CN115659796A - Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium - Google Patents
Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium Download PDFInfo
- Publication number
- CN115659796A CN115659796A CN202211294315.2A CN202211294315A CN115659796A CN 115659796 A CN115659796 A CN 115659796A CN 202211294315 A CN202211294315 A CN 202211294315A CN 115659796 A CN115659796 A CN 115659796A
- Authority
- CN
- China
- Prior art keywords
- temperature
- atmospheric
- determining
- predicted
- earth surface
- 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
Images
Abstract
The invention provides a method, a device, equipment and a readable storage medium for predicting a geothermal high-temperature abnormal area, wherein the method comprises the following steps: obtaining atmospheric parameters and normalization indexes corresponding to an area to be predicted, and obtaining earth surface temperature according to inversion of the atmospheric parameters; constructing a ground surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm, and determining a corrected ground surface temperature corresponding to the ground surface temperature simulation model; and determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature. The invention solves the technical problem that the prediction of the existing geothermal high-temperature anomaly is not accurate.
Description
Technical Field
The invention relates to the technical field of prediction, in particular to a method, a device and equipment for predicting a geothermal high-temperature abnormal area and a readable storage medium.
Background
The terrestrial heat high temperature anomaly is one of common geological disasters in plateau mountain areas, and can seriously affect the construction and maintenance of heavy infrastructure such as roads, railways and the like in plateau areas. By utilizing thermal infrared remote sensing data and an inversion technology, the method can monitor and predict the terrestrial heat high-temperature abnormity in the plateau mountain areas with large spatial range and long time sequence, and has the advantages of clear result, flexible method, cost saving and the like.
However, the altitude gradient, climate and hydrological conditions of the mountain land surface are changed violently, the complex terrain causes uneven distribution of solar radiation received by the ground, and the land and water thermal properties of the mountain valley region are different, so that a severe terrain effect and valley effect are generated, and the extraction precision and application effect of the ground surface temperature obtained based on thermal infrared remote sensing data inversion in the prediction work of the geothermal abnormal region are greatly reduced. Meanwhile, the influence and contribution of other terrestrial heat abnormal induction factors on the terrestrial heat high-temperature phenomenon can be ignored only by utilizing thermal infrared remote sensing, and the comprehensiveness and complexity of the occurrence of terrestrial heat high-temperature abnormality cannot be effectively reflected.
Disclosure of Invention
The invention provides a prediction method, a prediction device and a readable storage medium for a geothermal high-temperature abnormal area, which are used for solving the technical problem that the existing geothermal high-temperature abnormal prediction is inaccurate.
The invention provides a geothermal high-temperature abnormal area prediction method, which comprises the following steps:
obtaining an atmospheric parameter and a normalization index corresponding to an area to be predicted, and obtaining earth surface temperature according to inversion of the atmospheric parameter;
constructing a ground surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm, and determining a corrected ground surface temperature corresponding to the ground surface temperature simulation model;
and determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature.
According to the method for predicting the geothermal high-temperature abnormal area, provided by the invention, the atmospheric parameters comprise the surface emissivity, the atmospheric permeability and the atmospheric average temperature; the step of obtaining the atmospheric parameters corresponding to the area to be predicted comprises the following steps:
acquiring a mixed pixel vegetation ratio, a vegetation temperature ratio, a bare soil temperature ratio, an emissivity variable quantity, a preset emissivity, an atmospheric mode, an atmospheric water vapor content and a near-surface air temperature corresponding to an area to be predicted;
determining the surface emissivity according to the mixed pixel vegetation proportion, the vegetation temperature ratio, the bare soil temperature ratio, the emissivity change and the preset emissivity;
determining the atmospheric transmittance according to the atmospheric mode and the atmospheric water vapor content;
and determining the average atmospheric temperature according to the atmospheric mode and the near-surface air temperature.
According to the method for predicting the geothermal high-temperature abnormal area, the step of obtaining the earth surface temperature according to the atmospheric parameter inversion comprises the following steps:
determining an intermediate variable according to the atmospheric permeability and the surface emissivity;
and inverting to obtain the earth surface temperature according to the intermediate variable, the atmospheric average temperature, the preset brightness temperature and the preset regression coefficient.
According to the method for predicting the high-temperature abnormal geothermal region, the step of constructing a surface temperature simulation model according to the region to be predicted, the atmospheric parameter, the normalization index and a random forest algorithm comprises the following steps:
acquiring a standard vector, a solar zenith angle, solar direct radiation, sky scattered radiation, ambient reflected radiation and an elevation corresponding to the area to be predicted;
determining the gradient and the slope direction of the area to be predicted according to the standard vector;
determining corrected surface emissivity according to the gradient, a preset empirical coefficient, the solar zenith angle and the surface emissivity;
determining an accumulated solar radiation from the solar direct radiation, the sky scattered radiation and the ambient reflected radiation;
and constructing a surface temperature simulation model according to the elevation, the gradient, the slope direction, the corrected surface emissivity, the accumulated solar radiation, the normalized index and a random forest algorithm.
According to the method for predicting the high-temperature abnormal area of the geothermal heat, the step of determining the high-temperature abnormal prediction result of the area to be predicted according to the high-temperature abnormal induction factor including the corrected earth surface temperature comprises the following steps:
determining a certainty coefficient and a relative contribution value of each high-temperature abnormality induction factor according to the conditional probability, the prior probability, the segmentation contribution value and the segmentation level corresponding to each high-temperature abnormality induction factor;
and determining a high-temperature abnormal prediction result of the area to be predicted according to the certainty coefficient and the relative contribution value.
According to the method for predicting the geothermal high-temperature abnormal area, provided by the invention, the normalization index comprises a normalization water body index, a normalization vegetation index and a normalization snow index, and the step of acquiring the normalization index corresponding to the area to be predicted comprises the following steps:
obtaining green light wave band earth surface reflectivity, red light wave band earth surface reflectivity, near infrared wave band earth surface reflectivity and short wave infrared wave band earth surface reflectivity corresponding to an area to be predicted;
determining the normalized water body index according to the green light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
determining the normalized vegetation index according to the red light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
and determining the normalized snow index according to the green light wave band earth surface reflectivity and the short wave infrared wave band earth surface reflectivity.
The present invention also provides a geothermal high-temperature abnormal region prediction device, including:
the earth surface temperature inversion module is used for acquiring the atmospheric parameters and the normalization indexes corresponding to the area to be predicted and inverting to obtain the earth surface temperature according to the atmospheric parameters;
the earth surface temperature correction module is used for constructing an earth surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm and determining corrected earth surface temperature corresponding to the earth surface temperature simulation model;
and the high-temperature abnormity prediction module is used for determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the geothermal high-temperature abnormal region prediction method is realized according to any one of the above methods.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a geothermal high-temperature abnormal region prediction method as described in any one of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the method for predicting a geothermal high-temperature abnormal region as described in any one of the above.
According to the method, the device, the equipment and the readable storage medium for predicting the geothermal high-temperature abnormal area, the atmospheric parameters and the normalization index corresponding to the area to be predicted are obtained, the inversion is carried out according to the atmospheric parameters corresponding to the area to be predicted to obtain the surface temperature, then the surface temperature simulation model is built according to the area to be predicted, the atmospheric parameters, the normalization index and the random forest algorithm, the corrected surface temperature corresponding to the surface temperature simulation model is determined, finally the high-temperature abnormal prediction result of the area to be predicted is determined according to the high-temperature abnormal induction factor containing the corrected surface temperature, and the technical problem that the existing geothermal high-temperature abnormal prediction is inaccurate is solved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for predicting a geothermal high-temperature abnormal region according to the present invention;
FIG. 2 is a second flowchart of the method for predicting geothermal high temperature abnormal area according to the present invention;
FIG. 3 is a schematic structural diagram of a geothermal high-temperature abnormal region prediction device provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
The method for predicting the geothermal high-temperature abnormal region according to the present invention will be described with reference to fig. 1 to 2.
Referring to fig. 1, the present invention provides a method for predicting a geothermal high-temperature abnormal area, including:
specifically, firstly, acquiring an atmospheric parameter and a normalization index corresponding to an area to be predicted, wherein the atmospheric parameter comprises a surface emissivity epsilon, an atmospheric transmittance tau and an atmospheric average temperature T a The normalized index includes a normalized water body indexNDWI, NDVI and NDSI, wherein the surface emissivity is calculated by formula I, wherein P is the surface emissivity V Is the proportion of vegetation in the mixed pixel, R V Is the temperature ratio of vegetation, R S Is the temperature ratio of bare soil, d ε Is the emissivity change, epsilon, caused by the thermal radiation interaction of vegetation and bare earth V Is the emissivity of the vegetation, epsilon S Is the emissivity of bare earth, epsilon V ＝0.98672，ε S =0.96767; the relationship between the atmospheric transmission rate and the atmospheric mode and the atmospheric water vapor content is shown in table 1; average atmospheric temperature, atmospheric mode and near-surface air temperature T 0 The relationship between them is shown in table 2.
ε＝P V R V ε V +(1-P V )R S ε S +d ε Formula one
C = τ epsilon formula five
D = (1-tau) [1+ (1-epsilon) tau ] formula six
TABLE 1
| Atmospheric mode | Equation of relation |
| Tropical band | Ta＝17.9769+0.9172T 0 |
| Summer in mid latitude | Ta＝16.0110+0.9262T 0 |
| Middle latitude winter | Ta＝19.2704+0.9112T 0 |
TABLE 2
And respectively calculating a normalized water body index NDWI, a normalized vegetation index NDVI and a normalized snow cover index NDSI through a formula II, a formula III and a formula IV, wherein Green, red, NIR and SWIR respectively represent the earth surface reflectivity of a Green light wave band, the earth surface reflectivity of a Red light wave band, the earth surface reflectivity of a near infrared wave band and the earth surface reflectivity of a short wave infrared wave band.
Then, intermediate variables C and D are calculated according to a formula five and a formula six, wherein tau is the atmospheric transmittance, epsilon is the surface emissivity, and the surface temperature T is obtained by inversion according to the atmospheric parameters and the formula seven, wherein T a Is the average temperature of the atmosphere, T b For luminance temperature, a and b are regression coefficients, a = -62.7182, b = -0.4339.
200, constructing a ground surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm, and determining a corrected ground surface temperature corresponding to the ground surface temperature simulation model;
specifically, the process of constructing the surface temperature simulation model is as follows: first, the slope is calculatedAnd calculating the slope S and the slope A according to a formula eight and a formula nine respectively by using the surface temperature influence factors such as the degree S, the slope A and the like, wherein (n) x ,n y ,n z ) And the standard vector of each grid unit corresponding to the area to be predicted.
Then, according to a formula, performing terrain correction on the earth surface albedo subjected to radiometric calibration, atmospheric correction and broadband conversion to obtain the corrected earth surface emissivity, wherein alpha is i To correct surface emissivity, Z s The solar zenith angle, c is an empirical coefficient, and theta is a slope incident angle.
Secondly, direct solar radiation I corresponding to the area to be predicted b Sky scattered radiation I d And ambient reflected radiation I r Adding to obtain cumulative solar radiation, and calculating according to formula eleven and formula twelve to obtain solar direct radiation, wherein E 0 Is the solar constant (1367W/m 2), d r Is the correction coefficient of the distance between the day and the ground, DOY is the accumulated day of the year, tau b For direct atmospheric transmittance, θ is the actual solar incident angle. Calculating according to a formula thirteen, a formula fourteen and a formula fifteen to obtain sky scattered radiation, wherein I d,flat For sky scattered radiation in flat terrain, τ d For scattered radiation transmittance, SVF is sky visibility factor, h i The method is to divide a hemispherical space into n equal parts and calculate the maximum height angle found by the height angle formed by any slope element and a starting point slope element in the horizontal plane projection direction along light rays in each equal part. Calculating according to formula sixteenth and formula seventeen to obtain the ambient reflection radiation, wherein C t Parameters related to the terrain structure are represented, the parameters comprise anisotropic characteristics and geometric effects between the slope elements and surrounding visible slope elements, S is the slope, and rho is the average value of the albedo of surrounding adjacent pixel elements.
I b ＝E 0 ×d r ×τ b Xcos theta equation eleven
I d ＝I d,flat X SVF equation thirteen
I d,flat ＝E 0 ×d r ×τ d ×cosZ s Fourteen formula
I r ＝ρ×C t ×(I b +I d ) Seventeen formula
T RF = f (ELV, S, A, I, NDWI, NDVI, NDSI, α') equation eighteen
T C = f (I, NDWI, NDVI, NDSI, α') nineteen formulas
And finally, constructing a surface temperature simulation model by using a random forest algorithm, wherein T is shown as a formula eighteen RF For the simulated ground surface temperature value, f is a nonlinear function model constructed by a random forest algorithm, I is accumulated solar radiation, ELV is elevation, alpha' is ground surface albedo, NDWI is normalized water body index, NDVI is normalized vegetation index, and NDSI is normalized snow cover index; further, a terrain temperature simulation model constructed by using a random forest algorithm is utilized to remove terrain factors causing terrain effects of the terrain temperature, and a terrain corrected terrain surface temperature value can be obtained, wherein T is shown in the formula nineteen C To schoolA positive surface temperature value.
And 300, determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature.
Specifically, the method for acquiring the geothermal high-temperature abnormality inducing factor comprises the following steps: (1) selecting hot spring point data as a model training point; (2) The corrected surface temperature, fracture density, distance to the water system, and geomagnetic anomaly are selected as geothermal high-temperature anomaly inducing factor indexes (3), and the corrected surface temperature, fracture density, and geomagnetic anomaly are classified into a plurality of grades by using a natural breakpoint method. Then, the method for constructing the prediction model of the geothermal high-temperature abnormal region comprises the following steps: calculating the deterministic coefficient value for each of the evoked factors according to the equation twenty, where K CF Is a deterministic coefficient; p is a The conditional probability of the existence of geothermal anomalies in the hierarchical layer of the influence factor, here the ratio of the number of hot spring points in the hierarchy to the number of grids in the hierarchy; p s The prior probability of occurrence of geotherm anomaly is the ratio of the number of units with hot spring points in the prediction area to the total number of evaluation units in the prediction area.
Calculating each factor weight omega according to a formula twenty-one, wherein omega is a relative contribution value of a certain induction factor, Z i The deterministic coefficient segment contribution value representing a factor, i being the segment level of the deterministic coefficient. Determining coefficient K CF Multiplying the factor weight omega to obtain the predicted value of the geothermal abnormality of each factor, classifying the predicted value of each factor by using a natural breakpoint method into 4 grades, and sequentially dividing the predicted values into the following steps from high to low: and finally obtaining the prediction result of the geothermal high-temperature abnormal area.
According to the method, the atmospheric parameters and the normalization index corresponding to the area to be predicted are obtained, the earth surface temperature is obtained through inversion according to the atmospheric parameters corresponding to the area to be predicted, then the earth surface temperature simulation model is built according to the area to be predicted, the atmospheric parameters, the normalization index and the random forest algorithm, the corrected earth surface temperature corresponding to the earth surface temperature simulation model is determined, finally the high-temperature anomaly prediction result of the area to be predicted is determined according to the high-temperature anomaly induction factor containing the corrected earth surface temperature, and the technical problem that the existing geothermal high-temperature anomaly prediction is inaccurate is solved.
In an embodiment, the method for predicting a geothermal high-temperature abnormal region provided in the embodiment of the present application may further include:
step 110, acquiring a mixed pixel vegetation ratio, a vegetation temperature ratio, a bare soil temperature ratio, an emissivity variation, a preset emissivity, an atmospheric mode, an atmospheric water vapor content and a near-surface air temperature corresponding to an area to be predicted;
step 120, determining the surface emissivity according to the mixed pixel vegetation proportion, the vegetation temperature ratio, the bare soil temperature ratio, the emissivity change and the preset emissivity;
step 130, determining the atmospheric transmittance according to the atmospheric mode and the atmospheric water vapor content;
and 140, determining the average atmospheric temperature according to the atmospheric mode and the near-surface air temperature.
Specifically, obtaining atmospheric parameters corresponding to an area to be predicted, wherein the atmospheric parameters comprise surface emissivity epsilon, atmospheric permeability tau and atmospheric average temperature T a Calculating the surface emissivity epsilon through a formula I, wherein P is V Is the proportion of vegetation in the mixed pixel (i.e. the vegetation proportion of the mixed pixel in this embodiment), R V Is the temperature ratio of vegetation (i.e., vegetation temperature ratio in this example), R S Is the bare soil temperature ratio (i.e., bare soil temperature ratio in the present example), d ε Is the emissivity change (i.e., the emissivity change in this embodiment) caused by the thermal radiation interaction of vegetation and bare earth, ε V And epsilon S Emissivity of vegetation and emergence of bare soil, respectivelyRefractive index (i.e., predetermined emissivity in this embodiment), ε V ＝0.98672，ε S =0.96767; determining the atmospheric transmittance in atmospheric parameters according to the atmospheric modes and the atmospheric water vapor content in the table 1; the atmospheric average temperature in the atmospheric parameter is determined from the atmospheric mode and the near-surface air temperature in table 2.
The atmospheric parameters are obtained by obtaining various data corresponding to the area to be predicted.
In an embodiment, the method for predicting a geothermal high-temperature abnormal region provided in the embodiment of the present application may further include:
step 191, determining an intermediate variable according to the atmospheric permeability and the surface emissivity;
and step 192, performing inversion to obtain the earth surface temperature according to the intermediate variable, the atmospheric average temperature, the preset brightness temperature and the preset regression coefficient.
Specifically, determining intermediate variables C and D according to the fifth formula and the sixth formula, wherein tau is the atmospheric transmittance, epsilon is the surface emissivity, and inverting according to the atmospheric parameters and the seventh formula to obtain the surface temperature T, wherein T a Is the average temperature of the atmosphere, T b For luminance temperature, a and b are regression coefficients, a = -62.7182, b = -0.4339.
In the embodiment, the surface temperature is obtained by inverting data such as the atmospheric permeability, the surface emissivity, the atmospheric average temperature and the like.
In an embodiment, the method for predicting a geothermal high-temperature abnormal region provided in the embodiment of the present application may further include:
step 210, acquiring a standard vector, a solar zenith angle, solar direct radiation, sky scattered radiation, ambient reflected radiation and an elevation corresponding to the area to be predicted;
step 220, determining the gradient and the slope direction of the area to be predicted according to the standard vector;
step 230, determining and correcting the surface emissivity according to the gradient, a preset empirical coefficient, the solar zenith angle and the surface emissivity;
step 240, determining accumulated solar radiation according to the solar direct radiation, the sky scattered radiation and the ambient reflected radiation;
and 250, constructing a surface temperature simulation model according to the elevation, the gradient, the slope direction, the corrected surface emissivity, the accumulated solar radiation, the normalized index and a random forest algorithm.
Specifically, first, the gradient S and the gradient direction a are calculated according to formula eight and formula nine, respectively, where (n) is x ,n y ,n z ) The standard vector of each grid cell corresponding to the region to be predicted (i.e., the standard vector in the present embodiment).
Then, the terrain correction is performed on the earth surface albedo subjected to radiometric calibration, atmospheric correction and broadband conversion according to the formula ten to obtain the corrected earth surface emissivity (i.e. the corrected earth surface emissivity in the embodiment), wherein α is i To correct surface emissivity, Z s The solar zenith angle is c, which is an empirical coefficient (i.e. a preset empirical coefficient in this embodiment), and θ is a slope incident angle.
Secondly, directly radiating the sun I corresponding to the area to be predicted b Sky scattered radiation I d And ambient reflected radiation I r Adding to obtain cumulative solar radiation, and calculating according to formula eleven and formula twelve to obtain solar direct radiation, wherein E 0 Is the sun constant, d r Is the correction coefficient of the distance between the day and the ground, DOY is the accumulated day of the year, tau b For direct atmospheric transmittance, θ is the actual solar incident angle. Calculating according to a formula thirteen, a formula fourteen and a formula fifteen to obtain sky scattered radiation, wherein I d,flat For sky scattered radiation in flat terrain, τ d For scattered radiation transmittance, SVF is sky visibility factor, h i The method is to divide a hemispherical space into n equal parts and calculate the maximum height angle found by the height angle formed by any slope element and a starting point slope element in the horizontal plane projection direction along light rays in each equal part. Calculating according to formula sixteen and formula seventeen to obtain the ambient reflected radiation, wherein C t Representing parameters relating to the terrain structure, including anisotropic properties and geometric effects between the elements and surrounding visible elements, S being the slopeAnd the degree rho is the average value of the albedo of the surrounding adjacent pixels.
And finally, constructing a ground surface temperature simulation model by using a random forest algorithm, wherein T is shown in a formula eighteen RF For the simulated ground surface temperature value, f is a nonlinear function model constructed by a random forest algorithm, I is accumulated solar radiation, ELV is elevation, alpha' is ground surface albedo, NDWI is normalized water body index, NDVI is normalized vegetation index, and NDSI is normalized snow cover index; further, a terrain temperature simulation model constructed by using a random forest algorithm is utilized to remove terrain factors causing terrain effects of the terrain temperature, and a terrain corrected terrain surface temperature value can be obtained, wherein T is shown in the formula nineteen C Is the corrected surface temperature value.
In the embodiment, a surface temperature simulation model is constructed through various data corresponding to the area to be predicted.
In an embodiment, the method for predicting a geothermal high-temperature abnormal region provided in the embodiment of the present application may further include:
step 310, determining a certainty coefficient and a relative contribution value of each high-temperature abnormality induction factor according to the conditional probability, the prior probability, the segmentation contribution value and the segmentation level corresponding to each high-temperature abnormality induction factor;
and step 320, determining a high-temperature abnormal prediction result of the area to be predicted according to the certainty coefficient and the relative contribution value.
Specifically, the construction of the prediction model of the geothermal high-temperature abnormal region comprises the following steps: calculating the deterministic coefficient value for each of the evoked factors according to the formula twenty, where K CF Is a deterministic coefficient; p is a The conditional probability of the presence of geothermal anomalies within the hierarchical layer for the impact factor (i.e., the conditional probability in this embodiment), here the ratio of the number of hot springs within the hierarchy to the number of grids within the hierarchy; p s The prior probability of occurrence of geotherm anomaly (i.e. the prior probability in the present embodiment) is here the ratio of the number of units with hot spring points in the prediction region to the total number of evaluation units in the prediction region.
The respective factor weights ω are calculated according to the formula twenty-one, wherein,ω is the relative contribution of an inducing factor, Z i The segment contribution value representing a deterministic coefficient of a factor (i.e., the segment contribution value in this embodiment), i, is the segment level of the deterministic coefficient (i.e., the segment level in this embodiment). Determining a coefficient K CF Multiplying the factor weight omega to obtain the predicted value of the geothermal abnormality of each factor, classifying the predicted value of each factor by using a natural breakpoint method into 4 grades, and sequentially dividing the predicted values into the following steps from high to low: and finally obtaining the prediction result of the geothermal high-temperature abnormal area.
The embodiment determines the high-temperature abnormality prediction result of the area to be predicted according to the high-temperature abnormality inducing factor and the weight thereof.
Referring to fig. 2, in an embodiment, the method for predicting a geothermal high-temperature abnormal region according to the embodiment of the present application may further include:
and step 180, determining the normalized snow index according to the green light wave band earth surface reflectivity and the short wave infrared wave band earth surface reflectivity.
Specifically, a normalized water body index NDWI, a normalized vegetation index NDVI and a normalized snow cover index NDSI are respectively obtained through calculation by a formula II, a formula III and a formula IV, wherein Green, red, NIR and SWIR respectively represent the earth surface reflectivity of a Green light wave band, the earth surface reflectivity of a Red light wave band, the earth surface reflectivity of a near infrared wave band and the earth surface reflectivity of a short wave infrared wave band.
In the embodiment, the normalized water body index, the normalized vegetation index and the normalized snow index are determined through the surface reflectivity of various wave bands.
The present invention provides a geothermal high temperature abnormal region prediction apparatus, which can be referred to in correspondence with the above described geothermal high temperature abnormal region prediction method.
Referring to fig. 3, the present invention further provides a device for predicting a geothermal high temperature abnormal region, including:
the earth surface temperature inversion module 301 is used for acquiring the atmospheric parameters and the normalization index corresponding to the area to be predicted, and inverting according to the atmospheric parameters to obtain the earth surface temperature;
the earth surface temperature correction module 302 is used for constructing an earth surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm, and determining a corrected earth surface temperature corresponding to the earth surface temperature simulation model;
and the high-temperature anomaly prediction module 303 is configured to determine a high-temperature anomaly prediction result of the area to be predicted according to the high-temperature anomaly inducing factor including the corrected earth surface temperature.
Optionally, the atmospheric parameters include surface emissivity, atmospheric permeability, and atmospheric mean temperature; the surface temperature inversion module comprises:
the first acquisition unit is used for acquiring the vegetation proportion, the vegetation temperature ratio, the bare soil temperature ratio, the emissivity change, the preset emissivity, the atmospheric mode, the atmospheric water vapor content and the near-surface air temperature of the mixed pixel corresponding to the area to be predicted;
the earth surface emissivity determining unit is used for determining the earth surface emissivity according to the mixed pixel vegetation proportion, the vegetation temperature ratio, the bare soil temperature ratio, the emissivity change and the preset emissivity;
the atmosphere transmission rate determining unit is used for determining the atmosphere transmission rate according to the atmosphere mode and the atmosphere water vapor content;
and the atmosphere average temperature determining unit is used for determining the atmosphere average temperature according to the atmosphere mode and the near-surface air temperature.
Optionally, the surface temperature inversion module comprises:
the intermediate variable determining unit is used for determining an intermediate variable according to the atmospheric permeability and the surface emissivity;
and the earth surface temperature inversion unit is used for obtaining the earth surface temperature through inversion according to the intermediate variable, the atmospheric average temperature, the preset brightness temperature and the preset regression coefficient.
Optionally, the surface temperature correction module comprises:
the second acquisition unit is used for acquiring a standard vector, a solar zenith angle, solar direct radiation, sky scattered radiation, ambient reflected radiation and an elevation corresponding to the area to be predicted;
the first determination unit is used for determining the gradient and the slope direction of the area to be predicted according to the standard vector;
the corrected earth surface emissivity determining unit is used for determining the corrected earth surface emissivity according to the gradient, the preset empirical coefficient, the solar zenith angle and the earth surface emissivity;
an accumulated solar radiation determination unit for determining an accumulated solar radiation based on the solar direct radiation, the sky scattered radiation and the ambient reflected radiation;
and the earth surface temperature simulation model building unit is used for building an earth surface temperature simulation model according to the elevation, the gradient, the slope direction, the corrected earth surface emissivity, the accumulated solar radiation, the normalized index and a random forest algorithm.
Optionally, the high temperature anomaly prediction module includes:
the second determining unit is used for determining the certainty factor and the relative contribution value of each high-temperature abnormal induction factor according to the conditional probability, the prior probability, the sectional contribution value and the sectional level corresponding to each high-temperature abnormal induction factor;
and the high-temperature abnormal prediction result determining unit is used for determining the high-temperature abnormal prediction result of the area to be predicted according to the certainty coefficient and the relative contribution value.
Optionally, the normalized index includes a normalized water body index, a normalized vegetation index and a normalized snow cover index, and the surface temperature inversion module includes:
the third acquisition unit is used for acquiring green light wave band ground surface reflectivity, red light wave band ground surface reflectivity, near infrared wave band ground surface reflectivity and short wave infrared wave band ground surface reflectivity corresponding to the area to be predicted;
the normalized water body index determining unit is used for determining the normalized water body index according to the green light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
the normalized vegetation index determining unit is used for determining the normalized vegetation index according to the red light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
and the normalized snow index determining unit is used for determining the normalized snow index according to the green light wave band earth surface reflectivity and the short wave infrared wave band earth surface reflectivity.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor) 410, a communication Interface 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to perform the geothermal high temperature exception region prediction method.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, where the computer program product includes a computer program, where the computer program may be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, a computer can execute the method for predicting a geothermal high temperature abnormal region provided by the above methods.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the geothermal high temperature abnormal region prediction method provided by the above methods.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A geothermal high-temperature abnormal region prediction method is characterized by comprising the following steps:
obtaining an atmospheric parameter and a normalization index corresponding to an area to be predicted, and obtaining earth surface temperature according to inversion of the atmospheric parameter;
constructing a ground surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm, and determining a corrected ground surface temperature corresponding to the ground surface temperature simulation model;
and determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature.
2. The method for predicting the geothermal high-temperature abnormal region according to claim 1, wherein the atmospheric parameters comprise surface emissivity, atmospheric permeability and atmospheric average temperature; the step of obtaining the atmospheric parameters corresponding to the area to be predicted comprises the following steps:
acquiring a mixed pixel vegetation ratio, a vegetation temperature ratio, a bare soil temperature ratio, an emissivity variable quantity, a preset emissivity, an atmospheric mode, an atmospheric water vapor content and a near-surface air temperature corresponding to an area to be predicted;
determining the surface emissivity according to the mixed pixel vegetation proportion, the vegetation temperature ratio, the bare soil temperature ratio, the emissivity change and the preset emissivity;
determining the atmospheric transmittance according to the atmospheric mode and the atmospheric water vapor content;
and determining the average atmospheric temperature according to the atmospheric mode and the near-surface air temperature.
3. The method for predicting the geothermal high-temperature abnormal area according to claim 2, wherein the step of obtaining the earth surface temperature by inversion according to the atmospheric parameters comprises the following steps:
determining an intermediate variable according to the atmospheric permeability and the surface emissivity;
and obtaining the earth surface temperature through inversion according to the intermediate variable, the atmospheric average temperature, the preset brightness temperature and the preset regression coefficient.
4. The method for predicting the geothermal high-temperature abnormal region according to claim 2, wherein the step of constructing a ground surface temperature simulation model according to the region to be predicted, the atmospheric parameters, the normalized index and a random forest algorithm comprises the following steps:
acquiring a standard vector, a solar zenith angle, solar direct radiation, sky scattered radiation, ambient reflected radiation and an elevation corresponding to the area to be predicted;
determining the gradient and the slope direction of the area to be predicted according to the standard vector;
determining corrected surface emissivity according to the gradient, a preset empirical coefficient, the solar zenith angle and the surface emissivity;
determining an accumulated solar radiation from the solar direct radiation, the sky scattered radiation and the ambient reflected radiation;
and constructing a surface temperature simulation model according to the elevation, the gradient, the slope direction, the corrected surface emissivity, the accumulated solar radiation, the normalized index and a random forest algorithm.
5. The method according to claim 1, wherein the step of determining the high-temperature abnormality prediction result of the area to be predicted based on the high-temperature abnormality induction factor including the corrected surface temperature comprises:
determining a certainty coefficient and a relative contribution value of each high-temperature abnormality induction factor according to the corresponding conditional probability, prior probability, segment contribution value and segment level of each high-temperature abnormality induction factor;
and determining a high-temperature abnormal prediction result of the area to be predicted according to the certainty coefficient and the relative contribution value.
6. The method for predicting the geothermal high-temperature abnormal region according to claim 1, wherein the normalization index comprises a normalization water body index, a normalization vegetation index and a normalization snow cover index, and the step of obtaining the normalization index corresponding to the region to be predicted comprises the following steps:
obtaining green light wave band earth surface reflectivity, red light wave band earth surface reflectivity, near infrared wave band earth surface reflectivity and short wave infrared wave band earth surface reflectivity corresponding to an area to be predicted;
determining the normalized water body index according to the green light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
determining the normalized vegetation index according to the red light wave band earth surface reflectivity and the near infrared wave band earth surface reflectivity;
and determining the normalized snow index according to the green light wave band earth surface reflectivity and the short wave infrared wave band earth surface reflectivity.
7. A geothermal high-temperature abnormal region prediction device is characterized by comprising:
the earth surface temperature inversion module is used for acquiring the atmospheric parameters and the normalization indexes corresponding to the area to be predicted and inverting to obtain the earth surface temperature according to the atmospheric parameters;
the earth surface temperature correction module is used for constructing an earth surface temperature simulation model according to the area to be predicted, the atmospheric parameters, the normalization index and a random forest algorithm and determining corrected earth surface temperature corresponding to the earth surface temperature simulation model;
and the high-temperature abnormity prediction module is used for determining a high-temperature abnormity prediction result of the area to be predicted according to the high-temperature abnormity induction factor containing the corrected earth surface temperature.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the geothermal high temperature abnormal region prediction method according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the geothermal high-temperature abnormal region prediction method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the geothermal high temperature abnormal region prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211294315.2A CN115659796A (en) | 2022-10-21 | 2022-10-21 | Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211294315.2A CN115659796A (en) | 2022-10-21 | 2022-10-21 | Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115659796A true CN115659796A (en) | 2023-01-31 |
Family
ID=84989030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211294315.2A Pending CN115659796A (en) | 2022-10-21 | 2022-10-21 | Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115659796A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611592A (en) * | 2023-07-21 | 2023-08-18 | 成都理工大学 | Prediction method for geothermal abnormal region along railway corridor based on deep learning |
| CN117314204A (en) * | 2023-11-29 | 2023-12-29 | 四川省能源地质调查研究所 | Geothermal high-temperature abnormal region prediction method |
-
2022
- 2022-10-21 CN CN202211294315.2A patent/CN115659796A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116611592A (en) * | 2023-07-21 | 2023-08-18 | 成都理工大学 | Prediction method for geothermal abnormal region along railway corridor based on deep learning |
| CN116611592B (en) * | 2023-07-21 | 2023-10-20 | 成都理工大学 | Prediction method for geothermal abnormal region along railway corridor based on deep learning |
| CN117314204A (en) * | 2023-11-29 | 2023-12-29 | 四川省能源地质调查研究所 | Geothermal high-temperature abnormal region prediction method |
| CN117314204B (en) * | 2023-11-29 | 2024-01-30 | 四川省能源地质调查研究所 | Geothermal high-temperature abnormal region prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115659796A (en) | Method, device and equipment for predicting geothermal high-temperature abnormal region and readable storage medium | |
| CN103926634B (en) | A kind of terrestrial radiation mist remote-sensing monitoring method on daytime based on object oriented classification | |
| CN111368817B (en) | Method and system for quantitatively evaluating thermal effect based on earth surface type | |
| CN101738620B (en) | Method by utilizing passive microwave remote sensing data AMSR-E (Advanced Microwave Scanning Radiometer-EOS ) to invert surface temperature | |
| Mohr | Interannual, monthly, and regional variability in the wet season diurnal cycle of precipitation in sub-Saharan Africa | |
| CN111060992B (en) | Equal-weight conjugate precipitation detection method and system for satellite-borne microwave dioxygen detection channel | |
| CN112348812B (en) | Forest stand age information measurement method and device | |
| CN110427818A (en) | The deep learning satellite data cloud detection method of optic that high-spectral data is supported | |
| Wang et al. | Fractional vegetation cover estimation method through dynamic Bayesian network combining radiative transfer model and crop growth model | |
| Xu et al. | Evaluating spatial representativeness of station observations for remotely sensed leaf area index products | |
| Lin et al. | Deriving the spatiotemporal NPP pattern in terrestrial ecosystems of Mongolia using MODIS imagery | |
| Susaki et al. | Validation of MODIS albedo products of paddy fields in Japan | |
| Wu et al. | Downscaling of urban land surface temperature based on multi-factor geographically weighted regression | |
| CN108983324A (en) | A kind of temperature forecast method and system based on Kalman filtering | |
| Wu et al. | Algorithms for calculating topographic parameters and their uncertainties in downward surface solar radiation (DSSR) estimation | |
| CN106920231A (en) | A kind of remote sensing image clouds appraisal procedure based on full-colour image statistical nature | |
| Lou et al. | An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data | |
| CN114881620A (en) | Territorial space monitoring method and system based on satellite remote sensing | |
| CN114626966A (en) | Method for quantizing large-scale urban blue-green space cooling scale based on landscape pattern | |
| CN107576399B (en) | MODIS forest fire detection-oriented brightness and temperature prediction method and system | |
| CN116698691A (en) | Atmospheric fine particle AOD inversion method and device, electronic equipment and storage medium | |
| CN111597692A (en) | Surface net radiation estimation method, system, electronic equipment and storage medium | |
| CN117035066A (en) | Ground surface temperature downscaling method coupling geographic weighting and random forest | |
| KR101693705B1 (en) | Manufacturing method for medium- resolution simulation satellite image by multiple regression and system thereof | |
| Qing et al. | An optical water classification and quality control model (oc_qc model) for spectral diffuse attenuation coefficient |
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 |