CN113128778A - Model training method based on graded TS meteorological scoring - Google Patents
Model training method based on graded TS meteorological scoring Download PDFInfo
- Publication number
- CN113128778A CN113128778A CN202110463279.7A CN202110463279A CN113128778A CN 113128778 A CN113128778 A CN 113128778A CN 202110463279 A CN202110463279 A CN 202110463279A CN 113128778 A CN113128778 A CN 113128778A
- Authority
- CN
- China
- Prior art keywords
- meteorological
- value
- model
- loss
- prediction
- 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
- 238000012549 training Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001556 precipitation Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 19
- 238000012795 verification Methods 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003786 synthesis reaction 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a model training method based on hierarchical TS meteorological scoring, which comprises the following steps: s1, calculating the grading TS meteorological score of each prediction sample in the model according to the time sequence; s2, calculating the average value of the TS meteorological scores of all levels at a preset moment; s3 according to the loss function
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a model training method based on graded TS meteorological scoring.
Background
A predictive Score (thread Score/TS) is used to measure the quality of the prediction results of the meteorological prediction model. By setting different thresholds, a warning score of graded precipitation can be obtained. Higher scores indicate a smaller difference between true and predicted results, and vice versa.
The loss function is the most important part in machine learning in the field of artificial intelligence, and has the function of calculating the deviation between an actual result and a predicted result so as to reflect the learning effect of a model. Therefore, with the development of artificial intelligence technology, the machine learning method has been widely applied to the field of short-term prediction, especially to radar echo pattern prediction.
At present, for the design of a loss function of a short-lived model, the loss function carried by a machine learning platform is usually adopted, the loss function can only reflect the judging capability of the model on the weather of the whole sample, and the judging capability on various intensities of rainfall in the short-lived weather cannot be well met.
Disclosure of Invention
Therefore, the invention mainly aims to provide a model training method based on the graded TS meteorological score so as to meet the evaluation of the prediction capability of the model on precipitation with various intensities in the short-term weather, thereby improving the accuracy of the model on the prediction of the precipitation with various intensities.
In order to achieve the above object, the model training method based on the hierarchical TS meteorological score provided by the present invention includes the steps of:
s1, calculating the grading TS meteorological score of each prediction sample in the model according to the time sequence;
s2, calculating the average value of the TS meteorological scores of all levels at a preset moment;
s3 according to the loss function
Calculating a loss value; wherein loss is the loss average value of n samples, n is the number of samples, m is the number of grades, L is the numerical value of the grade, G (1) is the corresponding relation function of the grade and the threshold, TS is the value at the preset threshold
A function of the prognostic score of;
s4, the training direction of the model is corrected according to the loss value.
In a possible preferred embodiment, the G (1) comprises: precipitation, capillary rain/sporadic small snow, small rain/snow, medium rain/snow, heavy rain/snow, super heavy rain/snow, heavy rain/snow and heavy rain/snow of 8 levels,
In a possible preferred embodiment, the function of the prognostic score at the preset threshold is:
h is the correct times of rainfall forecast, namely, rainfall with the value larger than or equal to a preset threshold g is verified in the sample and the forecast result; f is the number of times of empty reporting, namely the samples are verified to have no precipitation more than or equal to a preset threshold value g and the prediction result is present; m is the number of times of missing report, namely the samples are verified to have precipitation more than or equal to a preset threshold value g and have no prediction result;
in a possible preferred embodiment, the prediction samples comprise: radar echo intensity data
In a possible preferred embodiment, the calculation formula of the average value of the TS weather scores at each level at the preset time is as follows:
The model training method based on the graded TS meteorological score can meet the assessment of the prediction capability of the model on the precipitation with various intensities in the short-term meteorological weather, so that the accuracy of the model on the precipitation with various intensities is improved, the prediction levels of the existing prediction model on the precipitation with different levels are comprehensively reflected, the training direction of the existing prediction model is guided, the precipitation prediction model which can meet all the levels in a balanced manner is corrected, and the prediction level of the existing prediction model is improved.
Detailed Description
The following describes in detail embodiments of the present invention. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In order to make those skilled in the art better understand the solution of the present invention, the following will clearly and completely describe the technical solution in the embodiment of the present invention in conjunction with the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not a whole embodiment. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
It is noted that the terms first, second and the like in the description and in the claims of the present invention are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
The invention provides a model training method based on hierarchical TS meteorological scoring, which is established based on the existing prediction model, and mainly has the improvement point that the model is evaluated specially aiming at the radar echo diagram prediction model by providing a loss function, so that the estimation of the prediction capability of the model on various intensities of rainfall in the short-term weather is met, and the accuracy of the model on the prediction of the rainfall with various intensities is improved.
As a preferred embodiment, the model related to the loss function in this case uses 1 hour radar echo intensity data, which is 1 piece every 6 minutes and 10 pieces per hour, to predict the future 1 hour radar echo intensity data. There are 20 time-sequential radar echo intensity data for each training sample. The first 10 samples are prediction samples used as input data for training, and the last 10 samples are verification samples used for comparing with prediction results and calculating loss values.
Specifically, the training steps of the model based on the hierarchical TS meteorological score are as follows:
first, 10 prediction samples are input to the model as training data, and the result is output as 10 prediction results. And the content of each piece of data is radar echo intensity, and the radar echo intensities of the prediction result and the verification sample are converted into precipitation millimeter numbers according to the Z-R relation.
Secondly, calculating the graded TS meteorological score of each prediction result according to the time sequence. The grading is to classify the precipitation strength into different grades according to the precipitation amount. In meteorology, precipitation levels are classified according to rain/snow, and in the embodiment, precipitation levels are preferably classified into 8 levels of no precipitation, rough rain/sporadic small snow, small rain/snow, medium rain/snow, heavy rain/snow, extra heavy rain/snow and heavy rain/snow.
In this embodiment, the level corresponds to the threshold value, where l is from 0 to 7 for 8 levels, and the unit of the precipitation threshold value is mm.
The TS weather score, also called as a warning score (TS), is a common method for judging weather prediction effect at present, and its calculation formula is as follows:
h is the correct times of rainfall forecast, namely, the rainfall of which the number is more than or equal to a certain preset threshold g is verified in the sample and the forecast result; f is the number of times of empty reporting, namely the samples are verified to have no precipitation more than or equal to a certain preset threshold value g and the predicted result is available; m is the number of times of missing report, namely the samples are verified to have precipitation more than or equal to a certain preset threshold value g and have no prediction result; and C is correct negation, namely, the correct negation is not used in the TS score, wherein the correct negation indicates that neither the verification sample nor the prediction result has precipitation which is greater than or equal to a certain preset threshold value g. The relationship is as follows:
for example, taking a precipitation data matrix of 100 × 100 size as an example, the TS weather score is calculated when l is 0, and g is 0 when l is 0. Firstly, according to a time sequence, respectively traversing data of 100 points by 100 points in a verification sample and a prediction result at a certain preset moment, and calculating H (0), namely the number of points which are more than or equal to 0 in both the verification sample and the prediction result; calculating F (0), namely verifying that the sample has no point which is greater than or equal to 0 and the prediction result has the number of points which is greater than or equal to 0; m (0) is calculated, i.e., the number of points at which the verification sample has a value equal to or greater than 0 and the prediction result has a value equal to or greater than 0.
And by analogy, calculating TS meteorological scores of other levels at the moment, and then summing and averaging to obtain a graded TS meteorological score of a prediction result at the moment, wherein the form of the graded TS meteorological score is as follows:
further, the hierarchical TS meteorological score at a certain moment is calculated by synthesis, and the formula is as follows:
wherein m is the number of levels, g is the corresponding relation function of the levels and the threshold, TS is the function of the TS meteorological score under a certain threshold, and TS is the average value of the TS meteorological scores of all levels. the ts has a value range of [0, 1], and the higher the value is, the smaller the difference between the verification sample and the prediction result is, otherwise, the larger the difference is.
Since the loss value also has a value range of [0, 1], a higher value indicates a larger difference between the verification sample and the prediction result, and vice versa. Therefore, to keep consistent with monotonicity of the loss values, 1 minus ts is used, i.e., ts is 1-ts.
Further, 10 successive time instants are calculated in chronological order
And then summing and averaging to obtain the loss values of the verification sample and the prediction result of a certain training, wherein the formula is as follows, n is the number of the prediction results, and in the model related to the loss function, n is 10:
further, in summary, a loss function based on the rating TS weather score is obtained, and the formula is as follows:
and i is the ith radar echo intensity data, so that the loss function firstly calculates TS meteorological scores of different levels at each moment according to the grade, then sums and averages, uses 1 to subtract TS for keeping consistency with monotonicity of the loss value, and finally sums and averages the result at each moment to obtain the loss values of the verification sample and the prediction result in a certain training.
Therefore, by calculating the loss value of the loss function, the prediction levels of the prediction model in the prior art to the rainfall with different levels can be comprehensively reflected, so that the training direction of the prior prediction model can be guided and corrected, and the rainfall prediction model which can meet all levels in a balanced manner can be obtained.
In conclusion, the model training method based on the graded TS meteorological score can meet the assessment of the prediction capability of rainfall with various intensities in the short-term weather, so that the accuracy of the model for predicting the rainfall with various intensities is improved, the prediction levels of the existing prediction model for the rainfall with different levels are comprehensively reflected, the training direction of the existing prediction model is guided, the rainfall prediction model capable of meeting all the levels in a balanced manner is corrected, and the prediction level of the existing prediction model is improved.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof, and any modification, equivalent replacement, or improvement made within the spirit and principle of the invention should be included in the protection scope of the invention.
It will be appreciated by those skilled in the art that, in addition to implementing the system, apparatus and various modules thereof provided by the present invention in the form of pure computer readable program code, the same procedures may be implemented entirely by logically programming method steps such that the system, apparatus and various modules thereof provided by the present invention are implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
In addition, all or part of the steps of the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a single chip, a chip, or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In addition, any combination of various different implementation manners of the embodiments of the present invention is also possible, and the embodiments of the present invention should be considered as disclosed in the embodiments of the present invention as long as the combination does not depart from the spirit of the embodiments of the present invention.
Claims (5)
1. A model training method based on hierarchical TS meteorological scoring is characterized by comprising the following steps:
s1, calculating the grading TS meteorological score of each prediction sample in the model according to the time sequence;
s2, calculating the average value of the TS meteorological scores of all levels at a preset moment;
s3 according to the loss function
Calculating a loss value; wherein loss is the loss average value of n samples, n is the number of samples, m is the number of grades, L is the numerical value of the grade, G (1) is the corresponding relation function of the grade and the threshold, and TS is the function of the premonition score under the preset threshold;
s4, the training direction of the model is corrected according to the loss value.
2. The method for model training based on hierarchical TS meteorological scoring according to claim 1, wherein G (1) comprises: precipitation, capillary rain/sporadic small snow, small rain/snow, medium rain/snow, heavy rain/snow, super heavy rain/snow, heavy rain/snow and heavy rain/snow of 8 levels,
3. The method for model training based on hierarchical TS meteorological scoring according to claim 1, wherein the function of the prognostic score at the preset threshold is as follows:
h is the correct times of rainfall forecast, namely, rainfall with the value larger than or equal to a preset threshold g is verified in the sample and the forecast result; f is the number of times of empty reporting, namely the samples are verified to have no precipitation more than or equal to a preset threshold value g and the prediction result is present; and M is the number of times of missing report, namely the samples are verified to have precipitation more than or equal to a preset threshold value g and the prediction result is not available.
4. The method of claim 1, wherein the prediction samples comprise: radar echo intensity data.
5. The method for model training based on TS meteorological scores in grades according to claim 1, wherein the calculation formula of the average value of the TS meteorological scores in each grade at the preset moment is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110463279.7A CN113128778B (en) | 2021-04-27 | 2021-04-27 | Model training method based on graded TS meteorological scoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110463279.7A CN113128778B (en) | 2021-04-27 | 2021-04-27 | Model training method based on graded TS meteorological scoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128778A true CN113128778A (en) | 2021-07-16 |
| CN113128778B CN113128778B (en) | 2022-08-26 |
Family
ID=76780459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110463279.7A Active CN113128778B (en) | 2021-04-27 | 2021-04-27 | Model training method based on graded TS meteorological scoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128778B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106405682A (en) * | 2016-08-29 | 2017-02-15 | 深圳先进技术研究院 | Rainfall prediction method and rainfall prediction device |
| CN108053061A (en) * | 2017-12-08 | 2018-05-18 | 天津大学 | A kind of solar energy irradiation level Forecasting Methodology based on improvement convolutional neural networks |
| CN110363327A (en) * | 2019-06-04 | 2019-10-22 | 东南大学 | Short based on ConvLSTM and 3D-CNN faces Prediction of Precipitation method |
| CN111062410A (en) * | 2019-11-05 | 2020-04-24 | 复旦大学 | Star information bridge weather prediction method based on deep learning |
| CN112051627A (en) * | 2020-08-21 | 2020-12-08 | 南方电网科学研究院有限责任公司 | Method, device and medium for correcting numerical mode multi-level rainfall forecast value |
| CN112180375A (en) * | 2020-09-14 | 2021-01-05 | 成都信息工程大学 | Meteorological radar echo extrapolation method based on improved TrajGRU network |
| CN112418480A (en) * | 2020-10-14 | 2021-02-26 | 上海眼控科技股份有限公司 | Meteorological image prediction method, meteorological image prediction device, computer equipment and storage medium |
| CN112698427A (en) * | 2020-12-09 | 2021-04-23 | 最美天气(上海)科技有限公司 | Short-term forecasting method and system based on space-time forecasting model |
-
2021
- 2021-04-27 CN CN202110463279.7A patent/CN113128778B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106405682A (en) * | 2016-08-29 | 2017-02-15 | 深圳先进技术研究院 | Rainfall prediction method and rainfall prediction device |
| CN108053061A (en) * | 2017-12-08 | 2018-05-18 | 天津大学 | A kind of solar energy irradiation level Forecasting Methodology based on improvement convolutional neural networks |
| CN110363327A (en) * | 2019-06-04 | 2019-10-22 | 东南大学 | Short based on ConvLSTM and 3D-CNN faces Prediction of Precipitation method |
| CN111062410A (en) * | 2019-11-05 | 2020-04-24 | 复旦大学 | Star information bridge weather prediction method based on deep learning |
| CN112051627A (en) * | 2020-08-21 | 2020-12-08 | 南方电网科学研究院有限责任公司 | Method, device and medium for correcting numerical mode multi-level rainfall forecast value |
| CN112180375A (en) * | 2020-09-14 | 2021-01-05 | 成都信息工程大学 | Meteorological radar echo extrapolation method based on improved TrajGRU network |
| CN112418480A (en) * | 2020-10-14 | 2021-02-26 | 上海眼控科技股份有限公司 | Meteorological image prediction method, meteorological image prediction device, computer equipment and storage medium |
| CN112698427A (en) * | 2020-12-09 | 2021-04-23 | 最美天气(上海)科技有限公司 | Short-term forecasting method and system based on space-time forecasting model |
Non-Patent Citations (1)
| Title |
|---|
| 方巍 等: "人工智能在短临降水预报中应用研究综述", 《南京信息工程大学学报（自然科学版）》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128778B (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117566B (en) | Mixed maintenance planning method based on product life prediction model | |
| CN108870090B (en) | Pipeline leakage detection method based on least square support vector machine information fusion | |
| Rougier et al. | Model and data limitations: the sources and implications of epistemic uncertainty | |
| CN104965787A (en) | Three-decision-based two-stage software defect prediction method | |
| CN109086770A (en) | A kind of image, semantic dividing method and model based on accurate scale prediction | |
| Huang et al. | Flood analysis in Langat River Basin using stochatic model | |
| CN113128778B (en) | Model training method based on graded TS meteorological scoring | |
| CN111626844A (en) | Enterprise credit assessment method and device based on big data analysis | |
| CN111192121A (en) | ANN-based automatic risk taxpayer early warning method and system | |
| CN109784586B (en) | Prediction method and system for danger emergence condition of vehicle danger | |
| CN114971009A (en) | Vehicle insurance risk prediction method and computer equipment | |
| CN110188115B (en) | Fire-fighting early warning method, device and system based on fuzzy matching | |
| CN116797226B (en) | Information security assessment method for coffee spot transaction based on big data | |
| JP2020140521A (en) | Human determination prediction device, prediction program and prediction method | |
| CN109625025A (en) | BTM equipment early warning system | |
| CN114637620A (en) | Database system abnormity classification prediction method based on SVM algorithm | |
| Stamataki et al. | Sensitivity analysis on resilience components throughout the lifecycle of an asset | |
| Lipecki et al. | Characteristic velocity of strong wind for wind engineering purposes | |
| CN117706663B (en) | Hail precipitation phenomenon quality control method and system based on multivariate data | |
| CN117932438A (en) | Service capacity early warning method and device for application system | |
| CN116611345A (en) | Rail bearing load prediction method and device, electronic equipment and storage medium | |
| KR20240066781A (en) | Predicting apparatus for loan arrears based on artificial intelligence and method thereof | |
| CN117974290A (en) | Credit scoring card development and scoring method and device for decision tree and logistic regression | |
| Seid Yassin | Ensemble learning performance analysis on road traffic accident data | |
| CN117371162A (en) | Apparatus and computer-implemented method for performing experiments using a technical system or model |
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 |