AU2020372283A1 - Lightning prediction method - Google Patents
Lightning prediction method Download PDFInfo
- Publication number
- AU2020372283A1 AU2020372283A1 AU2020372283A AU2020372283A AU2020372283A1 AU 2020372283 A1 AU2020372283 A1 AU 2020372283A1 AU 2020372283 A AU2020372283 A AU 2020372283A AU 2020372283 A AU2020372283 A AU 2020372283A AU 2020372283 A1 AU2020372283 A1 AU 2020372283A1
- Authority
- AU
- Australia
- Prior art keywords
- lightning
- forecasting
- order
- meteorological
- parameter
- 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.)
- Abandoned
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 238000007637 random forest analysis Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000001556 precipitation Methods 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000005381 potential energy Methods 0.000 claims description 4
- 238000002310 reflectometry Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 2
- 238000013213 extrapolation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A lightning prediction method, comprising the following steps: obtaining basic meteorological parameters of an area to be predicted; calculating high-order meteorological parameters related to lightning based on the high-order meteorological parameters of said area; obtaining lightning positioning observation data of said area, and performing grid processing on the lightning positioning observation data; based on a random forest algorithm, calculating the degree of correlation between each high-order meteorological parameter and lightning, and selecting the high-order meteorological parameter with the highest degree of correlation to lightning; establishing a forecasting model by utilizing an XGBoost algorithm based on the forecasting timeliness and the forecasting time; and based on the high-order meteorological parameters of said area, predicting the spatial distribution and occurrence probability of lightning by utilizing the prediction model.
Description
[0001] The disclosure relates to the field of disaster prevention and reduction, and more
particularly to a lightning prediction method.
[0002] Lightning is often accompanied by lightning flash and thunder, which is also called
lightning flash. It is an extremely spectacular and destructive natural phenomenon. The
lightning usually occurs in a cumulonimbus cloud with intense convection, or between a
charged thundercloud and a ground protrusion. The occurrence and development of the
lightning is a result of comprehensive effects made by natural and physical phenomenon, such
as atmospheric motion and the Earth's magnetic field. As a strong discharge phenomenon, the
current value during the occurrence of lightning can reach to tens of thousands amperes.
Moreover, the instantaneous voltage of the lightning is also very high, which can reach to
several million volts. The power of a middle-to-low intensity thunderstorm can reach to about
million watts, which is equivalent to an output power of a small nuclear power plant. Thus,
the energy released by the lightning is huge and its instantaneous destructiveness is extremely
strong. It is listed as one of the ten most serious natural disasters in the "United Nations
International Decade for Disaster Reduction". Therefore, in order to effectively reduce the
impact of lightning disasters on economic and social development and avoid the occurrence of
heavy casualties and economic loss accidents, it is very important to carry out lightning
warning.
[0003] The lightning warning is an indispensable part of the disastrous weather forecasting.
The improvement of its accuracy and forecasting service level is closely related to the development of the society and the safety of various industries and people's lives. Common lightning forecasting and warning methods are radar data extrapolation, numerical model direct forecasting, empirical forecasting based on meteorological elements and short-term forecasting based on an atmospheric electric field instrument. Among them, the accuracy of the numerical model direct forecasting is high, but the required calculation is very large and the cost is high. The required calculations of the radar data extrapolation and the empirical forecasting based on meteorological elements are much smaller than that of the numerical model direct forecasting, but the accuracy is low. The accuracy of the short-term forecasting based on an atmospheric electric field instrument is more accurate, but the forecasting timeless is very short.
[0004] The existing lightning warning methods have many disadvantages, such as low
accuracy, large computing resources and short forecasting timeliness. The current problem to
be solved is to reduce the calculations, save the costs, improve the forecasting timeliness, and
obtain a better accuracy.
[0005] It is one objective of the invention to provide a lightning prediction method which has
less calculation, low cost and high forecasting accuracy.
[0006] Technical scheme of the invention is as follows:
[0007] A lightning prediction method, comprising the following steps:
[0008] Sl: obtaining basic meteorological parameters of an area to be predicted;
[0009] S2: calculating high-order meteorological parameters related to lightning based on the
high-order meteorological parameters of said area;
[0010] S3: obtaining lightning positioning observation data of said area, and performing grid
processing on the lightning positioning observation data;
[0011] S4: based on a random forest algorithm, calculating the degree of correlation between
each high-order meteorological parameter and lightning, and selecting the high-order
meteorological parameter with the highest degree of correlation to lightning;
[0012] S5: establishing a forecasting model by utilizing an XGBoost algorithm based on
forecasting timeliness, forecasting time and the high-order meteorological parameter with the
highest degree of correlation to lightning;
[0013] S6: based on the high-order meteorological parameters of said area, predicting the
spatial distribution and occurrence probability of lightning by utilizing the forecasting model.
[0014] In a preferred technical scheme, the basic meteorological parameter includes the
temperature, humidity, dew point, vorticity, atmospheric pressure, convective precipitation,
non-convective precipitation, convective available potential energy and radar reflectivity at
different altitude in the area to be predicted.
[0015] In a preferred technical scheme, the high-order meteorological parameter includes A
index, K index, showalter index and severe weather threat index.
[0016] In a preferred technical scheme, in the step S3, "performing grid processing on the
lightning positioning observation data" means that the lightning positioning observation data is
converted to the gridded data having the same longitude, latitude and resolution as the basic meteorological parameters by means of gridding.
[0017] In a preferred technical scheme, in the step S4, "based on a random forest algorithm,
calculating the degree of correlation between each high-order meteorological parameter and
lightning" comprises the following steps: establishing a random forest model by taking each
high-order meteorological parameter as an eigenvector and taking the lightning positioning
observation data after being processed by the gridding as a target vector; calculating the
importance of each eigenvector by taking an out-of-bag function as an evaluation index; and
determining the degree of correlation between each high-order meteorological parameter and
lightning according to the importance of each eigenvector.
[0018] In a preferred technical scheme, in the step S5, "establishing a forecasting model by
utilizing an XGBoost algorithm based on the forecasting timeliness, the forecasting time and
the high-order meteorological parameter with the highest degree of correlation to lightning"
means that for each high-order meteorological parameter, performing Bayesian parameter
adjustment on the hyperparameter of the XGBoost algorithm through a hyperopt algorithm, in
which the historical data of the high-order meteorological parameter is used as the eigenvector,
the lightning positioning observation data after being processed by the gridding is used as the
target vector and a linear regression function is used as an objective parameter; and
establishing a forecasting model for the high-order meteorological parameters and the
lightning data at different forecasting time, namely obtaining a multi-time forecasting model.
[0019] In a preferred technical scheme, the step S6 comprising:
[0020] (1) inputting the high-order meteorological parameters within each forecasting time
into the multi-time forecasting model to obtain lightning forecasting data within each
forecasting time;
[0021] (2) recombining the lightning forecasting data sequence within the same forecasting
time to generate gridded lightning forecasting data based on the high-order meteorological
parameters of the area to be predicted.
[0022] Compared with the prior art, advantages of the invention are summarized as follows:
[0023] Compared with the numerical forecasting, the lightning forecasting method disclosed
by this invention significantly reduces the amount of calculation and greatly reduces the
calculation cost. Further, the forecasting model is established by the random forest algorithm
and the XGBoost algorithm. Compared with the numerical forecasting model based on a
complex solution of fluid mechanics equation with several Tflop/s, this method has the
advantages of less calculation and low cost. In addition, compared with a traditional
meteorological statistical model based on linear model, it introduces more nonlinearity and
higher complexity, so that the accuracy is higher, and its forecasting timeliness is equal to an
input global model forecasting timeliness which can be up to more than ten days.
[0024] The above description is only an overview of the technical solutions of this invention.
In order to clearly understand the technical means of this invention, it can be implemented in
accordance with the content of the specification. In order to make the other objectives, features
and advantages of this invention more obvious and understandable, the following preferred
embodiments are given.
[0025] In order to further explain the technical means and effects of the invention, the specific embodiments, structures, features and effects of the invention are further described in details combining with the following preferred embodiments.
[0026] This invention discloses a lightning prediction method, comprising the following steps:
[0027] Si: obtaining basic meteorological parameters of an area to be predicted;
[0028] S2: calculating high-order meteorological parameters related to lightning based on the
high-order meteorological parameters of said area;
[0029] S3: obtaining lightning positioning observation data of said area, and performing grid
processing on the lightning positioning observation data;
[0030] S4: based on a random forest algorithm, calculating the degree of correlation between
each high-order meteorological parameter and lightning, and selecting the high-order
meteorological parameter with the highest degree of correlation to lightning; it is because
when using the random forest algorithm to determine the importance of the high-order
meteorological parameters, there is no need to consider whether the high-order meteorological
parameters are linearly separable, and there is no need to normalize or standardize the features;
[0031] S5: establishing a forecasting model by utilizing an XGBoost algorithm based on the
forecasting timeliness, the forecasting time and the high-order meteorological parameter with
the highest degree of correlation to lightning.
[0032] The XGBoost algorithm is one of the boosting algorithms, and the idea of the Boosting
algorithm is to integrate many weak classifiers into a strong classifier. Moreover, since
XGBoost is a boosting tree model, it integrates many tree models into a strong classifier. In
this invention, the objective function of lightning forecasting is a linear regression function.
For each forecasting time and each time period, Bayesian optimization method is used to
optimize the coefficients, such as maximum depth, the number of trees, learning rate, the
number of samplings, and the sum of the smallest sample proportions of the terminal node, and then the obtained new observation data is put into a training sample at an interval for obtaining a new forecasting model. Therefore, the forecasting effects of the forecasting model of this invention can be continuously improved.
[0033] S6: based on the high-order meteorological parameters of said area, predicting the
spatial distribution and occurrence probability of lightning by utilizing the forecasting model.
[0034] In a preferred technical scheme, the basic meteorological parameter includes the
temperature, humidity, dew point, vorticity, atmospheric pressure, convective precipitation,
non-convective precipitation, convective available potential energy and radar reflectivity at
different altitude in the area to be predicted. Specially, the variables, such as the temperature,
humidity, dew point and vorticity of each barosphere, the convective precipitation,
non-convective precipitation and convective available potential energy of the ground, are
obtained from an EC global forecasting model every 3 hours for 72 hours. The radar
reflectivity is obtained from a regional forecasting model.
[0035] The high-order meteorological parameter includes A index, K index, showalter index
and severe weather threat index.
[0036] (1) The calculation formula of A index is:
[0037] A= T850-T500-(T850-Td850)-(T700-Td700)-(T500-Td500);
[0038] (2) The calculation formula of K index is:
[0039] K=T850-T500+Td850-(T700-Td700);
[0040] (3) The showalter index is defined as:
[0041] SI=T500-T' , in which, T' is the temperature of air parcel when wet air block on the
isobaric surface of 850hPa rises along a dry adiabat and then rises to 500hPa along a moist
adiabat after reaching a condensation level.
[0042] (4) The severe weather threat index is defined as:
[0043] SWEA -=12*Td850+20*(TT-49)+4*WF850+2*WF500+125*(sin(WD500-WD 850)+0.2)
, wherein, TT represents a total index value, if the sub-term of the formula is less than 0, the
value of the sub-term is zero, the unit of WF is "m/s", the rightmost sub-term must satisfy that
the range of WD850 is between 130°and 2500, the range of WD500 is between 21 0 °and 310°,
WD500 is greater than WD850, and when both WF850 and WF500 are greater than 7.5m/s,
the calculation is performed, otherwise it is zero.
[0044] In the above formulas, T represents a temperature, Td represents a potential
temperature, WF represents a wind speed, WD represents a wind direction, and the suffix
value represents the barosphere where the variable is located.
[0045] In the step S3, "performing grid processing on the lightning positioning observation
data" means that the lightning positioning observation data is converted to the gridded data
having the same longitude, latitude and resolution as the basic meteorological parameters by
means of gridding. This is because the lightning positioning observation data is site data, the
gridding method can be used to convert the lightning positioning observation data to the
gridded data having the same longitude, latitude and resolution as the basic meteorological
parameters.
[0046] In order to better illustrate the method of gridding, taking a grid point in the area to be
predicted as an example, the grid point is taken as the center of a circle and R is taken as the
radius, and the number of lightning flash is N, when R<20km and N/ R231/(5*5 ), the value of the grid point is 1, otherwise it is 0, and finally a two-dimensional matrix is obtained, which is the gridded lightning data.
[0047] In a preferred technical scheme, in the step S4, "based on a random forest algorithm, calculating the degree of correlation between each high-order meteorological parameter and
lightning" comprises the following steps: establishing the random forest model by taking each
high-order meteorological parameter as an eigenvector and taking the lightning positioning
observation data after being processed by the gridding as a target vector; calculating the
importance of each eigenvector by taking an out-of-bag function as an evaluation index; and
determining the degree of correlation between each high-order meteorological parameter and
lightning according to the importance of each eigenvector.
[0048] In addition, the high-order meteorological parameter with the highest degree of
correlation to lightning is one or more parameters selected from the A index, K index,
showalter index and severe weather threat index, and the parameter is used as the important
reference variable of the lightning forecasting.
[0049] In a preferred technical scheme, in the step S5, "establishing a forecasting model by
utilizing an XGBoost algorithm based on the forecasting timeliness, the forecasting time and
the high-order meteorological parameter with the highest degree of correlation to lightning"
means that for each high-order meteorological parameter, performing Bayesian parameter
adjustment on the hyperparameter of the XGBoost algorithm through a hyperopt algorithm, in
which the historical data of the high-order meteorological parameter is used as the eigenvector,
the lightning positioning observation data after being processed by the gridding is used as the
target vector and a linear regression function is used as an objective parameter; and
establishing a forecasting model for the high-order meteorological parameters and the
lightning data at different forecasting time, namely obtaining a multi-time forecasting model.
Specially, it comprises the following steps: (1) for each high-order meteorological parameter, performing Bayesian parameter adjustment on the hyperparameter of the XGBoost algorithm, such as iteration number, the number of trees, the depth of trees, through a hyperopt algorithm, in which the lightning positioning observation data after being processed by gridding is used as the target vector and a linear regression function is used as an objective parameter; (2) establishing the forecasting model for the high-order meteorological parameters and the lightning data at each forecasting time, namely obtaining the multi-time forecasting model.
[0050] In this invention, due to the following advantages of the XGBoost algorithm, the
XGBoost algorithm is used to establish the forecasting model. (1) The XGBoost algorithm
supports linear classifiers, which means that the logistic regression (classification problem)
and the linear regression (regression problem) of LI regularization term and L2 regularization
term are introduced; (2) the XGBoost algorithm conducts a two-order Taylor expansion on a
cost function and introduces a first order derivative and the second order derivative, so that the
whole objective can be clearly understood and how to perform the learning of the trees can be
deduced; (3) if a missing value exists in the sample, XGBoost can automatically learn the
splitting direction; (4) similar to the approach of RF, XG Boost supports a column sampling,
which can not only prevent overfitting, but also reduce the amount of calculation; (5) the cost
function of the XGBoost algorithm introduces a regularization term to control the complexity
of the model. The regularization term includes the number of all leaf nodes, and the square
sum of the L2 modulus of the score output by each leaf node. From the perspective of
Bayesian variance, the regularization term reduces the variance of the model and prevents the
model from overfitting; (6) After each iteration, XGBoost allocates a learning rate to the leaf
nodes, reduces the weight of each tree and reduces the influence of each tree, so that a better
learning space is obtained; (7) XGBoost tool supports parallelism, but it is not the parallelism
on a tree granularity, but the parallelism on a feature granularity. The most time-consuming
step of a decision tree is to sequence the value of the feature. Before the iteration, XGBoost
performs pre-sorting and saves it as a block structure. This structure is reused in each iteration,
so that it reduces the calculation of the model. It is also possible for the block structure to provide the parallelism for the model. When splitting the node, the gain of each feature is calculated, and the feature having the largest gain is chosen for the next splitting, so that the gain of each feature can be performed in multi-threads; (8) For the parallel approximate histogram algorithm, when splitting the tree nodes, the gain of each node needs to be calculated. If the amount of data is large, the features of all nodes should be sorted and the optimal splitting point can be obtained through traverse. This greedy method is extremely time-consuming. At this time, the approximate histogram algorithm is introduced to generate efficient splitting points, that is, a certain value after splitting is subtracted from a certain value before splitting to obtain a gain. In order to limit the growth of the tree, a threshold is introduced. When the gain is greater than the threshold, the splitting is performed. Generally,
XGBoost is the most commonly used for machine learning modeling of structured data. It is
also one of the best models.
[0051] In a preferred technical scheme, the step S6 comprising:
[0052] (1) Inputting the high-order meteorological parameters within each forecasting time
into the multi-time forecasting model to obtain lightning forecasting data within each
forecasting time;
[0053] (2) Recombining the lightning forecasting data sequence within the same forecasting
time to generate gridded lightning forecasting data.
[0054] The above-mentioned embodiments are only preferred embodiments of this invention
and cannot be used to limit the protection scope of this invention. Any non-substantial changes
and substitutions made by the person skilled in the art based on this invention fall within the
scope of this invention.
Claims (7)
- CLAIMS 1. A lightning prediction method, comprising:Sl: obtaining basic meteorological parameters of an area to be predicted;S2: calculating high-order meteorological parameters related to lightning based on thehigh-order meteorological parameters of said area;S3: obtaining lightning positioning observation data of said area, and performing gridprocessing on the lightning positioning observation data;S4: based on a random forest algorithm, calculating the degree of correlation between eachhigh-order meteorological parameter and lightning, and selecting the high-ordermeteorological parameter with the highest degree of correlation to lightning;S5: establishing a forecasting model by utilizing an XGBoost algorithm based on forecastingtimeliness, forecasting time and the high-order meteorological parameter with the highestdegree of correlation to lightning;S6: based on the high-order meteorological parameters of said area, predicting the spatialdistribution and occurrence probability of lightning by utilizing the forecasting model.
- 2. The method according to the claim 1, characterized in that the basic meteorologicalparameter includes the temperature, humidity, dew point, vorticity, atmospheric pressure,convective precipitation, non-convective precipitation, convective available potential energyand radar reflectivity at different altitude in the area to be predicted.
- 3. The method according to the claim 1, characterized in that the high-order meteorological parameter includes A index, K index, showalter index and severe weather threat index.
- 4. The method according to the claim 1, characterized in that in the step S3, "performinggrid processing on the lightning positioning observation data" means that the lightningpositioning observation data is converted to the gridded data having the same longitude,latitude and resolution as the basic meteorological parameters by means of gridding.
- 5. The method according to the claim 1, characterized in that in the step S4, "based on arandom forest algorithm, calculating the degree of correlation between each high-ordermeteorological parameter and lightning" comprises the following steps: establishing a randomforest model by taking each high-order meteorological parameter as an eigenvector and takingthe lightning positioning observation data after being processed by the gridding as a targetvector; calculating the importance of each eigenvector by taking an out-of-bag function as anevaluation index; and determining the degree of correlation between each high-ordermeteorological parameter and lightning according to the importance of each eigenvector.
- 6. The method according to the claim 1, characterized in that in the step S5, "establishingaforecasting model by utilizing an XGBoost algorithm based on forecasting timeliness,forecasting time and the high-order meteorological parameter with the highest degree ofcorrelation to lightning" means that for each high-order meteorological parameter, performingBayesian parameter adjustment on the hyperparameter of the XGBoost algorithm through ahyperopt algorithm, in which the historical data of the high-order meteorological parameter isused as an eigenvector, the lightning positioning observation data after being processed by thegridding is used as a target vector and a linear regression function is used as an objectiveparameter; and establishing a forecasting model for the high-order meteorological parametersand the lightning data at different forecasting time, namely obtaining a multi-time forecastingmodel.
- 7. The method according to the claim 6, characterized in that the step S6 comprising:(1) inputting the high-order meteorological parameters within each forecasting time into themulti-time forecasting model to obtain lightning forecasting data within each forecasting time;(2) recombining the lightning forecasting data sequence within the same forecasting time togenerate gridded lightning forecasting data.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911011363.4 | 2019-10-23 | ||
| CN201911011363.4A CN110796299A (en) | 2019-10-23 | 2019-10-23 | Thunder and lightning prediction method |
| PCT/CN2020/090434 WO2021077729A1 (en) | 2019-10-23 | 2020-05-15 | Lightning prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2020372283A1 true AU2020372283A1 (en) | 2021-11-25 |
Family
ID=69440985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020372283A Abandoned AU2020372283A1 (en) | 2019-10-23 | 2020-05-15 | Lightning prediction method |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN110796299A (en) |
| AU (1) | AU2020372283A1 (en) |
| WO (1) | WO2021077729A1 (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796299A (en) * | 2019-10-23 | 2020-02-14 | 国网电力科学研究院武汉南瑞有限责任公司 | Thunder and lightning prediction method |
| CN111695593A (en) * | 2020-04-29 | 2020-09-22 | 平安科技（深圳）有限公司 | XGboost-based data classification method and device, computer equipment and storage medium |
| CN111694047B (en) * | 2020-05-09 | 2021-03-23 | 吉林大学 | Borehole strain network topological structure abnormity detection method based on multi-channel singular spectrum |
| CN111913236A (en) * | 2020-07-13 | 2020-11-10 | 上海眼控科技股份有限公司 | Meteorological data processing method, meteorological data processing device, computer equipment and storage medium |
| CN111897030A (en) * | 2020-07-17 | 2020-11-06 | 国网电力科学研究院有限公司 | Thunderstorm early warning system and method |
| CN111915846B (en) * | 2020-08-11 | 2021-08-03 | 安徽亿纵电子科技有限公司 | Intelligent cloud lightning protection operation and maintenance system based on cloud computing |
| CN112731564B (en) * | 2020-12-26 | 2023-04-07 | 安徽省公共气象服务中心 | Intelligent thunder forecasting method based on Doppler weather radar data |
| CN112764129B (en) * | 2021-01-22 | 2022-08-26 | 易天气(北京)科技有限公司 | Method, system and terminal for thunderstorm short-term forecasting |
| CN113239946B (en) * | 2021-02-02 | 2023-10-27 | 广东工业大学 | Checking method for current-carrying capacity of power transmission line |
| CN113204903B (en) * | 2021-04-29 | 2022-04-29 | 国网电力科学研究院武汉南瑞有限责任公司 | Method for predicting thunder and lightning |
| CN113191568B (en) * | 2021-05-21 | 2024-02-02 | 上海市气象灾害防御技术中心(上海市防雷中心) | Meteorological-based urban operation management big data analysis and prediction method and system |
| CN113283653B (en) * | 2021-05-27 | 2024-03-26 | 大连海事大学 | Ship track prediction method based on machine learning and AIS data |
| CN114252706B (en) * | 2021-12-15 | 2023-03-14 | 华中科技大学 | Lightning early warning method and system |
| CN114442198B (en) * | 2022-01-21 | 2024-03-15 | 广西壮族自治区气象科学研究所 | Forest fire weather grade forecasting method based on weighting algorithm |
| CN114518612A (en) * | 2022-02-14 | 2022-05-20 | 广东省气象公共安全技术支持中心 | Thunderstorm risk early warning method and system and electronic equipment |
| CN114966233A (en) * | 2022-05-16 | 2022-08-30 | 国网电力科学研究院武汉南瑞有限责任公司 | Lightning forecasting system and method based on deep neural network |
| CN115273440A (en) * | 2022-07-23 | 2022-11-01 | 河南泽阳实业有限公司 | Early warning device based on big data intelligent analysis algorithm |
| CN116341391B (en) * | 2023-05-24 | 2023-08-04 | 华东交通大学 | Precipitation prediction method based on STPM-XGBoost model |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9753947B2 (en) * | 2013-12-10 | 2017-09-05 | Weather Decision Technologies, Inc. | Four dimensional weather data storage and access |
| CN104950186B (en) * | 2014-03-31 | 2018-06-12 | 乌托巴斯洞察公司 | The method and apparatus of thunder and lightning prediction |
| CN105068149B (en) * | 2015-07-24 | 2017-04-12 | 国家电网公司 | Multi-information integration-based thunder and lightning monitoring and forecasting method for electric transmission and transformation equipment |
| CN108052734A (en) * | 2017-12-12 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of method and system predicted based on meteorologic parameter amplitude of lightning current |
| CN108427041B (en) * | 2018-03-14 | 2020-03-17 | 南京中科九章信息技术有限公司 | Lightning early warning method, system, electronic equipment and storage medium |
| CN110334732A (en) * | 2019-05-20 | 2019-10-15 | 北京思路创新科技有限公司 | A kind of Urban Air Pollution Methods and device based on machine learning |
| CN110796299A (en) * | 2019-10-23 | 2020-02-14 | 国网电力科学研究院武汉南瑞有限责任公司 | Thunder and lightning prediction method |
-
2019
- 2019-10-23 CN CN201911011363.4A patent/CN110796299A/en active Pending
-
2020
- 2020-05-15 WO PCT/CN2020/090434 patent/WO2021077729A1/en active Application Filing
- 2020-05-15 AU AU2020372283A patent/AU2020372283A1/en not_active Abandoned
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021077729A1 (en) | 2021-04-29 |
| CN110796299A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020372283A1 (en) | Lightning prediction method | |
| US11353625B1 (en) | Systems and methods for forecasting lightning and severe storms | |
| CN111897030A (en) | Thunderstorm early warning system and method | |
| Saxena et al. | A review study of weather forecasting using artificial neural network approach | |
| CN114966233A (en) | Lightning forecasting system and method based on deep neural network | |
| De Luca et al. | Extreme rainfall in the Mediterranean | |
| Deng et al. | Visibility Forecast for Airport Operations by LSTM Neural Network. | |
| Benamrou et al. | A proposed model to forecast hourly global solar irradiation based on satellite derived data, deep learning and machine learning approaches | |
| Liu et al. | Estimation of precipitation induced by tropical cyclones based on machine‐learning‐enhanced analogue identification of numerical prediction | |
| Novitasari et al. | Weather parameters forecasting as variables for rainfall prediction using adaptive neuro fuzzy inference system (ANFIS) and support vector regression (SVR) | |
| Leal et al. | Short-term lightning prediction in the Amazon region using ground-based weather station data and machine learning techniques | |
| Essa et al. | A LSTM recurrent neural network for lightning flash prediction within southern africa using historical time-series data | |
| da Silva et al. | Forecast of convective events via hybrid model: WRF and machine learning algorithms | |
| Sen et al. | Analysis of PCA based adaboost machine learning model for predict mid-term weather forecasting | |
| Elkharrim et al. | Using statistical downscaling of GCM simulations to assess climate change impacts on drought conditions in the northwest of Morocco | |
| Sá et al. | Recurrent self-organizing map for severe weather patterns recognition | |
| Rossi et al. | Analysis of a statistically initialized fuzzy logic scheme for classifying the severity of convective storms in F inland | |
| Mandal et al. | Prediction of Wind Speed using Machine Learning | |
| Baudhanwala et al. | Machine learning approaches for improving precipitation forecasting in the Ambica River basin of Navsari District, Gujarat | |
| Alves et al. | Lightning Warning Prediction with Multi-source Data | |
| Hadipour et al. | Genetic programming for downscaling extreme rainfall events | |
| Rufus et al. | Thunderstorm Prediction Model Using SMOTE Sampling and Machine Learning Approach | |
| de Almeida et al. | Artificial neural network for data assimilation by WRF model in Rio de Janeiro, Brazil | |
| CN110727719A (en) | Lightning positioning data assimilation method based on dynamic relaxation approximation | |
| Chaparro et al. | Prediction of thunderstorm days in Chilean territory using machine learning techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| MK5 | Application lapsed section 142(2)(e) - patent request and compl. specification not accepted |