CN112308973A - Three-dimensional ocean element field intelligent construction method and system based on machine learning - Google Patents
Three-dimensional ocean element field intelligent construction method and system based on machine learning Download PDFInfo
- Publication number
- CN112308973A CN112308973A CN202011188788.5A CN202011188788A CN112308973A CN 112308973 A CN112308973 A CN 112308973A CN 202011188788 A CN202011188788 A CN 202011188788A CN 112308973 A CN112308973 A CN 112308973A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- data
- field
- ocean
- training
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 46
- 238000010276 construction Methods 0.000 title claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000012950 reanalysis Methods 0.000 claims description 11
- 238000004441 surface measurement Methods 0.000 claims description 11
- 238000003908 quality control method Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims 2
- 238000000034 method Methods 0.000 abstract description 9
- 238000011160 research Methods 0.000 abstract description 9
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 description 6
- 241000689227 Cora <basidiomycete fungus> Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a three-dimensional ocean element field intelligent construction method based on machine learning, which comprises the following steps: acquiring training data, wherein the training data comprises one-dimensional field observation data, two-dimensional sea surface observation data and three-dimensional gridding background field data; processing the training data, and outputting the processed training data as training sample characteristics; training a machine learning model, and training the machine learning model by using the characteristics of the training samples to obtain a prediction model; and constructing a three-dimensional ocean element field, and loading ocean surface element information, spatial grid information, prediction time information and optional background field element information into a prediction model in real time to construct the three-dimensional ocean element field. The method can overcome the defect that the three-dimensional ocean element field construction method in the prior art cannot meet the requirements for refinement and precision, organically integrates multi-source and multi-dimensional data, realizes intelligent reconstruction of the ocean three-dimensional element field by utilizing a machine learning technology, and meets the requirements for refined and precise ocean research and production.
Description
Technical Field
The invention relates to the technical field of data processing technology and machine learning, in particular to a three-dimensional ocean element field intelligent construction method and system based on machine learning.
Background
Accurate and reliable marine observation data are important prerequisites and necessary conditions for marine scientific research, global change research and marine high-efficiency production operation. In order to further and deeply reveal and predict the climate change and the evolution of the marine environment, the marine environment data with high space-time resolution, high precision and high reliability needs to be obtained, and scientific research and numerical simulation are developed on the basis, which become common knowledge of atmospheric marine scientific research. However, current observations have difficulty meeting the real world demands for ocean data wide area, high accuracy, and spatiotemporal continuity. Therefore, the construction of high spatial and temporal resolution ocean element fields draws a great deal of attention, and several solutions for scientific research and life production are successively presented.
The construction of the three-dimensional element field generally requires the organic fusion of multi-source data such as field observation data, multi-satellite observation data, background field and the like. However, as the kinds and the amount of observation data increase, the computing power, the numerical method and the assimilation technology pose huge challenges. The development of two traditional mainstream methods for recognizing the marine environment by marine statistical analysis and marine environment numerical prediction meets certain bottlenecks: due to the facts that a traditional linear method model is too simple, understanding of an ocean process is not comprehensive and deep enough, uncertainty of a numerical mode and limitation of mode resolution are caused, and the requirements of increasingly refined and precise research and production cannot be met.
Disclosure of Invention
The invention provides a three-dimensional ocean element field intelligent construction method and system based on machine learning, and aims to overcome the defect that the three-dimensional ocean element field construction method in the prior art cannot meet the requirements for refinement and precision.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
the invention provides a three-dimensional ocean element field intelligent construction method based on machine learning, which comprises the following steps:
acquiring training data, wherein the training data comprises one-dimensional field observation data, two-dimensional sea surface observation data and three-dimensional gridding background field data;
processing the training data, performing quality control on the one-dimensional field observation data, detecting and eliminating abnormal values, and interpolating the one-dimensional field observation data to a standard layer; performing quality control on the two-dimensional sea surface measurement data and the three-dimensional gridding background field data, interpolating the two-dimensional sea surface measurement data and the three-dimensional gridding background field data to a grid with the same spatial resolution, and interpolating the three-dimensional gridding background field data to a standard layer which is the same as the one-dimensional data; outputting the processed training data as training sample characteristics;
training a machine learning model, and training the machine learning model by using the characteristics of the training samples to obtain a prediction model;
and constructing a three-dimensional ocean element field, and loading ocean surface element information, spatial grid information, prediction time information and optional background field element information into a prediction model in real time to construct the three-dimensional ocean element field.
According to the three-dimensional ocean element field intelligent construction method based on machine learning, the one-dimensional field observation data at least comprises one of GTS, ARGO buoy and ocean station data; the two-dimensional sea surface measurement data at least comprises one of sea surface satellite remote sensing data and reanalysis data; the three-dimensional gridding background field data at least comprises one of reanalysis data and mode forecast data, such as HYCOM reanalysis and forecast data, CORA reanalysis data and WOA data.
The invention provides a three-dimensional ocean element field intelligent construction method based on machine learning.
The invention provides a three-dimensional ocean element field intelligent construction method based on machine learning, which comprises the following steps of: and interpolating the multi-source atmospheric and ocean data to the same time resolution.
The invention provides an intelligent construction method of a three-dimensional ocean element field for opportunistic machine learning, which is characterized by further comprising the following steps after the step of constructing the three-dimensional ocean element field: and establishing an inspection model, and performing precision inspection on the constructed three-dimensional ocean element field.
The invention provides a machine learning three-dimensional ocean element field intelligent construction system which is characterized by comprising the following steps:
the data module is used for acquiring training data;
the characteristic analysis module is used for processing training data;
a model module for training a machine learning model;
and the system module is used for constructing a three-dimensional ocean element field.
The machine-learning three-dimensional ocean element field intelligent construction system is characterized in that the system module is also used for carrying out rationality and precision inspection on the constructed three-dimensional ocean element field.
The invention has the following advantages:
the invention provides a three-dimensional ocean element field intelligent construction method based on machine learning, which comprises the following steps: acquiring training data, wherein the training data comprises one-dimensional field observation data, two-dimensional sea surface observation data and three-dimensional gridding background field data; processing the training data, performing quality control on the one-dimensional field observation data, detecting and eliminating abnormal values, and interpolating the one-dimensional field observation data to a standard layer; performing quality control on the two-dimensional sea surface measurement data and the three-dimensional gridding background field data, interpolating the two-dimensional sea surface measurement data and the three-dimensional gridding background field data to a grid with the same spatial resolution, and interpolating the three-dimensional gridding background field data to a standard layer which is the same as the one-dimensional data; outputting the processed training data as training sample characteristics; training a machine learning model, and training the machine learning model by using the characteristics of the training samples to obtain a prediction model; and constructing a three-dimensional ocean element field, and loading ocean surface element information, spatial grid information, prediction time information and optional background field element information into a prediction model in real time to construct the three-dimensional ocean element field. The method can overcome the defect that the three-dimensional ocean element field construction method in the prior art cannot meet the requirements for refinement and precision, organically integrates multi-source and multi-dimensional data, realizes intelligent reconstruction of the ocean three-dimensional element field by utilizing a machine learning technology, and meets the requirements for refined and precise ocean research and production.
Drawings
The invention and its features, aspects and advantages will become more apparent from reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings. Like reference symbols in the various drawings indicate like elements. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the invention.
Fig. 1 is a schematic flowchart of a three-dimensional ocean element field intelligent construction method based on machine learning according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a temperature-salt field constructed by using a three-dimensional ocean element field intelligent construction method based on machine learning provided by embodiment 1 of the present invention;
fig. 3 is a comparison diagram of the three-dimensional ocean element field intelligent construction method based on machine learning and the HYCOM reanalysis field provided in embodiment 1 of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application.
As shown in fig. 1, a method for intelligently constructing a three-dimensional ocean element field based on machine learning according to embodiment 1 of the present invention includes:
s101: acquiring training data, wherein the training data comprises one-dimensional field observation data, two-dimensional sea surface observation data and three-dimensional gridding background field data;
s102: processing the training data, performing quality control on the one-dimensional field observation data, detecting and eliminating abnormal values, and interpolating the one-dimensional field observation data to a standard layer; performing quality control on the two-dimensional sea surface measurement data and the three-dimensional gridding background field data, interpolating the two-dimensional sea surface measurement data and the three-dimensional gridding background field data to a grid with the same spatial resolution, and interpolating the three-dimensional gridding background field data to a standard layer which is the same as the one-dimensional data; outputting the processed training data as training sample characteristics;
s103: training a machine learning model, and training the machine learning model by using the characteristics of the training samples to obtain a prediction model;
s104: and constructing a three-dimensional ocean element field, and loading ocean surface element information, spatial grid information, prediction time information and optional background field element information into a prediction model in real time to construct the three-dimensional ocean element field.
Wherein, the one-dimensional field observation data in the step S101 at least includes one of GTS, ARGO buoy and marine station data; the two-dimensional sea surface measurement data at least comprises one of sea surface satellite remote sensing data and reanalysis data; the three-dimensional gridding background field data at least comprises one of reanalysis data and mode forecast data, such as HYCOM reanalysis and forecast data, CORA reanalysis data and WOA data. The training sample characteristics of step S102 include a two-dimensional sea surface observation element field, one-dimensional field observation data space information, one-dimensional field observation data time information, and optional background field element information. Step S102 further includes: and interpolating the multi-source atmospheric and ocean data to the same time resolution. Step S104 is followed by: s105, establishing an inspection model, and carrying out precision inspection on the constructed three-dimensional ocean element field. The machine learning model in step S103 includes, but is not limited to, a decision tree-based machine learning model (e.g., LightGBM, random forest, etc.) and a deep neural network (e.g., CNN, MLP, ResNet, etc.), and may also be used as a training engine based on other traditional or intelligent combined algorithms. And (3) carrying out hyper-parameter automatic tuning on the machine learning model by adopting a Bayesian optimization method (e.g. a hyper pt library).
As shown in the figure, the construction of the three-dimensional ocean element field is performed on the thermohaline field by using the embodiment 1, the one-dimensional field observation data adopts an Argo data set observed on the thermohaline field, the two-dimensional sea appearance measurement data adopts variables such as sea surface temperature, height anomaly and a sea surface 10m wind field, the three-dimensional grid background field data adopts a HYCOM mode to re-analyze data, the effect is shown in fig. 2, and the average absolute error of the constructed ocean temperature field with the global resolution of 0.25 degrees is MAE 0.38 ℃; the horizontal and vertical sections of the constructed temperature field are reasonable in structure, and the spatial distribution of the ocean temperature field can be accurately described; compared with the mode re-analysis data HYCOM, as shown in FIG. 3, the method has higher precision.
In summary, in the embodiment 1 of the invention, the marine big data space-time information can be fully mined, the multi-source and multi-dimensional data are organically fused, the intelligent reconstruction of the marine three-dimensional element field is realized by using the machine learning technology, and the requirements of refined and precise marine research and production are met.
Example 2:
the three-dimensional ocean element field intelligent construction system based on machine learning, which is realized by the three-dimensional ocean element field intelligent construction method based on machine learning provided by the embodiment 1, comprises:
the data module is used for acquiring training data;
the characteristic analysis module is used for processing training data;
a model module for training a machine learning model;
and the system module is used for constructing the three-dimensional ocean element field and carrying out precision inspection on the constructed three-dimensional ocean element field. The specific principle and beneficial effect are the same as those of the three-dimensional ocean element field intelligent construction method based on machine learning provided by embodiment 1, and are not repeated herein.
The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all equivalent structural changes made by using the contents of the present specification and the drawings, or any other related technical fields, are included in the scope of the present invention.
Claims (7)
1. A three-dimensional ocean element field intelligent construction method based on machine learning is characterized by comprising the following steps:
acquiring training data, wherein the training data comprises one-dimensional field observation data, two-dimensional sea surface observation data and three-dimensional gridding background field data;
processing the training data, performing quality control on the one-dimensional field observation data, detecting and eliminating abnormal values, and interpolating the one-dimensional field observation data to a standard layer; performing quality control on the two-dimensional sea surface measurement data and the three-dimensional gridding background field data, interpolating the two-dimensional sea surface measurement data and the three-dimensional gridding background field data to a grid with the same spatial resolution, and interpolating the three-dimensional gridding background field data to a standard layer which is the same as the one-dimensional data; outputting the processed training data as training sample characteristics;
training a machine learning model, and training the machine learning model by using the characteristics of the training samples to obtain a prediction model;
and constructing a three-dimensional ocean element field, and loading ocean surface element information, spatial grid information, prediction time information and optional background field element information into a prediction model in real time to construct the three-dimensional ocean element field.
2. The machine learning-based three-dimensional marine factor field intelligent construction method of claim 1, wherein the one-dimensional field observation data comprises at least one of GTS, ARGO buoy and marine station data; the two-dimensional sea surface measurement data at least comprises one of sea surface satellite remote sensing data and reanalysis data; the three-dimensional gridding background field data at least comprises one of reanalysis data and mode forecast data.
3. The machine learning-based intelligent construction method of the three-dimensional ocean element field according to claim 1, wherein the training sample characteristics comprise a two-dimensional ocean appearance measurement element field, one-dimensional field observation data space information, one-dimensional field observation data time information and optional background field element information.
4. The machine learning-based three-dimensional marine element field intelligent construction method according to claim 1, wherein the step of processing training data further comprises: and interpolating the multi-source atmospheric and ocean data to the same time resolution.
5. The intelligent construction method of three-dimensional ocean element field based on machine learning according to claim 1, wherein the step of "constructing three-dimensional ocean element field" further comprises the following steps: and establishing a detection model, and carrying out rationality and precision detection on the constructed three-dimensional ocean element field.
6. A three-dimensional ocean element field intelligent construction system based on machine learning is characterized by comprising the following steps:
the data module is used for acquiring training data;
the characteristic analysis module is used for processing training data;
a model module for training a machine learning model;
and the system module is used for constructing a three-dimensional ocean element field.
7. The machine-learned three-dimensional marine element field intelligent construction system according to claim 6, wherein the system module is further used for checking reasonableness and accuracy of the constructed three-dimensional marine element field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011188788.5A CN112308973A (en) | 2020-10-30 | 2020-10-30 | Three-dimensional ocean element field intelligent construction method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011188788.5A CN112308973A (en) | 2020-10-30 | 2020-10-30 | Three-dimensional ocean element field intelligent construction method and system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112308973A true CN112308973A (en) | 2021-02-02 |
Family
ID=74332560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011188788.5A Pending CN112308973A (en) | 2020-10-30 | 2020-10-30 | Three-dimensional ocean element field intelligent construction method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308973A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884217A (en) * | 2021-02-04 | 2021-06-01 | 国家海洋信息中心 | Sea surface height forecasting method based on multi-model integration |
| CN113063737A (en) * | 2021-03-26 | 2021-07-02 | 福州大学 | Ocean heat content remote sensing inversion method combining remote sensing and buoy data |
| CN114580561A (en) * | 2022-03-15 | 2022-06-03 | 中国海洋大学 | Machine learning fusion method and model for multisource sea surface physical elements |
| CN115438523A (en) * | 2022-11-09 | 2022-12-06 | 中关村睿宸卫星创新应用研究院 | Method, device, equipment and medium for reconstructing ocean three-dimensional chlorophyll concentration data |
| CN116797756A (en) * | 2023-08-16 | 2023-09-22 | 海博泰科技(青岛)有限公司 | Holographic ocean background field implementation method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416031A (en) * | 2018-03-12 | 2018-08-17 | 南京恩瑞特实业有限公司 | NRIET meteorology multi-source detection information convergence analysis systems |
| CN108981957A (en) * | 2018-05-31 | 2018-12-11 | 西北工业大学 | Submarine temperatures field reconstructing method based on self organizing neural network and Empirical Orthogonal Function |
| CN109543356A (en) * | 2019-01-07 | 2019-03-29 | 福州大学 | Consider the ocean interior temperature-salinity structure remote sensing inversion method of Space atmosphere |
-
2020
- 2020-10-30 CN CN202011188788.5A patent/CN112308973A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416031A (en) * | 2018-03-12 | 2018-08-17 | 南京恩瑞特实业有限公司 | NRIET meteorology multi-source detection information convergence analysis systems |
| CN108981957A (en) * | 2018-05-31 | 2018-12-11 | 西北工业大学 | Submarine temperatures field reconstructing method based on self organizing neural network and Empirical Orthogonal Function |
| CN109543356A (en) * | 2019-01-07 | 2019-03-29 | 福州大学 | Consider the ocean interior temperature-salinity structure remote sensing inversion method of Space atmosphere |
Non-Patent Citations (3)
| Title |
|---|
| 孙春健等: "卫星遥感重构海洋次表层研究进展", 《海洋信息》, no. 04, pages 21 - 26 * |
| 李直龙;左军成;纪棋严;罗凤云;庄圆;: "基于Argo剖面和SST以及SLA数据重构三维网格温度场", 海洋预报, no. 04 * |
| 陈建;姜祝辉;宿兴涛;闫恒乾;宋博;安玉柱;路凯程;: "多源资料重构三维海温场的先验误差估计和诊断分析", 海洋学报, no. 04 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884217A (en) * | 2021-02-04 | 2021-06-01 | 国家海洋信息中心 | Sea surface height forecasting method based on multi-model integration |
| CN112884217B (en) * | 2021-02-04 | 2022-03-15 | 国家海洋信息中心 | Sea surface height forecasting method based on multi-model integration |
| CN113063737A (en) * | 2021-03-26 | 2021-07-02 | 福州大学 | Ocean heat content remote sensing inversion method combining remote sensing and buoy data |
| CN114580561A (en) * | 2022-03-15 | 2022-06-03 | 中国海洋大学 | Machine learning fusion method and model for multisource sea surface physical elements |
| CN115438523A (en) * | 2022-11-09 | 2022-12-06 | 中关村睿宸卫星创新应用研究院 | Method, device, equipment and medium for reconstructing ocean three-dimensional chlorophyll concentration data |
| CN115438523B (en) * | 2022-11-09 | 2023-03-07 | 中关村睿宸卫星创新应用研究院 | Method, device, equipment and medium for reconstructing marine three-dimensional chlorophyll concentration data |
| CN116797756A (en) * | 2023-08-16 | 2023-09-22 | 海博泰科技(青岛)有限公司 | Holographic ocean background field implementation method |
| CN116797756B (en) * | 2023-08-16 | 2023-11-07 | 海博泰科技(青岛)有限公司 | Holographic ocean background field implementation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112308973A (en) | Three-dimensional ocean element field intelligent construction method and system based on machine learning | |
| JP2022105263A (en) | Multi-source timing data fault diagnosis method based on graph neural network, and medium | |
| CN115393540A (en) | Intelligent fusion method and system of three-dimensional marine environment field based on deep learning | |
| CN111784041A (en) | Wind power prediction method and system based on graph convolution neural network | |
| Li et al. | Deep spatio-temporal wind power forecasting | |
| CN116720156A (en) | Weather element forecasting method based on graph neural network multi-mode weather data fusion | |
| Morik et al. | Introduction to data mining for sustainability | |
| Jiang et al. | A holistic feature selection method for enhanced short-term load forecasting of power system | |
| CN115730684A (en) | Air quality detection system based on LSTM-CNN model | |
| CN114417693A (en) | Ocean three-dimensional temperature field inversion method based on deep learning | |
| Baïle et al. | Leveraging data from nearby stations to improve short-term wind speed forecasts | |
| CN110826810B (en) | Regional rainfall prediction method combining spatial reasoning and machine learning | |
| CN111461423A (en) | High-precision gridding air quality inference method, system, terminal equipment and storage medium | |
| CN113407524A (en) | Climate system mode multi-circle layer coupling data assimilation system | |
| CN116451821A (en) | Deep learning-based large-area new energy generation power prediction method and system | |
| CN118012850A (en) | Intelligent irrigation multisource information-oriented database construction system, method and equipment | |
| CN113984198A (en) | Short wave radiation prediction method and system based on convolutional neural network | |
| Ma et al. | Multi-features fusion for short-term photovoltaic power prediction | |
| CN110019167A (en) | Long-term new forms of energy resource data base construction method and system in one kind | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| Wang et al. | Operational climate prediction in the era of big data in China: Reviews and prospects | |
| CN113962432A (en) | Wind power prediction method and system integrating three-dimensional convolution and light-weight convolution threshold unit | |
| Zhu et al. | Research progress of the ultra-short term power forecast for PV power generation: A review | |
| Lu et al. | Application of offshore visibility forecast based on temporal convolutional network and transfer learning |
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 |