Mining area ecological restoration evaluation method based on remote sensing image

Abstract

The invention discloses a mining area ecological restoration evaluation method based on a remote sensing image, which is applied to the technical field of remote sensing image application, and comprises the following steps: acquiring Landsat image data of an ecological restoration mining area to be evaluated, and respectively calculating ecological restoration evaluation indexes, comprise a vegetation evaluation index, a humidity evaluation index, a bare soil evaluation index, a surface temperature evaluation index and a surface deformation evaluation index; constructing a time sequence prediction model obtained by fusing and weighting output results based on the ARMA model, the ARIMA model and the SARIMA model, and predicting an ecological restoration evaluation index in future time; and based on the characteristics of the mining area, screening a reference area, and based on the ecological restoration evaluation index of the to-be-evaluated ecological restoration mining area in the future time, the ecological restoration evaluation index of the to-be-evaluated ecological restoration mining area before damage and the ecological restoration evaluation index of the reference area, performing ecological restoration evaluation of the to-be-evaluated ecological restoration mining area in the future time. According to the method, the ecological restoration evaluation precision is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of remote sensing image application, and in particular to a mining area ecological restoration evaluation method based on remote sensing images. Background Art

[0003] With the continuous expansion of the scale of mine restoration and governance, studying the changes in the ecological environment of open-pit mines at different time and space scales, monitoring the coverage and growth of vegetation in mining areas, and reasonably evaluating the effectiveness of mine restoration are key issues that need to be solved in mining development. With the rise of satellite remote sensing monitoring technology, it has been widely used in the monitoring and evaluation of ecological restoration in mining areas due to its wide coverage, easy acquisition, and fast data update. Based on remote sensing images, obtaining ecological restoration influencing factors such as vegetation coverage to evaluate the ecological restoration of mining areas has become the current mainstream ecological restoration evaluation method. At present, the ecological restoration evaluation method based on remote sensing images has the following shortcomings: First, most of them focus on vegetation coverage as an influencing factor of ecological restoration, ignoring other influencing factors that can fully explain the degree of ecological restoration, resulting in insufficient accuracy of ecological restoration evaluation; second, there is a lack of ecological restoration evaluation in the time dimension, and it is impossible to effectively predict the ecological restoration situation in the future, resulting in insufficient reference for evaluating the effectiveness of mine restoration.

[0004] To this end, how to provide a mining area ecological restoration evaluation method based on remote sensing images that can fully consider the influencing factors of the degree of ecological restoration in mining areas, effectively improve the accuracy of ecological restoration evaluation, and effectively predict the ecological restoration in the future, make up for the shortcomings of existing ecological restoration evaluation methods in the time dimension, and provide more reference for evaluating the effectiveness of mine restoration is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0005] In view of this, the present invention proposes a mining area ecological restoration evaluation method based on remote sensing images.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A mining area ecological restoration evaluation method based on remote sensing images, including:

[0008] Step 1: Obtain Landsat image data of the ecological restoration mining area to be evaluated, perform preprocessing, and calculate the ecological restoration evaluation index of the ecological restoration mining area to be evaluated; the ecological restoration evaluation index includes: vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index, and surface deformation evaluation index;

[0009] Step 2: Construct a time series prediction model for the ecological restoration evaluation index, and predict the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future based on the time series prediction model; wherein the time series prediction model is obtained by fusion and weighting of the output results based on the ARMA model, the ARIMA model and the SARI MA model;

[0010] Step 3: Obtain the ecological restoration evaluation index of the mining area to be evaluated before it was destroyed, and based on the mining area characteristics before it was destroyed, screen the undamaged reference area within a preset range near the mining area to be evaluated, and conduct an ecological restoration evaluation of the mining area to be evaluated in the future based on the ecological restoration evaluation index of the mining area to be evaluated in the future, the ecological restoration evaluation index of the mining area to be evaluated before it was destroyed, and the ecological restoration evaluation index of the reference area.

[0011] Optionally, in step 1, preprocessing includes: radiation correction, atmospheric correction, mosaicking and cropping.

[0012] Optionally, in step 1, the vegetation evaluation index is calculated as follows:

[0013]

[0014] Among them, NDVI is the vegetation evaluation index; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band.

[0015] Optionally, in step 1, the calculation of the humidity evaluation index is as follows:

[0016] Wet=0.1511ρ Blue +0.1973ρ Green +0.3283ρ Red +0.3407ρ Nir -0.7117ρ Swir1 -0.4559ρ Swir2 ;

[0017] Among them, Wet is the humidity evaluation index; ρ Blue is the reflectivity of the blue band; ρ Green is the reflectivity of the green band; ρ Red is the reflectivity in the infrared band; ρ Nir is the reflectivity in the near-red band; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Swir2 is the reflectivity in the mid-infrared band 2.

[0018] Optionally, in step 1, the bare soil evaluation index is calculated as follows:

[0019] NDBSI=(IBI+SI) / 2;

[0020]

[0021] SI=[(ρ Swir1 +ρ Red )-(ρ Nir +ρ Blue )] / [(ρ Swir1 +ρ Red )+(ρ Nir +ρ Blue )];

[0022] Wherein, NDBSI is the bare soil evaluation index; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band; ρ Green is the reflectivity of the green band; ρ Blue is the reflectivity of the non-blue band.

[0023] Optionally, in step 1, the calculation of the surface temperature evaluation index is as follows:

[0024]

[0025] B(TS)=B(TS surface )+B(TS buliding );

[0026]

[0027] L 10 = gain × DN + bais;

[0028]

[0029] Among them, LST is the surface temperature evaluation index; K2 and K1 are calibration parameters; B(TS) is the overall blackbody radiation brightness value; B(TS surface ) is the black body radiation brightness value on the surface; B(TS buliding ) is the black body radiation brightness value of the building; L 10 is the radiation brightness value of the 10th band of the LandsatTIRS image; L↑ is the upward radiation brightness of the atmosphere; T is the transmittance of the atmosphere in the thermal infrared band; ε surface is the natural surface pixel emissivity; L↓ is the downward radiation brightness of the atmosphere; ε buliding is the relative emissivity of urban pixel; gain is the band gain value; DN is the pixel gray value; bais is the band offset value; P vis the vegetation coverage; NDVI is the vegetation evaluation index; NDVI Soli It is the NDVI value of completely bare soil or no vegetation cover area; NDVI Veg is the NDVI value of the pixel completely covered by vegetation.

[0030] Optionally, in step 1, the calculation of the surface deformation evaluation index is as follows:

[0031] SDI = |D(x)|;

[0032] Among them, SDI is the surface deformation evaluation index, and D(x) is the settlement value of the pixel.

[0033] Optionally, in step 2, a time series prediction model of the ecological restoration evaluation index is constructed, specifically:

[0034] Based on the ecological restoration evaluation index, the ARMA model, ARIMA model and SARIMA model were modeled and analyzed respectively, and the unknown parameters in the model were estimated and optimized until the standardized residual of the model was a normally distributed white noise sequence, and the ecological restoration evaluation index prediction model based on ARMA, ARIMA and SARIMA was obtained;

[0035] The output results of the ecological restoration evaluation index prediction models based on ARMA, ARIMA and SARIMA are weighted and fused to obtain the time series prediction model of the ecological restoration evaluation index, as follows:

[0036] I=α(ARMA)·S(ARMA)+α(ARIMA)·S(ARIMA)+α(SARIMA)·S(SARIMA);

[0037] Among them, I is the output result of the time series prediction model; S(ARMA), S(ARIMA) and S(SARIMA) are the output results of the ARMA model, ARIMA model and SARIMA model respectively; α(ARMA), α(ARIMA) and α(SARIMA) are the weights of the ARMA model, ARIMA model and SARIMA model respectively.

[0038] Optionally, in step 3, based on the mining area characteristics before the ecological restoration mining area to be evaluated is not damaged, an undamaged reference area within a preset range near the ecological restoration mining area to be evaluated is selected, specifically:

[0039] Mining area characteristics, including but not limited to: topography, slope and aspect, soil type, vegetation, temperature and rainfall;

[0040] Based on the mining area characteristics of the ecological restoration mining area to be evaluated before it was destroyed, the undamaged mining areas within the preset range near the ecological restoration mining area to be evaluated were screened by weighting the similarity of mining area characteristics, and the reference areas with a similarity greater than the preset threshold were obtained, as follows:

[0041] d i ≤r;

[0042] a i β a +b i β b +c i β c +e i β e +f i β f >g;

[0043] Among them, d i is the straight-line distance between the undamaged mining area i and the ecological restoration mining area to be evaluated; r is the radius of the preset range; a i 、b i 、c i 、e i 、f i are the topographic similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity between the undamaged mining area i and the ecological restoration mining area to be evaluated before the damage; β a , β b , β c , β e , β f are the weights of topography similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity respectively; g is the preset similarity threshold.

[0044] Optionally, in step 3, based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future, the ecological restoration evaluation index of the ecological restoration mining area to be evaluated before being destroyed, and the ecological restoration evaluation index of the reference area, an ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is conducted, specifically:

[0045] Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the ecological restoration mining area to be evaluated before being destroyed, the first ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out as follows:

[0046]

[0047] Among them, Z1 is the first ecological restoration evaluation; γ1, γ2, γ3, γ4, and γ5 are the weights of vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index, and surface deformation evaluation index, respectively; NDVI h 、Wet h 、NDBSI h , LST h 、SDI h They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated in the future; NDVI j 、Wet j 、NDBSI j , LST j 、SDI j They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated before it is destroyed;

[0048] Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the reference area, the second ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out as follows:

[0049]

[0050] Among them, Z2 is the second ecological restoration assessment; K is the number of reference areas; NDVI l.k 、Wet l.k 、NDBSI l.k , LST l.k 、SDI l.k They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the kth reference area respectively;

[0051] Based on the first ecological restoration evaluation and the second ecological restoration evaluation, the final ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is obtained by weighting, as follows:

[0052] Z=δ1Z1+δ2Z2;

[0053] Among them, Z is the final ecological restoration evaluation; δ1 and δ2 are the weights of the first and second ecological restoration evaluations, respectively.

[0054] Through the above technical solutions, it can be known that compared with the prior art, the present invention proposes a mining area ecological restoration evaluation method based on remote sensing images. By evaluating the mining area ecological restoration based on the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the mining area to be evaluated, the influencing factors of the degree of ecological restoration in the mining area are fully considered, and the accuracy of ecological restoration evaluation is effectively improved; by predicting the ecological restoration evaluation index of the mining area to be evaluated in the future time based on the time series prediction model obtained by fusion weighting of ARMA model, ARIMA model and SARI MA model, the deficiency of the existing ecological restoration evaluation method in the time dimension is made up, and more references are provided for evaluating the effectiveness of mine restoration; and, on the basis of taking the mining area to be evaluated before being destroyed as a reference, the present invention also screens similar mining areas within a preset range near the mining area to be evaluated based on the characteristics of the mining area, and uses the mining area to be evaluated before being destroyed as a reference for the mining area ecological restoration evaluation, further improving the accuracy of mining area ecological restoration evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0056] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Embodiment 1:

[0059] Embodiment 1 of the present invention discloses a method for evaluating ecological restoration of mining areas based on remote sensing images, such as Figure 1 As shown, including:

[0060] Step 1: Obtain Landsat image data of the ecological restoration mining area to be evaluated, perform preprocessing, and calculate the ecological restoration evaluation index of the ecological restoration mining area to be evaluated; the ecological restoration evaluation index includes: vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index.

[0061] Preprocessing, including: radiation correction, atmospheric correction, and mosaicking and cropping.

[0062] The calculation of vegetation evaluation index is as follows:

[0063]

[0064] Among them, NDVI is the vegetation evaluation index; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band.

[0065] In step 1, the calculation of humidity evaluation index is as follows:

[0066] Wet=0.1511ρ Blue +0.1973ρ Green +0.3283ρ Red +0.3407ρ Nir -0.7117ρ Swir1 -0.4559ρ Swir2 ;

[0067] Among them, Wet is the humidity evaluation index; ρ Blue is the reflectivity of the blue band; ρ Green is the reflectivity of the green band; ρ Red is the reflectivity in the infrared band; ρ Nir is the reflectivity in the near-red band; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Swir2 is the reflectivity in the mid-infrared band 2.

[0068] The calculation of bare soil evaluation index is as follows:

[0069] NDBSI=(IBI+SI) / 2;

[0070]

[0071] SI=[(ρ Swir1 +ρ Red )-(ρ Nir +ρ Blue )] / [(ρ Swir1 +ρ Red )+(ρ Nir +ρ Blue )];

[0072] Wherein, NDBSI is the bare soil evaluation index; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band; ρ Green is the reflectivity of the green band; ρ Blue is the reflectivity of the non-blue band.

[0073] The calculation of the surface temperature evaluation index is as follows:

[0074]

[0075] B(TS)=B(TS surface )+B(TS buliding );

[0076]

[0077] L 10 = gain × DN + bais;

[0078]

[0079] Among them, LST is the surface temperature evaluation index; K2 and K1 are calibration parameters; B(TS) is the overall blackbody radiation brightness value; B(TS surface ) is the black body radiation brightness value on the surface; B(TS buliding ) is the black body radiation brightness value of the building; L 10 is the radiation brightness value of the 10th band of the LandsatTIRS image; L↑ is the upward radiation brightness of the atmosphere; T is the transmittance of the atmosphere in the thermal infrared band; ε surface is the natural surface pixel emissivity; L↓ is the downward radiation brightness of the atmosphere; ε buliding is the relative emissivity of urban pixel; gain is the band gain value; DN is the pixel gray value; bais is the band offset value; Pv is the vegetation coverage; NDVI is the vegetation evaluation index; NDVI Soli It is the NDVI value of completely bare soil or no vegetation cover area; NDVI Veg is the NDVI value of the pixel completely covered by vegetation.

[0080] The calculation of the surface deformation evaluation index is as follows:

[0081] SDI = |D(x)|;

[0082] Among them, SDI is the surface deformation evaluation index, and D(x) is the settlement value of the pixel.

[0083] Step 2: Construct a time series prediction model for the ecological restoration evaluation index, and predict the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future based on the time series prediction model; wherein the time series prediction model is obtained by fusion and weighting of the output results of the ARMA model, ARIMA model and SARIMA model.

[0084] Construct a time series prediction model for the ecological restoration evaluation index, specifically:

[0085] Based on the ecological restoration evaluation index, the ARMA model, ARIMA model and SARIMA model were modeled and analyzed respectively, and the unknown parameters in the model were estimated and optimized until the standardized residual of the model was a normally distributed white noise sequence, and the ecological restoration evaluation index prediction model based on ARMA, ARIMA and SARIMA was obtained;

[0086] The output results of the ecological restoration evaluation index prediction models based on ARMA, ARIMA and SARIMA are weighted and fused to obtain the time series prediction model of the ecological restoration evaluation index, as follows:

[0087] I=α(ARMA)·S(ARMA)+α(ARIMA)·S(ARIMA)+α(SARIMA)·S(SARIMA);

[0088] Among them, I is the output result of the time series prediction model; S(ARMA), S(ARIMA) and S(SARIMA) are the output results of the ARMA model, ARIMA model and SARIMA model respectively; α(ARMA), α(ARIMA) and α(SARIMA) are the weights of the ARMA model, ARIMA model and SARIMA model respectively.

[0089] Step 3: Obtain the ecological restoration evaluation index of the mining area to be evaluated before it was destroyed, and based on the mining area characteristics before it was destroyed, screen the undamaged reference area within a preset range near the mining area to be evaluated, and conduct an ecological restoration evaluation of the mining area to be evaluated in the future based on the ecological restoration evaluation index of the mining area to be evaluated in the future, the ecological restoration evaluation index of the mining area to be evaluated before it was destroyed, and the ecological restoration evaluation index of the reference area.

[0090] Based on the characteristics of the mining area before the ecological restoration to be evaluated, the undamaged reference area within the preset range near the ecological restoration mining area to be evaluated is selected, specifically:

[0091] Mining area characteristics, including but not limited to: topography, slope and aspect, soil type, vegetation, temperature and rainfall;

[0092] Based on the mining area characteristics of the ecological restoration mining area to be evaluated before it was destroyed, the undamaged mining areas within the preset range near the ecological restoration mining area to be evaluated were screened by weighting the similarity of mining area characteristics, and the reference areas with a similarity greater than the preset threshold were obtained, as follows:

[0093] d i ≤r;

[0094] a i β a +b i β b +c i β c +e i β e +f i β f >g;

[0095] Among them, d i is the straight-line distance between the undamaged mining area i and the ecological restoration mining area to be evaluated; r is the radius of the preset range; a i 、b i 、c i 、e i 、f i are the topographic similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity between the undamaged mining area i and the ecological restoration mining area to be evaluated before the damage; β a , β b , β c , β e , β f are the weights of topography similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity respectively; g is the preset similarity threshold.

[0096] Based on the ecological restoration evaluation index of the mining area to be evaluated in the future, the ecological restoration evaluation index of the mining area to be evaluated before being destroyed, and the ecological restoration evaluation index of the reference area, the ecological restoration evaluation of the mining area to be evaluated in the future is carried out, specifically:

[0097] Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the ecological restoration mining area to be evaluated before being destroyed, the first ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out as follows:

[0098]

[0099] Among them, Z1 is the first ecological restoration evaluation; γ1, γ2, γ3, γ4, and γ5 are the weights of vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index, and surface deformation evaluation index, respectively; NDVI h 、Wet h 、NDBSI h , LST h 、SDI h They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated in the future; NDVI j 、Wet j 、NDBSI j , LST j 、SDI j They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated before it is destroyed;

[0100] Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the reference area, the second ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out as follows:

[0101]

[0102] Among them, Z2 is the second ecological restoration assessment; K is the number of reference areas; NDVI l.k 、Wet l.k 、NDBSI l.k , LST l.k 、SDI l.k They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the kth reference area respectively;

[0103] Based on the first ecological restoration evaluation and the second ecological restoration evaluation, the final ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is obtained by weighting, as follows:

[0104] Z=δ1Z1+δ2Z2;

[0105] Among them, Z is the final ecological restoration evaluation; δ1 and δ2 are the weights of the first and second ecological restoration evaluations, respectively.

[0106] The embodiment of the present invention discloses a mining area ecological restoration evaluation method based on remote sensing images. The mining area ecological restoration evaluation is performed based on the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the mining area to be evaluated for ecological restoration, and the influencing factors of the degree of ecological restoration in the mining area are fully considered, and the accuracy of ecological restoration evaluation is effectively improved; the ecological restoration evaluation index of the mining area to be evaluated for ecological restoration in the future is predicted based on the time series prediction model obtained by fusion weighting of ARMA model, ARIMA model and SARIMA model, which makes up for the shortcomings of the existing ecological restoration evaluation method in the time dimension and provides more reference basis for evaluating the effectiveness of mine restoration; and the present invention, on the basis of taking the mining area to be evaluated for ecological restoration before being destroyed as a reference, also screens the similarity mining areas within a preset range near the mining area to be evaluated for ecological restoration based on the characteristics of the mining area, and uses the mining area to be evaluated for ecological restoration before being destroyed as a reference for mining area ecological restoration evaluation, thereby further improving the accuracy of mining area ecological restoration evaluation.

[0107] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0108] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A mining area ecological restoration evaluation method based on remote sensing images, characterized in that: include: Step 1: Obtain Landsat image data of the ecological restoration mining area to be evaluated, perform preprocessing, and calculate the ecological restoration evaluation index of the ecological restoration mining area to be evaluated; wherein the ecological restoration evaluation index includes: vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index; Step 2: construct a time series prediction model for the ecological restoration evaluation index, and predict the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future based on the time series prediction model; wherein the time series prediction model is obtained by fusion and weighting of the output results of the ARMA model, the ARIMA model and the SARIMA model; Step 3: Obtain the ecological restoration evaluation index of the mining area to be evaluated for ecological restoration before it was destroyed, and based on the mining area characteristics of the mining area to be evaluated for ecological restoration before it was destroyed, screen an undamaged reference area within a preset range near the mining area to be evaluated for ecological restoration, and conduct an ecological restoration evaluation of the mining area to be evaluated for ecological restoration in the future based on the ecological restoration evaluation index of the mining area to be evaluated for ecological restoration in the future, the ecological restoration evaluation index of the mining area to be evaluated for ecological restoration before it was destroyed, and the ecological restoration evaluation index of the reference area.

2. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 1, the preprocessing includes: radiation correction, atmospheric correction, mosaicking and cropping.

3. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1 is characterized in that: In step 1, the vegetation evaluation index is calculated as follows: Among them, NDVI is the vegetation evaluation index; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band.

4. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 1, the calculation of the humidity evaluation index is as follows: Wet=0.1511ρ Blue +0.1973r Green +0.3283r Red +0.3407r Nir -0.7117r Swir1 -0.4559r Swir2 ; Among them, Wet is the humidity evaluation index; ρ Blue is the reflectivity of the blue band; ρ Green is the reflectivity of the green band; ρ Red is the reflectivity in the infrared band; ρ Nir is the reflectivity in the near-red band; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Swir2 is the reflectivity in the mid-infrared band 2.

5. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 1, the bare soil evaluation index is calculated as follows: NDBSI=(IBI+SI) / 2; SI=[(ρ Swir1 +r Red )-(p Nir +r Blue )] / [(ρ Swir1 +r Red )+(ρ Nir +r Blue )]; Wherein, NDBSI is the bare soil evaluation index; ρ Swir1 is the reflectivity of mid-infrared band 1; ρ Nir is the reflectivity in the near-red band; ρ Red is the reflectivity in the infrared band; ρ Green is the reflectivity of the green band; ρ Blue is the reflectivity of the non-blue band.

6. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 1, the calculation of the surface temperature evaluation index is as follows: B(TS)=B(TS surface )+B(TS buliding ); L 10 =gain×DN+discount; Among them, LST is the surface temperature evaluation index; K2 and K1 are calibration parameters; B(TS) is the overall blackbody radiation brightness value; B(TS surface ) is the black body radiation brightness value on the surface; B(TS buliding ) is the black body radiation brightness value of the building; L 10 is the radiation brightness value of the 10th band of the Landsat TIRS image; L↑ is the upward radiation brightness of the atmosphere; T is the transmittance of the atmosphere in the thermal infrared band; ε surface is the natural surface pixel emissivity; L↓ is the downward radiation brightness of the atmosphere; ε buliding is the relative emissivity of urban pixel; gain is the band gain value; DN is the pixel gray value; bais is the band offset value; P v is the vegetation coverage; NDVI is the vegetation evaluation index; NDVI Soli It is the NDVI value of completely bare soil or no vegetation cover area; NDVI Veg is the NDVI value of the pixel completely covered by vegetation.

7. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 1, the calculation of the surface deformation evaluation index is as follows: SDI = |D(x)|; Among them, SDI is the surface deformation evaluation index, and D(x) is the settlement value of the pixel.

8. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 2, a time series prediction model of the ecological restoration evaluation index is constructed, specifically: Based on the ecological restoration evaluation index, modeling and analysis of the ARMA model, the ARIMA model and the SARIMA model are performed respectively, and the unknown parameters in the model are estimated and optimized until the standardized residual of the model is a normally distributed white noise sequence, and the ecological restoration evaluation index prediction model based on ARMA, ARIMA and SARIMA is obtained; The output results of the ecological restoration evaluation index prediction model based on ARMA, ARIMA and SARIMA are weighted and fused to obtain the time series prediction model of the ecological restoration evaluation index, as follows: I=α(ARMA)·S(ARMA)+α(ARIMA)·S(ARIMA)+α(SARIMA)·S(SARIMA); Wherein, I is the output result of the time series prediction model; S(ARMA), S(ARIMA), and S(SARIMA) are the output results of the ARMA model, the ARIMA model, and the SARIMA model, respectively; α(ARMA), α(ARIMA), and α(SARIMA) are the weights of the ARMA model, ARIMA model, and SARIMA model, respectively.

9. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 3, based on the mining area characteristics of the ecological restoration mining area to be evaluated before it was destroyed, an undamaged reference area within a preset range near the ecological restoration mining area to be evaluated is selected, specifically: The mining area characteristics include but are not limited to: topography, slope and aspect, soil type, vegetation, temperature and rainfall; Based on the mining area characteristics of the ecological restoration mining area to be evaluated before it was destroyed, the undamaged mining areas within a preset range near the ecological restoration mining area to be evaluated are screened by weighting the similarity of mining area characteristics to obtain reference areas with a similarity greater than a preset threshold, as follows: d i ≤r； a i b a +b i b b +c i b c +e i b e +f i b f >g; Among them, d i is the straight-line distance between the undamaged mining area i and the ecological restoration mining area to be evaluated; r is the radius of the preset range; a i , b i 、c i 、e i 、f i are the topographic similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity between the undamaged mining area i and the ecological restoration mining area to be evaluated before the damage; β a , β b , β c , β e , β f are the weights of topography similarity, slope and aspect similarity, soil type similarity, vegetation similarity, and temperature and rainfall similarity respectively; g is the preset similarity threshold.

10. The method for evaluating ecological restoration of mining areas based on remote sensing images according to claim 1, characterized in that: In step 3, based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future, the ecological restoration evaluation index of the ecological restoration mining area to be evaluated before being destroyed, and the ecological restoration evaluation index of the reference area, the ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out, specifically: Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the ecological restoration mining area to be evaluated before being destroyed, the first ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is carried out as follows: Among them, Z1 is the first ecological restoration evaluation; γ1, γ2, γ3, γ4, and γ5 are the weights of vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index, and surface deformation evaluation index, respectively; NDVI h 、Wet h 、NDBSI h , LST h 、SDI h They are respectively the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated in the future; NDVI j 、Wet j 、NDBSI j , LST j 、SDI j They are respectively the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the ecological restoration mining area to be evaluated before it is destroyed; Based on the ecological restoration evaluation index of the ecological restoration mining area to be evaluated in the future and the ecological restoration evaluation index of the reference area, a second ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is conducted as follows: Among them, Z2 is the second ecological restoration assessment; K is the number of reference areas; NDVI l.k 、Wet l.k 、NDBSI l.k , LST l.k 、SDI l.k They are the vegetation evaluation index, humidity evaluation index, bare soil evaluation index, surface temperature evaluation index and surface deformation evaluation index of the kth reference area respectively; Based on the first ecological restoration evaluation and the second ecological restoration evaluation, the final ecological restoration evaluation of the ecological restoration mining area to be evaluated in the future is obtained by weighting, as follows: Z=δ1Z1+δ2Z2; Among them, Z is the final ecological restoration evaluation; δ1 and δ2 are the weights of the first and second ecological restoration evaluations, respectively.

Images