CN113240169A - Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling - Google Patents
Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling Download PDFInfo
- Publication number
- CN113240169A CN113240169A CN202110502963.1A CN202110502963A CN113240169A CN 113240169 A CN113240169 A CN 113240169A CN 202110502963 A CN202110502963 A CN 202110502963A CN 113240169 A CN113240169 A CN 113240169A
- Authority
- CN
- China
- Prior art keywords
- data
- radar echo
- short
- sampling
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000005070 sampling Methods 0.000 title claims abstract description 33
- 238000001556 precipitation Methods 0.000 claims abstract description 42
- 238000010586 diagram Methods 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims description 22
- 125000004122 cyclic group Chemical group 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 5
- 241000288105 Grus Species 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 241000219094 Vitaceae Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 235000021021 grapes Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a method for predicting short-term rainfall of a multi-level GRU network based on multi-mode data and up-down sampling, which belongs to the technical field of weather forecast and comprises the following steps: firstly, inputting a historical radar echo map and gridding atmosphere data at the time t, removing data noise and filling missing data; performing convolution and deconvolution on the spatio-temporal scale which is not matched with the radar echo diagram in the gridded atmospheric data to realize scale correspondence; then, inputting the radar echo map data and the atmospheric data into a network for coding to obtain a characteristic map; finally, splicing the two obtained characteristic graphs, inputting the two characteristic graphs into a network for decoding to obtain a future radar echo image and further obtain a future regional precipitation prediction; the method can improve the accuracy of precipitation prediction on multiple scales and fuse the image characteristics of various meteorological data.
Description
Technical Field
The invention belongs to the technical field of weather forecast, and particularly relates to a short-term rainfall prediction method of a circulating gate control unit network based on multi-mode data and up-down sampling.
Background
Changes in meteorological factors (such as wind speed, temperature, humidity, precipitation, etc.) have profoundly affected human lives. The method can accurately forecast future meteorological factors, and can be widely used in the fields of daily life, traffic transportation, agriculture, forestry, animal husbandry, disaster-causing weather refuge and the like. With the increasing number of earth observation satellites and the increasing enhancement of climate models, meteorological researchers are faced with larger-scale data.
At present, numerical prediction and artificial intelligence prediction based on numerical prediction data are the main methods for weather prediction. For numerical weather forecasting methods, short-term forecasting requires complex physical atmosphere model simulations. In recent years, machine learning and deep learning have begun to be applied to weather forecasts.
However, the traditional method mainly uses 2D-CNN or 3D-CNN, and the forecasting precision (mainly measured by CSI index) is not high; therefore, a new solution to solve the above problems is urgently needed.
Disclosure of Invention
The invention provides a short-term rainfall prediction method of a circulating gate control unit network based on multi-mode data and up-down sampling aiming at the defects in the prior art, the scheme is not only beneficial to the training of a model and the improvement of the prediction precision of the short-term rainfall, especially the prediction precision of rainstorm, but also can solve the technical problems of unbalanced rainfall data, low prediction precision of the rainstorm and less model fusion characteristics in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for short-term precipitation prediction based on a network of cyclic gate control units with multi-modal data and up-down sampling, the method comprising the steps of:
s1: input data and data cleaning, firstly, inputting a historical radar echo map and gridding atmospheric data at the time t, and performing default value linear interpolation supplement and wavelet transformation denoising on the input data to obtain processed input data; then, carrying out 1 × 1 convolution on the gridded atmospheric data which is not matched with space and time to adjust the number of characteristic channels, and then realizing scale correspondence through deconvolution; then, respectively inputting radar echo map data and gridded atmosphere data into a GRU network comprising two layers of down-sampling for coding, and splicing the two obtained feature maps to obtain a fusion feature map; finally, inputting the fusion characteristic diagram into a GRU network containing two layers of up-sampling for decoding to obtain a predicted radar echo image, obtaining future regional precipitation prediction through Z-R conversion, and outputting a short-term precipitation prediction result Yt,Yt+1,...,Yt+pWherein Y ist+qAnd (3) converting the radar echo diagram at the predicted t + q moment into a precipitation diagram, wherein q is more than or equal to 1 and less than or equal to p, and p represents the total number of the short imminent precipitation prediction moments.
The denoising process of the historical radar echo map sequence at the input t moment comprises the following steps:
first, the default data is filled using bilinear interpolation, which is shown below:
wherein QijIs a position (x) in the matrixi,yj) Is given by the value of (x, y) is the position of the default value in the matrix.
The atmospheric grid data is then denoised using a hard threshold wavelet transform.
S2: data processing using convolution and deconvolution calculations comprising the steps of:
and (3) adjusting the number of the characteristic channels by using a 1 × 1 convolution kernel, wherein the calculation formula is as follows:
wherein i represents the number of target characteristic channels of the convolution kernel mapping, and c represents the number of characteristic channels of the input data.
And (3) adjusting the size of the space of the new characteristic diagram obtained in the last step through deconvolution operation to ensure that the characteristic diagram scale is consistent with the radar echo image scale, wherein the calculation formula is as follows:
O＝K*I
where, is the matrix convolution operation, I is the matrix obtained in S21, and K is the deconvolution kernel. The parameters s, K, p of the deconvolution kernel K are set to conform to the following formula:
i＝(o-1)*s+k-2p
wherein i represents the width of the weather data square matrix, o represents the width of the radar echo map square matrix, s represents the convolution kernel moving step length, k represents the width of the convolution kernel, and p represents the width of the filling 0 value.
S3: and (3) encoding the characteristic graph and the characteristic fusion, respectively inputting radar echo graph data and gridding atmosphere data into an encoder network comprising two layers of down-sampling cyclic gate control units for encoding, and splicing the two obtained characteristic graphs. The encoder network is composed of a convolution layer, a circulation gating unit layer, a down-sampling layer and a circulation gating unit layer, a loss function selects a mean square error loss function, and an Adam optimizer selects the Adam optimizer. And splicing the radar echo image coding output by the encoder network and the gridding atmosphere data coding matrix on the characteristic channel.
S4: generating forecast and output precipitation forecast, inputting the fusion characteristic diagram into a decoder network containing two layers of up-sampled GRUs for decoding to obtain a forecast radar echo image, obtaining future regional precipitation forecast through Z-R transformation, and outputting a short-term precipitation forecast result Yt,Yt+1,...,Yt+pWherein Y ist+qAnd (3) converting the radar echo diagram at the predicted t + q moment into a precipitation diagram, wherein q is more than or equal to 1 and less than or equal to p, and p represents the total number of the short imminent precipitation prediction moments. Wherein the decoder network comprises a cyclic gate control unit, a deconvolution up-sampling unit, a cyclic gate control unit, a deconvolution up-sampling unitSample, cyclic gate control unit, and deconvolution up-sampling.
Compared with the prior art, the invention has the following beneficial effects: the invention discloses a short-term rainfall prediction method based on multimode data and a GRU network of up-down sampling, which is a method based on fusion of a plurality of meteorological features under different scales.
1. The method is beneficial to learning the geographical position information of an abstract place during the training of the model, and the prediction precision of short-term rainfall, especially the prediction precision of rainstorm, is improved;
2. the forecasting precision can be improved under different scales, and the method is suitable for regional forecasting in the practical application of weather forecasting.
3. The method reasonably uses various convolution kernel operations to reduce network parameters and can accelerate the model operation speed.
4. The method integrates various modal data, and finally improves the accuracy of model prediction.
Drawings
FIG. 1 is a schematic diagram of step S12;
FIG. 2 is a schematic diagram of step S34;
fig. 3 is a flow chart of a method of short-term precipitation prediction based on multimodal data and up-down sampled GRU networks.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
Example 1: referring to fig. 1-3, a method for predicting short-term precipitation based on multimodal data and up-down sampled GRU network includes the following steps:
s1: inputting a historical radar echo map and gridding atmospheric data at the time t, and performing default value linear interpolation supplement and wavelet transformation denoising on the input data to obtain processed input data;
s2: performing 1 × 1 convolution on the gridded atmospheric data which is not matched with time and space to adjust the number of characteristic channels, and then realizing scale correspondence through deconvolution;
s3: respectively inputting radar echo map data and gridded atmosphere data into a GRU network containing two layers of down-sampling for coding, splicing the two obtained feature maps to obtain a fusion feature map
S4: inputting the fusion characteristic diagram into a GRU network containing two layers of up-sampling for decoding to obtain a predicted radar echo image, obtaining future regional precipitation prediction through Z-R conversion, and outputting a short-term precipitation prediction result Yt,Yt+1,...,Yt+pWherein Y ist+qAnd (3) converting the radar echo diagram at the predicted t + q moment into a precipitation diagram, wherein q is more than or equal to 1 and less than or equal to p, and p represents the total number of the short imminent precipitation prediction moments.
In step S1, the denoising process for the historical radar echo map sequence at the input time t includes the following steps:
s11: the default data is filled using bilinear interpolation, which is shown below:
wherein QijIs a position (x) in the matrixi,yj) Is given by the value of (x, y) is the position of the default value in the matrix.
S12: denoising the atmospheric grid data by using hard threshold wavelet transform;
the convolution and deconvolution calculation used in step S2 includes the following steps:
s21: and (3) adjusting the number of the characteristic channels by using a 1 × 1 convolution kernel, wherein the calculation formula is as follows:
wherein i represents the number of target characteristic channels of the convolution kernel mapping, and c represents the number of characteristic channels of the input data.
S22: and (3) adjusting the size of the space of the new characteristic diagram obtained in the last step through deconvolution operation to ensure that the characteristic diagram scale is consistent with the radar echo image scale, wherein the calculation formula is as follows:
O＝K*I
where, is the matrix convolution operation, I is the matrix obtained in S21, and K is the deconvolution kernel. The parameters s, K, p of the deconvolution kernel K are set to conform to the following formula:
i＝(o-1)*s+k-2p
wherein i represents the width of the weather data square matrix, o represents the width of the radar echo map square matrix, s represents the convolution kernel moving step length, k represents the width of the convolution kernel, and p represents the width of the filling 0 value.
In step S3, the radar echo map data and the gridded atmosphere data are respectively input into an encoder network including two layers of down-sampling cyclic gate control units for encoding, and the two obtained feature maps are spliced. The encoder network is composed of a convolution layer, a circulation gating unit layer, a down-sampling layer and a circulation gating unit layer, a loss function selects a mean square error loss function, and an Adam optimizer selects the Adam optimizer. And splicing the radar echo image coding output by the encoder network and the gridding atmosphere data coding matrix on the characteristic channel.
In step S4, the fusion feature map is input into a decoder network including two layers of GRUs for decoding to obtain a predicted radar echo image, a future regional precipitation prediction is obtained through Z-R transformation, and a short-term precipitation prediction result Y is outputt,Yt+1,...,Yt+pWherein Y ist+qAnd (3) converting the radar echo diagram at the predicted t + q moment into a precipitation diagram, wherein q is more than or equal to 1 and less than or equal to p, and p represents the total number of the short imminent precipitation prediction moments. The decoder network is composed of a cyclic gate control unit, a deconvolution up-sampling unit, a cyclic gate control unit and a deconvolution up-sampling unit.
The following is a further description of the present embodiment by taking an embodiment as an example.
Detailed description of the preferred embodiment 1
The method verifies that the data set provides a radar echo map, gridding temperature and total precipitation for the Guangdong provincial weather bureau. The time span is between 2017 and 3 months to 2018 and 12 months. The resolution was 1 km and the matrix size was 300 × 1. The data interval was 12 minutes. The Z-R relationship represents the reflectivity Z and the precipitation intensity R (mm/h)In which dBZ is 10log10a+10blog10R, a, b are radar parameters, and in this experiment, the value is 58.53, 1.56. dBZ is commonly used to describe the precipitation, and in general the greater this value, the greater the reaction precipitation.
Gridded meteorological data (containing humidity at 9 altitudes, wind speed at 12 altitudes and 2 rainfall intensities, 13 characteristic channels in total) were provided for GRAPES in south china with a matrix size of 100 × 13 and a resolution of 3 km and 1 hour.
In combination with experimental experience, the radar echo map at the first 10 moments and the gridded temperature total precipitation are used in the experiment to predict the radar echo map at the later 10 moments.
The rainfall prediction evaluation index in the meteorological field is CSI score:
wherein TP is the correct forecast lattice point number, FN is the false report lattice point number, and FP is the false report lattice point number. The experiment aims to improve the CSI score of the grid sequence for rainfall prediction.
The method comprises the steps of firstly, inputting a historical radar echo map and gridded meteorological data (comprising 13 characteristic channels including humidity under 9 altitudes, wind speed under 12 altitudes and 2 rainfall intensities) at t moment, and supplementing and denoising missing values of the historical radar echo map and the gridded meteorological data; then, for the problem that the spatial-temporal resolutions are not the same, 1 × 1 convolution kernel is set to 1 × 1, and the parameters s, k, p of the deconvolution kernel are set to:
s＝3
k＝3
p＝0
mapping the gridded meteorological data to be consistent with the radar echo map data in scale; and then, respectively inputting the two feature maps into a GRU network containing two layers of down-sampling for coding, and splicing the two obtained feature maps to obtain a fused feature map. And finally, inputting the fusion characteristic graph into a GRU network containing two layers of up-sampling for decoding to obtain a predicted radar echo image, obtaining future regional precipitation prediction through Z-R conversion, and outputting a short-term precipitation prediction result.
Table 1 below is a table of model parameters for a GRU network including up and down sampling. By combining the experimental experience, the radar echo map and the gridding meteorological data at the first 10 moments are used in the experiment to predict the radar echo map at the later 10 moments.
Table 1 contains a list of model parameters for a GRU network sampled up and down
Note: 1) in the name e begins with the encoder structure and f begins with the predictor structure;
2) depth I/O refers to input depth to output depth;
the r value is the rainfall intensity grade obtained after Z-RC conversion, and the corresponding relation with rainfall broadcast is as follows
Table 2r value and precipitation broadcast correspondence as follows
| r value shift | Precipitation broadcast |
| r≥0.5 | Light rain |
| r≥2 | Light rain |
| r≥5 | Medium rain |
| r≥10 | Heavy rain |
| r≥30 | Heavy Rain |
The traditional method usually adopts 2DCNN or 3DCNN, the following table 3 shows the average scores of several models for predicting the CSI indexes of the experimental data under different levels, 2D-CNN is a model for performing time sequence images by using a two-dimensional convolutional neural network, 3D CNN is a model for representing the time sequence images by using a three-dimensional convolutional neural network by using 3D-CNN, and the higher the CSI index is, the higher the precipitation prediction precision is. As can be seen from the following table, the prediction score of the method is obviously improved compared with that of the traditional method.
TABLE 3 comparison of the prediction scores of the models implemented in the present invention with other methods
It should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, and all equivalent substitutions or substitutions made on the basis of the above-mentioned technical solutions belong to the scope of the present invention.
Claims (5)
1. The method for predicting the short-term rainfall of the GRU network based on the multi-mode data and the up-down sampling is characterized by comprising the following steps of: the method comprises the following steps:
s1: cleaning input data and data, inputting a historical radar echo map and gridding atmospheric data at the time t, and performing default value linear interpolation supplement and wavelet transformation denoising on the input data to obtain processed input data;
s2: data processing, namely performing 1 × 1 convolution on the latticed atmospheric data with unmatched time and space to adjust the number of characteristic channels, and then performing deconvolution to realize scale correspondence;
s3: coding the characteristic diagram and the characteristic fusion, namely respectively inputting radar echo diagram data and gridding atmosphere data into a GRU network comprising two layers of down-sampling for coding, and splicing the two obtained characteristic diagrams to obtain a fusion characteristic diagram;
s4: and generating a forecast and outputting the precipitation forecast.
2. The method of short-term precipitation prediction for GRU networks based on multimodal data and up-down sampling of claim 1, wherein: in step S1, the denoising process for the historical radar echo map sequence at the input time t includes the following steps:
s11: the default data is filled using bilinear interpolation, which is shown below:
wherein QijIs a position (x) in the matrixi,yj) Is larger than the value of (i, j) is larger than {1,2}, (x, y) is the position of the default value in the matrix;
s12: the atmospheric grid data is denoised using a hard threshold wavelet transform.
3. The method of short-term precipitation prediction for GRU networks based on multimodal data and up-down sampling of claim 1, wherein: the convolution and deconvolution calculation used in step S2 includes the following steps:
s21: and (3) adjusting the number of the characteristic channels by using a 1 × 1 convolution kernel, wherein the calculation formula is as follows:
wherein c represents the number of characteristic channels of the input data;
s22: and (3) adjusting the size of the space of the new characteristic diagram obtained in the last step through deconvolution operation to ensure that the characteristic diagram scale is consistent with the radar echo image scale, wherein the calculation formula is as follows:
O＝K*I
wherein, I is the matrix obtained in S21, K is the deconvolution kernel, and the parameters S, K, and p of the deconvolution kernel K are set according to the following formula:
i＝(o-1)*s+k-2p
wherein i represents the width of the weather data square matrix, o represents the width of the radar echo map square matrix, s represents the convolution kernel moving step length, k represents the width of the convolution kernel, and p represents the width of the filling 0 value.
4. The method of short-term precipitation prediction for GRU networks based on multimodal data and up-down sampling of claim 1, wherein: in step S3, the radar echo map data and the gridded atmosphere data are respectively input into an encoder network including two layers of down-sampling cyclic gate control units for encoding, and the two obtained feature maps are spliced; the encoder network consists of a convolution layer, a cyclic gating unit layer, a down-sampling layer and a cyclic gating unit layer, wherein the loss function selects a mean square error loss function, and the optimizer selects an Adam optimizer; and splicing the radar echo image coding output by the encoder network and the gridding atmosphere data coding matrix on the characteristic channel.
5. The method of short-term precipitation prediction for GRU networks based on multimodal data and up-down sampling of claim 1, wherein: in step S4, the fusion feature map is input to a decoder network including two layers of GRUs for decoding to obtain a predicted radar echo image, a future regional precipitation prediction is obtained through Z-R transformation, and a short-term precipitation prediction result Y is outputt,Yt+1,...,Yt+pWherein Y ist+qThe result of converting the radar echo diagram at the predicted time t + q into a precipitation diagram is shown, q is more than or equal to 1 and less than or equal to p, and p represents the total number of the short imminent precipitation prediction time; the decoder network is composed of a cyclic gate control unit, a deconvolution up-sampling unit, a cyclic gate control unit and a deconvolution up-sampling unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110502963.1A CN113240169A (en) | 2021-05-10 | 2021-05-10 | Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110502963.1A CN113240169A (en) | 2021-05-10 | 2021-05-10 | Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113240169A true CN113240169A (en) | 2021-08-10 |
Family
ID=77132982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110502963.1A Pending CN113240169A (en) | 2021-05-10 | 2021-05-10 | Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240169A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460555A (en) * | 2022-04-08 | 2022-05-10 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Radar echo extrapolation method and device and storage medium |
| CN114764602A (en) * | 2022-05-07 | 2022-07-19 | 东南大学 | Short-term rainfall prediction method based on space-time attention and data fusion |
| CN115016042A (en) * | 2022-06-06 | 2022-09-06 | 湖南师范大学 | Precipitation prediction method and system based on multi-encoder fusion radar and precipitation information |
| CN115390161A (en) * | 2022-07-26 | 2022-11-25 | 北京百度网讯科技有限公司 | Precipitation prediction method and device based on artificial intelligence |
| CN117991412A (en) * | 2024-04-07 | 2024-05-07 | 无锡九方科技有限公司 | Extreme precipitation prediction method and system based on multi-mode data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946762A (en) * | 2019-03-06 | 2019-06-28 | 重庆邮电大学移通学院 | A kind of method and system based on probability distribution Short-term Forecast precipitation |
| CN110363327A (en) * | 2019-06-04 | 2019-10-22 | 东南大学 | Short based on ConvLSTM and 3D-CNN faces Prediction of Precipitation method |
| CN111239739A (en) * | 2020-01-10 | 2020-06-05 | 上海眼控科技股份有限公司 | Weather radar echo map prediction method and device, computer equipment and storage medium |
| CN111708030A (en) * | 2020-05-28 | 2020-09-25 | 深圳市气象局(深圳市气象台) | Disaster weather forecasting method based on energy generation antagonism predictor |
| CN112232543A (en) * | 2020-08-31 | 2021-01-15 | 北京工业大学 | Multi-site prediction method based on graph convolution network |
| CN112734017A (en) * | 2021-04-01 | 2021-04-30 | 成都信息工程大学 | Method for establishing precipitation prediction model |
-
2021
- 2021-05-10 CN CN202110502963.1A patent/CN113240169A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946762A (en) * | 2019-03-06 | 2019-06-28 | 重庆邮电大学移通学院 | A kind of method and system based on probability distribution Short-term Forecast precipitation |
| CN110363327A (en) * | 2019-06-04 | 2019-10-22 | 东南大学 | Short based on ConvLSTM and 3D-CNN faces Prediction of Precipitation method |
| CN111239739A (en) * | 2020-01-10 | 2020-06-05 | 上海眼控科技股份有限公司 | Weather radar echo map prediction method and device, computer equipment and storage medium |
| CN111708030A (en) * | 2020-05-28 | 2020-09-25 | 深圳市气象局(深圳市气象台) | Disaster weather forecasting method based on energy generation antagonism predictor |
| CN112232543A (en) * | 2020-08-31 | 2021-01-15 | 北京工业大学 | Multi-site prediction method based on graph convolution network |
| CN112734017A (en) * | 2021-04-01 | 2021-04-30 | 成都信息工程大学 | Method for establishing precipitation prediction model |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460555A (en) * | 2022-04-08 | 2022-05-10 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Radar echo extrapolation method and device and storage medium |
| CN114764602A (en) * | 2022-05-07 | 2022-07-19 | 东南大学 | Short-term rainfall prediction method based on space-time attention and data fusion |
| CN115016042A (en) * | 2022-06-06 | 2022-09-06 | 湖南师范大学 | Precipitation prediction method and system based on multi-encoder fusion radar and precipitation information |
| CN115390161A (en) * | 2022-07-26 | 2022-11-25 | 北京百度网讯科技有限公司 | Precipitation prediction method and device based on artificial intelligence |
| CN115390161B (en) * | 2022-07-26 | 2023-11-24 | 北京百度网讯科技有限公司 | Precipitation prediction method and device based on artificial intelligence |
| CN117991412A (en) * | 2024-04-07 | 2024-05-07 | 无锡九方科技有限公司 | Extreme precipitation prediction method and system based on multi-mode data |
| CN117991412B (en) * | 2024-04-07 | 2024-06-04 | 无锡九方科技有限公司 | Extreme precipitation prediction method and system based on multi-mode data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363327B (en) | ConvLSTM and 3D-CNN-based short rainfall prediction method | |
| CN113240169A (en) | Short-term rainfall prediction method of GRU network based on multi-mode data and up-down sampling | |
| CN108508505B (en) | Heavy rainfall and thunderstorm forecasting method and system based on multi-scale convolutional neural network | |
| CN109001736B (en) | Radar echo extrapolation method based on deep space-time prediction neural network | |
| CN113255972B (en) | Short-term rainfall prediction method based on Attention mechanism | |
| CN116449462B (en) | Method, system, storage medium and equipment for predicting effective wave height space-time sequence of sea wave | |
| CN117233870B (en) | Short-term precipitation set forecasting and downscaling method based on multiple meteorological elements | |
| CN112417752B (en) | Cloud layer track prediction method and system based on convolution LSTM neural network | |
| CN111983732A (en) | Rainfall intensity estimation method based on deep learning | |
| CN116452901B (en) | Automatic extraction method for ocean culture area of remote sensing image based on deep learning | |
| CN116484189A (en) | ERA5 precipitation product downscaling method based on deep learning | |
| CN114764602A (en) | Short-term rainfall prediction method based on space-time attention and data fusion | |
| CN117008217A (en) | Short-time strong precipitation prediction method integrating self-attention module and Unet model | |
| CN116931129A (en) | Short-term precipitation prediction method, device, equipment and medium based on multi-mode set | |
| CN110046756B (en) | Short-term weather forecasting method based on wavelet denoising and Catboost | |
| CN114742206B (en) | Rainfall intensity estimation method for comprehensive multi-time space-scale Doppler radar data | |
| CN116958827A (en) | Deep learning-based abandoned land area extraction method | |
| CN113378476B (en) | Global 250-meter resolution space-time continuous leaf area index satellite product generation method | |
| CN117706660A (en) | Strong convection weather forecast method based on CNN-ViT technology | |
| CN117974444A (en) | Sea surface height super-resolution reconstruction method based on diffusion model | |
| CN117237677A (en) | Precipitation prediction correction method for overall similarity of strong precipitation space based on deep learning | |
| CN116679355A (en) | Precipitation prediction correction method based on cascade Attention-U-Net | |
| CN111104640A (en) | Rainfall observation and evaluation method and system based on analytic hierarchy process | |
| Kaparakis et al. | WF-UNet: Weather data fusion using 3d-unet for precipitation nowcasting | |
| CN114509825B (en) | Strong convection weather prediction method and system for improving three-dimensional confrontation generation neural network based on hybrid evolution algorithm |
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 |