Land utilization change monitoring method based on big data

Abstract

The invention relates to the technical field of data processing, in particular to a land utilization change monitoring method based on big data, and the method comprises the steps: collecting each item of data and land utilization rate data of each region, obtaining the influence degree of each item of data on the land utilization rate, dividing each region into region combinations, according to the influence degree of each item of data on the land utilization rate and the correlation of each item of data of each region combination, obtaining a weight adjustment factor of each region combination, and according to the weight adjustment factor of each region combination and the initial weight of each region combination, obtaining an adjustment weight of each region combination, according to the land resource utilization rate of each region at the latest sampling moment and the adjustment weight of each region combination, the Moran index of each region at the latest sampling moment is obtained, and then the abnormal region is obtained, and the accuracy of abnormal region identification is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a land use change monitoring method based on big data. Background Art

[0002] With the continuous growth of the global population and the acceleration of urbanization, the development and utilization of land resources are facing unprecedented pressure. Land use changes not only affect the ecological environment, but also have a profound impact on social and economic development, sustainable management and resource allocation. Traditional land use monitoring methods usually rely on manual surveys or low-frequency remote sensing data collection, which is difficult to reflect changes in real time and comprehensively, and is less efficient in dynamic and complex natural environments. Therefore, land use change monitoring methods based on big data have received more and more attention, and related research and applications have shown important value in agriculture, environmental protection, urban planning and other fields. These methods provide managers with real, reliable and timely data support, promote the realization of sustainable development goals, and promote the scientific and intelligent process of land use management.

[0003] The patent document with the current authorization announcement CN108564520B proposes a GIS vector data copyright authentication method based on the Moran index. By taking advantage of the stable spatial autocorrelation characteristics of geographic elements in GIS vector data and the characteristic that zero watermark uses important features of the original work to construct the original watermark signal, a zero watermark is constructed through the Moran index for copyright authentication of GIS vector data.

[0004] The Moran Index is an indicator that describes the autocorrelation between land utilization rate and land spatial position, and can be used to determine whether there are abnormal or unreasonable land utilization in each region based on the correlation. However, when detecting the abnormal land utilization in each region through the Moran Index, the weight in the Moran Index only considers the distance between the two regions, that is, the geographical location of the two regions, and ignores other influencing factors between the two regions, such as the total area of ​​the region, precipitation, etc. This will result in inaccurate Moran Index for each region, and thus the monitoring of the abnormal land utilization in each region through the Moran Index is not complete and accurate enough. Summary of the invention

[0005] In order to solve the problem that the weight in the Moran index only considers the distance between two areas and ignores other influencing factors between the two areas, resulting in inaccurate Moran index of each area, which affects the anomaly detection, the present invention proposes a land use change monitoring method based on big data, which includes the following steps: Collect each data and land utilization rate data of each area; obtain the influence of each data on land utilization rate; divide each area into various area combinations; Get the weight adjustment factor for each region combination: , represents the weight adjustment factor of the i-th regional combination; Represents the mean of the correlation of all item data of the i-th region combination; Represents the impact of the j-th data on land utilization rate; Represents the absolute value of the difference between the jth data values ​​of the two regions in the i-th region combination at the k-th sampling time; represents the mean of the absolute values ​​of the differences between the j-th data values ​​of two regions in the i-th region combination at all sampling times; J represents the number of data items; K represents the number of sampling times; The product of the weight adjustment factor of each regional combination and the initial weight of each regional combination is used as the adjustment weight of each regional combination; according to the adjustment weight of each regional combination, the Moran index of each region at the latest sampling time is obtained; based on the Moran index, the abnormal area is obtained.

[0006] The innovation of the present invention lies in that the present invention analyzes various influencing factors between different regions to obtain the degree of influence of each data on land utilization, so as to facilitate the subsequent adjustment of the initial weights of each regional combination by obtaining the weight adjustment factor according to the degree of influence of each data on land utilization, and calculate the Moran's index of each region according to the adjusted initial weight, thereby making the calculation of the Moran's index more accurate and the detection of unreasonable utilization of each region more accurate.

[0007] Preferably, obtaining the influence of each data on land utilization rate includes: ; In the formula, Represents the impact of the j-th data on land utilization rate; Represents the number of sampling moments; Represents the number of regions; Represents the jth data value of the nth region at the kth sampling moment; Represents the mean of the j-th data of all regions at the k-th sampling time; Represents the land utilization rate data value of the nth area at the kth sampling time; Represents the mean of the land utilization data of all regions at the kth sampling time; exp() represents an exponential function with a natural constant as the base.

[0008] This will facilitate the subsequent acquisition of the weight adjustment factor for each regional combination based on the impact of each data on land utilization.

[0009] Preferably, the dividing of the regions into region combinations comprises: Any two regions are recorded as a region combination, and several region combinations are obtained.

[0010] Preferably, obtaining the correlation of all item data of the region combination includes: Each data item of each area at all sampling moments is recorded as each data sequence of each area in turn; the Pearson correlation coefficient between each data sequence of two areas in the ith area combination is taken as the Pearson correlation coefficient of the jth data item of the ith area combination; the value of the Pearson correlation coefficient of the jth data item of the ith area combination plus one and divided by two is taken as the correlation of the jth data item of the ith area combination.

[0011] The greater the correlation of all item data of the regional combination, the greater the weight adjustment factor of the regional combination.

[0012] Preferably, the acquisition of the initial weights of the region combinations includes: The centroid of each region is obtained, and the distance between the centroids of two regions in any region combination is obtained as the initial weight of the region combination.

[0013] Preferably, the obtaining of the Moran index of each region at the latest sampling time according to the adjusted weight of each region combination includes: The Moran index of each region at the latest sampling moment is obtained according to the land resource utilization rate of each region at the latest sampling moment and the adjustment weight of each regional combination.

[0014] Improved the accuracy of the Moran Index.

[0015] Preferably, obtaining the abnormal area includes: A threshold T of abnormality is preset. If the abnormality of any area at the latest sampling moment is greater than the threshold T, the area is an abnormal area. At this time, an early warning is issued and the land resources of the area are replanned.

[0016] The obtained abnormal area is more accurate.

[0017] Preferably, the collecting of each data item and land utilization rate data of each area includes: The preset sampling time is one week / time, and the collection time is one year. The precipitation, humidity, and altitude of each area are collected through mobile meteorological equipment. The average slope, total area, etc. of each area are collected through field measurements to obtain each data of each area at each sampling time; The land utilization data of each area is collected through field measurement to obtain the land utilization data of each area at each sampling time.

[0018] The present invention has the following beneficial effects: the purpose of the present invention is to obtain the degree of influence of each data on land utilization rate by analyzing various influencing factors between different regions, so as to facilitate the subsequent adjustment of the initial weights of each regional combination by obtaining the weight adjustment factor according to the degree of influence of each data on land utilization rate, and calculate the Moran's index of each region according to the adjusted initial weight, thereby making the calculation of the Moran's index more accurate and the detection of unreasonable utilization of each region more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a flowchart of the steps of the land use change monitoring method based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0022] See also Figure 1 , which shows a flow chart of the steps of a land use change monitoring method based on big data provided by an embodiment of the present invention, the method comprising the following steps: S001. Collect every data and land utilization data of each area.

[0023] In the embodiment of the present invention, the land use monitoring area is divided into regions according to subjective experience to obtain a plurality of regions; The preset sampling time is one week / time, and the collection time is one year. The precipitation, humidity, and altitude of each area are collected through mobile meteorological equipment. The average slope, total area, etc. of each area are collected through field measurements to obtain each data of each area at each sampling time; The land utilization data of each area is collected through field measurement to obtain the land utilization data of each area at each sampling time.

[0024] It should be noted that each data of each region is time-series aligned with the land utilization data of each region.

[0025] S002. Obtain the impact of each data item on land utilization rate.

[0026] It should be noted that the Moran's index is an indicator that describes the autocorrelation between land utilization rate and land spatial position, and it can be used to determine whether there are abnormal or unreasonable land utilization in each region based on the correlation. However, when detecting the abnormal land utilization in each region through the Moran's index, the weight in the Moran's index only considers the distance between the two regions, that is, the geographical location of the two regions, and ignores other influencing factors between the two regions, such as the total area of ​​the region, precipitation, etc. This will result in inaccurate Moran's index for each region, and thus the monitoring of the abnormal land utilization in each region through the Moran's index is not complete and accurate enough.

[0027] It should be further explained that it is known that the degree of influence of each data on land utilization is different. Therefore, the present invention first needs to obtain the degree of influence of the data on the land utilization rate based on the similarity between any data and the land utilization data in all regions at all sampling times. The greater the similarity, the greater the influence of the data on the land utilization rate.

[0028] In this embodiment of the present invention, the influence degree of the j-th data on the land utilization rate is obtained: ; In the formula, Represents the impact of the j-th data on land utilization rate; Represents the number of sampling moments; Represents the number of regions; Represents the jth data value of the nth region at the kth sampling moment; Represents the mean of the j-th data of all regions at the k-th sampling time; Represents the land utilization rate data value of the nth area at the kth sampling time; represents the mean of the land utilization rate data of all regions at the kth sampling time; exp() represents an exponential function with a natural constant as the base; It represents the similarity between the j-th data and the land utilization rate data of the n-th region at the k-th sampling time. The closer the ratio is to 1, the higher the similarity between the j-th data and the land utilization rate data of the n-th region at the k-th sampling time, and the smaller the impact of the j-th data on the land utilization rate. Therefore, the similarity between the j-th data and the land utilization rate data of all regions at all sampling times is comprehensively considered to obtain the impact of the j-th data on the land utilization rate.

[0029] S003. Divide each region into various regional combinations, and obtain a weight adjustment factor for each regional combination according to the influence of each data on the land utilization rate and the relevance of each data in each regional combination.

[0030] It should be noted that since the weight in the Moran Index only considers the distance between two regions to obtain the initial weight between the two regions, and does not take into account other influencing factors between the two regions, it is necessary to first divide each region into several region combinations to obtain the weight adjustment factor of each region combination and adjust the initial weight of each region combination.

[0031] The logic for obtaining the weight adjustment factor of each regional combination is as follows: the greater the correlation of each data of any regional combination, the greater the weight adjustment factor of the regional combination, and the greater the fluctuation of any data between two regions in the regional combination at all sampling times, the smaller the correlation between the two regions in the regional combination, and the smaller the weight adjustment factor of the regional combination. However, if the data has a greater impact on land utilization, it means that more attention should be paid to the fluctuation of any data between the two regions in the regional combination at all sampling times.

[0032] In the embodiment of the present invention, any two regions are recorded as a region combination, and a plurality of region combinations are obtained; Each data item of each region at all sampling moments is recorded as each data item sequence of each region in turn; the Pearson correlation coefficient between each data item sequence of two regions in the ith regional combination is taken as the Pearson correlation coefficient of the jth data item of the ith regional combination; the value of the Pearson correlation coefficient of the jth data item of the ith regional combination plus one and divided by two is taken as the correlation of the jth data item of the ith regional combination; Get the weight adjustment factor for the i-th region combination: ; In the formula, represents the weight adjustment factor of the i-th regional combination; Represents the mean of the correlation of all item data of the i-th region combination; Represents the impact of the j-th data on land utilization rate; Represents the absolute value of the difference between the jth data values ​​of the two regions in the i-th region combination at the k-th sampling time; represents the mean of the absolute values ​​of the differences between the j-th data values ​​of two regions in the i-th region combination at all sampling times; J represents the number of data items; K represents the number of sampling times; Represents the correlation degree of the j-th data of the i-th regional combination at the current sampling time. The larger its value is, the more correlated the j-th data of the two regions in the i-th regional combination are, and the larger the weight adjustment factor of the i-th regional combination at the current sampling time is; Represents the fluctuation degree of the j-th data of the two regions in the i-th regional combination at all sampling times. The larger its value is, the lower the correlation of the j-th data of the two regions in the i-th regional combination is, and the smaller the weight adjustment factor of the i-th regional combination is. At this time, if the j-th data has a greater impact on the land utilization rate, it means that more attention should be paid to the fluctuation degree of the j-th data of the two regions in the i-th regional combination at all sampling times. Therefore Used for The value of is corrected; finally, the weight adjustment factor of the i-th regional combination is obtained by considering the fluctuation degree of all item data of the two regions in the i-th regional combination at all sampling times.

[0033] S004. According to the weight adjustment factor of each regional combination and the initial weight of each regional combination, the adjusted weight of each regional combination is obtained. According to the land resource utilization rate of each region at the latest sampling time and the adjusted weight of each regional combination, the Moran index of each region at the latest sampling time is obtained, and then the abnormal area is obtained.

[0034] It should be noted that, after correcting the initial weight of each regional combination according to the weight adjustment factor of each regional combination, the adjusted weight of each regional combination is obtained. Finally, the Moran's index of each region is obtained according to the adjusted weight of each regional combination and the land resource utilization rate of each region at the current sampling time. The abnormal land use situation of each region is detected by the Moran's index.

[0035] In the embodiment of the present invention, the centroid of each region is obtained, and the distance between the centroids of two regions in any region combination is obtained as the initial weight of the region combination; the weight adjustment factor of the i-th region combination is multiplied by the initial weight of the i-th region combination to obtain the adjusted weight of the i-th region combination; the Moran index of each region at the latest sampling time is obtained according to the land resource utilization rate of each region at the latest sampling time and the adjusted weight of each region combination; Construct a box plot of the Moran index of each area at the latest sampling time to obtain the degree of abnormality of each area at the latest sampling time; An abnormality threshold T is preset. If the abnormality level of any area at the latest sampling moment is greater than the abnormality threshold T, the area is an abnormal area. At this time, an early warning is issued in time and land resources in the area are replanned. In the embodiment of the present invention, T=0.7 is preset. In other embodiments, the implementer can preset the value of T according to the specific implementation situation.

[0036] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A land use change monitoring method based on big data, characterized in that: include: Collect every data and land utilization data of each area; Obtain the impact of each data on land utilization; Divide each area into various area combinations; Get the weight adjustment factor for each region combination: , represents the weight adjustment factor of the i-th regional combination; Represents the mean of the correlation of all item data of the i-th region combination; Represents the impact of the j-th data on land utilization rate; Represents the absolute value of the difference between the jth data values ​​of the two regions in the i-th region combination at the k-th sampling time; represents the mean of the absolute values ​​of the differences between the j-th data values ​​of two regions in the i-th region combination at all sampling times; J represents the number of data items; K represents the number of sampling times; The product of the weight adjustment factor of each regional combination and the initial weight of each regional combination is used as the adjustment weight of each regional combination; according to the adjustment weight of each regional combination, the Moran index of each region at the latest sampling time is obtained; based on the Moran index, the abnormal area is obtained.

2. The land use change monitoring method based on big data according to claim 1 is characterized in that: The influence degree of each data on land utilization rate includes: ； In the formula, Represents the impact of the j-th data on land utilization rate; Represents the number of sampling moments; Represents the number of regions; Represents the jth data value of the nth region at the kth sampling moment; Represents the mean of the j-th data of all regions at the k-th sampling time; Represents the land utilization rate data value of the nth area at the kth sampling time; Represents the mean of the land utilization data of all regions at the kth sampling time; exp() represents an exponential function with a natural constant as the base.

3. The land use change monitoring method based on big data according to claim 1 is characterized in that: The division of each area into various area combinations includes: Any two regions are recorded as a region combination, and several region combinations are obtained.

4. The land use change monitoring method based on big data according to claim 1 is characterized in that: The acquisition of the correlation of all item data of the regional combination includes: Each data item of each area at all sampling moments is recorded as each data sequence of each area in turn; the Pearson correlation coefficient between each data sequence of two areas in the ith area combination is taken as the Pearson correlation coefficient of the jth data item of the ith area combination; the value of the Pearson correlation coefficient of the jth data item of the ith area combination plus one and divided by two is taken as the correlation of the jth data item of the ith area combination.

5. The land use change monitoring method based on big data according to claim 1 is characterized in that: The acquisition of the initial weights of the regional combinations includes: The centroid of each region is obtained, and the distance between the centroids of two regions in any region combination is obtained as the initial weight of the region combination.

6. The land use change monitoring method based on big data according to claim 1 is characterized in that: The method of obtaining the Moran index of each region at the latest sampling time according to the adjusted weight of each region combination includes: The Moran index of each region at the latest sampling moment is obtained according to the land resource utilization rate of each region at the latest sampling moment and the adjustment weight of each regional combination.

7. The land use change monitoring method based on big data according to claim 1 is characterized in that: The obtaining of the abnormal area comprises: A threshold T of abnormality is preset. If the abnormality of any area at the latest sampling moment is greater than the threshold T, the area is an abnormal area. At this time, an early warning is issued and the land resources of the area are replanned.

8. The land use change monitoring method based on big data according to claim 1 is characterized in that: The data collected for each area and the land utilization rate data include: The preset sampling time is one week / time, and the collection time is one year. The precipitation, humidity, and altitude of each area are collected through mobile meteorological equipment. The average slope, total area, etc. of each area are collected through field measurements to obtain each data of each area at each sampling time; The land utilization data of each area is collected through field measurement to obtain the land utilization data of each area at each sampling time.

Images