CN109472393A - Space NO emissions reduction precipitation data detection method, device and electronic equipment - Google Patents
Space NO emissions reduction precipitation data detection method, device and electronic equipment Download PDFInfo
- Publication number
- CN109472393A CN109472393A CN201811159034.XA CN201811159034A CN109472393A CN 109472393 A CN109472393 A CN 109472393A CN 201811159034 A CN201811159034 A CN 201811159034A CN 109472393 A CN109472393 A CN 109472393A
- Authority
- CN
- China
- Prior art keywords
- surface temperature
- resolution
- precipitation data
- tested
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of space NO emissions reduction precipitation data detection methods.NO emissions reduction precipitation data detection method in space of the present invention include the following steps: according to sample areas second resolution daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index, and the satellite remote sensing precipitation data of the sample areas, it establishes and trains optimal stochastic forest algorithm model；By the area to be tested surface temperature on daytime of the first resolution, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtains the precipitation data of area to be tested first resolution；Residual error corrections are carried out to the precipitation data of the first resolution, obtain the space NO emissions reduction precipitation data of area to be tested.Space NO emissions reduction precipitation data detection method of the present invention can obtain the higher precipitation data of resolution ratio.
Description
Technical field
The present invention relates to weather information technical field, more particularly to a kind of space NO emissions reduction precipitation data detection method,
Device and electronic equipment.
Background technique
The strong change in time and space of precipitation often prevents the precipitation measurement at routinely base station station from accurately holding the space of precipitation
Distribution and Strength Changes, and Satellite microwave remote sensing technology can overcome this limitation, realization is realized in the world to precipitation
Observation, and for infrared/visible light can only reflect the information such as cloud thickness, the cloud level, satellite microwave can penetrate cloud body, benefit
More direct detection is carried out to cloud, rain with the interaction of precipitation particles in cloud and cloud particle and microwave, is realized to precipitation number
According to monitoring, however, since microwave remote sensing technique developing history is shorter, precipitation occurs in addition high randomness and heterogeneous makes
It is lower must to have microwave remote sensing precipitation data resolution ratio, it is difficult to reflect the spatial detail feature of precipitation.
Summary of the invention
Based on this, the object of the present invention is to provide a kind of space NO emissions reduction precipitation data detection methods, can obtain
The higher precipitation data of resolution ratio.
The present invention is achieved by the following scheme:
A kind of space NO emissions reduction precipitation data detection method, includes the following steps:
The surface temperature and night surface temperature on daytime of sample areas is obtained, and according to the surface temperature on daytime and night
The surface temperature round the clock that surface temperature obtains sample areas is poor；
Obtain the digital elevation model of sample areas and the vegetation index of sample areas；
By the sample areas of first resolution daytime surface temperature, night surface temperature, round the clock surface temperature it is poor, number
Elevation model and vegetation index resampling are second resolution identical with the satellite remote sensing precipitation data of the sample areas,
In, second resolution is less than first resolution；
According to sample areas second resolution daytime surface temperature, night surface temperature, round the clock surface temperature it is poor, number
The satellite remote sensing precipitation data of elevation model and vegetation index and the sample areas is established and trains optimal stochastic forest
Algorithm model, wherein the sample areas daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation
The input sample of model and vegetation index as the trained optimal stochastic forest algorithm model, the satellite of the sample areas are distant
Feel output sample of the precipitation data as the trained optimal stochastic forest algorithm model；
The surface temperature and night surface temperature on daytime of area to be tested is obtained, and according to the daytime of the area to be tested
The surface temperature round the clock that surface temperature and night surface temperature obtain area to be tested is poor；
Obtain the digital elevation model of area to be tested and the vegetation index of area to be tested；
By the area to be tested surface temperature on daytime of the first resolution, night surface temperature, round the clock surface temperature it is poor,
Digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtain the precipitation of area to be tested first resolution
Data；
Residual error corrections are carried out to the precipitation data of the first resolution, obtain the space NO emissions reduction precipitation of area to be tested
Data.
NO emissions reduction precipitation data detection method in space of the present invention, utilizes the sample area for having satellite remote sensing precipitation data
Domain daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index and sample area
The remote sensing precipitation data in domain establishes optimal random forests algorithm model, using the model, calculates the high score of area to be tested
The precipitation data of resolution, and residual error corrections are carried out to the precipitation data, obtain the precipitation data of more accurate space NO emissions reduction.
In one embodiment, residual error corrections are carried out to the precipitation data of the first resolution, obtains area to be tested
Space NO emissions reduction precipitation data, comprising:
The precipitation data of area to be tested first resolution is resampled to second resolution；
The precipitation of area to be tested second resolution after calculating area to be tested satellite remote sensing precipitation data and resampling
Difference between data obtains the first residual error；
By the first residual error spatial interpolation to first resolution, the second residual error of first resolution is obtained；
The precipitation data of area to be tested first resolution is added with the second residual error, obtains the space drop of area to be tested
Scale precipitation data.
In one embodiment, the vegetation index of the sample areas and the area to be tested is greater than zero.
In one embodiment, the first resolution is 1km*1km, and the second resolution is 25km*25km.
In one embodiment, by the sample areas of first resolution daytime surface temperature, night surface temperature, round the clock
Surface temperature is poor, digital elevation model and vegetation index resampling are identical as the satellite remote sensing precipitation data of the sample areas
Second resolution, comprising:
It calculates within the scope of second resolution pixel, the average value of all first resolution pixels.
Further, the present invention also provides a kind of space NO emissions reduction precipitation data detection devices, comprising:
First data acquisition module, for obtaining the surface temperature and night surface temperature on daytime of sample areas, and according to
The surface temperature round the clock that the surface temperature on daytime and night surface temperature obtain sample areas is poor, and obtains sample areas
The vegetation index of digital elevation model and sample areas；
First resampling module, for by the sample areas of first resolution daytime surface temperature, night surface temperature,
Surface temperature is poor round the clock, digital elevation model and vegetation index resampling are satellite remote sensing precipitation data with the sample areas
Identical second resolution；
Random forest training module, for according to sample areas second resolution daytime surface temperature, night earth's surface temperature
Degree, round the clock surface temperature be poor, satellite remote sensing precipitation data of digital elevation model and vegetation index and the sample areas,
Establish and train optimal stochastic forest algorithm model, wherein the sample areas daytime surface temperature, night surface temperature,
The input sample that surface temperature is poor round the clock, digital elevation model and vegetation index are as the trained optimal stochastic forest algorithm model
This, output sample of the satellite remote sensing precipitation data of the sample areas as the trained optimal stochastic forest algorithm model；
Second data acquisition module, for obtaining the surface temperature and night surface temperature on daytime of area to be tested, and root
According to the area to be tested daytime surface temperature and night surface temperature obtain area to be tested surface temperature round the clock it is poor, with
And obtain the digital elevation model of area to be tested and the vegetation index of area to be tested；
First precipitation data obtains module, for by the area to be tested surface temperature on daytime of the first resolution, night
Between surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtain
The precipitation data of area to be tested first resolution；
Residual error corrections module carries out residual error corrections for the precipitation data to the first resolution, obtains area to be detected
The space NO emissions reduction precipitation data in domain.
NO emissions reduction precipitation data detection device in space of the present invention, utilizes the sample area for having satellite remote sensing precipitation data
Domain daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index and sample area
The remote sensing precipitation data in domain establishes optimal random forests algorithm model, using the model, calculates the high score of area to be tested
The precipitation data of resolution, and residual error corrections are carried out to the precipitation data, obtain the precipitation data of more accurate space NO emissions reduction.
In one embodiment, the residual error corrections module, comprising:
Second resampling unit, for the precipitation data of area to be tested first resolution to be resampled to the second resolution
Rate；
First residual error acquiring unit, for calculate area to be tested satellite remote sensing precipitation data with it is to be detected after resampling
Difference between the precipitation data of region second resolution obtains the first residual error；
Second residual error acquiring unit, for obtaining the first residual error spatial interpolation to first resolution first and differentiating
Second residual error of rate；
NO emissions reduction precipitation data acquiring unit, for by the precipitation data of area to be tested first resolution and the second residual error
It is added, obtains the space NO emissions reduction precipitation data of area to be tested.
In one embodiment, the first resampling module includes resolution ratio computing unit, is differentiated for calculating second
Within the scope of rate pixel, the average value of all first resolution pixels.
Further, the present invention also provides a kind of computer-readable medium, it is stored thereon with computer program, the computer
Such as above-mentioned any one space NO emissions reduction precipitation data detection method is realized when program is executed by processor.
Further, the present invention also provides a kind of electronic equipment, including memory, processor and it is stored in the storage
Device and the computer program that can be executed by the processor when processor executes the computer program, are realized as above-mentioned
Any one space NO emissions reduction precipitation data detection method.
In order to better understand and implement, the invention will now be described in detail with reference to the accompanying drawings.
Detailed description of the invention
Fig. 1 is space NO emissions reduction precipitation data detection method flow chart in a kind of embodiment；
Fig. 2 is residual error corrections flow diagram in a kind of embodiment；
Fig. 3 is space NO emissions reduction precipitation data detection method flow chart in another embodiment；
Fig. 4 is space NO emissions reduction precipitation data structure of the detecting device schematic diagram in a kind of embodiment；
Fig. 5 is electronic devices structure schematic diagram in a kind of embodiment.
Specific embodiment
Referring to Fig. 1, in one embodiment, space NO emissions reduction precipitation data detection method includes the following steps:
Step S10: the surface temperature and night surface temperature on daytime of sample areas is obtained, and according to earth's surface on the daytime temperature
The surface temperature round the clock that degree and night surface temperature obtain sample areas is poor.
The sample areas is to have the region of satellite remote sensing precipitation data, and the size of the sample areas is that the satellite is distant
Feel the integral multiple of the resolution sizes of precipitation data.The surface temperature on daytime is surface temperature being averaged within entire daytime
Value, the night surface temperature are average value of the surface temperature at entire night, in one embodiment, earth's surface on the daytime temperature
Degree and the night surface temperature pass through satellite sensor modis (Moderate Imaging Spectroradiomete moderate-resolution
Imaging spectroradiometer) it obtains, the diurnal temperature difference of the sample areas is the surface temperature on daytime and institute
State the difference between night surface temperature.
Step S20: the digital elevation model of sample areas and the vegetation index of sample areas are obtained.
The digital elevation model (Digital Elevation Model), vehicle economy M are high by limited landform
Number of passes factually now to the digitized simulation of ground surface or terrain, the i.e. digital expression of topographical surface form, has numerical sequence battle array for one group
Column form indicates a kind of actual ground model of ground elevation, and the vegetation index is the spectral characteristic according to vegetation, by satellite
Visible light and near infrared band are combined, the vegetative coverage index of formation, qualitative and quantitative assessment vegetative coverage and its growth
Vigor.The value of vegetation index is usually -1 to 1, and in snow and ice cover, water body and desert areas, vegetation index is typically less than zero
Constant, in the present embodiment, the sample areas are the region that vegetation index is greater than zero.
Step S30: by the sample areas of first resolution daytime surface temperature, night surface temperature, round the clock earth's surface temperature
It spends poor, digital elevation model and vegetation index resampling is and the satellite remote sensing precipitation data identical second of the sample areas
Resolution ratio, wherein second resolution is less than first resolution.
Wherein, in the present embodiment, the surface temperature on daytime, night surface temperature, surface temperature is poor round the clock, number is high
The first resolution of journey model and vegetation index is 1km*1km, and the second resolution of satellite remote sensing precipitation data is 25km*
25km, therefore, it is necessary to by first resolution daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation
Model and vegetation index resampling are second resolution.
Step S40: according to sample areas second resolution daytime surface temperature, night surface temperature, round the clock earth's surface temperature
The satellite remote sensing precipitation data of poor, digital elevation model and vegetation index and the sample areas is spent, establishes and training is optimal
Random forests algorithm model.
The satellite remote sensing precipitation data of the sample areas is to be monitored in the sample areas by satellite remote sensing
Precipitation data, the optimal stochastic forest algorithm model be after repetition training, precipitation data calculate error reach the smallest
Random forests algorithm model.Wherein, the sample areas daytime surface temperature, night surface temperature, round the clock surface temperature it is poor,
The input sample of digital elevation model and vegetation index as the trained optimal stochastic forest algorithm model, the sample areas
Output sample of the satellite remote sensing precipitation data as the trained optimal stochastic forest algorithm model.
Step S50: the surface temperature and night surface temperature on daytime of area to be tested is obtained, and according to the area to be detected
Domain daytime surface temperature and night surface temperature obtain area to be tested surface temperature round the clock it is poor.
In the present embodiment, the region to be monitored daytime surface temperature and the night surface temperature pass through satellite pass
Sensor modis (Moderate Imaging Spectroradiomete moderate-resolution imaging spectroradiometer) is obtained
It takes.
Step S60: the digital elevation model of area to be tested and the vegetation index of area to be tested are obtained.
In the present embodiment, the area to be tested is the region that vegetation index is greater than zero.
Step S70: by the area to be tested surface temperature on daytime of the first resolution, night surface temperature, round the clock
Table temperature difference, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtain area to be tested first and divide
The precipitation data of resolution.
In the present embodiment, the precipitation data resolution ratio of the area to be tested acquired in the optimal stochastic forest algorithm model
For 1km*1km, but error is larger.
Step S80: carrying out residual error corrections to the precipitation data of the first resolution, obtains the space drop of area to be tested
Scale precipitation data.
The residual error be satellite remote sensing measurement precipitation data with it is to be checked acquired in the optimal stochastic forest algorithm model
The difference between the precipitation data in region is surveyed, residual error corrections are carried out to the precipitation data of high-resolution area to be tested, can be obtained
To the precipitation data of more accurate high-resolution area to be tested.
NO emissions reduction precipitation data detection method in space of the present invention, utilizes the sample area for having satellite remote sensing precipitation data
Domain daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index and sample area
The remote sensing precipitation data in domain establishes optimal random forests algorithm model, using the model, calculates the high score of area to be tested
The precipitation data of resolution, and residual error corrections are carried out to the precipitation data, obtain the precipitation data of more accurate space NO emissions reduction.
In one embodiment, in step S80, residual error corrections is carried out to the precipitation data of the first resolution, are obtained
The space NO emissions reduction precipitation data of area to be tested specifically comprises the following steps:
Step S81: the precipitation data of area to be tested first resolution is resampled to second resolution.
Step S82: the area to be tested second after calculating area to be tested satellite remote sensing precipitation data and resampling is differentiated
Difference between the precipitation data of rate obtains the first residual error.
Step S83: by the first residual error spatial interpolation to first resolution, the second residual error of first resolution is obtained.
Step S84: the precipitation data of area to be tested first resolution is added with the second residual error, obtains area to be tested
Space NO emissions reduction precipitation data.
Due to the high temporal-spatial heterogeneity of precipitation, the portion that cannot be effectively indicated by optimal stochastic forest algorithm model is certainly existed
Divide precipitation, i.e. residual error.The present invention is by by this part residual error carrying out NO emissions reduction and being added with 1km resolution ratio Simulation of Precipitation value
Mode minimizes model error.Since area to be tested satellite remote sensing precipitation data resolution ratio is 25km*25km, can lead to
Cross the precipitation data meter that area to be tested satellite remote sensing precipitation data value subtracts the area to be tested second resolution after resampling
Calculate the residual error obtained under 25km*25km resolution ratio.Due to the randomness that residual error generates, the present embodiment passes through spatial interpolation
Mode carries out NO emissions reduction to residual error, in the present embodiment, using thin plate spline function interpolation method (Thin-plate Spline) to residual
Difference carries out interpolation processing, to obtain optimal NO emissions reduction result.
In one embodiment, by first resolution daytime surface temperature, night surface temperature, round the clock surface temperature
Difference, digital elevation model and vegetation index resampling are second resolution, are the institutes by calculating within the scope of second resolution pixel
There is the average value of first resolution pixel to realize, i.e. within the scope of calculating 25km*25km, the average value of each 1km*1km.
In one embodiment, the precipitation data of area to be tested first resolution is resampled to second resolution, is
By calculating within the scope of second resolution pixel, the average value of all first resolution pixels calculates 25km* come what is realized
Within the scope of 25km, the average value of each 1km*1km.
Referring to Fig. 3, in a specific embodiment, NO emissions reduction precipitation data detection method in space of the present invention includes such as
Lower step:
Step S301: obtaining the surface temperature and night surface temperature on daytime of sample areas, and it is poor to calculate surface temperature round the clock.
Step S302: the digital elevation model of sample areas and the vegetation index of sample areas are obtained.
Step S303: by the first resolution of the sample areas daytime surface temperature, night surface temperature, round the clock
Table temperature difference, digital elevation model and vegetation index carry out resampling.
Step S304: according to sample areas daytime surface temperature, night surface temperature, round the clock surface temperature it is poor, number
Elevation model and vegetation index establish original sample collection S.
Step S305: k training sample set is extracted in original sample collection S by Bootstrap method.
Step S306: learning k training set, generates k decision-tree model with this.In Decision Tree Construction
In, 4 input variables are shared, n variable is randomly selected from 4 variables, each internal node is become using this n feature
Optimal divisional mode divides in amount, and n value is constant constant in the forming process of Random Forest model.
Step S307: the result of k decision tree is combined, and through repetition training, forms optimal stochastic forest algorithm mould
Type.
Step S308: the surface temperature and night surface temperature on daytime of area to be tested is obtained, area to be tested is calculated
Surface temperature is poor round the clock.
Step S209: the digital elevation model of area to be tested and the vegetation index of area to be tested are obtained.
Step S210: by the first resolution of the area to be tested daytime surface temperature, night surface temperature, round the clock
Surface temperature is poor, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtains area to be tested first
The precipitation data of resolution ratio.
Step S211: the precipitation data of area to be tested first resolution is resampled to second resolution.
Step S212: the area to be tested second after calculating area to be tested satellite remote sensing precipitation data and resampling is differentiated
Difference between the precipitation data of rate obtains the first residual error.
Step S213: by the first residual error spatial interpolation to first resolution, the second residual error of first resolution is obtained.
Step S214: the precipitation data of area to be tested first resolution is added with the second residual error, obtains area to be detected
The space NO emissions reduction precipitation data in domain.
NO emissions reduction precipitation data detection method in space of the present invention, utilizes the sample area for having satellite remote sensing precipitation data
Domain daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index and sample area
The remote sensing precipitation data in domain establishes optimal random forests algorithm model, using the model, calculates the high score of area to be tested
The precipitation data of resolution, and resampling is carried out to the precipitation data, residual error corrections are carried out with satellite remote sensing precipitation data, obtain height
The precipitation data of the space NO emissions reduction of precision.
Referring to Fig. 4, in one embodiment, space NO emissions reduction precipitation data detection device 40 of the present invention includes:
First data acquisition module 41, for obtaining the surface temperature and night surface temperature on daytime of sample areas, and root
The surface temperature round the clock for obtaining sample areas according to the surface temperature on daytime and night surface temperature is poor, and obtains sample areas
Digital elevation model and sample areas vegetation index；
First resampling module 42, for by the sample areas of first resolution daytime surface temperature, night earth's surface temperature
Degree, surface temperature is poor round the clock, digital elevation model and vegetation index resampling are satellite remote sensing precipitation with the sample areas
The identical second resolution of data；
Random forest training module 43, for according to sample areas second resolution daytime surface temperature, night earth's surface
Temperature, round the clock surface temperature be poor, digital elevation model and vegetation index and sample areas satellite remote sensing precipitation number
According to foundation and training optimal stochastic forest algorithm model；
Second data acquisition module 44, for obtaining the surface temperature and night surface temperature on daytime of area to be tested, and
According to the area to be tested daytime surface temperature and night surface temperature obtain area to be tested surface temperature round the clock it is poor,
And obtain the digital elevation model of area to be tested and the vegetation index of area to be tested；
First precipitation data obtain module 45, for by the area to be tested surface temperature on daytime of the first resolution,
Night surface temperature, round the clock surface temperature be poor, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtains
Take the precipitation data of area to be tested first resolution；
Residual error corrections module 46 carries out residual error corrections for the precipitation data to the first resolution, obtains to be detected
The space NO emissions reduction precipitation data in region.
In one embodiment, residual error corrections module 46 includes:
Second resampling unit 461, for the precipitation data of area to be tested first resolution to be resampled to second point
Resolution；
First residual error acquiring unit 462, for calculate after area to be tested satellite remote sensing precipitation data and resampling to
Difference between the precipitation data of detection zone second resolution obtains the first residual error；
Second residual error acquiring unit 463, for obtaining first point for the first residual error spatial interpolation to first resolution
Second residual error of resolution；
NO emissions reduction precipitation data acquiring unit 464, for by the precipitation data of area to be tested first resolution and second
Residual error is added, and obtains the space NO emissions reduction precipitation data of area to be tested.
In one embodiment, the first resampling module 42 includes first resolution computing unit 421, for calculating second
Within the scope of resolution ratio pixel, the area to be tested surface temperatures on daytime of all first resolution pixels, night surface temperature, round the clock
Surface temperature is poor, digital elevation model and vegetation index average value.
In one embodiment, the second resampling unit 461 includes second resolution computing unit 4611, for calculating the
Within the scope of two resolution ratio pixels, the average value of the first residual error of all first resolution pixels.
The present invention also provides a kind of computer-readable mediums, are stored thereon with computer program, which is located
Reason device realizes the precipitation data evaluation method based on random forests algorithm in above-mentioned any one embodiment when executing.
Referring to Fig. 5, in one embodiment, electronic equipment 50 of the invention includes memory 51 and processor 52, with
And the computer program that is stored in the memory 51 and can be executed by the processor 52, the processor 52 execute the meter
When calculation machine program, realize such as the precipitation data evaluation method based on random forests algorithm in above-mentioned any one embodiment.
In the present embodiment, controller 52 can be one or more application specific integrated circuit (ASIC), digital signal
Processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components.Storage medium 51 can be used it is one or more its
In include program code storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) on implement
Computer program product form.Computer-readable storage media includes permanent and non-permanent, removable and non-removable
Dynamic media can be accomplished by any method or technique information storage.Information can be computer readable instructions, data structure,
The module of program or other data.The example of the storage medium of computer includes but is not limited to: phase change memory (PRAM), it is static with
Machine access memory (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), only
It reads memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory techniques, read-only
Compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic magnetic
Disk storage or other magnetic storage devices or any other non-transmission medium, can be used for storage can be accessed by a computing device letter
Breath.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.
Claims (10)
1. a kind of space NO emissions reduction precipitation data detection method, which comprises the steps of:
The surface temperature and night surface temperature on daytime of sample areas is obtained, and according to the surface temperature on daytime and night earth's surface
The surface temperature round the clock that temperature obtains sample areas is poor；
Obtain the digital elevation model of sample areas and the vegetation index of sample areas；
By the sample areas of first resolution daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation
Model and vegetation index resampling are second resolution identical with the satellite remote sensing precipitation data of the sample areas, wherein
Second resolution is less than first resolution；
According to sample areas second resolution daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation
The satellite remote sensing precipitation data of model and vegetation index and the sample areas is established and trains optimal stochastic forest algorithm
Model, wherein the sample areas daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model
Input sample with vegetation index as the trained optimal stochastic forest algorithm model, the satellite remote sensing drop of the sample areas
Water number is according to the output sample as the trained optimal stochastic forest algorithm model；
The surface temperature and night surface temperature on daytime of area to be tested is obtained, and according to the earth's surface on daytime of the area to be tested
The surface temperature round the clock that temperature and night surface temperature obtain area to be tested is poor；
Obtain the digital elevation model of area to be tested and the vegetation index of area to be tested；
By the area to be tested surface temperature on daytime of the first resolution, night surface temperature, surface temperature is poor, digital round the clock
Elevation model and vegetation index input optimal stochastic forest algorithm model, obtain the precipitation number of area to be tested first resolution
According to；
Residual error corrections are carried out to the precipitation data of the first resolution, obtain the space NO emissions reduction precipitation number of area to be tested
According to.
2. NO emissions reduction precipitation data detection method in space according to claim 1, which is characterized in that differentiated to described first
The precipitation data of rate carries out residual error corrections, obtains the space NO emissions reduction precipitation data of area to be tested, comprising:
The precipitation data of area to be tested first resolution is resampled to second resolution；
The precipitation data of area to be tested second resolution after calculating area to be tested satellite remote sensing precipitation data and resampling
Between difference, obtain the first residual error；
By the first residual error spatial interpolation to first resolution, the second residual error of first resolution is obtained；
The precipitation data of area to be tested first resolution is added with the second residual error, obtains the space NO emissions reduction of area to be tested
Precipitation data.
3. NO emissions reduction precipitation data detection method in space according to claim 1, it is characterised in that:
The vegetation index of the sample areas and the area to be tested is greater than zero.
4. NO emissions reduction precipitation data detection method in space according to claim 1, it is characterised in that:
The first resolution is 1km*1km, and the second resolution is 25km*25km.
5. NO emissions reduction precipitation data detection method in space according to claim 1, which is characterized in that by first resolution
Sample areas daytime surface temperature, night surface temperature, surface temperature is poor round the clock, digital elevation model and vegetation index are adopted again
Sample is second resolution identical with the satellite remote sensing precipitation data of the sample areas, comprising:
It calculates within the scope of second resolution pixel, the average value of all first resolution pixels.
6. a kind of space NO emissions reduction precipitation data detection device characterized by comprising
First data acquisition module, for obtaining the surface temperature and night surface temperature on daytime of sample areas, and according to described
Daytime surface temperature and night surface temperature obtain sample areas surface temperature round the clock it is poor, and obtain sample areas number
The vegetation index of elevation model and sample areas；
First resampling module, for by the sample areas of first resolution daytime surface temperature, night surface temperature, round the clock
Surface temperature is poor, digital elevation model and vegetation index resampling are identical as the satellite remote sensing precipitation data of the sample areas
Second resolution；
Random forest training module, for according to sample areas second resolution daytime surface temperature, night surface temperature, daytime
Night surface temperature is poor, digital elevation model and vegetation index and sample areas satellite remote sensing precipitation data, establishes simultaneously
Training optimal stochastic forest algorithm model, wherein the sample areas daytime surface temperature, night surface temperature, round the clock
The input sample of table temperature difference, digital elevation model and vegetation index as the trained optimal stochastic forest algorithm model, institute
State output sample of the satellite remote sensing precipitation data of sample areas as the trained optimal stochastic forest algorithm model；
Second data acquisition module, for obtaining the surface temperature and night surface temperature on daytime of area to be tested, and according to institute
State area to be tested daytime surface temperature and night surface temperature obtain area to be tested surface temperature round the clock it is poor, and obtain
Take the digital elevation model of area to be tested and the vegetation index of area to be tested；
First precipitation data obtains module, for by the area to be tested surface temperature on daytime of the first resolution, night
Table temperature, round the clock surface temperature be poor, digital elevation model and vegetation index input optimal stochastic forest algorithm model, obtains to be checked
Survey the precipitation data of region first resolution；
Residual error corrections module carries out residual error corrections for the precipitation data to the first resolution, obtains area to be tested
Space NO emissions reduction precipitation data.
7. NO emissions reduction precipitation data detection device in space according to claim 6, which is characterized in that the residual error corrections mould
Block, comprising:
Second resampling unit, for the precipitation data of area to be tested first resolution to be resampled to second resolution；
First residual error acquiring unit, for calculating area to be tested satellite remote sensing precipitation data and the area to be tested after resampling
Difference between the precipitation data of second resolution obtains the first residual error；
Second residual error acquiring unit, for the first residual error spatial interpolation to first resolution, to be obtained first resolution
Second residual error；
NO emissions reduction precipitation data acquiring unit, for by the precipitation data of area to be tested first resolution and the second residual error phase
Add, obtains the space NO emissions reduction precipitation data of area to be tested.
8. NO emissions reduction precipitation data detection device in space according to claim 6, it is characterised in that:
The first resampling module includes resolution ratio computing unit, for calculating within the scope of second resolution pixel, Suo You
The average value of one resolution ratio pixel.
9. a kind of computer-readable medium, is stored thereon with computer program, it is characterised in that:
Realize that claim 1 to 5 any one space NO emissions reduction precipitation data such as is examined when the computer program is executed by processor
Survey method.
10. a kind of electronic equipment, including memory, processor and it is stored in the memory and can be executed by the processor
Computer program, it is characterised in that:
When the processor executes the computer program, any one space NO emissions reduction as described in claim 1 to 5 is realized
Precipitation data detection method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811159034.XA CN109472393B (en) | 2018-09-30 | 2018-09-30 | Spatial downscaling precipitation data detection method and device and electronic equipment |
| PCT/CN2019/106848 WO2020063458A1 (en) | 2018-09-30 | 2019-09-20 | Method and apparatus for detecting spatial downscaled precipitation data, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811159034.XA CN109472393B (en) | 2018-09-30 | 2018-09-30 | Spatial downscaling precipitation data detection method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109472393A true CN109472393A (en) | 2019-03-15 |
| CN109472393B CN109472393B (en) | 2021-01-15 |
Family
ID=65663493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811159034.XA Active CN109472393B (en) | 2018-09-30 | 2018-09-30 | Spatial downscaling precipitation data detection method and device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109472393B (en) |
| WO (1) | WO2020063458A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110738252A (en) * | 2019-10-14 | 2020-01-31 | 广州地理研究所 | Space autocorrelation machine learning satellite precipitation data downscaling method and system |
| CN110866364A (en) * | 2019-11-20 | 2020-03-06 | 中国科学院遥感与数字地球研究所 | Ground surface temperature downscaling method based on machine learning |
| WO2020063458A1 (en) * | 2018-09-30 | 2020-04-02 | 广州地理研究所 | Method and apparatus for detecting spatial downscaled precipitation data, and electronic device |
| CN111177652A (en) * | 2019-11-27 | 2020-05-19 | 中国科学院遥感与数字地球研究所 | Spatial downscaling method and system for remote sensing precipitation data |
| CN111401644A (en) * | 2020-03-19 | 2020-07-10 | 南京国准数据有限责任公司 | Rainfall downscaling space prediction method based on neural network |
| CN112699959A (en) * | 2021-01-11 | 2021-04-23 | 中国科学院地理科学与资源研究所 | Multi-source multi-scale precipitation data fusion method and device based on energy functional model |
| CN113237554A (en) * | 2021-05-07 | 2021-08-10 | 国家卫星气象中心(国家空间天气监测预警中心) | Method and device for generating surface temperature image under cloud and terminal equipment |
| CN114354655A (en) * | 2022-01-18 | 2022-04-15 | 国家卫星气象中心(国家空间天气监测预警中心) | Precipitation knowledge base construction method suitable for microwave detector |
| CN117148350A (en) * | 2023-10-27 | 2023-12-01 | 航天宏图信息技术股份有限公司 | SAR image-based earth surface temperature space downscaling method, device and equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221464B (en) * | 2021-05-21 | 2023-04-07 | 广东省科学院广州地理研究所 | Ground station and remote sensing observation rainfall data fusion method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015148887A1 (en) * | 2014-03-28 | 2015-10-01 | Northeastern University | System for multivariate climate change forecasting with uncertainty quantification |
| CN106021872A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Dynamic filtering modeling downscaling method of environment variable on the basis of low-resolution satellite remote sensing data |
| CN106019408A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Multi-source-remote-sensing-data-based high-resolution-ratio satellite remote-sensing estimation method |
| CN106021868A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Multi-rule algorithm-based remote sensing data downscaling method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8594375B1 (en) * | 2010-05-20 | 2013-11-26 | Digitalglobe, Inc. | Advanced cloud cover assessment |
| CN104318270A (en) * | 2014-11-21 | 2015-01-28 | 东北林业大学 | Land cover classification method based on MODIS time series data |
| CN107748736B (en) * | 2017-10-13 | 2021-11-26 | 河海大学 | Multi-factor remote sensing earth surface temperature space downscaling method based on random forest |
| CN109472393B (en) * | 2018-09-30 | 2021-01-15 | 广州地理研究所 | Spatial downscaling precipitation data detection method and device and electronic equipment |
-
2018
- 2018-09-30 CN CN201811159034.XA patent/CN109472393B/en active Active
-
2019
- 2019-09-20 WO PCT/CN2019/106848 patent/WO2020063458A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015148887A1 (en) * | 2014-03-28 | 2015-10-01 | Northeastern University | System for multivariate climate change forecasting with uncertainty quantification |
| CN106021872A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Dynamic filtering modeling downscaling method of environment variable on the basis of low-resolution satellite remote sensing data |
| CN106019408A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Multi-source-remote-sensing-data-based high-resolution-ratio satellite remote-sensing estimation method |
| CN106021868A (en) * | 2016-05-10 | 2016-10-12 | 浙江大学 | Multi-rule algorithm-based remote sensing data downscaling method |
Non-Patent Citations (1)
| Title |
|---|
| 郭佳: "基于随机森林的遥感干旱监测模型及其应用研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020063458A1 (en) * | 2018-09-30 | 2020-04-02 | 广州地理研究所 | Method and apparatus for detecting spatial downscaled precipitation data, and electronic device |
| WO2021073210A1 (en) * | 2019-10-14 | 2021-04-22 | 广东省科学院广州地理研究所 | Spatial autocorrelated machine learning satellite precipitation data downscaling method and system |
| CN110738252A (en) * | 2019-10-14 | 2020-01-31 | 广州地理研究所 | Space autocorrelation machine learning satellite precipitation data downscaling method and system |
| US11333796B2 (en) | 2019-10-14 | 2022-05-17 | Guangzhou Institute of geography, Guangdong Academy of Sciences | Spatial autocorrelation machine learning-based downscaling method and system of satellite precipitation data |
| CN110866364A (en) * | 2019-11-20 | 2020-03-06 | 中国科学院遥感与数字地球研究所 | Ground surface temperature downscaling method based on machine learning |
| CN111177652B (en) * | 2019-11-27 | 2021-10-01 | 中国科学院遥感与数字地球研究所 | Spatial downscaling method and system for remote sensing precipitation data |
| CN111177652A (en) * | 2019-11-27 | 2020-05-19 | 中国科学院遥感与数字地球研究所 | Spatial downscaling method and system for remote sensing precipitation data |
| CN111401644A (en) * | 2020-03-19 | 2020-07-10 | 南京国准数据有限责任公司 | Rainfall downscaling space prediction method based on neural network |
| CN112699959A (en) * | 2021-01-11 | 2021-04-23 | 中国科学院地理科学与资源研究所 | Multi-source multi-scale precipitation data fusion method and device based on energy functional model |
| CN113237554B (en) * | 2021-05-07 | 2022-04-26 | 国家卫星气象中心(国家空间天气监测预警中心) | Method and device for generating surface temperature image under cloud and terminal equipment |
| CN113237554A (en) * | 2021-05-07 | 2021-08-10 | 国家卫星气象中心(国家空间天气监测预警中心) | Method and device for generating surface temperature image under cloud and terminal equipment |
| CN114354655A (en) * | 2022-01-18 | 2022-04-15 | 国家卫星气象中心(国家空间天气监测预警中心) | Precipitation knowledge base construction method suitable for microwave detector |
| CN117148350A (en) * | 2023-10-27 | 2023-12-01 | 航天宏图信息技术股份有限公司 | SAR image-based earth surface temperature space downscaling method, device and equipment |
| CN117148350B (en) * | 2023-10-27 | 2024-01-30 | 航天宏图信息技术股份有限公司 | SAR image-based earth surface temperature space downscaling method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109472393B (en) | 2021-01-15 |
| WO2020063458A1 (en) | 2020-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472393A (en) | Space NO emissions reduction precipitation data detection method, device and electronic equipment | |
| CN111623722B (en) | Multi-sensor-based slope deformation three-dimensional monitoring system and method | |
| Zhang et al. | Uncertainty in geographical information | |
| CN109522788A (en) | City scope extracting method, device and electronic equipment based on random forest sorting algorithm | |
| Silvan-Cardenas et al. | Assessing fine-spatial-resolution remote sensing for small-area population estimation | |
| CN109447325A (en) | Precipitation data detection method, device and electronic equipment based on random forests algorithm | |
| CN111191673B (en) | Ground surface temperature downscaling method and system | |
| Choi et al. | Three-dimensional LiDAR data classifying to extract road point in urban area | |
| Humme et al. | Revealing Celtic fields from lidar data using kriging based filtering | |
| CN115100819B (en) | Landslide hazard early warning method and device based on big data analysis and electronic equipment | |
| CN109242786B (en) | Automatic morphological filtering method suitable for urban area | |
| CN117272191B (en) | Urban underground space intelligent mapping method and system | |
| CN112241844B (en) | Method and device for determining and updating environmental risk source background list of drinking water source area | |
| CN106228602A (en) | Determination method, device and the mobile unit of three-dimensional vehicle alternative area | |
| CN108398683B (en) | Long time sequence automatic interference measurement system and method | |
| CN114882191B (en) | Digital elevation model generation method, electronic equipment and computer readable storage device | |
| CN111080536A (en) | Self-adaptive filtering method for airborne laser radar point cloud | |
| CN115166874A (en) | Meteorological drought index SPI construction method based on machine learning | |
| Carlisle | Digital elevation model quality and uncertainty in DEM-based spatial modelling | |
| JP2023152480A (en) | Map data generating method, map data generating apparatus, and map data generating program | |
| CN114494625A (en) | High-precision topographic map manufacturing method and device and computer equipment | |
| CN115271332A (en) | Drought monitoring method | |
| Gong et al. | Error detection through consistency checking | |
| Alimohammadi et al. | A new approach for modeling uncertainty in remote sensing change detection process | |
| CN114742812B (en) | Low-altitude constellation-based multi-source remote sensing geophysical prospecting data integrated detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 510075 one of the compound No. 100, Xianlie Middle Road, Yuexiu District, Guangzhou City, Guangdong Province Patentee after: Guangzhou Institute of geography, Guangdong Academy of Sciences Address before: 510075 one of the compound No. 100, Xianlie Middle Road, Yuexiu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU INSTITUTE OF GEOGRAPHY |
|
| CP01 | Change in the name or title of a patent holder |