CN113095590A - High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field - Google Patents
High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field Download PDFInfo
- Publication number
- CN113095590A CN113095590A CN202110474013.2A CN202110474013A CN113095590A CN 113095590 A CN113095590 A CN 113095590A CN 202110474013 A CN202110474013 A CN 202110474013A CN 113095590 A CN113095590 A CN 113095590A
- Authority
- CN
- China
- Prior art keywords
- rainfall
- field
- microwave
- short
- horizontal
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 22
- 238000013213 extrapolation Methods 0.000 claims abstract description 13
- 230000002123 temporal effect Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 230000001788 irregular Effects 0.000 claims description 2
- 239000013598 vector Substances 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 230000008859 change Effects 0.000 abstract description 2
- 239000010410 layer Substances 0.000 description 31
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000002346 layers by function Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 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
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—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
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Environmental & Geological Engineering (AREA)
- Biodiversity & Conservation Biology (AREA)
- Atmospheric Sciences (AREA)
- Environmental Sciences (AREA)
- Primary Health Care (AREA)
- Ecology (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Radar Systems Or Details Thereof (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention provides a high spatial and temporal resolution reconstruction analysis and short-term prediction method for a microwave horizontal rainfall field, which specifically comprises the following steps: s1, building a microwave link rainfall observation network based on the distribution of the ground microwave stations, and carrying out meshing processing on a rainfall area; s2, calculating the average rain attenuation of the microwave link path, and performing reconstruction analysis of a rainfall field with high spatial-temporal resolution level according to the correlation between the rainfall intensities of all the positions in the rainfall area; and S3, based on the reconstructed high-space-time resolution continuous horizontal rainfall field, the prediction of the short-term rainfall field is realized by utilizing a deep learning method. The invention establishes a high-space-time resolution horizontal rainfall field reconstruction model and a rainfall field short-term extrapolation model considering rainfall space-time change characteristics, realizes the reconstruction and extrapolation prediction of the high-space-time resolution horizontal rainfall field by microwave link signals, and lays a technical foundation for establishing rainfall monitoring and early warning nets in a high-space-time resolution area.
Description
Technical Field
The invention relates to the field of rainfall measurement, in particular to a high spatial-temporal resolution reconstruction analysis and short-term prediction method for a microwave horizontal rainfall field.
Background
The method for measuring rainfall by using the attenuation effect of the microwave link is a new rainfall measurement technology appearing in recent years, has great potential and vital significance in aspects of monitoring natural disasters caused by strong rainfall, guaranteeing future high-technology military operations and the like, is an effective method for obtaining a high-space-time-resolution rainfall field, and has the advantages of large sampling space-time density, high resolution, wide coverage range and the like.
At present, the application of the microwave link in regional rainfall monitoring is just started, particularly, the rainfall field reconstruction analysis based on the satellite-ground microwave link is mostly realized based on an interpolation method, and no relevant scholars are internationally discussed and researched aiming at the short-term prediction of the rainfall field based on the satellite-ground microwave link. Based on the existing research, the invention establishes a horizontal rainfall field reconstruction model and a rainfall field short-term extrapolation model considering rainfall temporal-spatial variation characteristics, realizes the reconstruction analysis and extrapolation prediction of a high temporal-spatial resolution horizontal rainfall field by utilizing multi-station microwave link signals, and lays a technical foundation for establishing a rainfall monitoring early warning network in a high temporal-spatial resolution area.
Disclosure of Invention
The invention provides a high spatial-temporal resolution reconstruction analysis and short-term rainfall field prediction method for a microwave horizontal rainfall field.
In order to achieve the purpose, the invention provides the following scheme:
the high spatial-temporal resolution reconstruction analysis and short-term prediction method for the microwave horizontal rainfall field is characterized by comprising the following steps of:
s1, building a microwave link rainfall observation network composed of microwave links based on the distribution of the ground microwave stations, and carrying out gridding treatment on a rainfall area;
s2, calculating an average rainfall attenuation value of a microwave link path, and performing reconstruction analysis of a high-spatial-temporal-resolution level rainfall field according to the correlation between rainfall intensities of all positions in the rainfall region;
and S3, based on the reconstructed high-spatial-temporal-resolution horizontal rainfall field, predicting the short-term rainfall field by using a deep learning method.
Preferably, in S1, the types of the microwave link rainfall observation networks include a satellite-ground microwave link network and a ground microwave link network.
Preferably, the relevant factors composing the microwave link rainfall observation network include the number of the composing link networks, the length of the links, the density of the link networks and the spatial distribution of the link networks, and further include irregular grids based on the distribution condition and the uneven distribution of the satellites and the ground receiving stations.
Preferably, in S2, the step of reconstructing and analyzing the rainfall field with high spatial-temporal resolution level includes:
calculating the average rainfall condition of the microwave link path to obtain a path rainfall attenuation value;
obtaining the average rainfall intensity of all links through a power model;
and reconstructing the horizontal rainfall field with high space-time resolution by a kriging interpolation method or a short-distance weighting method based on the correlation between the rainfall intensities of all the positions in the rainfall region by using the obtained average rainfall intensity of all the links.
Preferably, in S3, the step of predicting the short rainfall field by using the deep learning method includes:
s3.1, constructing a deep learning network with an input and output structure for the high spatial and temporal resolution area rainfall field extrapolation;
s3.2, establishing a relation training set of the rainfall intensity in each grid and the rainfall intensities at n adjacent moments in the horizontal rainfall field through historical data;
s3.3, training the deep learning network by using an LSTM method and combining with the distribution characteristics of the rainfall intensity in the rainfall field actually measured in the training set, and establishing a mapping relation for predicting the rainfall intensity in the rainfall field at the next moment;
s3.4, according to the error between the rainfall intensity of the rainfall field and the actually measured rainfall field predicted at the next moment, adjusting the parameters of the LSTM model in an iteration mode until the loss function meets the termination condition or reaches the maximum iteration times;
and S3.5, predicting the rainfall intensity of the actually measured rainfall field according to the deep learning network model to obtain the predicted short-term rainfall field.
Preferably, the deep learning network comprises a sequence input layer, a convolutional layer, a pooling layer, an LSTM layer, a fully-connected layer, a regression layer, and an output layer.
Preferably, said S3.3 specifically comprises:
the sequence input layer receives rainfall field samples from the training set, the rainfall intensity characteristics in each rainfall field are extracted through the convolutional layer, the characteristic vectors generated after passing through the pooling layer are sent to the LSTM layer, output quantities are generated and enter the full-connection layer, and the rainfall intensity mapping relation in the rainfall field at the next moment is established through the full-connection layer.
Preferably, in S3.4, the termination condition is that the loss function loss is less than 0.01, and the maximum number of iterations is 500.
The invention has the beneficial effects that:
according to the high spatial and temporal resolution reconstruction analysis and short-term prediction method for the microwave horizontal rainfall field, a high spatial and temporal resolution horizontal rainfall field reconstruction model and a rainfall field short-term extrapolation model considering rainfall temporal and spatial variation characteristics are established, reconstruction and extrapolation prediction of the high spatial and temporal resolution horizontal rainfall field by microwave link signals are realized, and a technical foundation is laid for establishing rainfall monitoring and early warning networks in a high spatial and temporal resolution area.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a link network detection diagram of the present invention;
FIG. 3 is a schematic diagram of the prediction of a short rainfall field based on a deep learning network according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The invention utilizes the attenuation information of satellite-ground link or ground microwave link signals in the propagation of a rainfall region, carries out reconstruction analysis of a horizontal rainfall field with high space-time resolution through microwave link networking based on multiple stations, and carries out prediction of a short-term rainfall field based on deep learning, as shown in the attached figure 1. The method for high space-time resolution reconstruction analysis and short-term prediction of a microwave horizontal rainfall field by taking a satellite-ground link network as an embodiment mainly comprises the following steps:
the method comprises the following steps: based on the position of a ground satellite receiving station, a satellite-ground link network composed of k satellite-ground links is designed and built, the specific structure distribution of the satellite-ground link network is shown in fig. 2, wherein 40 ground stations receive signals of 5 broadcasting satellites, the satellite-ground link network is composed of 93 links, the received satellite signals are all vertically polarized, and the working frequency is 11.56 GHz-12.59 GHz.
As shown in fig. 2, the horizontal rainfall region is gridded, and the whole rainfall field is divided into 35 × 35 grids, and the resolution of each grid is 1 × 1km2The distribution of rain intensity within each grid is assumed to be uniform and the variation of rain intensity over vertical height is not taken into account.
Step two: and calculating the average rainfall condition of the satellite-ground link path. For the kth satellite-ground link in the rainfall area, the rainfall attenuation of the path is AR(k) Can be expressed as:
in the formula, h0Height of rain zone, theta elevation angle of satellite antenna, gammaiFor the attenuation of the ith lattice point, N represents the number of grids traversed by the kth link, L represents the length of the horizontal projection of the link on the ground, diRepresenting the projected length of the link in the ith mesh.
And obtaining the average rainfall intensity R (k) of all links by utilizing a power-law model according to the obtained rainfall attenuation value:
R(k)=[AR(k)sinθ/h0α]β-1
wherein, alpha and beta are power coefficient, h0Is the height of the rain zone, and theta is the satellite antenna elevation angle.
Reconstructing a horizontal rainfall field with high space-time resolution by using the obtained average rainfall intensity of all links and a kriging interpolation method according to the correlation between the rainfall intensities of all positions in the rainfall area:
in the formula, R (x)i,yi) Is the satellite-to-ground link at position R (x)t,yt) Inverted rainfall intensity, n denotes the number of satellite-to-ground links, λiRepresents R (x) as a weight coefficienti,yi) And R (x)t,yt) Is related toAnd (4) degree.
Step three: according to a continuous rainfall field reconstructed by a satellite-ground link network, a learning network for region rainfall field extrapolation with high space-time resolution is designed based on a deep learning mode, so that the short-term rainfall approaching process is predicted, and the method specifically comprises the following steps:
(1) a deep learning network with an Input/Output structure for high-spatial-resolution regional rainfall field extrapolation is designed, and as shown in fig. 3, the deep learning network provided by the present invention for realizing short-term rainfall field prediction includes 7 different functional layers, which are a Sequence Input Layer (Sequence Input Layer), a Convolutional Layer (Convolutional Layer), a Pooling Layer (Pooling Layer), a long-short time neural network Layer (LSTM Layer), a full connection Layer (full Connected), a Regression Layer (Regression Layer), and an Output Layer (Output Layer).
(2) Constructing a deep learning network with an input and output structure for the high spatial and temporal resolution area rainfall field extrapolation; establishing a relation training set of the raininess of each grid point and the raininess of n adjacent moments in the horizontal rainfall field by using historical data; and training the deep learning network by using an LSTM method and combining with the distribution characteristics of the rainfall intensity in the rainfall field actually measured in the training set. Specifically, a sequence input layer receives rainfall field samples from a training set, a two-dimensional convolution layer extracts rainfall intensity characteristics in each rainfall field through a convolution kernel of 3 x 3, a two-dimensional pooling layer is used for reducing redundant characteristic quantities and reflecting rainfall intensity spatial distribution information, the generated characteristic quantities enter an LSTM unit composed of a forgetting gate, an updating gate and an output gate, the generated output quantities enter a full-connection layer, and a mapping relation for predicting the rainfall intensity in the rainfall field at the next moment is established through the full-connection layer.
(3) And (3) predicting the error between the rainfall intensity of the rainfall field and the actually measured rainfall field according to the next moment, and adjusting the parameters of the LSTM model in an iteration mode until the loss function meets the termination condition or reaches the maximum iteration times. In the deep learning network, the termination condition may be that the loss function loss is less than 0.01, and the maximum iteration number is 500.
(4) And predicting the rainfall intensity of the actually measured rainfall field according to the determined deep learning network model to obtain the predicted short rainfall field.
The invention has the following beneficial effects:
the invention establishes a high-space-time resolution horizontal rainfall field reconstruction model and a rainfall field short-term extrapolation model considering rainfall space-time change characteristics, realizes the reconstruction and extrapolation prediction of the high-space-time resolution horizontal rainfall field by microwave link signals, and lays a technical foundation for establishing rainfall monitoring and early warning nets in a high-space-time resolution area.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.
Claims (8)
1. The high spatial-temporal resolution reconstruction analysis and short-term prediction method for the microwave horizontal rainfall field is characterized by comprising the following steps of:
s1, building a microwave link rainfall observation network composed of microwave links based on the distribution of the ground microwave stations, and carrying out gridding treatment on a rainfall area;
s2, calculating an average rainfall attenuation value of a microwave link path, and performing reconstruction analysis of a high-spatial-temporal-resolution level rainfall field according to the correlation between rainfall intensities of all positions in the rainfall region;
and S3, based on the reconstructed high-spatial-temporal-resolution horizontal rainfall field, predicting the short-term rainfall field by using a deep learning method.
2. The method for high spatial-temporal resolution reconstruction analysis and short-term prediction of a microwave horizontal rainfall field according to claim 1, wherein in S1, the types of the microwave link rainfall observation networks include a satellite-ground microwave link network and a ground microwave link network.
3. The method for high spatial-temporal resolution reconstruction analysis and short-term prediction of microwave horizontal rainfall field according to claim 2, wherein the relevant factors composing the microwave link rainfall observation network include the number of the links composing the link network, the length of the links, the density of the link network, the spatial distribution of the link network, and irregular grids based on the distribution condition and the uneven distribution of the satellite and the ground receiving station.
4. The method for high spatial and temporal resolution reconstruction analysis and shorthand prediction of a microwave horizontal rainfall field according to claim 1, wherein in S2, the step of high spatial and temporal resolution reconstruction analysis of a horizontal rainfall field comprises:
calculating the average rainfall condition of the microwave link path to obtain a path rainfall attenuation value;
obtaining the average rainfall intensity of all links through a power model;
and reconstructing the horizontal rainfall field with high space-time resolution by a kriging interpolation method or a short-distance weighting method based on the correlation between the rainfall intensities of all the positions in the rainfall region by using the obtained average rainfall intensity of all the links.
5. The method for high spatial and temporal resolution reconstruction analysis and short-term prediction of a microwave horizontal rainfall field according to claim 1, wherein the step of predicting the short-term rainfall field by using a deep learning method in S3 comprises:
s3.1, constructing a deep learning network with an input and output structure for the high spatial and temporal resolution area rainfall field extrapolation;
s3.2, establishing a relation training set of the rainfall intensity in each grid and the rainfall intensities at n adjacent moments in the horizontal rainfall field through historical data;
s3.3, training the deep learning network by using an LSTM method and combining with the distribution characteristics of the rainfall intensity in the rainfall field actually measured in the training set, and establishing a mapping relation for predicting the rainfall intensity in the rainfall field at the next moment;
s3.4, according to the error between the rainfall intensity of the rainfall field and the actually measured rainfall field predicted at the next moment, adjusting the parameters of the LSTM model in an iteration mode until the loss function meets the termination condition or reaches the maximum iteration times;
and S3.5, predicting the rainfall intensity of the actually measured rainfall field according to the deep learning network model to obtain the predicted short-term rainfall field.
6. The method of claim 5, wherein the deep learning network comprises a sequence input layer, a convolutional layer, a pooling layer, an LSTM layer, a fully-connected layer, a regression layer, and an output layer.
7. The microwave horizontal rainfall field high spatial-temporal resolution reconstruction analysis and shorthand prediction method according to claim 5, wherein the S3.3 specifically comprises:
the sequence input layer receives rainfall field samples from the training set, the rainfall intensity characteristics in each rainfall field are extracted through the convolutional layer, the characteristic vectors generated after passing through the pooling layer are sent to the LSTM layer, output quantities are generated and enter the full-connection layer, and the rainfall intensity mapping relation in the rainfall field at the next moment is established through the full-connection layer.
8. The method for high spatial and temporal resolution reconstruction analysis and short-term prediction of a microwave-level rainfall field according to claim 5, wherein in S3.4, the termination condition is that the loss function loss is less than 0.01, and the maximum iteration number is 500.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110474013.2A CN113095590B (en) | 2021-04-29 | 2021-04-29 | High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110474013.2A CN113095590B (en) | 2021-04-29 | 2021-04-29 | High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113095590A true CN113095590A (en) | 2021-07-09 |
CN113095590B CN113095590B (en) | 2022-04-29 |
Family
ID=76680595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110474013.2A Active CN113095590B (en) | 2021-04-29 | 2021-04-29 | High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113095590B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113820758A (en) * | 2021-09-09 | 2021-12-21 | 河海大学 | Near-ground three-dimensional rainfall field inversion method considering microwave link height difference |
CN113962083A (en) * | 2021-10-21 | 2022-01-21 | 中国人民解放军国防科技大学 | Microwave lean information rainfall field construction method based on sparse representation |
CN115291304A (en) * | 2022-08-03 | 2022-11-04 | 河海大学 | Omnidirectional antenna radial microwave intensive rainfall monitoring network deployment method |
CN115308817A (en) * | 2022-08-05 | 2022-11-08 | 中国人民解放军国防科技大学 | Signal learning and dynamic determination method based on reference signal characteristics |
CN115840908A (en) * | 2022-05-02 | 2023-03-24 | 河海大学 | Method for constructing PM2.5 three-dimensional dynamic monitoring field by microwave link based on LSTM model |
CN116383701A (en) * | 2023-04-13 | 2023-07-04 | 中国人民解放军国防科技大学 | Microwave link rainy period detection method based on learning reconstruction |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104656163A (en) * | 2015-02-04 | 2015-05-27 | 中国人民解放军理工大学 | Rainfall distribution and dynamic measurement method based on big-data mobile communication network |
WO2015182142A1 (en) * | 2014-05-28 | 2015-12-03 | 国立大学法人京都大学 | Weather forecasting system |
CN106324709A (en) * | 2016-10-21 | 2017-01-11 | 中国人民解放军理工大学 | Rainfall field reconstruction method by integrating microwave link, disdrometer, rain gauge and weather radar |
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 |
CN110008439A (en) * | 2019-03-25 | 2019-07-12 | 武汉大学 | Rainfall data Spatio-temporal modeling interpolation algorithm based on matrix decomposition |
CN110031916A (en) * | 2019-03-07 | 2019-07-19 | 中国人民解放军国防科技大学 | Rainfall intensity measurement method based on satellite-ground link attenuation effect |
CN110766795A (en) * | 2019-10-11 | 2020-02-07 | 中国人民解放军国防科技大学 | Method and system for detecting three-dimensional rainfall field by three-dimensional satellite-ground link dense-mesh network |
CN110850510A (en) * | 2019-11-05 | 2020-02-28 | 中国人民解放军国防科技大学 | Method for reconstructing vertical rainfall field based on satellite-ground link scanning |
CN111666656A (en) * | 2020-05-09 | 2020-09-15 | 江苏微之润智能技术有限公司 | Rainfall estimation method and rainfall monitoring system based on microwave rainfall attenuation |
CN111815037A (en) * | 2020-06-24 | 2020-10-23 | 河海大学 | Interpretable short-critical extreme rainfall prediction method based on attention mechanism |
CN112183886A (en) * | 2020-10-22 | 2021-01-05 | 南京信息工程大学 | Short-time approaching rainfall prediction method based on convolutional network and attention mechanism |
AU2021100001A4 (en) * | 2021-01-01 | 2021-03-18 | Baghavathi Priya, S. DR | Scientific model for predicting change in rainfall using climatic raster data mining |
-
2021
- 2021-04-29 CN CN202110474013.2A patent/CN113095590B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015182142A1 (en) * | 2014-05-28 | 2015-12-03 | 国立大学法人京都大学 | Weather forecasting system |
CN104656163A (en) * | 2015-02-04 | 2015-05-27 | 中国人民解放军理工大学 | Rainfall distribution and dynamic measurement method based on big-data mobile communication network |
CN106324709A (en) * | 2016-10-21 | 2017-01-11 | 中国人民解放军理工大学 | Rainfall field reconstruction method by integrating microwave link, disdrometer, rain gauge and weather radar |
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 |
CN110031916A (en) * | 2019-03-07 | 2019-07-19 | 中国人民解放军国防科技大学 | Rainfall intensity measurement method based on satellite-ground link attenuation effect |
CN110008439A (en) * | 2019-03-25 | 2019-07-12 | 武汉大学 | Rainfall data Spatio-temporal modeling interpolation algorithm based on matrix decomposition |
CN110766795A (en) * | 2019-10-11 | 2020-02-07 | 中国人民解放军国防科技大学 | Method and system for detecting three-dimensional rainfall field by three-dimensional satellite-ground link dense-mesh network |
CN110850510A (en) * | 2019-11-05 | 2020-02-28 | 中国人民解放军国防科技大学 | Method for reconstructing vertical rainfall field based on satellite-ground link scanning |
CN111666656A (en) * | 2020-05-09 | 2020-09-15 | 江苏微之润智能技术有限公司 | Rainfall estimation method and rainfall monitoring system based on microwave rainfall attenuation |
CN111815037A (en) * | 2020-06-24 | 2020-10-23 | 河海大学 | Interpretable short-critical extreme rainfall prediction method based on attention mechanism |
CN112183886A (en) * | 2020-10-22 | 2021-01-05 | 南京信息工程大学 | Short-time approaching rainfall prediction method based on convolutional network and attention mechanism |
AU2021100001A4 (en) * | 2021-01-01 | 2021-03-18 | Baghavathi Priya, S. DR | Scientific model for predicting change in rainfall using climatic raster data mining |
Non-Patent Citations (5)
Title |
---|
LU XU等: "Tomographic Reconstruction of Rainfall Fields Using Satellite Communication Links", 《2017 23RD ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS (APCC)》 * |
咸明皓 等: "基于星地链路的垂直降雨场反演方法", 《物理学报》 * |
姜世泰等: "基于微波链路的降雨场反演方法研究", 《物理学报》 * |
杨素慧等: "结合双流3D卷积和监控图像的降水临近预报", 《激光与电子学进展》 * |
赵迎诚 等: "微波链路网对降雨强度场反演的影响研究", 《电波科学学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113820758A (en) * | 2021-09-09 | 2021-12-21 | 河海大学 | Near-ground three-dimensional rainfall field inversion method considering microwave link height difference |
CN113820758B (en) * | 2021-09-09 | 2022-05-06 | 河海大学 | Near-ground three-dimensional rainfall field inversion method considering microwave link elevation difference |
CN113962083A (en) * | 2021-10-21 | 2022-01-21 | 中国人民解放军国防科技大学 | Microwave lean information rainfall field construction method based on sparse representation |
CN115840908A (en) * | 2022-05-02 | 2023-03-24 | 河海大学 | Method for constructing PM2.5 three-dimensional dynamic monitoring field by microwave link based on LSTM model |
CN115840908B (en) * | 2022-05-02 | 2023-07-14 | 河海大学 | Method for constructing PM2.5 three-dimensional dynamic monitoring field based on microwave link of LSTM model |
CN115291304A (en) * | 2022-08-03 | 2022-11-04 | 河海大学 | Omnidirectional antenna radial microwave intensive rainfall monitoring network deployment method |
CN115291304B (en) * | 2022-08-03 | 2023-06-16 | 河海大学 | Deployment method of omnidirectional antenna spoke type microwave dense rainfall monitoring network |
CN115308817A (en) * | 2022-08-05 | 2022-11-08 | 中国人民解放军国防科技大学 | Signal learning and dynamic determination method based on reference signal characteristics |
CN115308817B (en) * | 2022-08-05 | 2024-04-19 | 中国人民解放军国防科技大学 | Signal learning and dynamic determination method based on reference signal characteristics |
CN116383701A (en) * | 2023-04-13 | 2023-07-04 | 中国人民解放军国防科技大学 | Microwave link rainy period detection method based on learning reconstruction |
CN116383701B (en) * | 2023-04-13 | 2024-01-26 | 中国人民解放军国防科技大学 | Microwave link rainy period detection method based on learning reconstruction |
Also Published As
Publication number | Publication date |
---|---|
CN113095590B (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113095590B (en) | High spatial-temporal resolution reconstruction analysis and short-term prediction method for microwave horizontal rainfall field | |
CN109697323B (en) | Rainfall observation method integrating satellite remote sensing and mobile communication base station signals | |
Liu et al. | Accurate prediction scheme of water quality in smart mariculture with deep Bi-S-SRU learning network | |
CN111666656A (en) | Rainfall estimation method and rainfall monitoring system based on microwave rainfall attenuation | |
CN106815971B (en) | A kind of landslide disaster forecasting procedure based on RBF neural | |
Rios Gaona et al. | Measurement and interpolation uncertainties in rainfall maps from cellular communication networks | |
CN112512069B (en) | Network intelligent optimization method and device based on channel beam pattern | |
US20210341646A1 (en) | Weather parameter prediction model training method, weather parameter prediction method, electronic device and storage medium | |
CN110850510A (en) | Method for reconstructing vertical rainfall field based on satellite-ground link scanning | |
CN106779067A (en) | Soil moisture method for reconstructing and system based on multi- source Remote Sensing Data data | |
Zhang et al. | FNN-based prediction of wireless channel with atmospheric duct | |
CN112182063A (en) | Method for constructing hydrological forecasting model based on space-time characteristics | |
Ahuna et al. | Rainfall rate prediction based on artificial neural networks for rain fade mitigation over earth-satellite link | |
CN114357670A (en) | Power distribution network power consumption data abnormity early warning method based on BLS and self-encoder | |
CN116148796A (en) | Strong convection weather proximity forecasting method based on radar image extrapolation | |
CN113644996B (en) | Cell-level RSRP estimation method based on deep learning | |
Kumar et al. | Deep learning based scintillation prediction for satellite link using measured data | |
Bashir et al. | Decomposition and Harris hawks optimized multivariate wind speed forecasting utilizing sequence2sequence-based spatiotemporal attention | |
Sotiroudis et al. | Optimal artificial neural network design for propagation path-loss prediction using adaptive evolutionary algorithms | |
CN103916953B (en) | Method, system and the detection node of target positioning | |
Cheng et al. | CNN-based indoor path loss modeling with reconstruction of input images | |
CN117114168A (en) | Long-time-scale sea surface temperature intelligent forecasting method | |
CN104361399A (en) | Solar irradiation intensity minute-scale predication method | |
CN115840908B (en) | Method for constructing PM2.5 three-dimensional dynamic monitoring field based on microwave link of LSTM model | |
CN115392128A (en) | Method for simulating basin runoff by utilizing space-time convolution LSTM network |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |