CN110766219A - Haze prediction method based on BP neural network - Google Patents
Haze prediction method based on BP neural network Download PDFInfo
- Publication number
- CN110766219A CN110766219A CN201911000434.0A CN201911000434A CN110766219A CN 110766219 A CN110766219 A CN 110766219A CN 201911000434 A CN201911000434 A CN 201911000434A CN 110766219 A CN110766219 A CN 110766219A
- Authority
- CN
- China
- Prior art keywords
- data
- neural network
- haze
- prediction method
- method based
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000012417 linear regression Methods 0.000 claims description 10
- 238000003915 air pollution Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 5
- 230000001932 seasonal effect Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 6
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000018569 Respiratory Tract disease Diseases 0.000 description 1
- 206010057190 Respiratory tract infections Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012803 optimization experiment Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a haze prediction method based on an optimized BP neural network, which aims to break through the constraint of original thinking, provides a data optimization method of a new BP neural network in haze prediction, wherein correlation degree proportion data replaces the random weight of the traditional BP neural network to reduce prediction errors, and finally achieves the purposes of reducing errors, accelerating training and reducing training burden by carrying out experimental data processing, chart establishment and various debugging on a NET platform so as to improve the accuracy of prediction.
Description
Technical Field
The invention belongs to the technical field of environmental engineering in detection and early warning. Specifically, a haze prediction method based on an optimized BP neural network is designed.
Background
The current world develops at a high speed, but the long-term damage of the human society to the natural ecological environment is maintained behind the high-speed development, the self-regulation capacity of the environment is gradually weakened, the haze weather is particularly serious in the autumn and winter, the visual field range is narrowed, in addition, the haze is easy to induce cardiovascular diseases and respiratory tract infection, even respiratory tract diseases, lung hardening and canceration and lung function change are caused, along with the development of urbanization, relevant data show that the PM2.5 concentration does not decrease or inversely increase from 2015 to 2019 months in most cities in China, the appearance of the haze is inevitable in the historical development, and the necessary prevention and control of the haze is imperative by applying advanced scientific technology.
The rise of the neural network drives the development of data prediction, and obtains better effect, the superiority of the neural network in the aspect of data prediction attracts a large number of scholars and technicians in the field of haze prediction to combine the existing neural network with haze data to carry out optimization experiments, the influence factors of haze are complex and nonlinear, so that the combination of the influence factors and data such as environmental factors and meteorological factors is inevitable, most neural networks in the implementation stage decompose the data, the substance of the decomposition is not separated from the shadow of a linear model, the decomposition is more flexible, the problems of difficult training, instability, overfitting and the like are caused, the inventor further carries out data processing on the basis of the BP neural network, finds out the complex relation between each influence factor data and PM2.5 through correlation analysis in advance, and replaces the random weight of the traditional BP neural network with the correlation ratio data to reduce prediction errors, based on the current situation and background of the society, the haze data processing method and the haze data prediction method are scientific and accurate.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a haze prediction method based on a BP (back propagation) neural network, and aims to break through the constraint of original thinking, provide a new data optimization method of the BP neural network in haze prediction, and finally achieve the purposes of reducing errors, accelerating training and reducing training burden through experimental data processing, chart establishment and various kinds of debugging so as to improve the prediction accuracy.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: the haze prediction method based on the BP neural network is characterized by comprising the following steps:
step 01, collecting historical related data and haze data; historical correlation data.
And step 02, preprocessing and normalizing history related data and haze data.
And 03, charifying and visualizing historical related data and haze data.
And step 04, finding out the available historical related data according to the positive-negative ratio relation.
And step 05, establishing a linear regression equation and calculating the correlation among the data.
And step 06, classifying the data into time periods according to seasons.
And step 07, reasonably dividing data into two types of training and testing.
And step 08, establishing a BP neural network and unifying linear regression equations by using a platform tool.
And 09, replacing the random weight of the traditional BP neural network with the correlation ratio data.
And step 10, training the BP neural network by using the processed data.
And 11, iterating parameters and adjusting and optimizing the model.
And step 12, predicting by using the optimized BP neural network.
And step 13, outputting results according to requirements.
Preferably, the influencing factors are in particular PM2.5, PM10, PM2.5, NO2, PM10, NO, SO2, t (max), t (min) and all such methods associated therewith are verifiable as exploitable numbers.
Preferably, the initial weight is found by linear regression instead of the traditional random weight, so as to improve the efficiency.
Preferably, the data are classified according to seasonal time periods, so that a local smoothing concept is formed, and errors caused by overall smoothing are avoided.
Preferably, the input data of the neural network input layer is normalized temperature, pressure, wind speed, rainfall and snowfall data, and the output data of the neural network output layer is normalized haze concentration value.
Preferably, the data are classified mainly according to seasons, accuracy of the data is improved, the data are classified mainly in four seasons, and meanwhile the data are classified according to different time periods of the day.
Preferably, the haze concentration of the region can be predicted by using data of different regions, parameters of a prediction model of the haze concentration can be redefined according to actual conditions and requirements, and a network does not need to be reconstructed, so that the method has flexibility and portability.
Preferably, the predicted haze concentration data are marked according to the air pollution indexes of the national standard and the levels, and are sequentially divided into different air pollution levels.
The invention discloses a haze prediction method based on a BP neural network, which has the following beneficial effects:
according to the haze prediction method based on the BP neural network, the internal data systems of the environmental protection department and the meteorological department are collected, source data are established, normalization processing is carried out on the data, all the data are processed to the range of [ -1, 1], data which are not normalized are charified, a linear regression equation is established on the data, and therefore the haze data of three days in the future are predicted through the trained data, so that the haze data are predicted, the controllability is higher, the problems of detection and accuracy improvement of a large data set are solved, meanwhile, the haze concentration prediction of the area can be achieved by using the data of different areas, the parameters of a prediction model of the haze concentration can be redefined according to actual conditions and requirements, the network does not need to be rebuilt, and therefore the haze prediction method has flexibility and portability.
Drawings
FIG. 1 is a simple three-layer BP neural network structure;
FIG. 2 is a flow chart of a haze prediction method based on an optimized BP neural network according to the present invention;
FIG. 3 is the current stage correlation of factors;
FIG. 4 is a graph of partial data normalization results;
FIG. 5 is a training error graph;
FIG. 6 is a comparison graph of the optimized model, actual values;
FIG. 7 is an optimized predictive model, actual value versus data.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to fig. 1 to 7 and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. As shown in the attached figure 1, the haze prediction method based on the optimized BP neural network comprises the following steps:
step 01, finding an official network of an environmental protection department and a meteorological department, and collecting daily average PM2.5, PM10, PM2.5, NO2, PM10, NO, SO2, T (max) and T (min) from 2015 to 2019 of Leshan City as source data.
And step 02, smoothing a small part of missing data, and taking the average value of the last two days as the value of the missing data. And (4) carrying out normalization processing on the data, and processing all the data to the range of [ -1, 1 ]. The formula is as follows:
y is the normalized data, max is the maximum value of the data, and min is the minimum value of the data.
And 03, graphing the data which are not normalized to facilitate observation, preliminarily determining whether certain obvious relationship exists between the data, searching according to the positive-negative ratio relationship, directly abandoning the influence factors which are not changed obviously regularly for use, and screening the data.
And step 04, establishing a linear regression equation for the haze data and other data, finding out regression coefficients and correlation coefficients between the haze data and other data, and providing a thought for the subsequent BP neural network initial weight. The regression equation used is as follows:
Y＝AX+b
where Y is the set of sample outputs and X is the set of sample inputs. The expansion formula is shown below
y＝a0*x0+a1*x1+...+an*xn
The OLS solution formula of the coefficient A is shown as follows
A＝(XT*X)-1*XT*Y
And step 05, as the haze is obvious in seasonality, the data predicted by the BP neural network has certain smoothness, and the data are classified according to seasonal time periods, so that local smoothness is formed, and errors caused by integral smoothness are avoided.
And step 06, taking the data of the year 2015-plus-material 2018 as training data and the data of the year 2019 as test data.
And step 07, calculating each regression coefficient by taking the ratio as the initial weight of the BP neural network.
Step 08, training the network through adjusting errors and multiple experiments, wherein the accuracy is improved and overfitting is avoided, and the adopted activation functions are as follows:
and step 09, predicting the haze data of the three days in the future through the trained data.
And step 10, comparing the predicted data with the collected data to analyze the accuracy and feasibility.
Influencing factors are in particular PM2.5, PM10, PM2.5, NO2, PM10, NO, SO2, T (max), T (min) and all data which can be validated as being usable in this way in relation thereto,
the method utilizes linear regression to find initial weight to replace the traditional random weight so as to improve efficiency, classifies data according to seasonal time periods to form a thought of local smoothness and avoid errors caused by integral smoothness, input data of a neural network input layer are normalized temperature, pressure, wind speed, rainfall and snowfall data, output data of a neural network output layer are normalized haze concentration values, further, the data are mainly classified according to seasons to improve the accuracy of the data and are mainly classified into four seasons, meanwhile, the data in different time periods of the day are classified, meanwhile, the prediction of the haze concentration of the area can be realized by utilizing the data in different areas, parameters of a prediction model of the haze concentration can be redefined according to actual conditions and requirements, and the network does not need to be rebuilt, so that the method has flexibility and portability, more specifically, according to the air pollution index of the national standard, the predicted haze concentration data are marked according to the levels and are sequentially divided into different air pollution levels.
The working principle is as follows: during operation, the official website of the environmental protection and meteorological department collects the daily average PM2.5, PM10, PM2.5, NO2, PM10, NO, SO2, T (max), T (min) of Haoshan city from 2015 to 2019 as source data, smoothes a small part of missing data, takes the average value of the previous and the next two days as the value of the missing data, normalizes the data, processes all the data to the range of [ -1, 1], schematizes the non-normalized data to facilitate observation, preliminarily determines whether a certain obvious relationship exists between the data, searches according to the positive-negative ratio relationship, directly abandons and uses the influence factors without obvious regular change, screens the data, finds out the regression coefficient and the correlation coefficient by establishing a linear regression equation for haze data and other data, provides a thought for the subsequent initial weight of the BP neural network, and the haze is in obvious seasonality, the method comprises the steps of classifying data according to seasonal time periods, forming local smoothness, avoiding errors caused by overall smoothness, taking 2015-plus-2018 data as training data, taking 2019 data as test data, taking regression coefficients as initial weights of the BP neural network according to ratios, calculating, training the network through adjusting errors and multiple experiments, improving accuracy and avoiding over-fitting, predicting haze data of three days in the future through trained data, and comparing and analyzing accuracy and feasibility through the predicted data and collected data.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The BP neural network based haze prediction method according to claim, characterized by the following process steps:
step 01, collecting historical related data and haze data; historical correlation data.
And step 02, preprocessing and normalizing history related data and haze data.
And 03, charifying and visualizing historical related data and haze data.
And step 04, finding out the available historical related data according to the positive-negative ratio relation.
And step 05, establishing a linear regression equation and calculating the correlation among the data.
And step 06, classifying the data into time periods according to seasons.
And step 07, reasonably dividing data into two types of training and testing.
And step 08, establishing a BP neural network and unifying linear regression equations by using a platform tool.
And 09, replacing the random weight of the traditional BP neural network with the correlation ratio data.
And step 10, training the BP neural network by using the processed data.
And 11, iterating parameters and adjusting and optimizing the model.
And step 12, predicting by using the optimized BP neural network.
And step 13, outputting results according to requirements.
2. The BP neural network-based haze prediction method according to claim, wherein the influencing factors are PM2.5, PM10, PM2.5, NO2, PM10, NO, SO2, T (max), T (min) and all data related thereto that can be verified as being available.
3. The BP neural network-based haze prediction method according to claim, wherein linear regression is used to find initial weights instead of traditional random weights to improve efficiency.
4. The haze prediction method based on the BP neural network as claimed in the claim, wherein the data is classified according to seasonal time period, so as to form a local smoothing idea and avoid errors caused by the whole smoothing.
5. The haze prediction method based on the BP neural network as claimed in claim, wherein the input data of the neural network input layer is normalized temperature, pressure, wind speed, rainfall and snowfall data, and the output data of the neural network output layer is normalized haze concentration value.
6. The haze prediction method based on the BP neural network as claimed in the claim, wherein the data is classified mainly according to seasons, the accuracy of the data is improved, the data is classified mainly in four seasons, and meanwhile, the data is classified according to different time periods of the day.
7. The haze prediction method based on the BP neural network as claimed in the claim, wherein the haze concentration prediction of the region can be realized by using data of different regions, and the parameters of the haze concentration prediction model can be redefined according to actual conditions and requirements without reconstructing the network, so that the method has flexibility and portability.
8. The haze prediction method based on the BP neural network as claimed in the claim, wherein according to the air pollution index of the national standard, the predicted haze concentration data is marked according to the levels, and the levels are sequentially divided into different air pollution levels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911000434.0A CN110766219A (en) | 2019-10-21 | 2019-10-21 | Haze prediction method based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911000434.0A CN110766219A (en) | 2019-10-21 | 2019-10-21 | Haze prediction method based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110766219A true CN110766219A (en) | 2020-02-07 |
Family
ID=69331507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911000434.0A Pending CN110766219A (en) | 2019-10-21 | 2019-10-21 | Haze prediction method based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110766219A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508261A (en) * | 2020-12-03 | 2021-03-16 | 广东电网有限责任公司 | Neural network-based distribution transformer load hierarchical prediction method and device |
| CN115455814A (en) * | 2022-08-31 | 2022-12-09 | 南京云创大数据科技股份有限公司 | Pollution source searching and pollutant distribution predicting method and system based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909206A (en) * | 2017-11-15 | 2018-04-13 | 电子科技大学 | A kind of PM2.5 Forecasting Methodologies based on deep structure Recognition with Recurrent Neural Network |
| CN108133295A (en) * | 2018-01-11 | 2018-06-08 | 安徽优思天成智能科技有限公司 | A kind of motor-driven vehicle gas concentration continuous time Forecasting Methodology for target road section |
| CN108520311A (en) * | 2018-03-07 | 2018-09-11 | 中国地质大学（武汉） | In conjunction with the haze prediction model method for building up and system of SOFM nets and BP neural network |
| CN109063938A (en) * | 2018-10-30 | 2018-12-21 | 浙江工商大学 | Air Quality Forecast method based on PSODE-BP neural network |
| CN109447373A (en) * | 2018-11-16 | 2019-03-08 | 上海海事大学 | Haze method is predicted based on the LSTM neural network of python platform |
| CN109902881A (en) * | 2019-03-19 | 2019-06-18 | 武汉乐易创想科技有限公司 | PM2.5 concentration prediction method based on multivariate statistical analysis and LSTM fusion |
-
2019
- 2019-10-21 CN CN201911000434.0A patent/CN110766219A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909206A (en) * | 2017-11-15 | 2018-04-13 | 电子科技大学 | A kind of PM2.5 Forecasting Methodologies based on deep structure Recognition with Recurrent Neural Network |
| CN108133295A (en) * | 2018-01-11 | 2018-06-08 | 安徽优思天成智能科技有限公司 | A kind of motor-driven vehicle gas concentration continuous time Forecasting Methodology for target road section |
| CN108520311A (en) * | 2018-03-07 | 2018-09-11 | 中国地质大学（武汉） | In conjunction with the haze prediction model method for building up and system of SOFM nets and BP neural network |
| CN109063938A (en) * | 2018-10-30 | 2018-12-21 | 浙江工商大学 | Air Quality Forecast method based on PSODE-BP neural network |
| CN109447373A (en) * | 2018-11-16 | 2019-03-08 | 上海海事大学 | Haze method is predicted based on the LSTM neural network of python platform |
| CN109902881A (en) * | 2019-03-19 | 2019-06-18 | 武汉乐易创想科技有限公司 | PM2.5 concentration prediction method based on multivariate statistical analysis and LSTM fusion |
Non-Patent Citations (2)
| Title |
|---|
| 宋利红: "基于深度学习的雾霾预测方法研究" * |
| 张平华: "基于神经网络的雾霾预测模型实证研究" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508261A (en) * | 2020-12-03 | 2021-03-16 | 广东电网有限责任公司 | Neural network-based distribution transformer load hierarchical prediction method and device |
| CN112508261B (en) * | 2020-12-03 | 2021-09-03 | 广东电网有限责任公司 | Neural network-based distribution transformer load hierarchical prediction method and device |
| CN115455814A (en) * | 2022-08-31 | 2022-12-09 | 南京云创大数据科技股份有限公司 | Pollution source searching and pollutant distribution predicting method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105069525B (en) | Round-the-clock 96 Day Load Curve Forecastings and optimization update the system | |
| CN111340288B (en) | Urban air quality time sequence prediction method considering time-space correlation | |
| CN112686464A (en) | Short-term wind power prediction method and device | |
| CN109376960A (en) | Load Forecasting based on LSTM neural network | |
| CN110837137A (en) | Typhoon prediction alarm method | |
| CN113205203A (en) | CNN-LSTM-based building energy consumption prediction method and system | |
| CN108399470B (en) | Indoor PM2.5 prediction method based on multi-example genetic neural network | |
| CN112016175A (en) | Water supply pipe network pressure measuring point optimal arrangement method based on tree hierarchical clustering | |
| CN110766219A (en) | Haze prediction method based on BP neural network | |
| Fu et al. | An innovative decision making method for air quality monitoring based on big data-assisted artificial intelligence technique | |
| CN113987912A (en) | Pollutant on-line monitoring system based on geographic information | |
| CN114694767B (en) | PM2.5 concentration prediction method based on space-time diagram ordinary differential equation network | |
| CN114217025B (en) | Analysis method for evaluating influence of meteorological data on air quality concentration prediction | |
| CN116796141A (en) | GBDT regression model-based office building energy consumption prediction method | |
| CN115965136A (en) | Carbon emission comprehensive prediction system based on electric power big data | |
| CN115728463A (en) | Interpretable water quality prediction method based on semi-embedded feature selection | |
| CN114970946A (en) | PM2.5 pollution concentration long-term space prediction method based on deep learning model and empirical mode decomposition coupling | |
| CN114066070A (en) | Weather forecasting method based on artificial intelligence and numerical calculation | |
| CN117634678A (en) | Low-carbon park carbon emission prediction method based on actual operation scene | |
| CN115034422A (en) | Wind power short-term power prediction method and system based on fluctuation identification and error correction | |
| CN116128168A (en) | Weather prediction method based on causal expansion convolution and Autoformer | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| US20230223099A1 (en) | Predicting method of cell deconvolution based on a convolutional neural network | |
| CN113139671A (en) | Power load interval prediction method and system based on branch structure model | |
| CN112712213B (en) | Method and system for predicting deep migration learning energy consumption of concentrated air conditioning house |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200207 |
|
| RJ01 | Rejection of invention patent application after publication |