CN111027193A - Short-term water level prediction method based on regression model - Google Patents
Short-term water level prediction method based on regression model Download PDFInfo
- Publication number
- CN111027193A CN111027193A CN201911215167.9A CN201911215167A CN111027193A CN 111027193 A CN111027193 A CN 111027193A CN 201911215167 A CN201911215167 A CN 201911215167A CN 111027193 A CN111027193 A CN 111027193A
- Authority
- CN
- China
- Prior art keywords
- water level
- historical
- data
- rainfall
- level data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 227
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000630 rising effect Effects 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 238000001556 precipitation Methods 0.000 abstract description 2
- 230000002596 correlated effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a short-term water level prediction method based on a regression model, which is characterized by collecting and analyzing historical water level data of a water level observation point and historical rainfall data of a water level observation point region, respectively carrying out standardization processing on the historical water level data and the historical rainfall data, then setting an extraction time period and a time interval of the historical water level data and the historical rainfall data, importing the historical rainfall data and the historical water level data of each relevant rainfall observation point which are subjected to the standardization processing in the extraction time period into a training model, training and simulating the historical rainfall data and the historical water level data through a Bayesian ridge regression model, and finally obtaining a water level prediction result in a certain time period in the future of the water level observation point. The method of the invention considers the influence of different factors such as rainfall, precipitation time period, original water level and the like on the future water level change, and can more accurately predict the water level in the future in a short time.
Description
Technical Field
The invention belongs to the field of regional future water level prediction, and particularly relates to a short-term water level prediction method based on a regression model.
Background
The existing water level prediction mode is that data collection and statistics are carried out on water level measurement data of the point in the past years, and fitting and training are carried out through a mathematical model to obtain water level prediction for a long time in the future. Although the models are various, the model input variable is only the water level data of the point in the past year, so that the defects of poor adaptability, large error of predicted data, non-compliance with the actual situation and the like exist; meanwhile, the prediction time span of the model is long, and the timeliness of the model cannot be guaranteed. Therefore, a model for predicting the short-term water level by combining the historical rainfall and the water level change of the place is urgently needed, and the prediction accuracy is improved.
Disclosure of Invention
In view of the above technical problems in the prior art, the present invention is directed to a short-term water level prediction method based on a regression model.
The short-term water level prediction method based on the regression model is characterized by comprising the following steps of:
1) collecting and importing historical water level data of the water level observation points;
2) analyzing and processing the collected historical water level data, namely removing null values in the water level data, simultaneously removing abnormal values in the historical water level data by adopting a 6-time standard deviation method, and carrying out standardization processing on the historical water level data;
3) analyzing and processing the historical rainfall data of the water level observation point region, namely extracting the historical rainfall data of all associated rainfall observation points around the water level observation point, filling the missing historical rainfall data by adopting an associated historical rainfall data averaging method, and finally standardizing the historical rainfall data of each rainfall observation point;
4) establishing a future water level short-term prediction model of a water level observation point region, namely setting extraction time periods and time intervals of historical water level data and historical rainfall data according to different time points and different accuracy degrees of water level prediction, importing the historical rainfall data and the historical water level data of each associated rainfall observation point in the extraction time periods after standardization processing into a training model, training and simulating the historical rainfall data and the historical water level data through a Bayesian ridge regression model, and finally obtaining a water level prediction result of the water level observation point in a certain time period in the future.
The short-term water level prediction method based on the regression model is characterized in that in the step 2), the specific steps of analyzing and processing the collected historical water level data are as follows:
s1: removing null values in the water level data, namely removing time points of water level data missing;
s2: calculating the mean value of the historical water level data after the null value is removed, and calculating the standard deviation of the whole historical water level data through a standard deviation formula after the mean value of the historical water level data is obtained, wherein the calculation formula of the mean value is shown as a formula (1), and the calculation formula of the standard deviation is shown as a formula (2);
Wi-water level data representing a historical point in time;
σ -represents the standard deviation of the historical water level data;
s3: eliminating invalid data in all the historical water level data by a 6-time standard deviation method according to the mean value of the historical water level data obtained by the formula (1) and the standard deviation of the historical water level data obtained by the formula (2), namely eliminating all the historical water level data exceeding six times of the standard deviation range to ensure the accuracy of a prediction result, wherein the elimination process is shown as a formula (3);
s4: in order to see the rising and falling conditions of the historical water level of the water level observation point, the historical water level data is standardized, and the formula for carrying out the standardization is shown as a formula (4); in order to understand the rising and falling conditions of the water level, the historical water level data is processed by a difference method of adjacent time points to facilitate the analysis of the subsequent data, and the processing process of the difference method of the adjacent time points is shown as a formula (5);
WS=Wn-1-Wn(5)
w is historical water level data before standardization of the water level observation points;
Wmax-historical water level maximum data;
Wmin-historical water level minimum data;
WS-normalized historical water level data for water level observation points;
Wn-historical water level data for the nth time point of the water level observation point;
Wn-1-historical water level data for the (n-1) th time point of the water level observation point.
The short-term water level prediction method based on the regression model is characterized in that in the step 3), the specific process of analyzing and processing the historical rainfall data of the water level observation point region is as follows: selecting a plurality of rainfall observation points at the periphery of the water level observation points, extracting historical rainfall data of all the rainfall observation points, filling missing historical rainfall data by adopting a correlation historical rainfall data averaging method, and finally carrying out standardization processing on the historical rainfall data of each rainfall observation point, wherein the detailed standardization processing process is shown as a formula (6):
Rshistorical rainfall data of a certain rainfall observation point normalized at a certain time;
r is original historical rainfall data of a certain rainfall observation point at a certain moment;
Rmin-minimum historical rainfall values for all rainfall observation points at a time;
Rmax-maximum historical rainfall value for all rainfall observation points at a time.
The short-term water level prediction method based on the regression model is characterized by further comprising a model visualization process, and specifically comprises the following steps: and performing data training through the established short-term prediction model of the future water level in the water level observation point region to obtain a predicted water level value of the water level observation point in a future certain time period, and then displaying the matching condition of the historical water level data and the comparison condition of the predicted water level value in the future certain time period in the form of a broken line diagram to determine the accuracy of the established short-term prediction model of the future water level.
Compared with the prior art, the invention has the following beneficial effects:
the invention relates to a hydrologic big data processing method and application of a Bayesian ridge regression model in water level prediction, and analysis of existing hydrologic data and prediction of future water level of a region can be carried out through combination of the hydrologic big data processing method and the Bayesian ridge regression model. The invention plans to use the water level data of a water level prediction point (namely a water level observation point) and the real-time rainfall data around the water level prediction point as data input ends and combine a regression model to predict the future short-term water level of the water level prediction point. The method of the invention considers the influence of different factors such as rainfall, precipitation time period, original water level and the like on the future water level change, and can more accurately predict the water level in the future in a short time.
Drawings
Fig. 1 is a schematic flow chart of a short-term water level prediction method according to the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which should not be construed as limiting the scope of the invention.
The invention provides a technical scheme that: a new short-term hydrological prediction scheme comprising the following modeling steps:
the method comprises the following steps: collecting and importing water level data of the water level prediction points;
step two: analyzing and processing historical water level data of a water level prediction point area;
step three: analyzing and processing historical rainfall data of the water level prediction point area;
step four: establishing a future water level short-term prediction model in a water level prediction point area;
step five: the model is visualized and a conclusion is drawn. The flow chart of the short-term water level prediction method of the invention is shown in figure 1.
1. Collecting and importing water level data of the water level prediction points:
first, take 5173-W water level prediction points as an example, which correspond to 3 rainfall observation points of the associated rainfall points, namely 1689-R, 3534-R and 5921-R. And collecting and importing historical water level data of the water level observation points and historical rainfall data of the 3 rainfall observation points, wherein the collected data comprises a measuring station number, a station name, a time point (one historical rainfall measurement data is taken every 5 minutes) and a data value of the time point. The detailed data content required to be extracted by the rainfall observation point is shown in table 1. Meanwhile, according to the prediction precision requirement, the lead-in time range of the rainfall observation data is set to be 2016-12-01 to 2018-02-01, and the time interval of the samples is set to be 5 min.
TABLE 1 content table of measurement point data
2. Analyzing and processing the historical water level data of the 5173-W water level prediction point area:
performing data cleaning work on historical water level data collected in a 5173-W water level prediction point, removing time points of water level data missing, and simultaneously removing abnormal values by adopting a 6-time standard deviation method in order to avoid abnormal data in the water level data:
1) and (3) calculating the historical water level mean value of the observation point, namely performing mean value calculation on the collected historical water level data to obtain the water level mean value of the 5173-W water level prediction point, wherein the calculation is shown as a formula (1).
Wi-water level data representing a historical point in time;
2) calculating the historical water level standard deviation of the observation point: after obtaining the mean value of the historical water level data, calculating the standard deviation of the whole historical water level data through a standard deviation formula, wherein the detailed calculation is shown as a formula (2).
σ -represents the standard deviation of the historical water level data;
3) removing abnormal values in the historical water level data: and (3) eliminating invalid data in all the historical water level data by a 6-time standard deviation method according to the mean value of the historical water level data obtained by the formula (1) and the standard deviation of the historical water level data obtained by the formula (2), namely eliminating all the historical water level data exceeding six times of the standard deviation range. In order to guarantee the accuracy of the prediction result, the elimination process is shown as a formula (3), namely, each effective historical water level data is required to be in the range limited by the formula (3).
4) Water level observation point water historical water level data standardization: in order to see the rising and falling conditions of the historical water level of the water level observation point, the historical water level data of the observation point is standardized, and the formula for carrying out the standardization is shown as a formula (4); in order to know the rising and falling conditions of the historical water level, the historical water level data is processed by a difference method of adjacent time points to facilitate the analysis of the subsequent historical water level data, and the difference method processing process of the historical water level data of the adjacent time points is shown as a formula (5);
WS=Wn-1-Wn(5)
w is historical water level data before standardization of the water level observation points;
Wmax-historical water level maximum data;
Wmin-historical water level minimum data;
WS-normalized historical water level data for water level observation points;
Wn-historical water level data for the nth point in time of the water level observation (larger n representing longer time);
Wn-1-historical water level data for the (n-1) th time point of the water level observation point.
3. Analyzing and processing the historical rainfall data of the 5173-W water level prediction point area:
extracting historical rainfall data of all correlated rainfall observation points around a 5173-W water level prediction point, namely three rainfall observation points of 1689-R, 3534-R and 5921-R, filling missing historical rainfall data by adopting a correlated historical rainfall data averaging method, and finally carrying out standardization processing on the historical rainfall data of each rainfall observation point, wherein the detailed standardization process is shown as a formula (6):
Rshistorical rainfall data of a certain rainfall observation point normalized at a certain time;
r is original historical rainfall data of a certain rainfall observation point at a certain moment;
Rmin-minimum historical rainfall values for all rainfall observation points at a time;
Rmax-maximum observation point of all rainfall at a certain momentHistorical rain values.
4. Establishing a short-term prediction model of the future water level in the region:
1) setting the extraction time periods and time intervals of the historical water level data and the historical rainfall data according to different time points and different accuracy degrees of water level prediction, for example, in the embodiment, setting the analysis and training time of the historical water level and the rainfall data to randomly select training samples and observation samples from 2016-02-01 to 2018-02-01, importing the historical rainfall data and the historical water level data of each correlated rainfall observation point which are subjected to standardization processing in the extraction time period into a training model, and finally performing model operation.
2) Setting historical water level data by group extraction: extracting the water level data in groups, wherein the extraction interval of each group of data is as follows: taking the water level data at a certain time as time origin data, and simultaneously extracting the water level data of the time point, which is-15 min, -45min, -75min, -105min later, and 3 hours and 6 hours later, as a group of water level data. The required historical water level data sets of the water level points are sequentially extracted according to the time sequence by the method.
3) Setting historical rainfall data by group extraction: extracting the historical rainfall data in groups, wherein the extraction interval of each group of data is as follows: with the rainfall data at a certain time as time origin data, the rainfall data of the past 1,2,3,5 … … 55 hours and the rainfall data of the future 1,2,3,4,5,6 hours are extracted by the fibonacci number series as a set of historical rainfall data. The required rainfall point historical rainfall data sets are sequentially extracted according to the time sequence by the method.
4) Establishing a model: the weights of rainfall data and water level data at different time points are set through a Bayesian ridge regression model, the longer the data is from the prediction time, the lower the weight is, and the closer the data is from the prediction time, the higher the weight is. And importing the historical water level data group and the historical water level data group into a value model for training and simulation, and fitting the data by using a Bayesian ridge regression model. And finally, obtaining water level prediction work of 1 hour in a certain future time period for the predicted water level point.
5. Model visualization and conclusions:
the expected water level value of the water level point is obtained through the model establishment and data training, and the historical fitting situation and the future predicted water level prediction situation are displayed in the form of a line graph, so that the accuracy of the established future water level short-term prediction model is determined.
The statements in this specification merely set forth a list of implementations of the inventive concept and the scope of the present invention should not be construed as limited to the particular forms set forth in the examples.
Claims (4)
1. A short-term water level prediction method based on a regression model is characterized by comprising the following steps:
1) collecting and importing historical water level data of the water level observation points;
2) analyzing and processing the collected historical water level data, namely removing null values in the water level data, simultaneously removing abnormal values in the historical water level data by adopting a 6-time standard deviation method, and carrying out standardization processing on the historical water level data;
3) analyzing and processing the historical rainfall data of the water level observation point region, namely extracting the historical rainfall data of all associated rainfall observation points around the water level observation point, filling the missing historical rainfall data by adopting an associated historical rainfall data averaging method, and finally standardizing the historical rainfall data of each rainfall observation point;
4) establishing a future water level short-term prediction model of a water level observation point region, namely setting extraction time periods and time intervals of historical water level data and historical rainfall data according to different time points and different accuracy degrees of water level prediction, importing the historical rainfall data and the historical water level data of each associated rainfall observation point in the extraction time periods after standardization processing into a training model, training and simulating the historical rainfall data and the historical water level data through a Bayesian ridge regression model, and finally obtaining a water level prediction result of the water level observation point in a certain time period in the future.
2. The method as claimed in claim 1, wherein the step 2) of analyzing the collected historical water level data comprises the following steps:
s1: removing null values in the water level data, namely removing time points of water level data missing;
s2: calculating the mean value of the historical water level data after the null value is removed, and calculating the standard deviation of the whole historical water level data through a standard deviation formula after the mean value of the historical water level data is obtained, wherein the calculation formula of the mean value is shown as a formula (1), and the calculation formula of the standard deviation is shown as a formula (2);
Wi-water level data representing a historical point in time;
σ -represents the standard deviation of the historical water level data;
s3: eliminating invalid data in all the historical water level data by a 6-time standard deviation method according to the mean value of the historical water level data obtained by the formula (1) and the standard deviation of the historical water level data obtained by the formula (2), namely eliminating all the historical water level data exceeding six times of the standard deviation range to ensure the accuracy of a prediction result, wherein the elimination process is shown as a formula (3);
s4: in order to see the rising and falling conditions of the historical water level of the water level observation point, the historical water level data is standardized, and the formula for carrying out the standardization is shown as a formula (4); in order to understand the rising and falling conditions of the water level, the historical water level data is processed by a difference method of adjacent time points to facilitate the analysis of the subsequent data, and the processing process of the difference method of the adjacent time points is shown as a formula (5);
WS=Wn-1-Wn(5)
w is historical water level data before standardization of the water level observation points;
Wmax-historical water level maximum data;
Wmin-historical water level minimum data;
WS-normalized historical water level data for water level observation points;
Wn-historical water level data for the nth time point of the water level observation point;
Wn-1-historical water level data for the (n-1) th time point of the water level observation point.
3. The method for predicting short-term water level based on regression model as claimed in claim 1, wherein in step 3), the specific process of analyzing and processing the historical rainfall data of the water level observation point region is as follows: selecting a plurality of rainfall observation points at the periphery of the water level observation points, extracting historical rainfall data of all the rainfall observation points, filling missing historical rainfall data by adopting a correlation historical rainfall data averaging method, and finally carrying out standardization processing on the historical rainfall data of each rainfall observation point, wherein the detailed standardization processing process is shown as a formula (6):
Rshistorical rainfall data of a certain rainfall observation point normalized at a certain time;
r is original historical rainfall data of a certain rainfall observation point at a certain moment;
Rmin-minimum historical rainfall values for all rainfall observation points at a time;
Rmax-maximum historical rainfall value for all rainfall observation points at a time.
4. The regression model-based short-term water level prediction method according to claim 1, further comprising a model visualization process, specifically: and performing data training through the established short-term prediction model of the future water level in the water level observation point region to obtain a predicted water level value of the water level observation point in a future certain time period, and then displaying the matching condition of the historical water level data and the comparison condition of the predicted water level value in the future certain time period in the form of a broken line diagram to determine the accuracy of the established short-term prediction model of the future water level.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911215167.9A CN111027193A (en) | 2019-12-02 | 2019-12-02 | Short-term water level prediction method based on regression model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911215167.9A CN111027193A (en) | 2019-12-02 | 2019-12-02 | Short-term water level prediction method based on regression model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111027193A true CN111027193A (en) | 2020-04-17 |
Family
ID=70207752
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911215167.9A Pending CN111027193A (en) | 2019-12-02 | 2019-12-02 | Short-term water level prediction method based on regression model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111027193A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112461340A (en) * | 2020-12-03 | 2021-03-09 | 上海普适导航科技股份有限公司 | Fault correcting and detecting method and device for water level meter |
CN112799154A (en) * | 2020-12-28 | 2021-05-14 | 恒瑞通(福建)信息技术有限公司 | Ecological environment big data prediction and early warning method and terminal |
CN113155102A (en) * | 2021-02-24 | 2021-07-23 | 时代云英(深圳)科技有限公司 | River comprehensive treatment system |
CN113916318A (en) * | 2021-08-31 | 2022-01-11 | 福建枋洋水利投资发展有限公司 | Dam safety monitoring method based on water regime monitoring |
CN114091362A (en) * | 2022-01-24 | 2022-02-25 | 江西飞尚科技有限公司 | Water level prediction method, system, storage medium and equipment |
CN114881380A (en) * | 2022-07-12 | 2022-08-09 | 太极计算机股份有限公司 | Deep learning-based down-scaling processing method and system for aeronautical meteorological data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105843942A (en) * | 2016-04-01 | 2016-08-10 | 浙江大学城市学院 | Urban flood prevention decision support system based on big data technique |
CN109272146A (en) * | 2018-08-23 | 2019-01-25 | 河海大学 | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network |
CN109389238A (en) * | 2017-08-14 | 2019-02-26 | 中国电力科学研究院 | A kind of short-term load forecasting method and device based on ridge regression |
CN109920489A (en) * | 2019-01-16 | 2019-06-21 | 浙江大学 | It is a kind of that model and method for building up are hydrocracked based on Lasso-CCF-CNN |
CN109978235A (en) * | 2019-03-04 | 2019-07-05 | 宁波市气象服务中心 | A kind of flooded water level prediction method of product based on sample learning |
-
2019
- 2019-12-02 CN CN201911215167.9A patent/CN111027193A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105843942A (en) * | 2016-04-01 | 2016-08-10 | 浙江大学城市学院 | Urban flood prevention decision support system based on big data technique |
CN109389238A (en) * | 2017-08-14 | 2019-02-26 | 中国电力科学研究院 | A kind of short-term load forecasting method and device based on ridge regression |
CN109272146A (en) * | 2018-08-23 | 2019-01-25 | 河海大学 | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network |
CN109920489A (en) * | 2019-01-16 | 2019-06-21 | 浙江大学 | It is a kind of that model and method for building up are hydrocracked based on Lasso-CCF-CNN |
CN109978235A (en) * | 2019-03-04 | 2019-07-05 | 宁波市气象服务中心 | A kind of flooded water level prediction method of product based on sample learning |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112461340A (en) * | 2020-12-03 | 2021-03-09 | 上海普适导航科技股份有限公司 | Fault correcting and detecting method and device for water level meter |
CN112799154A (en) * | 2020-12-28 | 2021-05-14 | 恒瑞通(福建)信息技术有限公司 | Ecological environment big data prediction and early warning method and terminal |
CN113155102A (en) * | 2021-02-24 | 2021-07-23 | 时代云英(深圳)科技有限公司 | River comprehensive treatment system |
CN113155102B (en) * | 2021-02-24 | 2021-11-19 | 时代云英(深圳)科技有限公司 | River comprehensive treatment system |
CN113916318A (en) * | 2021-08-31 | 2022-01-11 | 福建枋洋水利投资发展有限公司 | Dam safety monitoring method based on water regime monitoring |
CN113916318B (en) * | 2021-08-31 | 2024-08-13 | 福建枋洋水利投资发展有限公司 | Dam safety monitoring method based on water regime monitoring |
CN114091362A (en) * | 2022-01-24 | 2022-02-25 | 江西飞尚科技有限公司 | Water level prediction method, system, storage medium and equipment |
CN114881380A (en) * | 2022-07-12 | 2022-08-09 | 太极计算机股份有限公司 | Deep learning-based down-scaling processing method and system for aeronautical meteorological data |
CN114881380B (en) * | 2022-07-12 | 2022-09-23 | 太极计算机股份有限公司 | Deep learning-based down-scaling processing method and system for aeronautical meteorological data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111027193A (en) | Short-term water level prediction method based on regression model | |
CN111104981B (en) | Hydrological prediction precision evaluation method and system based on machine learning | |
CN111045117B (en) | Climate monitoring and predicting platform | |
CN106779223B (en) | Photovoltaic system power generation real-time prediction method and device | |
CN112286924A (en) | Data cleaning technology for dynamic identification of data abnormality and multi-mode self-matching | |
CN108802535B (en) | Screening method, main interference source identification method and device, server and storage medium | |
CN103984938B (en) | Remote sensing time series abnormity detection method | |
CN109359770B (en) | Model and method for predicting heatstroke occurrence based on machine learning | |
CN111784022B (en) | Short-time adjacent large fog prediction method based on combination of Wrapper method and SVM method | |
CN108802856B (en) | AI-based source data dynamic correction and forecast system and working method thereof | |
CN112633781B (en) | Vehicle energy consumption evaluation method based on Internet of vehicles big data | |
CN105427194A (en) | Method and device for electricity sales amount prediction based on random forest regression | |
CN112883075B (en) | Landslide universal type ground surface displacement monitoring data missing and outlier processing method | |
CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
CN112116149A (en) | Multi-station medium and long term runoff rolling probability prediction method considering forecast uncertainty associated evolution characteristics | |
CN114462511A (en) | PM based on XGboost algorithm2.5Data anomaly identification method | |
CN115935283A (en) | Drought cause tracing method based on multivariate nonlinear causal analysis | |
CN113592308A (en) | Monitoring data alarm threshold extraction method based on normal model | |
CN117151649A (en) | Construction method management and control system and method based on big data analysis | |
CN114330120A (en) | 24-hour PM prediction based on deep neural network2.5Method of concentration | |
CN118280069A (en) | GIS-based power grid disaster monitoring and early warning system | |
CN107808241B (en) | Stainless steel surface detection result comprehensive analysis system | |
CN112016744B (en) | Forest fire prediction method and device based on soil moisture and storage medium | |
CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
CN113960700B (en) | Objective inspection, statistics and analysis system for regional numerical forecasting result |
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 |