高自己的生成能力和判别能力，当二者达到一个平衡时即完成计算。The core idea of GAN comes from the Nash equilibrium of game theory. It sets the two parties involved as a generator and a discriminator. The purpose of the generator is to learn the real data distribution as much as possible, and the purpose of the discriminator is to discriminate as accurately as possible. Whether the input data comes from the real data or the generator; the two models need to be continuously optimized at the same time, each improving its own generating ability and discriminating ability, and the calculation is completed when the two reach a balance.
常规对抗神经网络是不能直接实现自动参数的率定，因为没有真实的样本。因此必须在每次生成器输出生成样本时，采用水文模型进行最优参数的选择，作为下次判别器迭代计算的真实样本输入。Conventional adversarial neural networks cannot directly achieve automatic parameter calibration because there are no real samples. Therefore, each time the generator outputs a generated sample, the hydrological model must be used to select the optimal parameters as the real sample input for the next discriminator iterative calculation.
可以看出判别器和生成器的损失值，它们都逐渐接近于1，说明模型是收敛的。It can be seen that the loss values of the discriminator and the generator are gradually close to 1, indicating that the model is converged.
水文模型的确定性系数，可以看到由初期的0.78提升到0.86.说明神经网络可以用于水文模型参数优化。The certainty coefficient of the hydrological model can be seen to be improved from 0.78 in the initial stage to 0.86. It shows that the neural network can be used for the optimization of hydrological model parameters.
可以看到当确定性系数比上次优秀时，损失值会突然增大，说明更新真实值后判定器会自动重新训练，且很快收敛。因此进行优选得到最优参数时，是以确定性系数作为优选原则。It can be seen that when the certainty coefficient is better than the last time, the loss value will suddenly increase, indicating that the determiner will automatically retrain after updating the true value, and it will converge quickly. Therefore, when performing optimization to obtain the optimal parameters, the deterministic coefficient is used as the optimization principle.
深度学习网络的学习能力相当强，当给定一个真实样本后，生成模型可以迅速的收敛到真实样本的范围，由于真实值也是需要迭代更新的，所以极容易出现过拟合问题，直接导致收敛速度慢或陷入局部最优。本发明采用用休眠局部神经元、权重正则化和调整神经元数据等方法解决这些问题。The learning ability of the deep learning network is quite strong. When a real sample is given, the generated model can quickly converge to the range of the real sample. Since the real value also needs to be updated iteratively, it is extremely prone to overfitting problems, which directly lead to convergence. Slow or stuck in a local optimum. The present invention solves these problems by using dormant local neurons, weight regularization, and adjustment of neuron data.
对于本发明最核心问题就是找出有资料流域的最优参数，因此可以加入最优搜寻策略对生成样本进行优选，提高整个网络的性能。The core problem of the present invention is to find the optimal parameters of the data basin. Therefore, an optimal search strategy can be added to optimize the generated samples to improve the performance of the entire network.
本发明采用对抗神经网络之所以能推出最优参数，是因为它每一次迭代都是在上次最好的一个分布空间内，随机变化来而产生。The reason why the present invention adopts the adversarial neural network to derive the optimal parameters is that each iteration is generated by random changes in the best distribution space of the last time.

Claims (4)

  1. 一种基于对抗神经网络的有资料地区水文参数率定方法，它包括：An adversarial neural network-based calibration method for hydrological parameters in areas with data, which includes:
    步骤1、采集土壤质地、植被覆盖度、土地利用率、地形数据、径流系数、年蒸发总量、比降和坡度数据；Step 1. Collect soil texture, vegetation coverage, land utilization, terrain data, runoff coefficient, total annual evaporation, gradient and slope data;
    步骤2、将率定区域划分为30平方公里以下的计算单元；Step 2. Divide the calibration area into calculation units below 30 square kilometers;
    步骤3、根据水文模型参数的物理特性，确定每一个计算单元每一个参数下垫面及气象相关因子；Step 3. Determine the underlying surface and meteorological related factors of each parameter of each calculation unit according to the physical characteristics of the parameters of the hydrological model;
    步骤4、采用对抗神经网络GAN对有资料流域水文参数的自动率定，对抗神经网络GAN以噪声作为输入，通过水文模型进行参数优选，得到每个单元最优的水文参数。Step 4. The adversarial neural network GAN is used to automatically calibrate the hydrological parameters of the watershed with data. The adversarial neural network GAN takes noise as the input, and optimizes the parameters through the hydrological model to obtain the optimal hydrological parameters for each unit.
  2. 根据权利要求1所述的一种基于对抗神经网络的有资料地区水文参数率定方法，其特征在于：步骤3所述每一个参数下垫面及气象相关因子为：A method for calibration of hydrological parameters in areas with data based on adversarial neural network according to claim 1, characterized in that: the underlying surface of each parameter and the meteorological correlation factor described in step 3 are:
    Figure PCTCN2020123715-appb-100001
    Figure PCTCN2020123715-appb-100001
    Figure PCTCN2020123715-appb-100002
    Figure PCTCN2020123715-appb-100002
  3. 根据权利要求1所述的一种基于对抗神经网络的有资料地区水文参数率定方法，其特征在于：步骤4所述采用对抗神经网络GAN进行水文参数的自动率定的方法为：A kind of hydrological parameter calibration method based on adversarial neural network according to claim 1, it is characterized in that: the method that adopts adversarial neural network GAN to automatically calibrate hydrological parameters described in step 4 is:
    步骤4.1、以正态分布的噪声作为生成器的输入生成样本；Step 4.1. Generate samples with normally distributed noise as the input of the generator;
    步骤4.2、将生成的样本集输入到水文模型中进行优选得到最优参数；Step 4.2. Input the generated sample set into the hydrological model for optimization to obtain the optimal parameters;
    步骤4.3、将水文模型输出的最优参数和生成器生成的样本输入到判别器的判别真假。Step 4.3: Input the optimal parameters output by the hydrological model and the samples generated by the generator to the discriminator to judge the true and false.
  4. 根据权利要求3所述的一种基于对抗神经网络的有资料地区水文参数率定方法，其特征在于：步骤4.2所述将生成的样本集输入到水文模型中进行优选得到最优参数时，是以确定性系数作为优选原则。A method for calibration of hydrological parameters in areas with data based on adversarial neural network according to claim 3, characterized in that: in step 4.2, when the generated sample set is input into the hydrological model for optimization to obtain the optimal parameters, it is The deterministic coefficient is used as the preferred principle.
PCT/CN2020/123715 2020-08-14 2020-10-26 Adversarial neural network-based hydrological parameter calibration method for data region WO2022032874A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010820500.5 2020-08-14
CN202010820500.5A CN111914488B (en) 2020-08-14 2020-08-14 Data area hydrologic parameter calibration method based on antagonistic neural network

Publications (1)

Publication Number Publication Date
WO2022032874A1 true WO2022032874A1 (en) 2022-02-17

Family

ID=73283208

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/123715 WO2022032874A1 (en) 2020-08-14 2020-10-26 Adversarial neural network-based hydrological parameter calibration method for data region

Country Status (2)

Country Link
CN (1) CN111914488B (en)
WO (1) WO2022032874A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114740155A (en) * 2022-03-30 2022-07-12 内蒙古农业大学 Forest ecosystem evapotranspiration detection device and method
CN116108672A (en) * 2023-02-17 2023-05-12 南京声远声学科技有限公司 Outdoor sound propagation prediction model construction method based on geographic information system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102034003A (en) * 2010-12-16 2011-04-27 南京大学 Watershed hydrological model design method based on storage capacity curve and TOPMODEL
CN111144552A (en) * 2019-12-27 2020-05-12 河南工业大学 Multi-index grain quality prediction method and device
CN111160430A (en) * 2019-12-19 2020-05-15 广东工业大学 Water resource optimization configuration method based on artificial intelligence algorithm

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI246338B (en) * 2004-04-09 2005-12-21 Asustek Comp Inc A hybrid model sprite generator and a method to form a sprite
KR101802455B1 (en) * 2016-11-16 2017-11-28 한국외국어대학교 연구산학협력단 System for estimating reainfild according to spatial-scale of rainfall and method thereof
CN108133292A (en) * 2017-12-25 2018-06-08 贵州东方世纪科技股份有限公司 A kind of water and soil balance computational methods based on artificial intelligence
US11315012B2 (en) * 2018-01-12 2022-04-26 Intel Corporation Neural network training using generated random unit vector
AR109623A1 (en) * 2018-02-16 2019-01-09 Pescarmona Enrique Menotti PROCESS AND SYSTEM OF ANALYSIS AND HYDROLOGICAL MANAGEMENT FOR BASINS
CN112088383A (en) * 2018-05-10 2020-12-15 松下半导体解决方案株式会社 Neural network construction device, information processing device, neural network construction method, and program
CN109493303B (en) * 2018-05-30 2021-08-17 湘潭大学 Image defogging method based on generation countermeasure network
CN109840873A (en) * 2019-02-02 2019-06-04 中国水利水电科学研究院 A kind of Cross Some Region Without Data Hydro-Model Parameter Calibration Technology fields method based on machine learning
CN110533578A (en) * 2019-06-05 2019-12-03 广东世纪晟科技有限公司 A kind of image interpretation method based on condition confrontation neural network
CN110598794A (en) * 2019-09-17 2019-12-20 武汉思普崚技术有限公司 Classified countermeasure network attack detection method and system
CN110633859B (en) * 2019-09-18 2024-03-01 西安理工大学 Hydrologic sequence prediction method integrated by two-stage decomposition
CN110796253A (en) * 2019-11-01 2020-02-14 中国联合网络通信集团有限公司 Training method and device for generating countermeasure network
CN111080155B (en) * 2019-12-24 2022-03-15 武汉大学 Air conditioner user frequency modulation capability evaluation method based on generation countermeasure network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102034003A (en) * 2010-12-16 2011-04-27 南京大学 Watershed hydrological model design method based on storage capacity curve and TOPMODEL
CN111160430A (en) * 2019-12-19 2020-05-15 广东工业大学 Water resource optimization configuration method based on artificial intelligence algorithm
CN111144552A (en) * 2019-12-27 2020-05-12 河南工业大学 Multi-index grain quality prediction method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
FENG RUI: "Prediction of Runoff Series in Jiulong River Basin Based on LSTM Model", CHINA MASTER’S THESES FULL-TEXT DATABASE, 15 January 2020 (2020-01-15), XP055900094 *
GUO YI, WU XIN-MIAO, QIE ZHI-HONG, RAN YAN-LI: "Parameter Calibration of MIKE SHE Model Based on BP Neural Network", JOURNAL OF YANGTZE RIVER SCIENTIFIC RESEARCH INSTITUTE, vol. 36, no. 3, 31 March 2019 (2019-03-31), pages 26 - 30, XP055900097, ISSN: 1001-5485, DOI: 10.11988/ckyyb.20170992 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114740155A (en) * 2022-03-30 2022-07-12 内蒙古农业大学 Forest ecosystem evapotranspiration detection device and method
CN114740155B (en) * 2022-03-30 2023-10-10 内蒙古农业大学 Detection device and method for evapotranspiration of forest ecosystem
CN116108672A (en) * 2023-02-17 2023-05-12 南京声远声学科技有限公司 Outdoor sound propagation prediction model construction method based on geographic information system
CN116108672B (en) * 2023-02-17 2024-01-23 南京声远声学科技有限公司 Outdoor sound propagation prediction model construction method based on geographic information system

Also Published As

Publication number Publication date
CN111914488B (en) 2023-09-01
CN111914488A (en) 2020-11-10

Similar Documents

Publication Publication Date Title
CN109858647B (en) Regional flood disaster risk evaluation and estimation method coupled with GIS and GBDT algorithm
CN109272146B (en) Flood prediction method based on deep learning model and BP neural network correction
Deng et al. Simulation of land use/land cover change and its effects on the hydrological characteristics of the upper reaches of the Hanjiang Basin
CN110619432B (en) Feature extraction hydrological forecasting method based on deep learning
Dumedah et al. Selecting model parameter sets from a trade-off surface generated from the non-dominated sorting genetic algorithm-II
CN111461457A (en) Foundation pit displacement prediction method based on particle swarm optimization BP neural network
Yarar et al. Modelling level change in lakes using neuro-fuzzy and artificial neural networks
CN108345735A (en) A kind of Watershed Hydrologic Models parameter calibrating method
WO2022032874A1 (en) Adversarial neural network-based hydrological parameter calibration method for data region
CN111259522B (en) Multi-watershed parallel calibration method of hydrologic model in geographic space
CN107133686A (en) City-level PM2.5 concentration prediction methods based on Spatio-Temporal Data Model for Spatial
CN113176393B (en) HASM model-based three-dimensional estimation method and system for soil organic carbon reserves
CN113139329B (en) Xinanjiang model parameter calibration method based on hydrological similarity and artificial neural network
WO2022032873A1 (en) Adversarial neural network-based hydrological parameter calibration method for data-lacking region
Fu et al. Assessment and prediction of regional climate based on a multimodel ensemble machine learning method
Wang et al. A data‐driven approach for flood prediction using grid‐based meteorological data
CN116189794A (en) Rammed earth water salt content measurement method
CN116796799A (en) Method for creating small-river basin flood rainfall threshold model in area without hydrologic data
CN113111590A (en) Urban flood model runoff sensitivity parameter identification method based on artificial neural network
CN111914465B (en) Clustering and particle swarm optimization-based method for calibrating hydrologic parameters of non-data region
Jahangir et al. Application of artificial neural networks to the simulation of climate elements, drought forecast by two indicators of SPI and PNPI, and mapping of drought intensity; case study of Khorasan Razavi
Zhai et al. Wet Aggregate Stability Predicting of Soil in Multiple Land-Uses Based on Support Vector Machine
Sharma et al. SWAT model application for simulating water balance and water yield in the lower Sutlej Sub-basin
Goudarzia et al. Corrected Proof
CN111914430A (en) Data-based regional hydrological parameter calibration method based on clustering and particle swarm optimization

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20949368

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19.05.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20949368

Country of ref document: EP

Kind code of ref document: A1