CN114154627B - Soil profile measuring method and device based on GIS and double-layer neural network - Google Patents
Soil profile measuring method and device based on GIS and double-layer neural network Download PDFInfo
- Publication number
- CN114154627B CN114154627B CN202210123119.2A CN202210123119A CN114154627B CN 114154627 B CN114154627 B CN 114154627B CN 202210123119 A CN202210123119 A CN 202210123119A CN 114154627 B CN114154627 B CN 114154627B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- soil
- target
- neural network
- double
- 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.)
- Active
Links
- 239000002689 soil Substances 0.000 title claims abstract description 173
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 177
- 238000005070 sampling Methods 0.000 claims abstract description 52
- 238000003062 neural network model Methods 0.000 claims abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 40
- 239000002366 mineral element Substances 0.000 claims abstract description 31
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 238000003556 assay Methods 0.000 claims abstract description 4
- 239000000523 sample Substances 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 16
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 10
- 229910052737 gold Inorganic materials 0.000 claims description 10
- 239000010931 gold Substances 0.000 claims description 10
- 238000013145 classification model Methods 0.000 claims description 9
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 6
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000010408 sweeping Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- ZOXJGFHDIHLPTG-UHFFFAOYSA-N Boron Chemical compound [B] ZOXJGFHDIHLPTG-UHFFFAOYSA-N 0.000 claims description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 3
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 claims description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 3
- PXGOKWXKJXAPGV-UHFFFAOYSA-N Fluorine Chemical compound FF PXGOKWXKJXAPGV-UHFFFAOYSA-N 0.000 claims description 3
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 claims description 3
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 3
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 claims description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 3
- 235000008331 Pinus X rigitaeda Nutrition 0.000 claims description 3
- 235000011613 Pinus brutia Nutrition 0.000 claims description 3
- 241000018646 Pinus brutia Species 0.000 claims description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 3
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 claims description 3
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 claims description 3
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims description 3
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 claims description 3
- 229910052782 aluminium Inorganic materials 0.000 claims description 3
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims description 3
- 229910052785 arsenic Inorganic materials 0.000 claims description 3
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 claims description 3
- 229910052796 boron Inorganic materials 0.000 claims description 3
- 229910052793 cadmium Inorganic materials 0.000 claims description 3
- BDOSMKKIYDKNTQ-UHFFFAOYSA-N cadmium atom Chemical compound [Cd] BDOSMKKIYDKNTQ-UHFFFAOYSA-N 0.000 claims description 3
- 229910052791 calcium Inorganic materials 0.000 claims description 3
- 239000011575 calcium Substances 0.000 claims description 3
- 229910052804 chromium Inorganic materials 0.000 claims description 3
- 239000011651 chromium Substances 0.000 claims description 3
- 229910017052 cobalt Inorganic materials 0.000 claims description 3
- 239000010941 cobalt Substances 0.000 claims description 3
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 claims description 3
- 229910052802 copper Inorganic materials 0.000 claims description 3
- 239000010949 copper Substances 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 229910052731 fluorine Inorganic materials 0.000 claims description 3
- 239000011737 fluorine Substances 0.000 claims description 3
- 229910052732 germanium Inorganic materials 0.000 claims description 3
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical compound [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 claims description 3
- 210000002364 input neuron Anatomy 0.000 claims description 3
- PNDPGZBMCMUPRI-UHFFFAOYSA-N iodine Chemical compound II PNDPGZBMCMUPRI-UHFFFAOYSA-N 0.000 claims description 3
- 239000011133 lead Substances 0.000 claims description 3
- 239000011777 magnesium Substances 0.000 claims description 3
- 229910052749 magnesium Inorganic materials 0.000 claims description 3
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 claims description 3
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 claims description 3
- 229910052753 mercury Inorganic materials 0.000 claims description 3
- 229910052750 molybdenum Inorganic materials 0.000 claims description 3
- 239000011733 molybdenum Substances 0.000 claims description 3
- 229910052759 nickel Inorganic materials 0.000 claims description 3
- 229910052757 nitrogen Inorganic materials 0.000 claims description 3
- 210000004205 output neuron Anatomy 0.000 claims description 3
- 239000011574 phosphorus Substances 0.000 claims description 3
- 229910052698 phosphorus Inorganic materials 0.000 claims description 3
- 229910052700 potassium Inorganic materials 0.000 claims description 3
- 239000011591 potassium Substances 0.000 claims description 3
- 229910052711 selenium Inorganic materials 0.000 claims description 3
- 239000011669 selenium Substances 0.000 claims description 3
- 229910052709 silver Inorganic materials 0.000 claims description 3
- 239000004332 silver Substances 0.000 claims description 3
- 229910052708 sodium Inorganic materials 0.000 claims description 3
- 239000011734 sodium Substances 0.000 claims description 3
- 229910052712 strontium Inorganic materials 0.000 claims description 3
- CIOAGBVUUVVLOB-UHFFFAOYSA-N strontium atom Chemical compound [Sr] CIOAGBVUUVVLOB-UHFFFAOYSA-N 0.000 claims description 3
- 239000011593 sulfur Substances 0.000 claims description 3
- 229910052717 sulfur Inorganic materials 0.000 claims description 3
- 229910052720 vanadium Inorganic materials 0.000 claims description 3
- LEONUFNNVUYDNQ-UHFFFAOYSA-N vanadium atom Chemical compound [V] LEONUFNNVUYDNQ-UHFFFAOYSA-N 0.000 claims description 3
- 229910052725 zinc Inorganic materials 0.000 claims description 3
- 239000011701 zinc Substances 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 claims description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 abstract description 14
- 239000011707 mineral Substances 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 abstract description 12
- 239000000126 substance Substances 0.000 abstract description 6
- 238000012360 testing method Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 abstract description 3
- 230000001089 mineralizing effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000033558 biomineral tissue development Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000004856 soil analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V9/00—Prospecting or detecting by methods not provided for in groups G01V1/00 - G01V8/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a method and equipment for measuring a soil profile based on a GIS (geographic information system) and a double-layer neural network, belongs to the technical field of chemical exploration and mineral exploration, and is used for solving the technical problems that the arrangement position and the line distance of the conventional soil profile measurement are difficult to determine, the construction of a plurality of soil profiles consumes manpower and material resources and higher assay expenditure, and the soil profile cannot completely display abnormal characteristics due to overlarge line distance. The method comprises the following steps: on the basis of system sampling and analysis testing, a small amount of implemented soil profiles and sampling analysis data are used as training samples, a plurality of soil profiles and sampling points are encrypted in an interpolation mode according to preset line distance multiplied by point distance through a trained double-layer BP neural network model, the information content of the analysis data is improved, then a plain-section diagram of main mineral elements is made according to laboratory analysis data and prediction data, peak areas on the plain-section diagram are connected into an element abnormal long shaft, and the target position of the groove exploration is determined by combining a topographic map and a remote sensing image.
Description
Technical Field
The application relates to the field of chemical exploration and mineral exploration, in particular to a soil profile measuring method and device based on a GIS and a double-layer neural network.
Background
Soil geochemical survey, soil survey for short, has long been an important means in geological mineral survey, mining area detailed survey, and mining point inspection and regional chemical exploration anomaly inspection. Through finding out the geochemical distribution characteristics of elements in the soil, the geochemical anomaly is determined, mineral exploration, resource evaluation, ecological environment investigation, soil quality geochemical evaluation and basic geological research are developed, and the application service is provided for various aspects of economic and social development of geological mineral products, agricultural ecological environment and the like.
The mineral exploration has important guiding significance for mineral development. The existing mineral exploration methods mainly comprise geological methods, geophysical prospecting methods, chemical prospecting methods, remote sensing methods and the like. In the geological ore finding process of an area with relatively thick earth surface covered by a fourth system, in order to reduce an ore finding target area, firstly, area soil is selected for measurement, and then soil profile measurement is carried out on a circled element abnormal target area, so that the purposes of verifying abnormity, reducing the ore finding target area and highlighting ore finding key points are achieved. However, the method has the disadvantages that the arrangement position and the line distance of the soil profile survey line are difficult to determine, a large amount of manpower, material resources, time constraints and higher test expenses are required for constructing a plurality of soil profiles, and in many cases, due to capital limitation, excessive soil profiles cannot be implemented in the field, only a limited number of soil profiles can be implemented, and then sampling is carried out according to a certain point distance.
Disclosure of Invention
The embodiment of the application provides a soil profile measuring method and equipment based on a GIS and a double-layer neural network, which are used for solving the following technical problems: the arrangement position and the line distance of the existing soil profile measurement are difficult to determine, the construction of a plurality of soil profiles consumes manpower, material resources and higher assay expenditure, and the soil profile cannot completely display the abnormal characteristics of the soil due to the overlarge line distance.
The embodiment of the application adopts the following technical scheme:
on one hand, the embodiment of the application provides a soil profile measuring method based on a GIS and a double-layer neural network, and the method comprises the following steps: a plurality of abnormal target areas are circled through the work of the areal soil sweeping surface, the areas where the abnormal target areas are located are abnormal areas, and abnormal concentration centers are determined in the abnormal target areas; in the abnormal area, implementing a preset number of soil profiles according to a first preset line distance, and determining sampling points on the soil profiles according to a first preset point distance; determining the geographic information of the sampling point based on a GIS technology; the geographic information comprises longitude and latitude information and elevation information; collecting a soil sample at the sampling point, and carrying out experimental analysis on the soil sample to obtain soil element analysis data of the sampling point; taking the geographic information of the sampling points and the soil element analysis data as training samples to train a double-layer BP neural network model; performing kriging interpolation encryption according to a second preset line distance multiplied by a second preset point distance to obtain a plurality of encrypted soil profiles and encrypted sampling points thereof, and outputting soil element prediction data of each encrypted sampling point through the trained double-layer BP neural network model; according to the soil element analysis data and the soil element prediction data, making a horizontal sectional view of main mineral elements on each soil section; connecting the peak areas of each horizontal sectional view to obtain the abnormal long axis of the main mineral element; and superposing the abnormal long shaft and the abnormal target area, determining a target channel sounding position in the direction perpendicular to the abnormal long shaft at the abnormal concentration center so as to guide a technician to perform channel sounding verification at the target channel sounding position, and revealing an ore body through channel sounding so as to determine the position of the ore body.
According to the embodiment of the application, the soil profiles and the sampling points with limited quantity are encrypted through the improved double-layer BP neural network model, so that the information quantity of analysis data in the abnormal region of the soil is improved, the abnormal element characteristics of the soil profiles can be comprehensively displayed under the limit of limited funds, and the main mineralization element abnormal long shaft is obtained. And then the abnormal long axis of the main mineral forming element and the abnormal target area of the element are superposed for analysis, so that a more accurate target slot exploration position is obtained, a geological team member is guided to find the hidden deposit more quickly, mineral leakage is avoided, mineral finding efficiency is improved, a better mineral finding effect is obtained, and positive guiding significance is provided for mineral finding work.
In a possible implementation mode, an abnormal target area is circled through the work of an area soil sweeping surface, the area where the abnormal target area is located is an abnormal area, and an abnormal concentration center is determined in the abnormal target area, which specifically comprises the following steps: calculating the initial average value X of the content X of the main mineral elements in the working area according to the analysis result of the assay0And initial standard deviation S0(ii) a Wherein the main mineral element is one of nitrogen, phosphorus, potassium, boron, manganese, molybdenum, selenium, iodine, germanium, fluorine, zinc, copper, cobalt, vanadium, arsenic, chromium, cadmium, mercury, lead, nickel, sodium, aluminum, strontium, calcium, magnesium, sulfur, gold and silver; according to the removing conditions: x is greater than or equal to X0－ 3S0And is less than or equal to X0+ 3S0Iteratively eliminating the extra-high value and the extra-low value of the element content to obtain a new data set; repeating the iterative elimination process on the obtained data set until the data meeting the elimination condition cannot be found; calculating the average X of the resulting data set1And standard deviation S1(ii) a According to A = X1+ 2S1Obtaining an abnormal lower limit A of main mineral elements in the working area; dividing outer, middle and inner 3 concentration zones of the abnormal target area by 1 time, 2 times and 4 times of the lower limit A of the abnormality respectively, and drawing an abnormal graph; the working area comprises a plurality of abnormal target areas, and the areas of the plurality of abnormal target areas are abnormal areas; determining the area with the content of the main mineral elements in the abnormal target area larger than a first preset threshold value as the abnormality of the abnormal target areaA concentration center.
In a possible embodiment, before training the double-layer BP neural network model by using the geographic information of the soil profile and the sampling point and the soil element analysis data as training samples, the method further comprises: obtaining a soil profile measurement sample analysis result implemented in the abnormal area, and taking the sample analysis result as training data; performing data enhancement on the training data to obtain enhanced training data; determining the optimal number of hidden layer nodes of the double-layer BP neural network model; and training the double-layer BP neural network model with the optimal hidden layer node number through the enhanced training data to obtain the trained double-layer BP neural network model.
In a possible embodiment, determining the optimal number of hidden layer nodes of the two-layer BP neural network model specifically includes: according to
Determining the number A of hidden layer nodes of the double-layer BP neural network model1(ii) a Wherein x is the input neuron number of the double-layer BP neural network model; y is the output neuron number of the double-layer BP neural network model; n is a constant and has a value range of: n is not less than 1 and not more than 10; determining the number of hidden layer nodes A based on the value of n1The value range is as follows: a. the1Is greater than or equal to
And is not more than
(ii) a Sequentially taking integer values from small to large in the value range, and respectively taking the integer values as the number of hidden nodes of the double-layer BP neural network model; and training the double-layer BP neural network model again and calculating the prediction precision, and circulating the training until the optimal number of hidden nodes enabling the double-layer BP neural network model to have the highest prediction precision is found.
According to the method and the device, data enhancement is performed on less training data, so that more training data are obtained, and the training effect of the double-layer BP neural network model is enhanced. And the prediction precision of the double-layer BP neural network is improved by adjusting the number of hidden nodes of the double-layer BP neural network model.
In a possible embodiment, a horizontal section diagram of the main mineralizing elements on each soil section is made according to the soil element analysis data and the soil element prediction data, and the horizontal section diagram specifically comprises the following steps: drawing an element content curve graph on each soil section according to soil element analysis data corresponding to each sampling point to obtain a horizontal cross-section corresponding to each soil section; and drawing an element content curve graph on each encrypted soil section according to soil element prediction data corresponding to each encrypted sampling point to obtain a plain-section graph corresponding to each encrypted soil section.
In one possible embodiment, superimposing the abnormal long axis with the abnormal target area, determining the target probing position in the direction perpendicular to the abnormal long axis at the center of the abnormal concentration, specifically comprises: superposing the abnormal long axis of the main mineral element and the plurality of abnormal target areas together; determining an abnormal target area with a larger matching degree with the abnormal long axis as a target abnormal target area in the plurality of abnormal target areas; and making a perpendicular line in a direction perpendicular to the abnormal long axis at the abnormal concentration center of the target abnormal target area, and determining the position of the intersection point as the target groove detection position.
In one possible embodiment, after superimposing the abnormal long axis with the abnormal target zone, determining a target sounding location at the center of the abnormal concentration in a direction perpendicular to the abnormal long axis, the method further comprises: judging whether the target sounding position is occupied or not; and if the target slot probing position is occupied, determining that the target slot probing position is not beneficial to carrying out slot probing work, and offsetting the target slot probing position by a preset distance towards the direction of the abnormal concentration center to determine the next target slot probing position.
In a possible implementation manner, the determining whether the target sounding location is occupied specifically includes: judging whether the target sounding position is occupied or not, and specifically comprising the following steps: acquiring a hyperspectral remote sensing image of a preset area around the target groove detection position; training an SVM classifier through an Indian Pines data set to obtain a remote sensing image classification model; inputting the hyperspectral remote sensing images into the remote sensing image classification model, and identifying various ground feature characteristics in the hyperspectral remote sensing images and positions of the ground feature characteristics; wherein the feature at least comprises: engineering, buildings, roads, water conservancy facilities; and if the target position of the grooved probe is consistent with the position of at least one feature of the ground object, determining that the target position of the grooved probe is occupied.
According to the embodiment of the application, whether the target groove detection position has influence factors of inconvenient exploration such as engineering, buildings, roads and water conservancy facilities or not is identified through the remote sensing image classification model, so that the target groove detection position is adjusted, a technician is guided to explore on the spot more accurately, the influence factors of the inconvenient exploration are found after the technician arrives at the site, and the method for automatically selecting other sites for exploration can be more accurate.
In one possible embodiment, the method further comprises: the direction of the compacted soil profile is consistent with the direction of the implemented soil profile.
On the other hand, this application embodiment still provides a soil profile measuring equipment based on GIS and double-deck neural network, and equipment includes: at least one processor; and a memory communicatively coupled to the at least one processor; the storage stores instructions executable by the at least one processor to enable the at least one processor to perform a method for measuring a soil profile based on a GIS and double-layer neural network according to any one of the above embodiments.
According to the soil profile measuring method and device based on the GIS and the double-layer neural network, the abnormal long axis of the element of a certain mineral with the mineralization potential can be quickly and accurately found in the prospecting work, geological team members are guided to quickly find the blind deposit, a good prospecting effect is achieved, time and efficiency are saved, and economic benefits and social benefits with 'quick', 'good' and 'province' are obtained.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
fig. 1 is a flowchart of a soil profile measuring method based on a GIS and a double-layer neural network according to an embodiment of the present disclosure;
FIG. 2 is an illustration of an abnormal diagram of an element abnormal target area provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a soil profile and a compacted soil profile provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of a horizontal sectional view and an abnormal long axis of a primary mineralizing element according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a target sounding location according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a soil profile measuring device based on a GIS and a double-layer neural network according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
The embodiment of the application provides a soil profile measuring method based on a GIS and a double-layer neural network, and the execution main body is soil profile measuring equipment based on the GIS and the double-layer neural network. As shown in fig. 1, the method for measuring a soil profile based on a GIS and a double-layer neural network specifically includes steps 101-105:
Before soil profile measurement work is carried out, the soil profile measurement work needs to be carried out in an area mode, main mineral elements in a working area are determined by analyzing the content of various elements in soil in the working area, and soil analysis items comprise analysis of elements such as nitrogen, phosphorus, potassium, boron, manganese, molybdenum, selenium, iodine, germanium, fluorine, zinc, copper, cobalt, vanadium, arsenic, chromium, cadmium, mercury, lead, nickel, sodium, aluminum, strontium, calcium, magnesium, sulfur, gold, silver and the like. The method for determining the main mineral elements is mature, so that the existing method is adopted, and the details are not repeated in the application.
Further, after the main mineral elements are determined, the abnormal target area is circled according to the concentration distribution condition of the main mineral elements. Then, determining an abnormal concentration center in the abnormal target area, which comprises the following specific steps:
according to the soil element analysis result in the area soil scanning work, calculating the initial average value X of the content X of the main mineral element in the working area0And initial standard deviation S0Then according to the removing condition: x is greater than or equal to X0－ 3S0And is less than or equal to X0+ 3S0Expressed by a mathematical formula as X0－ 3S0≤X≤X0+ 3S0Removing less than X0－ 3S0Has an extremely high content of elements and is greater than X0+ 3S0Has a very low content of elements (A) and a retention of X or more0－ 3S0And is less than or equal to X0+ 3S0To obtain a new data set. And then, repeating the iterative elimination process on the obtained new data set until the data meeting the elimination condition cannot be found in the data set. Calculating the average X of the resulting data set1And standard deviation S1. Then according to A = X1+ 2S1And obtaining an abnormal lower limit A of the main mineral elements in the abnormal target area. Are respectively different inAnd dividing 3 concentration zones outside, in and inside the abnormal target area by 1 time, 2 times and 4 times of the lower normal limit A, and drawing an abnormal graph. The area where the plurality of abnormal target areas are located is an abnormal area which is smaller than the working area. And then determining the area with the main mineral element content larger than a first preset threshold value in the abnormal target area as an abnormal concentration center of the abnormal target area.
In one embodiment, as shown in fig. 2, assuming that the main mineral element in the working area is a gold element, the areas indicated by reference numerals 1, 2, and 3 are 3 abnormal target areas of the circled gold element, and since the 3 abnormal target areas are closer in distance, the entire area shown in fig. 2 is divided into one abnormal area. And the working area is larger than the abnormal area, and there may be a plurality of abnormal areas in the working area, which are not shown in the figure, and only one abnormal area is shown as an example. Taking the abnormal target area 1 as an example, the lower limit a of abnormality of the metal element in the abnormal target area 1 is calculated according to the method1Then, the content of gold element is larger than A1And less than 2A1Is divided into an outer concentration zone of the abnormal target region 1 (as shown in the outermost circle of the element abnormal target region 1 in fig. 2), and the content of gold element is more than 2A1And less than 4A1Is divided into a middle concentration zone of the abnormal target area 1 (as shown by the middle circle of the abnormal target area 1 of the element in figure 2), and the content of the gold element is more than 4A1Is divided into inner concentration zones of the abnormal target region 1 (as shown by the innermost circle of the elemental abnormal target region 1 in fig. 2). Typically, the first predetermined threshold is greater than 4A1And the area with the content of the gold element larger than the first preset threshold value is the concentration center of the gold element. It should be noted that not all abnormal target regions have tertiary concentration zones at the same time, as shown in the abnormal target region 3 in fig. 2, only the outer and middle concentration zones have secondary concentration zones.
102, implementing a preset number of soil profiles according to a first preset line distance in the abnormal area, determining sampling points on the soil profiles according to the first preset point distance, and determining geographic information of each sampling point based on a GIS technology. And collecting a soil sample at the sampling point, and carrying out experimental analysis on the soil sample to obtain soil element analysis data of the sampling point.
Specifically, a technician needs to manually implement a limited number of soil profiles in the abnormal area according to a first preset line distance, sample each soil profile according to a first preset point distance, and send the sampled soil profiles to a qualified laboratory for analysis and test to obtain soil element analysis data. And acquiring geographic information of each sampling point, wherein the geographic information comprises longitude and latitude information and elevation information. The soil element analysis data includes data such as the content of various elements contained in the soil sample and the content of main mineral elements.
In the field of chemical exploration and prospecting, soil profile measurement is performed in an abnormal area to perform sampling analysis test, so that the conventional operation of chemical exploration and prospecting is realized. The soil profile measuring method based on the GIS and the double-layer neural network provided by the embodiment of the application is to perform subsequent steps on the basis of the existing work.
And 103, taking the geographic information of the sampling points and the soil element analysis data as training samples, training a double-layer BP neural network model, carrying out kriging interpolation encryption according to a second preset line distance multiplied by a second preset point distance to obtain a plurality of encrypted soil profiles and encrypted sampling points thereof, and outputting soil element prediction data of each encrypted sampling point through the trained double-layer BP neural network model.
Firstly, a double-layer BP neural network model is constructed and trained in advance, and the specific construction and training method is as follows:
and acquiring geographic information of sampling points on the soil profile implemented in the target area with the abnormal elements and soil element analysis data as training data. And then, performing data enhancement on the training data to obtain enhanced training data.
Further in accordance with
Determining the number A of hidden layer nodes of the double-layer BP neural network model1(ii) a Wherein x is the input neuron number of the double-layer BP neural network model; y is the output neuron number of the double-layer BP neural network model; n is a constant and has a value range of n being greater than or equal to 1 and less than or equal to 10.
Further, based on the value of n, the number A of hidden layer nodes is determined1The value range is as follows: a. the1Is greater than or equal to
And is not more than
I.e. by
. And sequentially taking integer values from small to large in the value range, and respectively taking the integer values as the number of hidden nodes of the double-layer BP neural network model. And then training the double-layer BP neural network model with the number of the hidden nodes adjusted again and calculating the prediction precision, and circulating the training until the optimal number of the hidden nodes which enable the double-layer BP neural network model to have the highest prediction precision is found. And then training the double-layer BP neural network model with the optimal hidden layer node number by enhancing the training data to obtain the trained double-layer BP neural network model.
Further, the soil profile laying direction implemented in the abnormal area is taken as a reference, and the encrypted soil profile laying direction subjected to interpolation encryption is determined. The layout length of the encrypted soil profile is also based on the implemented soil profile layout length, so that the layout direction and the layout length of the soil profile which is encrypted by interpolation are basically consistent with the direction and the length of the implemented soil profile.
Further, according to the determined layout direction and the determined layout length, multiplying a second preset line distance by a second preset point distance to perform kriging interpolation, namely encrypting a plurality of soil profiles in the abnormal area according to the second preset line distance interpolation, and determining a plurality of encrypted sampling points on each encrypted soil profile according to the second preset point distance. And then acquiring the geographic information of each encrypted sampling point based on the GIS technology.
As a possible implementation manner, the second preset line distance is smaller than the first preset line distance, and the second preset point distance may be the same as or different from the first preset point distance.
In one embodiment, fig. 3 is a schematic view of a soil profile and a compacted soil profile provided in an embodiment of the present application. As shown in fig. 3, it is assumed that the straight lines B1 and B2 are two soil profiles artificially implemented according to a first preset line distance in the abnormal area, and the black point on each soil profile is the sampling point determined according to the first preset point distance. And the C1, the C2 and the C3 are encrypted soil profiles which are subjected to interpolation encryption at a second preset line distance, and black points on each encrypted soil profile are encrypted sampling points determined according to the second preset point distance. In practical application, the soil profile and the sampling points can be encrypted according to the line distance of 100m multiplied by the point distance of 20 m.
It should be noted that, in order to clearly show the arrangement and encryption method of the soil section lines and prevent the lines from being too many to cause confusion in the picture, contour lines and concentration bands are not drawn in fig. 3, but it can be known that the three abnormal target areas in fig. 3 are the three abnormal target areas in fig. 2, only the background is changed. The soil section line in fig. 3 is only an example, and does not represent that the soil section line is set according to the direction and length shown in the figure in the actual operation process, and the implementation direction and length of the soil section line need to be determined according to various factors such as terrain and capital in the actual operation process, and need to be adjusted according to specific situations.
And further, inputting the geographic information of the encrypted sampling points on each encrypted soil profile into the trained double-layer BP neural network model to obtain the soil element prediction data of the encrypted sampling points.
104, according to the soil element analysis data and the soil element prediction data, making a horizontal sectional view of main mineral elements on each soil section; and connecting the peak areas of each horizontal sectional view to obtain the abnormal long axis of the main mineral element.
Specifically, on each soil section, drawing an element content curve graph according to soil element analysis data corresponding to each sampling point to obtain a horizontal cross-section corresponding to each soil section; and drawing an element content curve graph on each encrypted soil section according to the soil element prediction data corresponding to each encrypted sampling point to obtain a plain-section graph corresponding to each encrypted soil section. And connecting the peak areas of the horizontal sectional views to obtain the abnormal long axis of the main mineral element.
In one embodiment, the soil section lines and the encrypted soil section at the abnormal target area 2 in fig. 3 are enlarged to obtain fig. 4. As shown in fig. 4, B1, C1, C2, C3 and B2 are B1, C1, C2, C3 and B2 in fig. 3. A coordinate system (not shown) of each soil profile is established with each soil profile as an x-axis and a direction perpendicular to the soil profile as a y-axis. Wherein the y-axis represents the content of primary mineralizing elements. Taking the encrypted soil section C1 as an example, in a coordinate system of C1, an element content curve chart shown as a curve P2 in FIG. 3 is drawn according to the content of main mineralization elements at each sampling point, and the curve chart is named as a P2 horizontal section diagram. The same method is adopted to obtain the plain section pictures P1 and P3-P5. Then, the peak regions of the horizontal sectional views P1 to P5 are connected to each other, and the abnormal long axis Z of the main synthetic mineral element is obtained, and in fig. 4, the abnormal long axis Z is formed by two broken lines. The arc line passing through 5 soil sections on the abnormal target area 2 in fig. 2 is a schematic diagram of the position of the abnormal long axis Z, and is represented by a solid line to distinguish from the edge of the abnormal target area 2.
And 105, overlapping the abnormal long axis with the abnormal target area, and determining the position of the target groove probe in the direction perpendicular to the abnormal long axis in the abnormal concentration.
Specifically, the abnormal long axis of the main mineral element and the abnormal target area are superimposed on the same map, and an abnormal target area having a large degree of coincidence with the abnormal long axis is selected as a target abnormal target area from among the plurality of abnormal target areas. Then, at the abnormal concentration center of the target abnormal target area, a perpendicular line is drawn in a direction perpendicular to the abnormal long axis, and the position of the intersection point is determined as the target groove detection position.
In an embodiment, fig. 5 is a schematic diagram of a target sounding location provided by an embodiment of the present application, and as shown in fig. 4, according to the geographic location information, the abnormal long axis Z of the primary mineralizing element obtained in fig. 4 and all abnormal target areas in the abnormal area are superimposed together. If the degree of coincidence between the abnormal target area 2 and the abnormal long axis Z is large, the abnormal target area 2 is a target abnormal target area, the area S is an abnormal concentration center of the abnormal target area 2, a perpendicular line is drawn to the abnormal long axis Z at the area S, the boundary between the abnormal long axis Z and the abnormal long axis Z is a target groove detection position, and in fig. 5, the black rectangle T1 is a target groove detection position.
Further, whether the target sounding position is occupied or not is judged, and the specific method is as follows:
and acquiring a hyperspectral remote sensing image of a preset area around the target groove detection position. Training an SVM classifier through an Indian Pines data set to obtain a remote sensing image classification model. And inputting the hyperspectral remote sensing images into the remote sensing image classification model, and identifying various ground feature characteristics and the position of each ground feature characteristic in the hyperspectral remote sensing images. Wherein, the ground feature characteristics include at least: engineering, buildings, roads, and water conservancy facilities.
In one embodiment, a hyperspectral remote sensing image within a range of 500 meters around a target groove detection position is obtained through a remote sensing technology, then an SVM (support vector machine) classifier is trained through an Indian pins data set to obtain a remote sensing image classification model, the Indian pins data set is selected because the data set is used, landscapes in image data comprise farmlands, roads, railways, houses, other buildings, smaller roads and water areas, and ore body surveys in mountainous areas or zones with little human smoke, so that the data set almost comprises all ground object types needing to be detected in the application, and the method is most suitable for training of the remote sensing image classification model in the application.
Further, if the target position is occupied, it is indicated that the target position is not favorable for carrying out the tank-finding work. Therefore, the position of the next target groove detection is determined by offsetting the preset distance towards the direction of the abnormal concentration center.
And further, outputting the finally obtained target groove detection position to guide a technician to perform groove detection verification on the target groove detection position, revealing the ore body through the groove detection and determining the position of the ore body.
The application provides a soil profile measuring method based on GIS and double-layer neural network, can be through modified double-layer BP neural network model, carry out the interpolation with less soil profile and its sample and encrypt, thereby increase the information content that the soil profile was measured, and then can show the unusual characteristic of soil profile comparatively comprehensively, find target groove exploration position comparatively accurately, have positive guiding significance to developing of finding the ore work, can reduce a lot of work that need artifical the completion, promote and find the ore success rate.
In addition, the embodiment of the present application further provides a soil profile measuring device based on a GIS and a double-layer neural network, and as shown in fig. 6, the soil profile measuring device 600 based on a GIS and a double-layer neural network specifically includes:
at least one processor 601; and a memory 602 communicatively coupled to the at least one processor 601; wherein the memory 602 stores instructions executable by the at least one processor 601 to cause the at least one processor 601 to perform:
a plurality of abnormal target areas are circled through the work of the soil sweeping surface with the area, the area where the abnormal target areas are located is an abnormal area, and an abnormal concentration center is determined in the abnormal target areas;
in the abnormal area, implementing a preset number of soil profiles according to a first preset line distance, and determining sampling points on the soil profiles according to a first preset point distance;
determining geographic information of sampling points based on a GIS technology; the geographic information comprises longitude and latitude information and elevation information;
collecting a soil sample at a sampling point, and carrying out experimental analysis on the soil sample to obtain soil element analysis data of the sampling point;
taking the geographic information of the sampling points and the soil element analysis data as training samples, and training a double-layer BP neural network model; performing kriging interpolation encryption according to a second preset line distance multiplied by a second preset point distance to obtain a plurality of encrypted soil profiles and encrypted sampling points thereof, and outputting soil element prediction data of each encrypted sampling point through a trained double-layer BP neural network model;
according to the soil element analysis data and the soil element prediction data, making a horizontal sectional view of main mineral elements on each soil section;
connecting the peak areas of each horizontal sectional view to obtain the abnormal long axis of the main mineral element;
and superposing the abnormal long shaft and the abnormal target area, and determining the position of the target channel probe in the direction perpendicular to the abnormal long shaft in the abnormal concentration center so as to guide a technician to perform channel probe verification at the position of the target channel probe, uncovering an ore body through channel probe and determining the position of the ore body.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the present application. In some cases, the actions or steps recited in the present application may be performed in an order different than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the embodiments of the present application pertain. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the present application.
Claims (8)
1. A soil profile measuring method based on a GIS and a double-layer neural network is characterized by comprising the following steps:
through the work of the regional soil sweeping surface, a plurality of unusual target areas are circled out, and the region in which unusual target areas are located is unusual district to confirm unusual concentration center in unusual target area, specifically include:
calculating the initial average value X of the content X of the main mineral elements in the working area according to the analysis result of the assay0And initial standard deviation S0(ii) a Wherein the main mineral element is one of nitrogen, phosphorus, potassium, boron, manganese, molybdenum, selenium, iodine, germanium, fluorine, zinc, copper, cobalt, vanadium, arsenic, chromium, cadmium, mercury, lead, nickel, sodium, aluminum, strontium, calcium, magnesium, sulfur, gold and silver;
according to the removing conditions: x is greater than or equal to X0－ 3S0And is less than or equal to X0+ 3S0Iteratively eliminating the extra-high value and the extra-low value of the element content to obtain a new data set; repeating the iterative elimination process on the obtained data set until the data meeting the elimination condition cannot be found;
calculating the average X of the resulting data set1And standard deviation S1；
According to A = X1+ 2S1Obtaining an abnormal lower limit A of main mineral elements in the working area;
dividing outer, middle and inner 3 concentration zones of the abnormal target area by 1 time, 2 times and 4 times of the lower limit A of the abnormality respectively, and drawing an abnormal graph; the working area comprises a plurality of abnormal target areas, and the areas of the plurality of abnormal target areas are abnormal areas;
determining the area, with the content of the main mineral elements being greater than a first preset threshold value, in the abnormal target area as an abnormal concentration center of the abnormal target area;
in the abnormal area, implementing a preset number of soil profiles according to a first preset line distance, and determining sampling points on the soil profiles according to a first preset point distance;
determining the geographic information of the sampling point based on a GIS technology; the geographic information comprises longitude and latitude information and elevation information;
collecting a soil sample at the sampling point, and carrying out experimental analysis on the soil sample to obtain soil element analysis data of the sampling point;
taking the geographic information of the sampling points and the soil element analysis data as training samples to train a double-layer BP neural network model; performing kriging interpolation encryption according to a second preset line distance multiplied by a second preset point distance to obtain a plurality of encrypted soil profiles and encrypted sampling points thereof, and outputting soil element prediction data of each encrypted sampling point through the trained double-layer BP neural network model;
according to the soil element analysis data and the soil element prediction data, a horizontal sectional view of main mineral elements on each soil section is made, and the method specifically comprises the following steps:
drawing an element content curve graph on each soil section according to soil element analysis data corresponding to each sampling point to obtain a horizontal cross-section corresponding to each soil section;
drawing an element content curve graph on each encrypted soil section according to soil element prediction data corresponding to each encrypted sampling point to obtain a plain-section graph corresponding to each encrypted soil section;
connecting the peak areas of each horizontal sectional view to obtain the abnormal long axis of the main mineral element;
and superposing the abnormal long shaft and the abnormal target area, determining a target channel sounding position in the direction perpendicular to the abnormal long shaft at the abnormal concentration center so as to guide a technician to perform channel sounding verification at the target channel sounding position, and revealing an ore body through channel sounding so as to determine the position of the ore body.
2. The method for measuring the soil profile based on the GIS and the double-layer neural network as claimed in claim 1, wherein before training the double-layer BP neural network model by using the geographic information of the sampling points and the soil element analysis data as training samples, the method further comprises:
obtaining a soil profile measurement sample analysis result implemented in the abnormal area, and taking the sample analysis result as training data;
performing data enhancement on the training data to obtain enhanced training data;
determining the optimal number of hidden layer nodes of the double-layer BP neural network model;
and training the double-layer BP neural network model with the optimal hidden layer node number through the enhanced training data to obtain the trained double-layer BP neural network model.
3. The method for measuring the soil profile based on the GIS and the double-layer neural network as claimed in claim 2, wherein the determining the optimal number of hidden layer nodes of the double-layer BP neural network model specifically comprises:
according to
Determining the number A of hidden layer nodes of the double-layer BP neural network model1(ii) a Wherein x is the input neuron number of the double-layer BP neural network model; y is the output neuron number of the double-layer BP neural network model; n is a constant and has a value range of n being greater than or equal to 1 and less than or equal to 10;
determining the number of hidden layer nodes A based on the value of n1The value range is as follows: a. the1Is greater than or equal to
And is not more than
；
Sequentially taking integer values from small to large in the value range, and respectively taking the integer values as the number of hidden nodes of the double-layer BP neural network model; and training the double-layer BP neural network model again and calculating the prediction precision, and circulating the training until the optimal number of hidden nodes enabling the double-layer BP neural network model to have the highest prediction precision is found.
4. The method according to claim 1, wherein the step of superposing the abnormal long axis and the abnormal target region to determine the target sounding position in the direction perpendicular to the abnormal long axis at the abnormal concentration center comprises:
superposing the abnormal long axis of the main mineral element and the plurality of abnormal target areas together;
determining an abnormal target area which is matched with the abnormal long shaft to a larger extent from a plurality of abnormal target areas as a target abnormal target area;
and drawing a perpendicular line in a direction perpendicular to the abnormal long axis at the abnormal concentration center of the target abnormal target area, and determining the position of the intersection point as the target groove detection position.
5. The method of claim 1, wherein after superimposing the abnormal long axis with the abnormal target area and determining the target sounding location from the abnormal concentration center to a direction perpendicular to the abnormal long axis, the method further comprises:
judging whether the target sounding position is occupied or not;
and if the target slot probing position is occupied, determining that the target slot probing position is not beneficial to carrying out slot probing work, and offsetting the target slot probing position by a preset distance towards the direction of the abnormal concentration center to determine the next target slot probing position.
6. The method for measuring the soil profile based on the GIS and the double-layer neural network as claimed in claim 5, wherein the step of judging whether the target sounding position is occupied specifically comprises the steps of:
acquiring a hyperspectral remote sensing image of a preset area around the target groove detection position;
training an SVM classifier through an Indian Pines data set to obtain a remote sensing image classification model;
inputting the hyperspectral remote sensing images into the remote sensing image classification model, and identifying various ground feature characteristics in the hyperspectral remote sensing images and positions of the ground feature characteristics; wherein the feature at least comprises: engineering, buildings, roads, water conservancy facilities;
and if the target position of the grooved probe is consistent with the position of at least one feature of the ground object, determining that the target position of the grooved probe is occupied.
7. The method for measuring the soil profile based on the GIS and the double-layer neural network as claimed in claim 1, wherein the method further comprises:
the direction of the compacted soil profile is consistent with the direction of the implemented soil profile.
8. A GIS and double-layer neural network-based soil profile measuring device is characterized by comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of GIS and bi-layer neural network based soil profiling according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210123119.2A CN114154627B (en) | 2022-02-10 | 2022-02-10 | Soil profile measuring method and device based on GIS and double-layer neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210123119.2A CN114154627B (en) | 2022-02-10 | 2022-02-10 | Soil profile measuring method and device based on GIS and double-layer neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114154627A CN114154627A (en) | 2022-03-08 |
| CN114154627B true CN114154627B (en) | 2022-05-20 |
Family
ID=80450138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210123119.2A Active CN114154627B (en) | 2022-02-10 | 2022-02-10 | Soil profile measuring method and device based on GIS and double-layer neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114154627B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971215A (en) * | 2022-05-06 | 2022-08-30 | 中化地质矿山总局地质研究院 | Vegetation coverage area chemical exploration abnormity checking method and device, electronic equipment and medium |
| CN114596498B (en) * | 2022-05-10 | 2022-07-29 | 湖北省地质调查院 | Assignment method and system for geochemical sampling blind area and storage medium |
| CN114971234B (en) * | 2022-05-11 | 2023-04-07 | 北京中色测绘院有限公司 | Soil general survey technical method |
| WO2024182962A1 (en) * | 2023-03-06 | 2024-09-12 | 青海省地质矿产勘查开发局 | Target selection method for lithium and potassium-containing anticline |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102841081A (en) * | 2012-08-30 | 2012-12-26 | 湖南科技大学 | Prediction method for distribution of each heavy metal in polluted flow on soil-water interface of non-ferrous metal orefield |
| CN106996969A (en) * | 2017-03-03 | 2017-08-01 | 北京农业质量标准与检测技术研究中心 | A kind of heavy metal-polluted soil spatial distribution Forecasting Methodology and system |
| CN110442666A (en) * | 2019-08-02 | 2019-11-12 | 中国地质调查局发展研究中心 | A kind of mineral resource prediction method and system based on neural network model |
| CN111274264A (en) * | 2020-01-16 | 2020-06-12 | 朱恒华 | Real-time transmission analysis system for water and soil detection indexes of mine geological environment |
| KR102211421B1 (en) * | 2020-06-17 | 2021-02-02 | 에스케이건설 주식회사 | Method and system for determining tbm control parameters based on prediction geological condition ahead of tunnel face |
| AU2020103698A4 (en) * | 2020-11-01 | 2021-02-04 | Anhui University of Science and Technology | Monitoring method for dynamic height of overburden failure during underground coal seam mining |
| CN112733780A (en) * | 2021-01-19 | 2021-04-30 | 哈尔滨航天恒星数据系统科技有限公司 | System and method for constructing soil available phosphorus analysis model based on satellite images |
| CN112986538A (en) * | 2021-05-06 | 2021-06-18 | 中南大学 | Large-area soil heavy metal detection and space-time distribution characteristic analysis method and system |
| CN114001684A (en) * | 2021-11-16 | 2022-02-01 | 信阳师范学院 | Soil erosion measuring system and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108761564A (en) * | 2018-08-07 | 2018-11-06 | 青海省地质调查院（（青海省地质矿产研究所）） | A kind of Cenozoic Magmatic Cu Polymetallic Mineralization Belt method |
| CN110824582A (en) * | 2019-11-22 | 2020-02-21 | 马忠元 | Comprehensive exploration method for polymetallic minerals |
-
2022
- 2022-02-10 CN CN202210123119.2A patent/CN114154627B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102841081A (en) * | 2012-08-30 | 2012-12-26 | 湖南科技大学 | Prediction method for distribution of each heavy metal in polluted flow on soil-water interface of non-ferrous metal orefield |
| CN106996969A (en) * | 2017-03-03 | 2017-08-01 | 北京农业质量标准与检测技术研究中心 | A kind of heavy metal-polluted soil spatial distribution Forecasting Methodology and system |
| CN110442666A (en) * | 2019-08-02 | 2019-11-12 | 中国地质调查局发展研究中心 | A kind of mineral resource prediction method and system based on neural network model |
| CN111274264A (en) * | 2020-01-16 | 2020-06-12 | 朱恒华 | Real-time transmission analysis system for water and soil detection indexes of mine geological environment |
| KR102211421B1 (en) * | 2020-06-17 | 2021-02-02 | 에스케이건설 주식회사 | Method and system for determining tbm control parameters based on prediction geological condition ahead of tunnel face |
| AU2020103698A4 (en) * | 2020-11-01 | 2021-02-04 | Anhui University of Science and Technology | Monitoring method for dynamic height of overburden failure during underground coal seam mining |
| CN112733780A (en) * | 2021-01-19 | 2021-04-30 | 哈尔滨航天恒星数据系统科技有限公司 | System and method for constructing soil available phosphorus analysis model based on satellite images |
| CN112986538A (en) * | 2021-05-06 | 2021-06-18 | 中南大学 | Large-area soil heavy metal detection and space-time distribution characteristic analysis method and system |
| CN114001684A (en) * | 2021-11-16 | 2022-02-01 | 信阳师范学院 | Soil erosion measuring system and method |
Non-Patent Citations (5)
| Title |
|---|
| Detection of oasis soil composition and analysis of environmental parameters based on hyperspectral image and GIS;Yingfeng Chen 等;《Arabian Journal of Geosciences》;20211231;1-13 * |
| 基于GIS 和BP神经网络的泥石流危险性分析——以延边州为例;卢雨溪 等;《科学技术创新》;20191231;58-59 * |
| 基于GIS与BP神经网络的矿区塌陷易发性预测;王绅皓 等;《煤矿安全》;20210930;第52卷(第9期);218-223、230 * |
| 基于双层神经网络与 GIS可视化的土壤重金属污染评价;王芬 等;《农业工程学报》;20100430;第26卷(第4期);162-168 * |
| 浅析土壤测量与土壤剖面测量在地质找矿上的应用;卢刚 等;《找矿技术》;20180331;95-96 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114154627A (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114154627B (en) | Soil profile measuring method and device based on GIS and double-layer neural network | |
| Xu et al. | Extraction and statistics of discontinuity orientation and trace length from typical fractured rock mass: A case study of the Xinchang underground research laboratory site, China | |
| Wellmann et al. | Uncertainties have a meaning: Information entropy as a quality measure for 3-D geological models | |
| Pinheiro et al. | Geostatistical simulation to map the spatial heterogeneity of geomechanical parameters: A case study with rock mass rating | |
| Yalcin | GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in Ardesen (Turkey): comparisons of results and confirmations | |
| Shamo et al. | Linear spatial interpolation and analysis of annual average daily traffic data | |
| Journel et al. | Evaluation of mineral reserves: a simulation approach | |
| CN104749624B (en) | A kind of seismic facies identification and its uncertain quantitative assessment synchronization realizing method | |
| Abbaszadeh Shahri et al. | A hybrid ensemble-based automated deep learning approach to generate 3D geo-models and uncertainty analysis | |
| CN102928877B (en) | Based on the seismic attribute fusion method of D-S evidence theory | |
| Yang et al. | Quantification of uncertainty associated with evidence layers in mineral prospectivity mapping using direct sampling and convolutional neural network | |
| Madani et al. | A hierarchical cosimulation algorithm integrated with an acceptance–rejection method for the geostatistical modeling of variables with inequality constraints | |
| Cornah et al. | Comparison of three geostatistical approaches to quantify the impact of drill spacing on resource confidence for a coal seam (with a case example from Moranbah North, Queensland, Australia) | |
| CN117741808A (en) | Geological crack detection method based on geological exploration | |
| Lima et al. | Assisted history-matching for the characterization and recovery optimization of fractured reservoirs using connectivity analysis | |
| Süzen | Data driven landslide hazard assessment using geographical information systems and remote sensing | |
| Lipp et al. | Geochemical mapping by unmixing alluvial sediments: An example from northern Australia | |
| Sharifi et al. | Efficiency evaluating of automatic lineament extraction by means of remote sensing (Case study: Venarch, Iran) | |
| Sekulić et al. | SPATIAL MULTI-CRITERIA EVALUATION METHOD FOR PLANNING OF OPTIMAL ROADS ALIGNMENTS, WITH EMPHASIZE ON ROBUSTNESS ANALYSIS. | |
| De Lima et al. | Characterization and modeling of the fault network of a Brazilian pre-salt reservoir and upscaling results | |
| Ramos et al. | Geostatistics for air quality mapping: Case of Baguio City, Philippines | |
| He et al. | Gaussian process model of surrounding rock classification based on digital characterization of rock mass structure and its application | |
| Houran et al. | USING GIS DATA AND MACHINE LEARNING FOR MINERAL MAPPING. STUDY CASE, BOU SKOUR EASTERN ANTI-ATLAS, MOROCCO | |
| Rowden et al. | A novel triggerless approach for mass wasting susceptibility modeling applied to the Boston Mountains of Arkansas, USA | |
| Singh et al. | Exploring Soil Spatial Variability with GIS, Remote Sensing, and Geostatistical Approach |
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 |