A method and system for evaluating the intensity of land cover change in polar regions

Abstract

The present disclosure proposes a method and system for evaluating the intensity of land cover changes in polar regions, including the following steps: obtaining remote sensing image data of the polar region to be identified; using the random forest method to classify the remote sensing data to obtain bare rock and water information in the polar region; using the visual interpretation method to extract the outer edge of the glacier in the polar region to be identified, and using the threshold method to identify the glacier type; performing spatial overlay analysis on the glacier area, rock mass and water body area obtained from the remote sensing image data obtained in different periods to obtain the change area, and calculating the intensity of land cover changes. The present disclosure uses remote sensing images as a data source to obtain the land cover changes in key areas, classifies the land cover in the Antarctic coastal zone, and combines the application of spatial analysis methods and statistical analysis methods to realize the analysis of the intensity of land cover changes in the polar coastal zone.

Description

Technical Field

[0001] The present disclosure relates to the technical field related to remote sensing technology, and in particular, to a method and system for evaluating the intensity of land cover changes in polar regions. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] With the development of remote sensing and GIS technology, LUCC (land use / land cover change) research has gradually deepened and expanded. This method has been used in different fields such as land management, ecological monitoring, and environmental protection to carry out related research. Existing land cover change evaluation methods are mainly applied to land, and the constructed indicator system is also mainly based on terrestrial land cover types. Statistical analysis methods are usually used to evaluate the changes in land use type area per unit time, focusing on changes in land cover attributes and emphasizing the direct role of people in land cover changes. These methods are not applicable to polar regions in terms of classification system and indicator system. At the same time, the evaluation targets are mainly based on direct human effects, and are not applicable to polar regions.

[0004] Antarctica is an important cold source in the world. Its surface cover is sensitive to global climate change. At the same time, changes in Antarctic surface cover have an important counter-effect on global climate change. Antarctic surface cover changes are most active in the land-sea combination area at the edge of the continent, which has unique surface cover characteristics. Existing land use / cover change (LUCC) evaluation models are mainly applicable to land areas with strong human interference, with the research goal of reflecting the intensity of dynamic changes in land use / cover. Commonly used LUCC models include land use change rate models, land use degree change models and land use quantity change models. Existing models, whether classification systems or evaluation index systems, are only applicable to low-latitude land areas and cannot be applied to polar regions where few people go. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for evaluating the intensity of land cover changes in polar regions, which uses remote sensing images as a data source to obtain land cover changes in key areas, classifies land cover in the Antarctic coastal zone, and combines spatial analysis methods and statistical analysis methods to realize the intensity analysis of land cover changes in the polar coastal zone.

[0006] In order to achieve the above objectives, the present disclosure adopts the following technical solutions:

[0007] One or more embodiments provide a method for evaluating the intensity of land cover change in polar regions, comprising the following steps:

[0008] Acquire remote sensing image data of the polar regions to be identified;

[0009] Based on remote sensing data, random forest method is used to classify and obtain information on bare rocks and water bodies in polar regions;

[0010] Based on remote sensing data, visual interpretation is used to extract the outer edge of the glaciers in the polar regions to be identified, and the threshold method is used to identify the glacier types.

[0011] Spatial superposition analysis was performed on the glacier areas, rock areas and water areas obtained from remote sensing image data acquired in different periods to obtain the change areas and calculate the intensity of surface cover change.

[0012] One or more embodiments provide a system for evaluating the intensity of land cover change in polar regions, including:

[0013] An acquisition module: configured to acquire remote sensing image data of a polar region to be identified;

[0014] The first recognition module is configured to classify the remote sensing data using the random forest method to obtain the bare rock and water information in the polar region;

[0015] The second identification module is configured to extract the outer edge of the glacier in the polar region to be identified by visual interpretation based on the remote sensing data, and identify the glacier type by using a threshold method;

[0016] Analysis module: It is configured to perform spatial overlay analysis on glacier areas, rock areas and water areas obtained from remote sensing image data acquired in different periods, obtain change areas, and calculate the intensity of surface cover change.

[0017] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps described in the above method are completed.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] By extracting different information from remote sensing data, dividing them into bare rock water bodies and glacier areas, and using different methods to identify them, we can accurately identify the land cover types in the polar regions and improve the accuracy of identification. We can obtain the intensity of land cover changes in the polar coastal areas and, based on the intensity of the changes, monitor and evaluate climate change in the Antarctic region, thereby achieving global climate anomaly monitoring.

[0020] The advantages of the present disclosure and the advantages of additional aspects will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The exemplary embodiments of the present disclosure and the description thereof are used to explain the present disclosure but do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of a method for evaluating the intensity of land cover change in Example 1 of the present disclosure;

[0023] Figure 2 is a flow chart of a random forest classification method according to Embodiment 1 of the present disclosure;

[0024] Figure 3 It is the Erase and Intersect identification block diagram of Embodiment 1 of the present disclosure. DETAILED DESCRIPTION

[0025] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0027] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof. It should be noted that, in the absence of conflict, the various embodiments in the present disclosure and the features in the embodiments can be combined with each other. The embodiments will be described in detail below in conjunction with the accompanying drawings.

[0028] The evaluation model disclosed in the present invention uses satellite remote sensing data as a data source, obtains long-term series land cover data, establishes a land cover classification system for the Antarctic region, and combines spatial analysis methods to evaluate the intensity of changes in surface cover in the Antarctic coastal zone based on the rate of change of surface cover type area, thereby achieving climate change monitoring and evaluation. This is explained below with a specific embodiment.

[0029] Example 1

[0030] In the technical solutions disclosed in one or more embodiments, Figure 1 As shown, a method for evaluating the intensity of land cover change in polar regions includes the following steps:

[0031] Step 100: Acquire remote sensing image data of the polar region to be identified and pre-process;

[0032] Step 200: Based on the collected remote sensing data, the random forest method is used for classification to obtain the bare rock and water body information in the polar region;

[0033] Step 300: extracting the outer edge of the glacier in the polar region to be identified using a visual interpretation method based on the collected remote sensing data, and identifying the glacier type using a threshold method;

[0034] Step 400: Perform spatial overlay analysis on the glacier area, rock mass and water body area obtained from remote sensing image data acquired in different periods to obtain the change area, and calculate the intensity of the surface cover change.

[0035] In this embodiment, different information is extracted from the remote sensing data, which is divided into bare rock water bodies and glacier areas, and different methods are used for identification, so that the land cover types in the polar regions can be accurately identified, the accuracy of identification can be improved, and the intensity of land cover changes in the polar coastal zone can be obtained. Based on the intensity of changes, climate change monitoring and evaluation in the Antarctic region can be achieved, thereby realizing global climate anomaly monitoring.

[0036] In step 100, the method of obtaining and preprocessing remote sensing image data of polar regions is as follows:

[0037] 101. Determine the time period for collecting remote sensing data and determine the area for data collection.

[0038] Optionally, HY-1C / 1D (Ocean No. 1) and GF (Gaofen) (No. 1-4, No. 3 is C-band SAR image, and the others are multispectral and panchromatic images) satellite remote sensing data are used as data sources. The remote sensing data includes multispectral and panchromatic images, and C-band SAR images (GF3 images).

[0039] Specifically, the collection of remote sensing data can choose February of each year as the data window period.

[0040] The remote sensing data collection time of this embodiment is set to the Antarctic summer, when the amount of sea ice in the coastal zone is relatively the least, and the days are long and the nights are short, which is conducive to visible light data imaging. The collected data include HY-1C / 1D and GF series remote sensing images, and the cloud coverage threshold for visible light data is set to less than 10%.

[0041] The data collection area can be specifically as follows: visible light data needs to cover a set distance to land and a fixed ice range to sea, and SAR data needs to cover the entire polar region to be identified. The set distance to land can be several kilometers, such as 5 kilometers.

[0042] Specifically, the regional division can be as follows: collect the vector data of the Antarctic coastline, and use the coastline as the benchmark to make a buffer zone of 5 kilometers inland and to the outer edge of the sea ice. Starting from the South Pole 0°E, the longitude 15° is used as the dividing buffer zone to form 24 sector-shaped polar regions to be identified.

[0043] Step 102, a method for preprocessing remote sensing image data, using a unified mathematical reference to perform geometric correction and radiation correction on the remote sensing data.

[0044] Specifically, the unified mathematical reference may adopt the Stereographic_South_Pole projection and the GCS_WGS_1984 earth coordinate system.

[0045] The land cover categories of the Antarctic coastal zone can be divided according to the surface cover characteristics of the Antarctic coastal zone. The land cover categories include glaciers (01), icebergs (02), fast ice (03), floating ice (04), bare rocks (05), sea water (06), etc.

[0046] Surface cover information extraction, using HY-1C / 1D, GF series multispectral images, remote sensing software ENVI / IDL and Weka software, based on the processed data, the random forest method is used to classify the polar surface cover and obtain the prediction results. The random forest method is used to complete the training and supervised classification of bare rock and water samples to be identified in the polar regions.

[0047] Specifically, based on the random forest classification method, the evolutionary tree resampling method is used to extract multiple samples from the original sample, a decision tree model is built for each evolutionary tree sample, and then multiple decision trees are combined to make predictions, and the final prediction result is obtained by voting.

[0048] Optional, random forest based classification step, such as Figure 2 As shown, including the following:

[0049] Step 201: obtain original data samples, randomly select sample 1, sample 2, ... sample n from the original input, and form a new training set S to replace the original data samples;

[0050] Step 202: randomly select a portion of samples from S as an evolutionary tree training set to form a one-to-one corresponding regression tree;

[0051] Step 203: Based on the acquired polar region remote sensing data, a voting method is used to determine the classification result of each classification tree.

[0052] Using the GF3 imagery obtained from remote sensing, namely the C-band SAR imagery, and taking historical data as reference, the visual interpretation method is used to extract the outer edge of the glacier in the polar region to be identified.

[0053] Among them, the method of extracting the outer edge of the glacier in the polar region to be identified by using the visual interpretation method includes the following steps:

[0054] Step 301: The glacier has obvious morphological features on the SAR image. Based on historical data and expert knowledge or experience, the outer edge of the glacier at the beginning of the study is determined to form the vector data of the glacier in the initial period.

[0055] Step 302: Based on the GF3 images of different periods, the outer edge line of the glacier is modified on the basis of the vector data of the initial period of the glacier to form the glacier data sets of each period.

[0056] The method of identifying the glacier surface according to the determined glacier outer edge by the threshold method, including the method of identifying and extracting icebergs, fixed ice and floating ice, comprises the following steps:

[0057] Step 311: For each period of glacier data set, the remote sensing image data of each period is grayed, and ArcGIS is used to distinguish glacier types according to the gray value. The glacier types include icebergs, fixed ice and floating ice.

[0058] ArcGIS is a desktop application geographic information system platform that integrates many functions such as spatial data display, editing, query retrieval, statistics, report generation, spatial analysis and advanced mapping.

[0059] Among them, in the process of distinguishing glacier types according to grayscale values, the grayscale value intervals corresponding to icebergs, fast ice and floating ice can be determined based on the collected historical data.

[0060] Since icebergs, fixed ice and floating ice have different thicknesses, their grayscale values ​​on SAR images are different. By obtaining the grayscale intervals of the three types of surface cover through sample statistics, the efficiency and accuracy of recognition can be greatly improved compared to manual recognition.

[0061] Step 312: According to the spatial distribution characteristics and discreteness characteristics of the glacier-type land cover, the areas corresponding to the divided glacier types are manually corrected to obtain the glacier-type land cover data set and determine the glacier area.

[0062] Furthermore, spatial overlay analysis of glacier areas, rock masses, and water areas obtained from remote sensing image data acquired in different periods can be combined with expert experience for further manual intervention and classification correction to form a land cover classification dataset for each period.

[0063] Specifically, ArcGIS was used to perform spatial overlay analysis on the same type of surface data from two adjacent periods using the Erase tool and the Intersect tool. The Erase and Intersect identification diagrams are shown in the figure. Figure 3As shown in the figure, the unchanged area (area represented by α), the area increased (area represented by β) and the area decreased (area represented by γ) are extracted, the area is counted to form a vector data set, and the area data after superposition analysis is statistically analyzed to obtain the land cover classification data set for each period.

[0064] In step 400, specifically, the intensity of change of the land cover in the polar coastal zone is calculated based on the rate of change of the land cover type area.

[0065] The change intensity of a single land cover type is: the sum of the area of ​​the increased area and the area of ​​the decreased area of ​​a certain land cover type is the first area, the sum of the area of ​​the unchanged area and the area of ​​the decreased area is the second area, and the ratio of the first area to the second area is the change intensity of the corresponding land cover type, which is expressed as follows:

[0066] ∈ i =(β+γ) / (α+γ)

[0067] ∈ i Represents the intensity of land cover change of the i-th type.

[0068] The comprehensive land cover type change intensity formula is expressed as:

[0069]

[0070] ∈ represents the comprehensive intensity of land cover change.

[0071] If the land cover has not changed, ∈ is 0, and if ∈ is greater than 1, it is a drastic change. The specific classification table is as follows:

[0072] ∈Interval Strength classification 0 No change 0-0.2 Mild 0.2-0.5 Moderate 0.5-0.8 Strong 0.8-1 powerful ＞1 severe

[0073] If the evaluation result is moderate or below, it means that the climate difference between the two periods is basically at a normal level; if the evaluation result is strong, it means that the climate difference between the two periods is slightly abnormal; if the evaluation result is strong, it means that the climate difference between the two periods is relatively obvious and needs to be paid attention to; if the evaluation result is severe, it means that the climate difference between the two periods is large and we need to be vigilant about global climate anomalies.

[0074] Example 2

[0075] Based on Example 1, this embodiment provides a system for evaluating the intensity of land cover changes in polar regions, including:

[0076] An acquisition module: configured to acquire remote sensing image data of a polar region to be identified;

[0077] The first recognition module is configured to classify the remote sensing data using the random forest method to obtain the bare rock and water information in the polar region;

[0078] The second identification module is configured to extract the outer edge of the glacier in the polar region to be identified by visual interpretation based on the remote sensing data, and identify the glacier type by using a threshold method;

[0079] Analysis module: It is configured to perform spatial overlay analysis on glacier areas, rock areas and water areas obtained from remote sensing image data acquired in different periods, obtain change areas, and calculate the intensity of surface cover change.

[0080] Example 3

[0081] Based on Example 1, this embodiment provides an electronic device, characterized in that it includes a memory and a processor, and computer instructions stored in the memory and running on the processor, and when the computer instructions are executed by the processor, the steps described in the method of the above embodiment are completed.

[0082] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0083] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A method for evaluating the intensity of land cover change in polar regions, characterized in that: The steps include: Acquire remote sensing image data of the polar regions to be identified; Based on remote sensing data, random forest method is used to classify and obtain information on bare rocks and water bodies in polar regions; Based on remote sensing data, visual interpretation is used to extract the outer edge of the glaciers in the polar regions to be identified, and the threshold method is used to identify the glacier types. Spatial superposition analysis was performed on the glacier areas, rock mass and water body areas obtained from remote sensing image data acquired at different times to obtain the change areas and calculate the intensity of surface cover change; The intensity of land cover change in the polar coastal zone is calculated based on the rate of change of land cover type area. The change intensity of a single surface cover type is: the sum of the area of ​​the increased area and the area of ​​the decreased area of ​​a certain surface cover type is the first area, the sum of the area of ​​the unchanged area and the area of ​​the decreased area is the second area, and the ratio of the first area to the second area is the change intensity of the corresponding surface cover type.

2. The method for evaluating the intensity of land cover change in polar regions according to claim 1, characterized in that: Land cover types include glaciers, icebergs, fast ice, floating ice, bare rock, and seawater.

3. The method for evaluating the intensity of land cover change in polar regions according to claim 1, characterized in that: Obtain remote sensing image data of the polar region to be identified, specifically: Determine the period of remote sensing data collection based on the climate of the polar region, and divide the data collection area into sectors centered at the poles; The collected remote sensing image data is subjected to geometric correction and radiation correction using a unified mathematical reference.

4. The method for evaluating the intensity of land cover change in polar regions according to claim 1, characterized in that: Based on the classification of random forest method, multiple samples are extracted from the original sample using the evolutionary tree resampling method, decision tree modeling is performed on each evolutionary tree sample, and then multiple decision trees are combined to make predictions, and the final prediction result is obtained by voting.

5. The method for evaluating the intensity of land cover change in polar regions according to claim 1, characterized in that: The method of extracting the outer edge of the glacier in the polar region to be identified by visual interpretation includes the following steps: Based on historical data and expert knowledge or experience, determine the outer edge of the glacier at the beginning of the study period to form the vector data of the initial period of the glacier; Based on remote sensing image data from different periods, the glacier outer edge line is modified on the basis of the vector data of the initial period of the glacier to form glacier data sets for each period.

6. A method for evaluating the intensity of land cover change in polar regions according to claim 5, characterized in that: The method of identifying the glacier surface according to the determined glacier outer edge by the threshold method, including the method of identifying and extracting icebergs, fixed ice and floating ice, comprises the following steps: For the glacier edge of each period, the remote sensing image data of each period was grayed out, and ArcGIS was used to distinguish the glacier types according to the gray value; According to the spatial distribution characteristics and discrete features of glacier-type surface cover, the areas corresponding to the divided glacier types are artificially corrected to determine the glacier areas.

7. A method for evaluating the intensity of land cover change in polar regions according to claim 6, characterized in that: A spatial overlay analysis was performed on the glacier areas, rock bodies and water bodies obtained from remote sensing image data acquired in different periods. Specifically, ArcGIS was used to perform spatial overlay analysis on the same type of surface data in two adjacent periods using the Erase tool and the Intersect tool to obtain a land cover classification dataset.

8. A surface cover change intensity assessment system for polar regions, characterized in that: include: An acquisition module: configured to acquire remote sensing image data of a polar region to be identified; The first recognition module is configured to classify the remote sensing data using the random forest method to obtain the bare rock and water information in the polar region; The second identification module is configured to extract the outer edge of the glacier in the polar region to be identified by visual interpretation based on the remote sensing data, and identify the glacier type by using a threshold method; Analysis module: configured to perform spatial overlay analysis on glacier areas, rock bodies and water bodies obtained from remote sensing image data acquired at different times, obtain change areas, and calculate the intensity of surface cover change; The intensity of land cover change in the polar coastal zone is calculated based on the rate of change of land cover type area. The change intensity of a single surface cover type is: the sum of the area of ​​the increased area and the area of ​​the decreased area of ​​a certain surface cover type is the first area, the sum of the area of ​​the unchanged area and the area of ​​the decreased area is the second area, and the ratio of the first area to the second area is the change intensity of the corresponding surface cover type.

9. An electronic device, characterized in that: The method comprises a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps described in any one of the methods of claims 1 to 7 are completed.

Images