CN112668790B - Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network - Google Patents
Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network Download PDFInfo
- Publication number
- CN112668790B CN112668790B CN202011617345.3A CN202011617345A CN112668790B CN 112668790 B CN112668790 B CN 112668790B CN 202011617345 A CN202011617345 A CN 202011617345A CN 112668790 B CN112668790 B CN 112668790B
- Authority
- CN
- China
- Prior art keywords
- lightning
- center
- time
- neural network
- cluster
- 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.)
- Active
Links
Classifications
-
- 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
Abstract
The invention discloses a lightning prediction method based on a space-time sequence clustering algorithm and an LSTM neural network, which belongs to the technical field of computer science. The invention can automatically calculate the clustering radius of the density clustering DBSCAN, and the LSTM neural network has small prediction error and high precision on the longitude and latitude of the lightning center, and can basically meet the actual lightning prediction requirement. According to the invention, the LSTM neural network is used for solving the lightning prediction problem for the first time, and the previous method generally uses polynomial fitting or other fitting methods to simulate the complex process of moving the lightning center incompletely.
Description
Technical Field
The invention belongs to the technical field of computer science, and particularly relates to a lightning prediction method based on a space-time sequence clustering algorithm and an LSTM neural network.
Background
Lightning disasters are one of the ten most serious natural disasters. Lightning is often accompanied by gusts and storms, resulting in damage to electrical distribution systems, communication equipment, and household appliances of the resident, and even more, to casualties of people and animals. As early as the 18 th century in the united states, franklin invented a lightning rod using the philadelphia lightning strike test. People never stop the step for three hundred years to prevent, control and early warn thunder and lightning. The lightning is monitored in real time by measuring tools such as a radar, a satellite, a lightning positioning instrument and the like.
At present, the lightning prediction method comprises the following steps: the traditional lightning prediction method utilizes a related calculation method to establish a potential force prediction equation through historical observation data, and establishes a lightning short-time proximity prediction model and method. The early warning based on the weather research and forecast model WRF ((Weather Research and Forecast Model) is a research on weather forecast and weather, the model can forecast weather for a global model, and numerically simulate weather phenomena for a regional model.
However, researchers have studied that the WRF model has less application in lightning early warning. The method is characterized in that the extrapolation of various observation materials is utilized to perform the proximity early warning, the current popular neural network algorithm, clustering algorithm and the like are utilized to process and model the observation data, and the reasonable extrapolation is utilized to perform the proximity early warning. Lightning forecast based on numerical model, recent forecast based on data fusion and efficient extrapolation of various high observation frequencies.
In recent years, the problem of lightning prediction is frequently studied by using a neural network, and Geng et al propose a ConvLstm-based LightNet, an encoder-decoder model and a deconvolution model are added, WRF prediction data are introduced in data aspect to correct the prediction data, but the effect of the method on short-time lightning prediction is not obvious. Feng Chong et al propose clustering-based lightning proximity prediction, from the study of spatial data characteristics and analysis methods, simulation analysis of the distribution characteristics of lightning positioning data on different planes, determination of the distribution characteristics of the lightning positioning data on longitude and latitude planes, clustering analysis of the lightning data by using a classical algorithm DBSCAN, analysis of the influence of input parameters on clustering results by a large number of simulation analysis, selection of appropriate parameters to obtain corresponding clustering results, and finally establishment of a polynomial fitting prediction method by analysis of cloud centroid distance, boundary point distance and lightning stroke frequency to predict short-time lightning. The method and the method both use a DBSCAN clustering algorithm, but the method uses a large number of parameters to analyze the clustering result, adopts a large number of parameter comparison forms to increase the difficulty in the process of finding the clustering center, reduces the accuracy of determining the clustering center, has no universality in selecting different lightning data parameters, and is very unfriendly to users without professional backgrounds.
At present, a clustering algorithm and a neural network are utilized to solve the lightning prediction problem, but the clustering radius in the DBSCAN clustering algorithm is not automatically given, and the clustering radius is obtained through empirical values or after a large number of clustering radii are given, so that the clustering radius meets the requirement.
Disclosure of Invention
The invention aims to: the invention aims to provide a lightning prediction method based on a space-time sequence clustering algorithm and an LSTM neural network, wherein the value of the clustering radius is automatically given through lightning data input on a time slice, the size of the clustering radius does not need to be adjusted repeatedly, and the lightning center is determined more accurately, more quickly and more conveniently by combining the clustering algorithm.
The technical scheme is as follows: in order to achieve the above purpose, the invention adopts the following technical scheme:
a lightning prediction method based on a space-time sequence clustering algorithm and an LSTM neural network comprises the following steps:
1) The improvement process of density clustering DBSCAN algorithm based on thunder and lightning prediction problem;
2) And predicting the short-time lightning by using the LSTM neural network.
Further, in the step 1), the lightning data to be predicted in a period of time is divided into time slices, and the lightning data to be predicted in a period of time is selected; the data comprise longitude, latitude, lightning intensity, lightning gradient of lightning, and moment of lightning; dividing the data into time slices; it is assumed that the movement of the lightning centre is jumping between divided time slices, i.e. the lightning centre is stationary for the divided time periods.
Further, in the step 1), euclidean distances between all lightning active geographic positions on a time slice are calculated to obtain a distance set D (i) ＝(d 1 ，d 2 ，...，d h ，...)Wherein i represents the number of common lightning activities over the time slice, d h Representing the distance between some two lightning activities over this time slice, h representing the distance between some two lightning activities over the time slice (i) Is a statistic of the distance between some two lightning activities over this time slice.
Further, in the step 1), the distance set D is counted (i) In the interval V1[0,0.1 ], V2[0.1,0.2 ], V3[0.2,0.3 ], V4[0.3, 0.4), V5[0.4, 0.5) are m 1 ，m 2 ，m 3 ，m 4 ，m 5 Representing and constructing a statistical matrix
Taking median values of intervals V1, V2, V3, V4 and V5 as p1, p2, p3, p4 and p5, and calculating by using a formula
Searching for clusters by the obtained Eps neighborhood value and defined mints = 2 and by examining the Eps neighborhood for each point in the lightning dataset; if the minimum number of points contained in the Eps neighborhood of the point O exceeds the number of MinPts, creating a cluster taking the point O as a core object; when no new points are added to any cluster, a cluster of lightning clusters is determined. Q is referred to as a noise point if q does not belong to any one of the clusters of lightning clusters.
Further, in said step 1), the lightning activity (o) on the determined lightning cluster 1 ，o 2 ，...，o n ) Geographic location o of (2) 1 (w 1 ，v 1 )，o 2 (w 2 ，v 2 )，......，，o n (w n ，v n ) And pass through the formulaObtaining the lightning center k by adopting an average value method>Wherein o is n Representing the activity of a certain lightning center on the cluster, w n And v n Latitude and longitude representing the activity of a certain lightning centre on the cluster, +.>And->Representing the average of all lightning center latitudes and longitudes over the cluster.
Further, in the step 2), a lightning center change data is processed, where the lightning center change data includes a start-stop time T of a time slice, a longitude L of a lightning center, a latitude W of the lightning center, an intensity ST of the lightning center (an average value of all lightning activity intensities of one cluster), a gradient SL of the lightning center (an average value of all lightning activity gradients of one cluster), and a number of lightning strokes Num on the time slice is counted.
Further, in the step 2), data T, L, ST, SL, num on different time slices of a lightning center are input into a longitude LSTM neural network to obtain a longitude value of the lightning activity in the next time sequence; all lightning center data T, W, ST, SL, num of a lightning activity are input into a latitude LSTM neural network to obtain the latitude value of the lightning activity in the next time sequence.
The beneficial effects are that: compared with the prior art, the lightning prediction method based on the space-time sequence clustering algorithm and the LSTM neural network provided by the invention has the advantages that according to the change of longitude and latitude of the lightning center, the DBSCAN density clustering algorithm based on the lightning prediction improvement is utilized to obtain the Eps value and the lightning center of each time slice, and the geographic position of the lightning center of the next time slice is predicted through the LSTM neural network. The invention can automatically calculate the clustering radius of the density clustering DBSCAN, and the LSTM neural network has small prediction error and high precision on the longitude and latitude of the lightning center, and can basically meet the actual lightning prediction requirement. According to the invention, the LSTM neural network is used for solving the lightning prediction problem for the first time, and the previous method generally uses polynomial fitting or other fitting methods to simulate the complex process of moving the lightning center incompletely.
Drawings
FIG. 1 is a diagram of an improved process framework of the density clustering DBSCAN algorithm of the present invention;
FIG. 2 is a block diagram of the LSTM neural network prediction process for short-term lightning according to the present invention;
fig. 3 is a graph of lightning center position variation.
Detailed Description
The invention is further described below in conjunction with the detailed description.
The lightning prediction method based on the space-time sequence clustering algorithm and the LSTM neural network is characterized by comprising an improvement process of density clustering DBSCAN algorithm based on the lightning prediction problem and a prediction process of short-time lightning by utilizing the LSTM neural network; the specific description is as follows:
a, an improvement process of a density clustering DBSCAN algorithm based on a lightning prediction problem comprises the following steps:
step A1, dividing time slices of lightning data to be predicted within a period of time, and selecting the lightning data to be predicted within the period of time; the data comprise longitude, latitude, lightning intensity, lightning gradient of lightning, and moment of lightning; the data was divided into time slices every 10 minutes.
Assume that: between the divided time slices, the movement of the lightning centre is jumped, i.e. the lightning centre is stationary for the divided time period.
Step A2, calculating Euclidean distances among all lightning activity geographic positions on a time slice to obtain a distance set D (i) ＝(d 1 ，d 2 ，...，d h ，...)Wherein i represents the number of common lightning activities over the time slice, d h Indicating this timeThe distance between two lightning activities on the spacer, h, is expressed in the set D (i) Is a statistic of the distance between some two lightning activities over this time slice.
Step A3, counting distance set D (i) In the interval V1[0,0.1 ], V2[0.1,0.2 ], V3[0.2,0.3 ], V4[0.3, 0.4), V5[0.4, 0.5) are m 1 ，m 2 ，m 3 ，m 4 ，m 5 Representing and constructing a statistical matrix
Description: the lightning center is calculated by dividing the lightning activities with the geographical positions closer to each other into one lightning center, and if the geographical positions of the two lightning activities are far more than 0.5 degree apart (the actual distance is more than about 50 km), namely, the intervals of V1, V2, V3, V4 and V5 which are not divided are not counted, then statistics are not necessary, and the two lightning activities are not necessarily divided into one lightning center.
Step A4, taking median values of intervals V1, V2, V3, V4 and V5 as p1, p2, p3, p4 and p5, and calculating by using a formula
Step A5, searching for clusters by obtaining Eps neighborhood values and defined mints=2 and by examining the Eps neighborhood for each point in the lightning dataset. If the minimum number of points contained in the Eps neighborhood of the point O exceeds the number of MinPts, creating a cluster taking the point O as a core object;
step A6, determining clusters of lightning aggregation when no new points are added to any clusters. Q is referred to as a noise point if q does not belong to any cluster of lightning aggregation;
step A7, determining lightning Activity on lightning aggregation cluster (o 1 ，o 2 ，...，o n ) Geographic location o of (2) 1 (w 1 ，v 1 )，o 2 (w 2 ，v 2 )，......，，o n (w n ，v n ) And pass through the formula Obtaining the lightning center k by adopting an average value method>
Wherein o is n Representing the activity of a certain lightning center on the cluster, w n And v n Representing the latitude and longitude of the activity of a certain lightning center on the cluster,and->Representing the average of all lightning center latitudes and longitudes over the cluster.
And B, predicting short-time lightning by using an LSTM neural network, wherein the method comprises the following steps of:
step B1, processing lightning center change data, wherein the lightning center change data comprise starting and stopping time T of a time slice, longitude L of a lightning center, latitude W of the lightning center, intensity ST of the lightning center (average value of all lightning activity intensities of one cluster), gradient SL of the lightning center (average value of all lightning activity gradients of one cluster) and statistics of lightning stroke times Num on the time slice;
step B2, inputting data T, L, ST, SL and Num on different time slices of a lightning center into a longitude LSTM neural network to obtain a longitude value of the lightning activity in the next time sequence; all lightning center data T, W, ST, SL, num of a lightning activity are input into a latitude LSTM neural network to obtain the latitude value of the lightning activity in the next time sequence.
Examples
The lightning prediction method based on the space-time sequence clustering algorithm and the LSTM neural network specifically comprises the following steps:
before calculating the lightning center of lightning activity, firstly, the selected lightning data which is to be predicted to have the most frequent lightning activity in a period of time is divided into time slices every 10 minutes, and the data is sourced from the weather bureau of Hunan province. In this example, lightning data of 6 months and 17 days in 2010 of Hunan province were selected for analysis. After a large amount of thunder and lightning data are collected, weather experience shows that the error of the data obtained by the positioning mode of the three-station time difference direction finding method is smaller, and the data of which the data positioning mode is not the three-station time difference direction finding method is deleted. The lightning center is calculated by an improved density clustering DBSCAN method, and the method comprises the following steps:
in the first step, from lightning data of the year 6 and 17 in the year 2010 of Hunan province, the lightning activities are found to be relatively dense from 3:55 in the early morning, and in order to analyze the movement trend of the lightning center, the lightning data of 10 minutes after 3:55 minutes are selected, and each 10 minutes of the data is divided into one time slice and 13 time slices. The following is a 4:15-4:25 time slice lightning activity table:
and a second step of: calculating Euclidean distances among all lightning activity geographic positions on a time period slice to obtain a distance set D i ＝(d 1 ，d 2 ，...，d h ，...)Wherein the units of Euclidean distance are: a degree; statistical distance set D i In the interval V1[0,0.1), V2[0.1,0.2 ], V3[0.2,0.3), V4[0.3, 0.4), V5[0.4, 0.5), and constructing a statistical matrix ]>Taking the median values of intervals V1, V2, V3, V4 and V5 as p1, p2, p3, p4 and p5, and calculating +.>
And a third step of: clusters are searched by obtaining Eps neighborhood values and defined mints=2 and by examining the Eps neighborhood for each point in the lightning dataset. If the minimum number of points contained in the Eps neighborhood of the point O exceeds the number of MinPts, creating a cluster taking the point O as a core object; when no new points are added to any cluster, a cluster of lightning clusters is determined. Q is referred to as a noise point if q does not belong to any cluster of lightning aggregation; lightning (o) on a defined cluster of lightning clusters 1 ，o 2 ，...，o n ) Geographic location o of (2) 1 (w 1 ，v 1 )，o 2 (w 2 ，v 2 ))，......，，o n (w n ，v n ) And pass through the formula Obtaining the lightning center k by adopting an average value method>
The following is a table showing lightning centers on all time slices for the improved DBSCAN algorithm:
the following is a table of lightning center changes:
FIG. 3 shows a diagram of the change of the location of the lightning center, wherein the data of the change of the geographic location of the lightning center is used for predicting short-time lightning by using an LSTM neural network, and the following steps are specifically operated:
the first step: processing lightning center change data in the lightning centers C1, C2 and C3, wherein the lightning center change data comprise starting and stopping time T of a time slice, longitude L of the lightning center, latitude W of the lightning center, strength ST of the lightning center (average value of all lightning activity strengths of one cluster), gradient SL of the lightning center (average value of all lightning activity gradients of one cluster), and counting lightning stroke times m on the time slice;
the following is a table of lightning center C1 variation:
| T | L | W | ST | SL | Num |
| 4:05～4:15 | 109.9085 | 26.6765 | -34.919000 | -3.550000 | 2 |
| 4:15～4:25 | 110.1515 | 26.75475 | -38.259750 | -7.325000 | 4 |
| 4:25～4:35 | 110.228667 | 26.748333 | -50.165500 | -8.200000 | 6 |
| 4:35～4:45 | 110.197000 | 26.734500 | -12.904100 | 0.680000 | 10 |
| 4:45～4:55 | 110.011000 | 26.729714 | -35.824286 | -9.628571 | 5 |
| 4:55～5:05 | 110.244857 | 26.785857 | 18.799143 | 3.571429 | 7 |
| 5:05～5:15 | 110.308667 | 26.697667 | 18.403000 | 4.533333 | 3 |
| 5:35～5:45 | 110.138000 | 26.761000 | -44.340500 | -11.85000 | 2 |
| 5:45～5:55 | 110.226000 | 26.733750 | -57.509250 | -11.22500 | 4 |
secondly, inputting all lightning center data T, L, ST, SL and Num of a lightning activity into a longitude LSTM neural network to obtain a longitude value of the lightning activity in a next time sequence; all lightning center data T, W, ST, SL, num of a lightning activity are input into a latitude LSTM neural network to obtain the latitude value of the lightning activity in the next time sequence.
The foregoing is merely a preferred embodiment of the present invention, and it will be apparent to those skilled in the art that modifications and variations can be made without departing from the technical principles of the present invention, and the modifications and variations should also be regarded as the scope of the invention.
Claims (2)
1. A lightning prediction method based on a space-time sequence clustering algorithm and an LSTM neural network is characterized in that: the method comprises the following steps:
1) The improvement process of density clustering DBSCAN algorithm based on thunder and lightning prediction problem;
in the step 1), time slice division is carried out on the lightning data to be predicted within a period of time, and the lightning data to be predicted within a period of time is selected; the data comprise longitude, latitude, lightning intensity, lightning gradient of lightning, and moment of lightning; dividing the data into time slices; assuming that the movement of the lightning center is jumped between divided time slices;
firstly, calculating Euclidean distances among all lightning activity geographic positions on a time slice to obtain a distance set D (i) ＝(d 1 ，d 2 ，...，d h ，...)Wherein i represents the number of common lightning activities over the time slice, d h Representing the distance between some two lightning activities over this time slice, h representing the distance between some two lightning activities over the time slice (i) Counting the distance between two lightning activities on the same time slice;
second, statistical distance set D (i) In the interval V1[0,0.1 ], V2[0.1,0.2 ], V3[0.2,0.3 ], V4[0.3, 0.4), V5[0.4, 0.5) are m 1 ，m 2 ，m 3 ，m 4 ，m 5 Representing and constructing a statistical matrix
Taking median values of intervals V1, V2, V3, V4 and V5 as p1, p2, p3, p4 and p5, and calculating by using a formula
Searching for clusters by the obtained Eps neighborhood value and defined mints = 2 and by examining the Eps neighborhood for each point in the lightning dataset; if the minimum number of points contained in the Eps neighborhood of the point O exceeds the number of MinPts, creating a cluster taking the point O as a core object; when no new points are added to any cluster, a cluster of lightning clusters is determined; q is referred to as a noise point if q does not belong to any cluster of lightning aggregation;
then, the lightning activity (o) on the lightning cluster determined in said step 1) 1 ,o 2 ,...,o n ) Geographic location o of (2) 1 (w 1 ,v 1 ),o 2 (w 2 ,v 2 ),......，,o n (w n ,v n ) And pass through the formula Obtaining lightning center by average value method>Wherein o is n Representing the activity of a certain lightning center on the cluster, w n And v n Latitude and longitude representing the activity of a certain lightning centre on the cluster, +.>And->Representing the average value of the latitude and longitude of all lightning centers on the cluster;
2) Predicting short-time lightning by using an LSTM neural network;
in the step 2), processing lightning center change data, wherein the lightning center change data comprises starting and stopping time T of a time slice, longitude L of a lightning center, latitude W of the lightning center, strength ST of the lightning center, gradient SL of the lightning center and statistics of lightning stroke times Num on the time slice.
2. The lightning prediction method based on the space-time sequence clustering algorithm and the LSTM neural network as claimed in claim 1, wherein the method is characterized by comprising the following steps of: in the step 2), data T, L, ST, SL and Num on different time slices of a lightning center are input into a longitude LSTM neural network to obtain a longitude value of the lightning activity in the next time sequence; all lightning center data T, W, ST, SL, num of a lightning activity are input into a latitude LSTM neural network to obtain the latitude value of the lightning activity in the next time sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011617345.3A CN112668790B (en) | 2020-12-30 | 2020-12-30 | Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011617345.3A CN112668790B (en) | 2020-12-30 | 2020-12-30 | Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112668790A CN112668790A (en) | 2021-04-16 |
| CN112668790B true CN112668790B (en) | 2023-07-25 |
Family
ID=75411445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011617345.3A Active CN112668790B (en) | 2020-12-30 | 2020-12-30 | Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668790B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327022B (en) * | 2021-05-18 | 2022-05-03 | 重庆莱霆防雷技术有限责任公司 | Lightning protection safety risk management system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
| CN105118047A (en) * | 2015-07-15 | 2015-12-02 | 陕西师范大学 | Auroral oval boundary position prediction method based on interplanetary and geomagnetic parameters |
| CN106251026A (en) * | 2016-08-16 | 2016-12-21 | 南京信息工程大学 | Thunder and lightning based on PDBSCAN algorithm closes on trend prediction method |
| CN108427041A (en) * | 2018-03-14 | 2018-08-21 | 南京中科九章信息技术有限公司 | Lightning Warning method, system, electronic equipment and storage medium |
| CN108520023A (en) * | 2018-03-22 | 2018-09-11 | 合肥佳讯科技有限公司 | A kind of identification of thunderstorm core and method for tracing based on Hybrid Clustering Algorithm |
| CN109061774A (en) * | 2018-06-26 | 2018-12-21 | 合肥佳讯科技有限公司 | A kind of thunderstorm core relevance processing method |
| CN109738970A (en) * | 2018-12-07 | 2019-05-10 | 国网江苏省电力有限公司电力科学研究院 | The method, apparatus and storage medium for realizing Lightning Warning are excavated based on lightning data |
| CN111290053A (en) * | 2020-02-29 | 2020-06-16 | 华南理工大学 | Thunderstorm path prediction method based on Kalman filtering |
-
2020
- 2020-12-30 CN CN202011617345.3A patent/CN112668790B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
| CN105118047A (en) * | 2015-07-15 | 2015-12-02 | 陕西师范大学 | Auroral oval boundary position prediction method based on interplanetary and geomagnetic parameters |
| CN106251026A (en) * | 2016-08-16 | 2016-12-21 | 南京信息工程大学 | Thunder and lightning based on PDBSCAN algorithm closes on trend prediction method |
| CN108427041A (en) * | 2018-03-14 | 2018-08-21 | 南京中科九章信息技术有限公司 | Lightning Warning method, system, electronic equipment and storage medium |
| CN108520023A (en) * | 2018-03-22 | 2018-09-11 | 合肥佳讯科技有限公司 | A kind of identification of thunderstorm core and method for tracing based on Hybrid Clustering Algorithm |
| CN109061774A (en) * | 2018-06-26 | 2018-12-21 | 合肥佳讯科技有限公司 | A kind of thunderstorm core relevance processing method |
| CN109738970A (en) * | 2018-12-07 | 2019-05-10 | 国网江苏省电力有限公司电力科学研究院 | The method, apparatus and storage medium for realizing Lightning Warning are excavated based on lightning data |
| CN111290053A (en) * | 2020-02-29 | 2020-06-16 | 华南理工大学 | Thunderstorm path prediction method based on Kalman filtering |
Non-Patent Citations (2)
| Title |
|---|
| 基于过程的输电线路雷电活动描述新方法;吴敏;王韬;赵淳;王佩;郭钧天;陈路;潘佳鑫;罗飞;;电网技术(03);329-335 * |
| 时空序列预测方法综述;黎维;陶蔚;周星宇;潘志松;;计算机应用研究(10);2881-2888 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112668790A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022089031A1 (en) | Network optimization method based on big data and artificial intelligence | |
| CN102253426B (en) | Method for predicting lightning motion by space density clustering | |
| CN108268597A (en) | A kind of moving-target activity probability map construction and behavior intension recognizing method | |
| CN110430578B (en) | Method for realizing cell azimuth prediction based on mobile terminal data | |
| CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
| Viegas et al. | Convergence in the Spanish and Portuguese NUTS 3 regions: An exploratory spatial approach | |
| CN107784165B (en) | Surface temperature field multi-scale data assimilation method based on photovoltaic power station | |
| CN107832876A (en) | Subregion peak load Forecasting Methodology based on MapReduce frameworks | |
| CN113379107B (en) | Regional ionosphere TEC forecasting method based on LSTM and GCN | |
| CN112668790B (en) | Lightning prediction method based on space-time sequence clustering algorithm and LSTM neural network | |
| Johansson et al. | Crime hotspots: An evaluation of the KDE spatial mapping technique | |
| CN110717619A (en) | Multi-scale space-time load prediction method and system for bottom-up power distribution network | |
| CN113327022A (en) | Lightning protection safety risk management system and method | |
| CN110322067A (en) | Location of mobile users prediction technique based on factor graph model | |
| CN110503267A (en) | Wealth case forecasting system and prediction technique are invaded in city based on spatial and temporal scales adaptive model | |
| CN114205831B (en) | Method, device, storage medium and equipment for determining optimization scheme | |
| CN111833224A (en) | Urban main and auxiliary center boundary identification method based on population grid data | |
| CN110348717A (en) | Base station value methods of marking and device based on grid granularity | |
| CN103218516A (en) | Clustered and retrogressed single-step predication method of airport noises | |
| CN102254090B (en) | Method for estimating lightning density distribution and annual average ground flash density (NG) value by kernel density estimation | |
| CN112561392A (en) | Evaluation system and method for green space service level of city park | |
| CN116796904A (en) | Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit | |
| CN103218523A (en) | Method for visualizing airport noise based on grid queues and piecewise fitting | |
| Frei et al. | Modeling spatial embedded social networks | |
| CN112561121B (en) | Rework trend prediction method and system based on mobile phone signaling 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |