CN116383728A - Meteorological prediction method based on zoned SVM - Google Patents

Meteorological prediction method based on zoned SVM Download PDF

Info

Publication number
CN116383728A
CN116383728A CN202310653755.0A CN202310653755A CN116383728A CN 116383728 A CN116383728 A CN 116383728A CN 202310653755 A CN202310653755 A CN 202310653755A CN 116383728 A CN116383728 A CN 116383728A
Authority
CN
China
Prior art keywords
sample
model
svm
support vector
vector machine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310653755.0A
Other languages
Chinese (zh)
Inventor
杨泓
钟雪
陈云强
卢军
罗珊珊
杨佳庚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Meteorological Service Center
Original Assignee
Sichuan Meteorological Service Center
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 Sichuan Meteorological Service Center filed Critical Sichuan Meteorological Service Center
Priority to CN202310653755.0A priority Critical patent/CN116383728A/en
Publication of CN116383728A publication Critical patent/CN116383728A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/27—Regression, e.g. linear or logistic regression
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • 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

Landscapes

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

Abstract

The invention discloses a meteorological prediction method based on a zoning SVM, which belongs to the technical field of meteorological prediction and solves the problem of lower prediction accuracy rate in the case of nonlinear data in the prior art, and comprises the following steps: dividing the area to be predicted into area grids, respectively collecting historical flight weather prediction factors, and constructing a regression model sample and a model verification sample by combining weather information in the area; building a support vector machine model, and optimizing parameters in the support vector machine model by adopting an ant colony algorithm; training a support vector machine model by using a regression model sample to obtain a globally optimal support vector machine model; and inputting the model verification sample into a globally optimal support vector machine model for verification. Through the scheme, the invention has the advantages of simple logic, accuracy, reliability and the like.

Description

Meteorological prediction method based on zoned SVM
Technical Field
The invention relates to the technical field of weather prediction, in particular to a weather prediction method based on a zoned SVM.
Background
The flight weather prediction factor in the technology mainly comprises: air temperature, precipitation, visibility, wind direction, relative humidity, wind speed, total cloud cover, low cloud cover, and the like. The weather forecast can guide daily production and life of human beings. Currently, traditional meteorological predictions rely on priors, such as thermodynamic properties of the atmosphere, statistical analysis of data, and ensemble learning involving multiple models with different initial conditions. In addition, in the statistical analysis of data, it is necessary to determine the relationship between the dependent variable and the independent variable, and to obtain the relationship from a complex mapping relationship. The method needs to screen from massive information, and if the data has nonlinearity, the accuracy is lower.
Therefore, it is highly desirable to provide a weather prediction method based on a zoned SVM, which is simple in logic, accurate and reliable.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a meteorological prediction method based on a zoned SVM, which adopts the following technical scheme:
a weather prediction method based on a zoned SVM comprises the following steps:
dividing the area to be predicted into area grids, respectively collecting historical flight weather prediction factors, and constructing a regression model sample and a model verification sample by combining weather information in the area;
building a support vector machine model, and optimizing parameters in the support vector machine model by adopting an ant colony algorithm;
training a support vector machine model by using a regression model sample to obtain a globally optimal support vector machine model;
and inputting the model verification sample into a globally optimal support vector machine model for verification.
Further, the method further comprises the following steps: and normalizing the collected historical flight weather prediction factors.
Further, the method further comprises the following steps: and carrying out correlation degree calculation on the normalized flying weather prediction factor by adopting a pearson correlation coefficient, combining weather information in the subareas, and obtaining a regression model sample and a model verification sample.
Further, the pearson correlation coefficient
Figure SMS_1
The expression of (2) is:
Figure SMS_2
wherein,,
Figure SMS_5
representing the covariance of sample set X and sample set Y; />
Figure SMS_6
Representing the standard deviation of the sample set X; />
Figure SMS_8
Representing the standard deviation of the sample set Y; />
Figure SMS_4
Represents +.>
Figure SMS_9
A sample number; />
Figure SMS_11
Represents +.>
Figure SMS_12
A sample number; />
Figure SMS_3
Representing a sampleAverage value of set X; />
Figure SMS_7
Representing the average value of the sample set Y; />
Figure SMS_10
Representing the partial autocorrelation coefficients.
Further, the method further comprises the following steps: carrying out weather prediction on any regional grid by using a globally optimal support vector machine model, and carrying out sectional fitting by adopting a linear regression equation; and carrying out feedback correction by adopting the fitting effect to obtain the best fitting model.
Further, the support vector machine model performs type recognition on the sample, and the method comprises the following steps:
presetting a kernel function K, and constructing a cost function by using a regression model sample
Figure SMS_13
The expression is:
Figure SMS_14
and (3) applying constraint conditions:
Figure SMS_15
wherein,,
Figure SMS_16
representing a classification interface vector; />
Figure SMS_17
Indicate->
Figure SMS_18
Actual errors; b represents an intercept; />
Figure SMS_19
Representing a transpose of the classification interface vector matrix; c represents a penalty factor; />
Figure SMS_20
Represents +.sup.th containing kernel function K>
Figure SMS_21
Actual errors;
and constructing a Lagrangian function, and judging the type of the acquired sample according to the KKT condition.
Further, the expression of the lagrangian function is:
Figure SMS_22
wherein,,
Figure SMS_23
and->
Figure SMS_24
Representing the lagrangian multiplier.
Further, the expression of the KKT condition is:
Figure SMS_25
wherein,,
Figure SMS_26
。
further, the type judgment is expressed as:
Figure SMS_27
。
compared with the prior art, the invention has the following beneficial effects:
(1) According to the characteristic of rapid boundary layer weather change, the method creatively uses a segmented SVM method, adopts a segmented fitting mode for different areas, and automatically performs the division of the areas by adopting a mode of carrying out feedback correction on the fitting effect, thereby achieving the maximum fitting effect.
(2) The present invention seeks an optimal compromise between the complexity of the model (i.e. the learning accuracy for a particular training sample) and the learning ability (i.e. the ability to identify the sample without error) based on limited sample information, in order to obtain the best generalization ability. The SVM overcomes the defects of over-learning, local extreme points, dimension disasters and the like of the neural network and the traditional classifier, and has stronger generalization capability.
In conclusion, the method has the advantages of simple logic, accuracy, reliability and the like, and has high practical value and popularization value in the technical field of weather prediction.
Drawings
For a clearer description of the technical solutions of the embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and should not be considered as limiting the scope of protection, and other related drawings may be obtained according to these drawings without the need of inventive effort for a person skilled in the art.
FIG. 1 is a logic flow diagram of the present invention.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the present invention will be further described with reference to the accompanying drawings and examples, and embodiments of the present invention include, but are not limited to, the following examples. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
In this embodiment, the term "and/or" is merely an association relationship describing the association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone.
The terms first and second and the like in the description and in the claims of the present embodiment are used for distinguishing between different objects and not for describing a particular sequential order of objects. For example, the first target object and the second target object, etc., are used to distinguish between different target objects, and are not used to describe a particular order of target objects.
In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, unless otherwise indicated, the meaning of "a plurality" means two or more. For example, the plurality of processing units refers to two or more processing units; the plurality of systems means two or more systems.
As shown in fig. 1, the embodiment provides a weather prediction method based on a zoned SVM, and the following flight weather prediction factors are selected: air temperature, precipitation, visibility, wind direction, relative humidity, wind speed, total cloud cover, low cloud cover. (mist on the ground when the cloud is grounded). And forming input and output samples according to the data collected in the history and haze, icing, rainfall and strong wind, dividing the samples into regression model samples and model verification samples, obtaining a boundary layer weather prediction model based on SVM, and predicting weather conditions of future boundaries by using the model.
Specifically, the weather prediction method of the present embodiment includes the following steps:
firstly, dividing a region grid of a region to be predicted, respectively collecting historical flight weather prediction factors, and constructing a regression model sample and a model verification sample by combining weather information in the region. In this step, the collected historical flight weather predictors are normalized. On the basis of normalization processing, the correlation of the data needs to be obtained so as to obtain a reliable regression model sample.
In this embodiment, the normalized flying weather prediction factor is obtained by using pearson correlation coefficient to calculate the correlation degree, and the regression model is obtained by combining the weather information in the subareaSample and model verification sample, wherein pearson correlation coefficient
Figure SMS_28
The expression of (2) is:
Figure SMS_29
wherein,,
Figure SMS_31
representing the covariance of sample set X and sample set Y; />
Figure SMS_33
Representing the standard deviation of the sample set X; />
Figure SMS_38
Representing the standard deviation of the sample set Y; />
Figure SMS_32
Represents +.>
Figure SMS_34
A sample number; />
Figure SMS_37
Represents +.>
Figure SMS_39
A sample number; />
Figure SMS_30
Representing the average value of the sample set X; />
Figure SMS_35
Representing the average value of the sample set Y; />
Figure SMS_36
Representing the partial autocorrelation coefficients.
In this embodiment, an optimal tradeoff is sought between the complexity of the model (i.e., the learning accuracy for a particular training sample) and the learning ability (i.e., the ability to identify samples without error), and the type identification of samples by the support vector machine model, which includes the steps of:
presetting a kernel function K, and constructing a cost function by using a regression model sample
Figure SMS_40
The expression is:
Figure SMS_41
and (3) applying constraint conditions:
Figure SMS_42
wherein,,
Figure SMS_43
representing a classification interface vector; />
Figure SMS_44
Representing a first actual error; b represents an intercept; />
Figure SMS_45
Representing a transpose of the classification interface vector matrix; c represents a penalty factor; />
Figure SMS_46
Represents +.sup.th containing kernel function K>
Figure SMS_47
Actual errors;
the Lagrangian function is constructed with the expression:
Figure SMS_48
wherein,,
Figure SMS_49
and->
Figure SMS_50
Representing the lagrangian multiplier.
Judging the type of the acquired sample according to a KKT condition, wherein the expression of the KKT condition is as follows:
Figure SMS_51
wherein,,
Figure SMS_52
。
the type judgment expression is:
Figure SMS_53
。
secondly, building a support vector machine model, and optimizing parameters in the support vector machine model by adopting an ant colony algorithm, wherein the parameters are specifically:
(1) Initializing a penalty factor c and a kernel function parameter K in the support vector machine parameters;
(2) Training a support vector machine by using the normalized sample data;
(3) And setting the maximum iteration times, and performing global optimization on the penalty factor c and the kernel function parameter K by utilizing an ant colony algorithm to finally obtain an optimal prediction model.
Thirdly, training a support vector machine model by using a regression model sample to obtain a globally optimal support vector machine model;
and fourthly, inputting the model verification sample into a globally optimal support vector machine model for verification.
In addition, in the embodiment, weather prediction is performed on any regional grid by using a globally optimal support vector machine model, and a linear regression equation is adopted for segmented fitting; and carrying out feedback correction by adopting the fitting effect to obtain the best fitting model.
The above embodiments are only preferred embodiments of the present invention and are not intended to limit the scope of the present invention, but all changes made by adopting the design principle of the present invention and performing non-creative work on the basis thereof shall fall within the scope of the present invention.

Claims (9)

1. The weather prediction method based on the zoned SVM is characterized by comprising the following steps of:
dividing the area to be predicted into area grids, respectively collecting historical flight weather prediction factors, and constructing a regression model sample and a model verification sample by combining weather information in the area;
building a support vector machine model, and optimizing parameters in the support vector machine model by adopting an ant colony algorithm;
training a support vector machine model by using a regression model sample to obtain a globally optimal support vector machine model;
and inputting the model verification sample into a globally optimal support vector machine model for verification.
2. The zoned SVM-based weather prediction method of claim 1, further comprising: and normalizing the collected historical flight weather prediction factors.
3. The zoned SVM-based weather prediction method of claim 2, further comprising: and carrying out correlation degree calculation on the normalized flying weather prediction factor by adopting a pearson correlation coefficient, combining weather information in the subareas, and obtaining a regression model sample and a model verification sample.
4. A zoned SVM-based weather prediction method in accordance with claim 3, wherein the pearson correlation coefficient
Figure QLYQS_1
The expression of (2) is:
Figure QLYQS_2
，
wherein,,
Figure QLYQS_5
representing the covariance of sample set X and sample set Y; />
Figure QLYQS_6
Representing the standard deviation of the sample set X; />
Figure QLYQS_11
Representing the standard deviation of the sample set Y; />
Figure QLYQS_3
Represents +.>
Figure QLYQS_7
A sample number; />
Figure QLYQS_9
Represents +.>
Figure QLYQS_12
A sample number; />
Figure QLYQS_4
Representing the average value of the sample set X; />
Figure QLYQS_8
Representing the average value of the sample set Y; />
Figure QLYQS_10
Representing the partial autocorrelation coefficients.
5. The zoned SVM-based weather prediction method of claim 1, further comprising: carrying out weather prediction on any regional grid by using a globally optimal support vector machine model, and carrying out sectional fitting by adopting a linear regression equation; and carrying out feedback correction by adopting the fitting effect to obtain the best fitting model.
6. The method for weather prediction based on a zoned SVM according to claim 4, wherein the support vector machine model performs type recognition on the samples, comprising the steps of:
presetting a kernel function K, and constructing a cost function by using a regression model sample
Figure QLYQS_13
The expression is:
Figure QLYQS_14
，
and (3) applying constraint conditions:
Figure QLYQS_15
，
wherein,,
Figure QLYQS_16
representing a classification interface vector; />
Figure QLYQS_17
Represents the first->
Figure QLYQS_18
Actual errors; b represents an intercept; />
Figure QLYQS_19
Representing a transpose of the classification interface vector matrix; c represents a penalty factor; />
Figure QLYQS_20
Represents the first +.>
Figure QLYQS_21
Actual errors;
and constructing a Lagrangian function, and judging the type of the acquired sample according to the KKT condition.
7. The zoned SVM-based weather prediction method of claim 6, wherein the expression of the lagrangian function is:
Figure QLYQS_22
，
wherein,,
Figure QLYQS_23
and->
Figure QLYQS_24
Representing the lagrangian multiplier.
8. The zoned SVM-based weather prediction method of claim 7, wherein the KKT condition is expressed as:
Figure QLYQS_25
，
wherein,,
Figure QLYQS_26
。
9. the zoned SVM-based weather prediction method of claim 8, wherein the type judgment is expressed as:
Figure QLYQS_27
。
CN202310653755.0A 2023-06-05 2023-06-05 Meteorological prediction method based on zoned SVM Pending CN116383728A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310653755.0A CN116383728A (en) 2023-06-05 2023-06-05 Meteorological prediction method based on zoned SVM

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310653755.0A CN116383728A (en) 2023-06-05 2023-06-05 Meteorological prediction method based on zoned SVM

Publications (1)

Publication Number Publication Date
CN116383728A true CN116383728A (en) 2023-07-04

Family

ID=86977281

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310653755.0A Pending CN116383728A (en) 2023-06-05 2023-06-05 Meteorological prediction method based on zoned SVM

Country Status (1)

Country Link
CN (1) CN116383728A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779203A (en) * 2016-12-08 2017-05-31 贵州电网有限责任公司电力科学研究院 A kind of plateau mountain area wind power forecasting method based on different wind speed section
CN108182468A (en) * 2018-03-19 2018-06-19 哈尔滨理工大学 A kind of correcting algorithm of the segmentation Support vector regression based on ant group algorithm optimization
US20210332796A1 (en) * 2017-12-14 2021-10-28 Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. Method and apparatus for icing prediction, method and apparatus for generatng icing prediction model
CN114548571A (en) * 2022-02-25 2022-05-27 国网山东省电力公司潍坊供电公司 Photovoltaic power generation prediction method and device based on Bayesian ridge regression
CN114581141A (en) * 2022-03-08 2022-06-03 国网上海市电力公司 Short-term load prediction method based on feature selection and LSSVR
CN114723112A (en) * 2022-03-25 2022-07-08 国网甘肃省电力公司电力科学研究院 Wind power output ultra-short-term prediction method based on multi-dimensional meteorological factor phase space reconstruction
CN115099531A (en) * 2022-08-19 2022-09-23 国网江苏省电力有限公司苏州供电分公司 Power transmission line lightning stroke early warning method and system based on support vector machine
WO2023063888A2 (en) * 2021-10-14 2023-04-20 Envision Digital International Pte. Ltd. Method and apparatus for predicting wind power, and device and storage medium thereof

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779203A (en) * 2016-12-08 2017-05-31 贵州电网有限责任公司电力科学研究院 A kind of plateau mountain area wind power forecasting method based on different wind speed section
US20210332796A1 (en) * 2017-12-14 2021-10-28 Beijing Goldwind Science & Creation Windpower Equipment Co., Ltd. Method and apparatus for icing prediction, method and apparatus for generatng icing prediction model
CN108182468A (en) * 2018-03-19 2018-06-19 哈尔滨理工大学 A kind of correcting algorithm of the segmentation Support vector regression based on ant group algorithm optimization
WO2023063888A2 (en) * 2021-10-14 2023-04-20 Envision Digital International Pte. Ltd. Method and apparatus for predicting wind power, and device and storage medium thereof
CN114548571A (en) * 2022-02-25 2022-05-27 国网山东省电力公司潍坊供电公司 Photovoltaic power generation prediction method and device based on Bayesian ridge regression
CN114581141A (en) * 2022-03-08 2022-06-03 国网上海市电力公司 Short-term load prediction method based on feature selection and LSSVR
CN114723112A (en) * 2022-03-25 2022-07-08 国网甘肃省电力公司电力科学研究院 Wind power output ultra-short-term prediction method based on multi-dimensional meteorological factor phase space reconstruction
CN115099531A (en) * 2022-08-19 2022-09-23 国网江苏省电力有限公司苏州供电分公司 Power transmission line lightning stroke early warning method and system based on support vector machine

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
杨泓等: "四川高速公路安全行车气象风险指数与预警提示发布系统", 《公路与水路运输 工程科技Ⅱ辑》, pages 2 *
许晓宁: "基于支持向量机的逐日降水预报模型研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 1, pages 009 - 201 *

Similar Documents

Publication Publication Date Title
Lagerquist et al. Machine learning for real-time prediction of damaging straight-line convective wind
US10019658B2 (en) Identifying visual storm signatures from satellite images
CN110728411B (en) High-low altitude area combined rainfall prediction method based on convolutional neural network
CN106228125B (en) Method for detecting lane lines based on integrated study cascade classifier
Xia et al. A hybrid method based on extreme learning machine and k-nearest neighbor for cloud classification of ground-based visible cloud image
CN110648014B (en) Regional wind power prediction method and system based on space-time quantile regression
CN109146063B (en) Multi-segment short-term load prediction method based on important point segmentation
CN114549914A (en) Airplane large-area icing detection method and detection system
CN113705877A (en) Real-time monthly runoff forecasting method based on deep learning model
CN116776238B (en) Dynamic risk assessment method and system for flood and drought disasters based on multi-source information
CN116776745B (en) Method and system for predicting pollutant concentration and track movement based on edge calculation
Badhiye et al. Analysis of Temperature and Humidity Data for Future value prediction
CN112802005A (en) Automobile surface scratch detection method based on improved Mask RCNN
CN112116265A (en) Industry landscape index construction method driven by electric power data
CN115186228A (en) Lattice point data-based tangent line identification method and device
CN117237902B (en) Robot character recognition system based on deep learning
Kim et al. Time series prediction of tropical storm trajectory using self-organizing incremental neural networks and error evaluation
Kamani et al. Shape matching using skeleton context for automated bow echo detection
CN116383728A (en) Meteorological prediction method based on zoned SVM
CN113033910A (en) Photovoltaic power generation power prediction method, storage medium and terminal equipment
CN112363171B (en) Autonomous tracking method for solving passive warning picture target track crossing
Dubey K-Means based radial basis function neural networks for rainfall prediction
Obakrim et al. Learning the spatiotemporal relationship between wind and significant wave height using deep learning
Mubeen et al. A novel approach for predicting the tc center of remotely sensed images using pso based density matrix
Bojja et al. Design and development of artificial intelligence system for weather forecasting using soft computing techniques

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination