Method and apparatus for using transfer learning to locate igneous carbonate rock-type rare earth deposits

1 . A transfer learning positioning method for igneous carbonate-type rare earth mineralization, comprising:

acquiring electrical, magnetic, seismic, and gravity exploration data for a target area;

performing transfer learning positioning on the electrical, magnetic, seismic, and gravity exploration data to determine a cross-sectional image corresponding to an abnormal position of the electrical, magnetic, seismic, and gravity exploration data associated with an igneous carbonate-type rare earth mineralization in the target area;

performing feature decomposition and dimension reduction, feature enhancement, and weighted fusion processing on the cross-sectional image;

segmenting a spatial occurrence form of the igneous carbonate-type rare earth mineralized geological body in the cross-sectional image after the weighted fusion processing to obtain a spatial occurrence form of the igneous carbonate-type rare earth mineralized geological body in the target area;

wherein the transfer learning positioning of the electrical, magnetic, seismic, and gravity exploration data comprises:

analyzing the electrical, magnetic, seismic, and gravity exploration data to obtain data volumes corresponding to electrical resistivity anomalies, magnetization anomalies, velocity anomalies, and density anomalies for igneous carbonate-type rare earth mineralization; and

performing location identification on the data volumes corresponding to the electrical resistivity anomalies, magnetization anomalies, velocity anomalies, and density anomalies, respectively; and

wherein the cross-sectional image corresponding to the location identification of the respective anomalies comprises:

a digital cross-sectional image of the electrical resistivity anomaly, a digital cross-sectional image of the magnetization anomaly, a digital cross-sectional image of the velocity anomaly, and a digital cross-sectional image of the density anomaly.

2 . The method according to claim 1 , wherein determining the cross-sectional image corresponding to the abnormal position of the data for the igneous carbonate-type rare earth mineralization in the target area comprises:

generating digital cross-sectional images of electrical resistivity anomaly, magnetization anomaly, velocity anomaly, and density anomaly at the same depth for the data volumes corresponding to electrical resistivity anomalies, magnetization anomalies, velocity anomalies, and density anomalies, respectively;

configuring the digital cross-sectional images of the electrical resistivity anomaly, magnetization anomaly, velocity anomaly, and density anomaly in a common coordinate system.

3 . The method according to claim 1 , wherein performing feature decomposition and dimension reduction on the cross-sectional image comprises:

using a transfer learning selection network to perform stepwise dimension reduction on the input signal and output the reduced feature, performing initial feature extraction on the digital cross-sectional images of the electrical resistivity anomaly, magnetization anomaly, velocity anomaly, and density anomaly, respectively, to obtain reduced features at different scales for each image.

4 . The method according to claim 3 , wherein performing feature enhancement on the cross-sectional image comprises:

calculating the initial feature correlation coefficient between different scales of reduced features using Spearman correlation for each image;

removing irrelevant initial features based on the comparison result between the correlation coefficient and the coefficient threshold to obtain enhanced features.

5 . The method according to claim 4 , wherein performing weighted fusion processing on the enhanced cross-sectional image comprises:

calculating an initial weight matrix corresponding to each cross-sectional image using the local nuclear norm and average operation;

performing interpolation operation using the soft-max operation and bicubic interpolation on the initial weight matrix to obtain weight coefficients corresponding to each cross-sectional image;

maintaining the structural information and detail information of each cross-sectional image using the a local energy map algorithm;

using similarity measurement as a fusion decision value and using a weighted averaging fusion rule to compare the fusion results calculated by the local energy calculation.

6 . Method as claimed in claim 4 , characterized in that for each image at different scales, the initial feature correlation calculated using Spearman correlation includes:

The Spearman correlation coefficient of the initial features of M output channels of the i-th layer convolution module is used to represent:

The Spearman correlation coefficient

r

s

k

 is used to represent the correlation between the initial features

F

i

,

1

:

M

i

k

 of the i-th layer convolution module outputting M channels,

r

S

k

=

1

-

6

⁢

∑

i

=

1

M

d

2

M

⁡

(

M

2

-

1

)

where d is the rank difference between

F

i

,

p

k

⁢

and

⁢

F

i

,

q

k

,

 p,q∈{1,2,L,M i }; k represents the image category number; the minimum number of features is selected with

r

s

k

 as the selected features after feature selection, represented by

F

i

,

1

:

C

k

.

7 . The method as described in claim 5 , characterized by: performing weighted fusion processing on the enhanced sectional images, comprising: calculating the initial weight matrix

S

i

,

*

k

of the image using local nuclear norm and average operation according to the following formula:

S

i

,

*

k

(

x

,

y

)

=

∑

p

=

x

-

t

p

=

x

+

t

∑

q

=

y

-

t

q

=

y

+

t



F

)

i

,

1

:

C

k

(

p

,

q

)



*

(

2

⁢

t

+

1

)

·

(

2

⁢

t

+

1

)

where p,q∈{1,2,L,M i }, x, and y represent the pixel coordinates, t represents the step size for iterating over all pixels, and k represents the image category number, The following equation is used to perform interpolation of the weight matrix using soft-max operation and bicubic interpolation to obtain weight coefficients

ω

i

k

:

ω

i

k

(

x

,

y

)

=

S

i

,

*

k

(

x

,

y

)

S

i

,

*

1

(

x

,

y

)

+

S

i

,

*

2

(

x

,

y

)

,

k

∈

{

1

,

2

}

Considering the specificity and locality of underground targets, Local Energy Map is used to preserve the structural and detailed information of the image:

LE

k

(

x

,

y

)

=

∑

m

∑

n

L

⁢

{

I

k

}

⁢

(

x

+

m

,

y

+

n

)

2

where LE k (x,y) represents the total energy map function, L{Ik} represents the local energy map function, m×n represents the size of the neighbourhood, and the similarity measurement between I 1 and I 2 is calculated as the fusion decision value using the following equation:

M

⁡

(

x

,

y

)

=

2

⁢

∏

k

=

1

,

2

(

∑

m

∑

n

L

⁢

{

I

k

}

⁢

(

x

+

m

,

y

+

n

)

)

∑

k

=

1

,

2

LE

k

(

x

,

y

)

Let M(x,y)∈[−1,1] be the similarity measure between I 1 and I 2 , where a value closer to 1 indicates a stronger similarity between the images, Set a threshold value T, if M(x,y)<T, then use the weighted averaging fusion rule to calculate the fusion result:

F

M

<

T

(

x

,

y

)

=

ω

i

1

(

x

,

y

)

⁢

I

1

(

x

,

y

)

+

ω

i

2

(

x

,

y

)

⁢

I

2

(

x

,

y

)

If M(x,y)≥T, then the fusion result is calculated by comparing the local energy:

F

M

≥

T

(

x

,

y

)

=

{

L

⁢

{

I

1

}

⁢

(

x

,

y

)

,

if

⁢

LE

1

(

x

,

y

)

≥

LE

2

(

x

,

y

)

L

⁢

{

I

2

}

⁢

(

x

,

y

)

,

if

⁢

LE

1

(

x

,

y

)

<

LE

2

(

x

,

y

)

The fusion strategy is represented as:

F

⁡

(

x

,

y

)

=

{

F

M

<

T

(

x

,

y

)

,

if

⁢

M

⁡

(

x

,

y

)

<

T

F

M

≥

T

(

x

,

y

)

,

if

⁢

M

⁡

(

x

,

y

)

≥

T

.