CN110888186A - Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model - Google Patents
Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model Download PDFInfo
- Publication number
- CN110888186A CN110888186A CN201911204076.5A CN201911204076A CN110888186A CN 110888186 A CN110888186 A CN 110888186A CN 201911204076 A CN201911204076 A CN 201911204076A CN 110888186 A CN110888186 A CN 110888186A
- Authority
- CN
- China
- Prior art keywords
- data
- hail
- model
- index
- gbdt
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
Landscapes
- Environmental & Geological Engineering (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a hail and short-time strong precipitation forecasting method, which comprises the following steps: acquiring ground meteorological observation station data of three hours before hail and short-time strong precipitation occur in a certain area every 3 to 9 months in the past year and a plurality of sounding station data of the upstream of the area; expanding hail process data with relatively small data volume in the data through a SMOTE oversampling algorithm to obtain an oversampled data set; reducing the dimension of the oversampled data set by adopting a PCA method; dividing the samples in the reduced-dimension data set into a training set and a testing set; constructing a GBDT + LR model, taking the features extracted by leaf nodes of the GBDT model as input features of the LR model, and training and testing the GBDT + LR model through samples of a training set and a testing set; collecting ground meteorological observation station data three hours before a time point to be predicted of a region, obtaining a plurality of sounding station data of the upstream of the region, substituting the data into a trained GBDT + LR model, and judging whether hail or short-time strong precipitation occurs at the time point to be predicted.
Description
Technical Field
The invention relates to the field of weather forecast, in particular to a hail and short-time heavy precipitation forecasting method.
Background
In weather forecast, hail and short-time strong precipitation have the characteristics of short period of production and extinction, small range of affected area and severe weather change. They have a great influence on the industry, agriculture and the daily life of people.
The forecast of hail and short-term strong rainfall can use meteorological radar, but the information reflected by the meteorological radar is only live, and the detection space scale is small, so that the meteorological radar can not forecast in advance for a long time.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method for forecasting hail and short-term strong rainfall based on a GBDT + LR model, which realizes accurate forecasting of the hail and the short-term strong rainfall by utilizing the relation of physical field data and provides powerful support for accurately forecasting the strong convection weather.
Therefore, the invention adopts the following technical scheme:
a method for forecasting hail and short-time strong rainfall based on a GBDT + LR model comprises the following steps:
s1, raw data acquisition: acquiring ground meteorological observation station data of three hours before hail and short-time strong precipitation occur in 3-9 months every year in a certain area, and acquiring a plurality of sounding station data at the upstream of the area;
s2, expanding the hail process data with relatively small data volume in the data through a SMOTE oversampling algorithm to obtain an oversampled data set;
s3, adopting a PCA method to reduce the dimension of the oversampled data set;
s4, data set partitioning: dividing the samples in the reduced-dimension data set into a training set and a testing set;
s5, constructing a GBDT + LR model, taking the features extracted by leaf nodes of the GBDT model as input features of the LR model, and training and testing the GBDT + LR model through samples of the training set and the testing set;
s6, collecting ground meteorological observation station data three hours before the to-be-predicted time point of the region, and acquiring a plurality of sounding station data of the upstream of the region;
and S7, performing PCA dimensionality reduction on the data in the S6, inputting the data into a trained GBDT + LR model, and judging whether hail or short-time strong precipitation occurs at the predicted time point.
The GBDT + LR model is constructed by the following process:
(1) constructing a GBDT model as follows:
wherein β is the corresponding weight of each basic learner, α is the parameter of each basic learner, and the parameter
For M data (x)i,yi) The loss function of (a) is the minimum optimal solution P,
let the loss function L:
wherein l is the loss function of the basic learner for each iteration,
then:
for each sample xiA gradient descent direction can be obtained, namely:
optimizing equation (8) yields:
further obtain βn：
And finally obtaining an iterative description of the GBDT algorithm model:
Fn(x)＝Fn-1(x)+βnh(x；αn) (13)
(2) an LR two-classification model based on a Sigmoid function is connected behind the GBDT model in series, wherein the Sigmoid function is shown as the following formula:
where θ is the weight coefficient of the model, and x is the parameter of the leaf node extracted by the GBDT model.
By adjusting parameters of the GBDT model and the LR model, when the maximum iteration number is 10, the learning rate is 0.02, and the maximum depth of the tree is set to be 4, the obtained hail short-time strong rainfall forecast model is optimal.
In step S2, the expanding the hail process data by the SMOTE oversampling algorithm includes the following steps:
1) for each sample x of hail process dataiCalculating Euclidean distances from the sample to other samples in the hail process data;
2) setting sampling multiplying power according to the proportion of the samples, selecting a plurality of samples in the similar hail process data, and setting the selected adjacent points as
3) For each randomly selected neighbor point
New sample points were constructed according to equation (1):
and expanding the hail process data.
In step S1, the ground meteorological observation site data includes ground level air pressure, sea level air pressure, temperature, dew point temperature, relative humidity, water vapor pressure, 2 minute average wind direction, 2 minute average wind speed, 10 minute average wind direction, and 10 minute average wind speed.
In step S1, the data of the sounding site includes effective convective energy cap (J · kg)-1) Optimum convection effective potential energy BCAPE (J.kg)-1) Convection suppression energy CIN (J.kg)-1) K-index KI, Samson index SI, lift index LI, optimum lift index BLI, modified K-index MK, deep convection index DCI, modified deep convection index MDCI, micro downburst daily potential index MDPI, convection stability index IC, optimum convection stability index BIC, conditional stability index IL, conditional-convection stability index ICL, total index TT, amount of atmospheric water PW (cm), convective condensation height CCL (hpa), convective temperature TCON (DEG C), elevated condensation temperature TC (DEG C), elevated condensation height PC (hpa), free convective height C (LFhpa), equilibrium height PE (hpa), 0 ℃ layer height ZH (gpm), -30 ℃ layer height FH (gpm), strong threat weather index SWEAT, thunderstorm high wind index WINDEX, storm relative vorticity index SRH, energy vorticity index EHI, rough survey number BRN, storm intensity index SSI, SWISS thunderstorm index SWISS00 and SWISS thunderstorm index SWISS 12.
In an embodiment of the invention, the area is an Tianjin area, the plurality of sounding sites are Beijing sounding meteorological stations, a Schchen platform sounding meteorological station, a nutlet sounding meteorological station, a Chifeng sounding meteorological station and a Zhangkou sounding meteorological station, and the ground meteorological observation site data is the ground meteorological observation site data of the Tianjin city meteorological office from 2006 to 2018 years and from 3 to 9 months of hail and three hours before the occurrence of short-time strong precipitation, and 55 hail process data and 397 short-time strong precipitation process data are collected from 2006 to 2018 years. Expanding the hail process data to 385 by using a SMOTE oversampling algorithm; and reducing the dimensionality of the hail short-time strong precipitation data set from 195 dimensionality to 30 dimensionality by adopting a PCA (principal component analysis) method, and dividing the data set subjected to dimensionality reduction into a training set and a test set according to the proportion of 8: 2.
The invention has the following beneficial effects:
the method for forecasting the hail and the short-time strong rainfall based on the GBDT + LR model utilizes the ground physical field data of a meteorological observation station and the meteorological data of an upstream sounding station of the observation station, trains and fits the data through the GBDT + LR model, and obtains the correlation between the data and the hail and the short-time strong rainfall. The method uses physical field data recorded hourly, so that the advance of forecasting can be increased, and forecasting can be carried out 1 hour or several hours in advance.
2. The GBDT + LR model has excellent performance, the hit rate of hail is 0.902, and the critical success index is 0.859; the hit rate of short-term heavy precipitation is 0.946, the critical success index is 0.855, the forecast can be accurately carried out, and the influence of hail and short-term heavy precipitation weather on the society is reduced.
Drawings
Fig. 1 is a distribution diagram of sounding sites employed in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of the SMOTE algorithm;
FIG. 3 is a GBDT + LR model diagram in an embodiment of the invention;
FIG. 4 is a graph of the number of iterations of the tree versus the critical success index in an embodiment of the present invention;
FIG. 5 is a graph of learning rate versus threshold success index for an embodiment of the present invention;
FIG. 6 is a graph of maximum depth of the tree versus critical success index in an embodiment of the present invention.
Detailed Description
The method of the present invention is described in detail below with reference to the accompanying drawings and examples.
Example one
This embodiment is illustrated in Tianjin area. The method for forecasting hail and short-time strong rainfall in Tianjin area based on GBDT + LR model comprises the following steps:
step S1, acquisition of raw data:
the method for acquiring ground meteorological observation station data of a plurality of hours before hail and short-time strong precipitation occur from 3 to 9 months annually in 2006 to 2018 by the Tianjin urban weather bureau comprises the following steps: ground-level air pressure, sea-level air pressure, temperature, dew point temperature, relative humidity, water vapor pressure, 2 minute average wind direction, 2 minute average wind speed, 10 minute average wind direction, and 10 minute average wind speed. In this example, data was collected 3 hours before hail and short term strong precipitation occurred.
Referring to fig. 1, data (data of 8 points early and 8 points late) of five sounding sites of an air sounding meteorological station in the upstream beijing of tianjin, an air sounding meteorological station on a chenchenchenge platform, a nutlet air sounding meteorological station, a akang air sounding meteorological station and a family opening air sounding meteorological station are selected, and the data include: effective potential energy of convection CAPE (J.kg)-1) Optimum convection effective potential energy BCAPE (J.kg)-1) Convection suppression energy CIN (J.kg)-1) K-index KI, Samson index SI, lift index LI, optimum lift index BLI, modified K-index MK, deep convection index DCI, modified deep convection index MDCI, micro downburst daily potential index MDPI, convection stability index IC, optimum convection stability index BIC, conditional stability index IL, conditional-convection stability index ICL, total index TT, amount of atmospheric water PW (cm), convective condensation height CCL (hpa), convective temperature TCON (DEG C), elevated condensation temperature TC (DEG C), elevated condensation height PC (hpa), free convective height C (LFhpa), equilibrium height PE (hpa), 0 ℃ layer height ZH (gpm), -30 ℃ layer height FH (gpm), strong threat weather index SWEAT, thunderstorm high wind index WINDEX, storm relative vorticity index SRH, energy vorticity index EHI, rough survey number BRN, storm intensity index SSI, The Swiss Rampy index SWISS00 and the Swiss Rampy index SWISS12 are 33 physical quantity data in total.
The above collected 55 hail process data and 397 short-time heavy precipitation process data from 2006 to 2018.
Step S2, because the acquired hail process data has the problems of unbalanced samples and small data size compared with the short-time heavy precipitation process data set, the hail process data is extended by using a SMOTE (synthetic timing over-sampling) oversampling algorithm.
A schematic diagram of the SMOTE oversampling algorithm is shown in fig. 2, and the specific steps are as follows:
step 1: for each sample x in the class with a small number of samplesiCalculating Euclidean distances from the sample to other samples in a few categories;
step 2: setting sampling multiplying power according to the proportion of the samples, selecting the samples in 55 similar minority classes, and setting the selected adjacent points as
And 3, step 3: for each randomly selected neighbor point
New sample points were constructed according to equation (1):
since sampling multiplying power of a minority sample in the SMOTE algorithm influences prediction accuracy, the sampling multiplying power is increased, and classification accuracy of the minority sample can be improved, the 55 hail process data are expanded to 385 in the embodiment.
Step S3, data dimension reduction:
in the data set obtained in the step S2, the data of the five upstream sounding sites and the data of the ground observation site are used for constructing a hail and short-time heavy precipitation forecast model, and the data are 195-dimensional in total; and the data volume of the training set data is not enough, so that the overfitting problem is easily caused. In order to solve the over-fitting problem, the data needs to be subjected to dimensionality reduction.
The invention adopts PCA (principal Component analysis) method to perform dimensionality reduction treatment. The PCA method converts a given set of correlation quantities into another set of uncorrelated variables through linear transformation, and these new variables are arranged in an order in which the variances decrease in order to extract principal components of data.
The principal components extracted by the PCA dimension reduction method can eliminate redundant information of an original data space under the condition of keeping variance information, and variables of each principal component are orthogonal.
Suppose that a sample space formed by N-dimensional M samples is X ∈ RM×NThe specific calculation steps of PCA are as follows:
constructing a linear expression of PCA, as shown in formula (2):
in the formula: vector quantity
The kth dimension representing the ith sample, y the principal component, and a the eigenvector coefficients.
Calculate the average of the kth dimension in sample space, i.e.:
calculating a variance matrix between any two dimensions a and b, namely:
each eigenvalue and corresponding eigenvector are obtained by calculating a variance matrix of the sample set, and the influence of each eigenvector on the overall variance is proportional to the eigenvalue. And sorting the characteristic values from large to small. In which the first T larger eigenvalues (lambda)1≥λ2≥λ3...≥λT≧ 0) is the variance corresponding to the first T principal components.
Determining the percentage of the first T principal components in the total variance of the data, wherein the calculation formula is shown as (5):
in the formula: lambda [ alpha ]nRepresents the nth characteristic value; snnIs the diagonal non-zero element of the variance matrix.
And 4, dividing the data set:
and after PCA (principal component analysis) dimensionality reduction processing is carried out on the SMOTE oversampled data set, the dimensionality of the hail short-time strong precipitation data set is reduced to 30 dimensions. For the obtained data set, 385 hail and 397 short-time strong precipitation data were divided at a ratio of 8:2, and the divided sample distributions are shown in table 1.
TABLE 1 training set and test set partitioning
Step 5, constructing a GBDT + LR model:
the model used in the present invention is the GBDT + LR model. The GBDT model is as follows:
wherein β is the corresponding weight of each basic learner, α is the parameter of each basic learner, and the parameter
For M data (x)i,yi) The loss function of (a) minimizes the optimal solution P.
Let the loss function L:
where l is the loss function of the base learner for each iteration.
Then:
for each sample xiA gradient descent direction can be obtained, namely:
optimizing equation (8) yields:
further obtain βn：
And finally obtaining the iteration description of the GBDT algorithm model:
Fn(x)＝Fn-1(x)+βnh(x；αn) (13)
the main parameters of the GBDT model training are the selection of the maximum iteration number of the tree, the model learning rate, and the maximum depth of the tree, and these three parameters are selected as shown in fig. 4 to 6, respectively, where the abscissa represents the three selected parameters, and the ordinate is the critical success index. As can be seen from fig. 4 to 6, in the parameter selection, when the maximum number of iterations is selected to be 10, the learning rate is set to be 0.02, and the maximum depth of the tree is set to be 4, the evaluation result of the model is optimal.
The forecasting of hail and short-term strong precipitation of the invention belongs to the problem of two classifications, therefore, an LR (logistic regression) two classification models based on a sigmoid function are connected in series behind a GBDT model. The Sigmoid function is shown in equation (14):
where θ is a weight coefficient of the model, and x is a parameter of the leaf node extracted by the GBDT. The loss function of LR is shown in equation (15):
since the log-loss function has good discrimination ability for the data of bernoulli distribution, the LR model has excellent characteristics for the binary problem of 0,1 with good characteristic data.
The GBDT + LR classification model adopts a method that the GBDT model splits and screens the characteristics, the characteristics after leaf node splitting are transmitted to the LR model, and the classification result is obtained through LR model training. The GBDT + LR model inherits the extraction characteristics of the GBDT model, the capability of obtaining the split discrete characteristics and the excellent classification capability of the LR model on the discrete distribution characteristics. Therefore, the features extracted by the leaf nodes of the GBDT are used as the input features of the LR model and trained, and a good classifying effect of hail and short-time strong precipitation can be obtained. A schematic diagram of the GBDT + LR model is shown in fig. 3.
Evaluation indexes used by the method of the present invention are hit rate (POD), False Alarm Rate (FAR), and Critical Success Index (CSI).
According to the data division results, 626 hail and short-term heavy rainfall samples form a training set, and 156 hail and short-term heavy rainfall samples form a testing set. The results of the 156 hail short-time strong precipitation test sets after training by the GBDT + LR model are shown in tables 2 and 3:
TABLE 2 evaluation of the forecast result of global GBDT + LR model hail
TABLE 3 evaluation of short-term heavy rainfall forecast results of GBDT + LR model
The data in the table show that the hit rate of hail is 0.902, and the critical success index is 0.859; the hit rate of short-time heavy precipitation is 0.946 and the critical success index is 0.855, which shows that the GBDT + LR model has excellent performance.
And S6, collecting ground meteorological observation station data three hours before the time point to be predicted in the Tianjin area, and acquiring a plurality of sounding station data of the upstream of the area.
And S7, performing PCA dimensionality reduction on the data in the S6, inputting the data into a trained GBDT + LR model, and judging whether hail or short-time strong precipitation occurs at the predicted time point.
Claims (9)
1. A method for forecasting hail and short-time strong rainfall based on a GBDT + LR model comprises the following steps:
s1, raw data acquisition: acquiring ground meteorological observation station data of three hours before hail and short-time strong precipitation occur in 3-9 months every year in a certain area, and acquiring a plurality of sounding station data at the upstream of the area;
s2, expanding the hail process data with relatively small data volume in the data through a SMOTE oversampling algorithm to obtain an oversampled data set;
s3, adopting a PCA method to reduce the dimension of the oversampled data set;
s4, data set partitioning: dividing the samples in the reduced-dimension data set into a training set and a testing set;
s5, constructing a GBDT + LR model, taking the features extracted by leaf nodes of the GBDT model as input features of the LR model, and training and testing the GBDT + LR model through samples of the training set and the testing set;
s6, collecting ground meteorological observation station data three hours before the to-be-predicted time point of the region, and acquiring a plurality of sounding station data of the upstream of the region;
and S7, performing PCA dimensionality reduction on the data in the S6, inputting the data into a trained GBDT + LR model, and judging whether hail or short-time strong precipitation occurs at the predicted time point.
2. The method of hail and short term heavy precipitation forecasting according to claim 1, characterized by: the construction process of the GBDT + LR model is as follows:
(1) constructing a GBDT model as follows:
wherein β is the corresponding weight of each basic learner, α is the parameter of each basic learner, and the parameter
For M data (x)i,yi) The loss function of (a) is the minimum optimal solution P,
let the loss function L:
wherein l is the loss function of the basic learner for each iteration,
then:
for each sample xiA gradient descent direction can be obtained, namely:
optimizing equation (8) yields:
further obtain βn：
And finally obtaining an iterative description of the GBDT algorithm model:
Fn(x)＝Fn-1(x)+βnh(x；αn) (13)
(2) an LR two-classification model based on a Sigmoid function is connected behind the GBDT model in series, wherein the Sigmoid function is shown as the following formula:
where θ is the weight coefficient of the model, and x is the parameter of the leaf node extracted by the GBDT model.
3. The method of hail and short term heavy precipitation forecasting according to claim 2, characterized by: the maximum iteration number of the GBDT + LR model is 10, the learning rate is 0.02, and the maximum depth of the tree is set to be 4.
4. The method of hail and short term heavy precipitation forecasting according to claim 3, characterized by: in step S2, the expanding the hail process data by the SMOTE oversampling algorithm includes the following steps:
1) for each sample x of hail process dataiCalculating Euclidean distances from the sample to other samples in the hail process data;
2) setting sampling multiplying power according to the proportion of the samples, selecting a plurality of samples in the similar hail process data, and setting the selected adjacent points as
3) For each randomly selected neighbor point
New sample points were constructed according to equation (1):
and expanding the hail process data.
5. The method of hail and short term heavy precipitation forecasting according to claim 4, characterized by: in step S1, the ground meteorological observation site data includes ground level air pressure, sea level air pressure, temperature, dew point temperature, relative humidity, water vapor pressure, 2 minute average wind direction, 2 minute average wind speed, 10 minute average wind direction, and 10 minute average wind speed.
6. The method of hail and short term heavy precipitation forecasting according to claim 5, characterized by: in step S1, the data of the sounding site includes effective convective energy cap (J · kg)-1) Optimum convection effective potential energy BCAPE (J.kg)-1) Convection suppression energy CIN (J.kg)-1) K-index KI, Samson index SI, lift index LI, optimum lift index BLI, modified K-index MK, deep convection index DCI, modified deep convection index MDCI, micro downburst daily potential index MDPI, convection stability index IC, optimum convection stability index BIC, conditional stability index IL, conditional-convection stability index ICL, total index TT, amount of atmospheric water PW (cm), convective condensation height CCL (hpa), convective temperature TCON (DEG C), elevated condensation temperature TC (DEG C), elevated condensation height PC (hpa), free convective height C (LFhpa), equilibrium height PE (hpa), 0 ℃ layer height ZH (gpm), -30 ℃ layer height FH (gpm), strong threat weather index SWEAT, thunderstorm high wind index WINDEX, storm relative vorticity index SRH, energy vorticity index EHI, rough survey number BRN, storm intensity index SSI, SWISS thunderstorm index SWISS00 and SWISS thunderstorm index SWISS 12.
7. The method of hail and short term heavy precipitation forecasting according to claim 6, characterized by: the method is characterized in that the certain region is an Tianjin region, the plurality of sounding sites are a Beijing sounding meteorological station, a chenchenge sounding meteorological station, a nutlet sounding meteorological station, a Chifeng sounding meteorological station and a Zhangkou sounding meteorological station, and the ground meteorological observation site data is the ground meteorological observation site data of the Tianjin city weather station from 2006 to 2018 in 3 to 9 months per year and three hours before the occurrence of short-time strong precipitation, and 55 hail process data and 397 short-time strong precipitation process data from 2006 to 2018 are collected.
8. The method of hail and short term heavy precipitation forecasting according to claim 7, characterized by: expanding the hail process data to 385 by using a SMOTE oversampling algorithm; and reducing the dimensionality of the hail short-time strong precipitation data set from 195 dimensions to 30 dimensions by adopting a PCA method.
9. The method of hail and short term heavy precipitation forecasting according to claim 8, characterized by: and dividing the reduced data set into a training set and a testing set according to the ratio of 8: 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911204076.5A CN110888186A (en) | 2019-11-29 | 2019-11-29 | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911204076.5A CN110888186A (en) | 2019-11-29 | 2019-11-29 | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110888186A true CN110888186A (en) | 2020-03-17 |
Family
ID=69749648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911204076.5A Pending CN110888186A (en) | 2019-11-29 | 2019-11-29 | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110888186A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111521990A (en) * | 2020-05-11 | 2020-08-11 | 沈阳工业大学 | Rainfall analysis method based on multilayer radar echo data |
| CN111796343A (en) * | 2020-06-15 | 2020-10-20 | 兰州中心气象台(兰州干旱生态环境监测预测中心) | Strong convection weather short-time approaching recognition method based on artificial intelligence algorithm |
| CN111898675A (en) * | 2020-07-30 | 2020-11-06 | 北京云从科技有限公司 | Credit wind control model generation method and device, scoring card generation method, machine readable medium and equipment |
| CN112926664A (en) * | 2021-03-01 | 2021-06-08 | 南京信息工程大学 | Feature selection and CART forest short-time strong rainfall forecasting method based on evolutionary algorithm |
| CN114169520A (en) * | 2021-11-10 | 2022-03-11 | 安徽农业大学 | Method for improving decision tree by space-time gradient |
| CN115356789A (en) * | 2022-10-08 | 2022-11-18 | 南京气象科技创新研究院 | Plum rain period short-time strong precipitation grading early warning method |
| CN115456264A (en) * | 2022-09-01 | 2022-12-09 | 北京科技大学 | Method for predicting end point carbon content and end point temperature of small and medium-sized converters |
| CN116245259A (en) * | 2023-05-11 | 2023-06-09 | 华能山东发电有限公司众泰电厂 | Photovoltaic power generation prediction method and device based on depth feature selection and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140280214A1 (en) * | 2013-03-15 | 2014-09-18 | Yahoo! Inc. | Method and system for multi-phase ranking for content personalization |
| US20150120712A1 (en) * | 2013-03-15 | 2015-04-30 | Yahoo! Inc. | Customized News Stream Utilizing Dwelltime-Based Machine Learning |
| CN105182450A (en) * | 2015-10-15 | 2015-12-23 | 成都信息工程大学 | Short-time early warning system for severe convection weather |
| CN106526708A (en) * | 2016-09-21 | 2017-03-22 | 广东奥博信息产业有限公司 | Intelligent early-warning analysis method for meteorological severe convection weather based on machine learning |
| CN107844867A (en) * | 2017-11-22 | 2018-03-27 | 广州优视网络科技有限公司 | Data processing method, device and equipment |
| CN108646319A (en) * | 2018-08-09 | 2018-10-12 | 深圳市雅码科技有限公司 | A kind of heavy showers forecasting procedure and system in short-term |
| CN108931826A (en) * | 2018-04-16 | 2018-12-04 | 武汉中心气象台(长江流域水文气象预报台湖北省决策气象服务中心) | A kind of rainstorm prediction method based on parting dosing method |
| CN110489719A (en) * | 2019-07-31 | 2019-11-22 | 天津大学 | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data |
-
2019
- 2019-11-29 CN CN201911204076.5A patent/CN110888186A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140280214A1 (en) * | 2013-03-15 | 2014-09-18 | Yahoo! Inc. | Method and system for multi-phase ranking for content personalization |
| US20150120712A1 (en) * | 2013-03-15 | 2015-04-30 | Yahoo! Inc. | Customized News Stream Utilizing Dwelltime-Based Machine Learning |
| CN105182450A (en) * | 2015-10-15 | 2015-12-23 | 成都信息工程大学 | Short-time early warning system for severe convection weather |
| CN106526708A (en) * | 2016-09-21 | 2017-03-22 | 广东奥博信息产业有限公司 | Intelligent early-warning analysis method for meteorological severe convection weather based on machine learning |
| CN107844867A (en) * | 2017-11-22 | 2018-03-27 | 广州优视网络科技有限公司 | Data processing method, device and equipment |
| CN108931826A (en) * | 2018-04-16 | 2018-12-04 | 武汉中心气象台(长江流域水文气象预报台湖北省决策气象服务中心) | A kind of rainstorm prediction method based on parting dosing method |
| CN108646319A (en) * | 2018-08-09 | 2018-10-12 | 深圳市雅码科技有限公司 | A kind of heavy showers forecasting procedure and system in short-term |
| CN110489719A (en) * | 2019-07-31 | 2019-11-22 | 天津大学 | Wind speed forecasting method based on DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM data |
Non-Patent Citations (5)
| Title |
|---|
| 德阳市气象局: "《县级气象综合业务实用手册》", 31 October 2018 * |
| 柴东红: "影响河北省雷电活动的天气系统及雷电潜势预报", 《第十届防雷减灾论坛——雷电灾害与风险评估》 * |
| 王辉: "《农学概论》", 28 February 2018 * |
| 王雪萍: "基于RF、XGBoost和FFM集成的CTR预估", 《万方数据学位论文》 * |
| 路志英: "基于深度学习的短时强降水天气识别", 《天津大学学报(自然科学与工程技术版)》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111521990A (en) * | 2020-05-11 | 2020-08-11 | 沈阳工业大学 | Rainfall analysis method based on multilayer radar echo data |
| CN111521990B (en) * | 2020-05-11 | 2022-04-29 | 沈阳工业大学 | Rainfall analysis method based on multilayer radar echo data |
| CN111796343A (en) * | 2020-06-15 | 2020-10-20 | 兰州中心气象台(兰州干旱生态环境监测预测中心) | Strong convection weather short-time approaching recognition method based on artificial intelligence algorithm |
| CN111898675A (en) * | 2020-07-30 | 2020-11-06 | 北京云从科技有限公司 | Credit wind control model generation method and device, scoring card generation method, machine readable medium and equipment |
| CN112926664A (en) * | 2021-03-01 | 2021-06-08 | 南京信息工程大学 | Feature selection and CART forest short-time strong rainfall forecasting method based on evolutionary algorithm |
| CN112926664B (en) * | 2021-03-01 | 2023-11-24 | 南京信息工程大学 | Feature selection and CART forest short-time strong precipitation prediction method based on evolutionary algorithm |
| CN114169520A (en) * | 2021-11-10 | 2022-03-11 | 安徽农业大学 | Method for improving decision tree by space-time gradient |
| CN115456264A (en) * | 2022-09-01 | 2022-12-09 | 北京科技大学 | Method for predicting end point carbon content and end point temperature of small and medium-sized converters |
| CN115356789A (en) * | 2022-10-08 | 2022-11-18 | 南京气象科技创新研究院 | Plum rain period short-time strong precipitation grading early warning method |
| CN116245259A (en) * | 2023-05-11 | 2023-06-09 | 华能山东发电有限公司众泰电厂 | Photovoltaic power generation prediction method and device based on depth feature selection and electronic equipment |
| CN116245259B (en) * | 2023-05-11 | 2023-10-31 | 华能山东泰丰新能源有限公司 | Photovoltaic power generation prediction method and device based on depth feature selection and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110888186A (en) | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model | |
| CN110728411B (en) | High-low altitude area combined rainfall prediction method based on convolutional neural network | |
| Zhou et al. | Maximum nighttime urban heat island (UHI) intensity simulation by integrating remotely sensed data and meteorological observations | |
| Torrielli et al. | Extreme wind speeds from long-term synthetic records | |
| Brocca et al. | Application of a model-based rainfall-runoff database as efficient tool for flood risk management | |
| Olsson et al. | Statistical atmospheric downscaling of short-term extreme rainfall by neural networks | |
| CN112907113B (en) | Vegetation change cause identification method considering spatial correlation | |
| CN113935228B (en) | L-band rough sea surface radiation bright temperature simulation method based on machine learning | |
| CN113836808A (en) | PM2.5 deep learning prediction method based on heavy pollution feature constraint | |
| CN111882128B (en) | TCN-based flood season climate trend prediction method | |
| CN115877483A (en) | Typhoon path forecasting method based on random forest and GRU | |
| Balti et al. | Big data based architecture for drought forecasting using LSTM, ARIMA, and Prophet: Case study of the Jiangsu Province, China | |
| Maier-Gerber et al. | Statistical–dynamical forecasting of subseasonal North Atlantic tropical cyclone occurrence | |
| CN116826737A (en) | Photovoltaic power prediction method, device, storage medium and equipment | |
| CN112200042A (en) | Method for analyzing ecological change trend by using space-time ecological environment remote sensing fractal dimension | |
| CN114819260A (en) | Dynamic generation method of hydrologic time series prediction model | |
| CN117541626B (en) | Remote sensing image change detection method based on deep learning | |
| CN113671599A (en) | Global climate mode-based login cyclone identification method | |
| CN110119494A (en) | It is a kind of based on main passive microwave remote sensing observation tropical cyclone determine strong method automatically | |
| Miller et al. | A preliminary assessment of using spatiotemporal lightning patterns for a binary classification of thunderstorm mode | |
| CN113536373A (en) | Desensitization meteorological data generation method | |
| CN110059423B (en) | Tropical cyclone objective strength determining method based on multi-factor generalized linear model | |
| CN116702588A (en) | Wind power plant key weather factor forecasting method and system based on multi-source data | |
| Dong et al. | Quality control algorithm for marine meteorological data based on interest degree association rules | |
| CN114998719A (en) | Forest fire prediction method based on deep learning and multi-source remote sensing data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200317 |