Bayesian model grassland degradation risk remote sensing diagnosis method and device

Abstract

The invention discloses a bayesian model grassland degradation risk remote sensing diagnosis method and device. The method comprises the following steps: acquiring one or more of vegetation coverage, above-ground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, above-ground biomass change trend, net primary productivity change trend and evapotranspiration change trend of a target area acquired according to an observation period by using a remote sensing technology as input data; and inputting the input data into a pre-constructed Bayesian model, and outputting an estimation result of the grassland degradation risk level through the Bayesian model. By adopting the technical scheme, the grassland degradation risk level can be objectively evaluated by integrating the various data and utilizing the Bayesian model, a unified evaluation result is obtained, and a data basis is conveniently provided for grassland degradation condition understanding and treatment.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a remote sensing diagnosis method, device, medium and system for grassland degradation risk based on a Bayesian model. Background Art

[0002] Grassland degradation is one of the main manifestations of desertification. It is a phenomenon in which climate or human interference exceeds the threshold of the self-regulating capacity of grassland ecosystems, making it difficult for them to recover and developing in the opposite direction, resulting in reverse succession changes. The intuitive manifestations of grassland degradation are vegetation degradation and soil degradation, among which vegetation degradation is more sensitive and rapid than soil degradation. Vegetation degradation is manifested in individuals as a decrease in vegetation height and coverage, and in community structure as a decrease in vegetation components, an increase in degradation indicator species, a decrease in grassland dominant species, and a decrease in aboveground biomass. At the regional scale, vegetation degradation is manifested in a decrease in vegetation coverage, a decrease in the yield of high-quality forage, a decrease in grassland productivity, and a decrease in grassland quality. .

[0003] At present, there is no unified standard for grassland degradation risk assessment. There are problems such as inconsistent grading index benchmarks, unclear grassland degradation thresholds, and low precision in quantitative inversion of grassland parameters. Therefore, although some scholars have put forward academic research reports, due to inconsistent standards, it is impossible to form an effective grassland degradation risk assessment and diagnosis mechanism. Summary of the invention

[0004] The embodiment of the present application provides a remote sensing diagnosis method and device for grassland degradation risk based on a Bayesian model. This solution can solve the problems existing in the prior art, such as the inconsistency of grassland degradation risk assessment, the inability to form an effective assessment report and the inability to provide diagnostic opinions. The present invention proposes a remote sensing diagnosis method, device, medium and system for grassland degradation risk based on a Bayesian model. The method uses remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; the input data is input into a pre-constructed Bayesian model, and the estimated result of the grassland degradation risk level is output through the Bayesian model. By adopting the technical solution provided by the present invention, the above-mentioned multiple data can be integrated, and the grassland degradation risk level can be objectively evaluated using the Bayesian model to obtain a unified evaluation result, which is convenient for providing a data basis for understanding and managing grassland degradation.

[0005] The present application embodiment provides a remote sensing diagnosis method for grassland degradation risk based on the Yes model, the method comprising: Using remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The input data is input into a pre-built Bayesian model, and the estimated result of grassland degradation risk level is output through the Bayesian model.

[0006] Furthermore, the training process of the Bayesian model includes: Build an initial model; The data collected according to the preset period is used as sample data, and the initial model is used to conduct nonlinear quantitative risk assessment on the grassland degradation risk level of the target period; The nonlinear quantitative risk assessment is evaluated using data actually collected during the target period, and the parameters of the initial model are adjusted according to the evaluation results to obtain a Bayesian model with an accuracy rate that meets the requirements.

[0007] Furthermore, the vegetation coverage is calculated using the normalized vegetation index in remote sensing data; The aboveground biomass is calculated using a random forest model using remote sensing data and MODIS red, blue, near-infrared bands and NDVI, DVI, SAVI, RVI, and EVI vegetation indices; The net primary productivity is calculated from photosynthetically active radiation and actual light energy utilization efficiency, wherein the photosynthetically active radiation is calculated based on the absorption ratio of total solar radiation and photosynthetically active radiation; The evapotranspiration includes the amount of water evaporated from vegetation and land surface.

[0008] Furthermore, the vegetation coverage change trend is determined by the following formula: ; Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

[0009] Furthermore, the aboveground biomass variation trend is determined using the following formula: ; Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

[0010] Furthermore, the net primary productivity change trend is determined by the following formula: ; Where n is the statistical year number and i is the statistical year; is the average net primary productivity of the grid cell in year i, is the changing trend of net primary productivity of a single pixel.

[0011] Furthermore, the evapotranspiration variation trend is determined by the following formula: ; Where n is the statistical year number and i is the statistical year; is the average evapotranspiration of the grid cell in year i; is the changing trend of evapotranspiration of a single pixel.

[0012] The present application embodiment provides a Bayesian model grassland degradation risk remote sensing diagnosis device, the device comprising: An input data acquisition module is used to use remote sensing technology to acquire one or more of vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The prediction module is used to input the input data into a pre-built Bayesian model, and output an estimated result of the grassland degradation risk level through the Bayesian model.

[0013] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the Bayesian model grassland degradation risk remote sensing diagnosis method as described in the embodiment of the present application is implemented.

[0014] An embodiment of the present application also provides a Bayesian model grassland degradation risk remote sensing diagnosis system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the Bayesian model grassland degradation risk remote sensing diagnosis method provided in the embodiment of the present application.

[0015] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: The technical solution provided in this application can adopt the "state + trend" method to select eight remote sensing parameters, including vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, and the corresponding change trends of the above four indicators, to construct a remote sensing assessment index system for grassland degradation risk. The Bayesian network model is introduced to diagnose grassland ecological degradation risks, realizing nonlinear assessment of grassland degradation risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a flow chart of the remote sensing diagnosis method of grassland degradation risk using a Bayesian model provided in Example 1 of the present application; Figure 2a This is a schematic diagram of the grassland degradation risk level assessment results of a certain region in 2010 provided in Example 1 of the present application; Figure 2b This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2015 provided in Example 1 of the present application; Figure 2c This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2020 provided in Example 1 of the present application; Figure 2d This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2022 provided in Example 1 of the present application; Figure 3 It is a schematic diagram of the structure of the Bayesian model grassland degradation risk remote sensing diagnosis device provided in Example 2 of the present application; Figure 4 It is a structural schematic diagram of an electronic device provided in Example 5 of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0018] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0019] Embodiment 1 Figure 1 It is a flow chart of the Bayesian model grassland degradation risk remote sensing diagnosis method provided in Example 1 of the present application. This embodiment is applicable to the situation of grassland degradation risk assessment. The method can be executed by the Bayesian model grassland degradation risk remote sensing diagnosis device provided in the embodiment of the present application. The device can be implemented by software and / or hardware, and can be integrated into an electronic device for remote sensing diagnosis of grassland degradation risk based on the Bayesian model.

[0020] like Figure 1 As shown, the method includes: S110, using remote sensing technology to obtain one or more of vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend, and evapotranspiration change trend of the target area collected according to the observation period as input data; Among them, remote sensing data refers to the information obtained by observing the earth's surface through remote sensing technology using sensors installed on various remote sensing platforms (such as satellites, aircraft, drones, etc.). These sensors can detect and record electromagnetic radiation signals reflected, emitted or scattered by surface objects in different bands (such as visible light band, infrared band, microwave band, etc.), and then convert these signals into data formats that can be analyzed and processed. Common ones include image data (for example, satellite images look like pictures) and spectral curve data.

[0021] For example, the sensors carried by the Landsat series of satellites can obtain image data in multiple bands, such as multispectral images containing blue light bands, green light bands, red light bands, near-infrared bands, etc., which can clearly present the characteristics of different surface objects in different bands (such as vegetation presenting specific colors and texture characteristics, water bodies showing low reflectivity in the near-infrared band, etc.); for example, synthetic aperture radar (SAR) satellites (such as Sentinel-1 satellites) use microwave bands for observations and can obtain radar images of the surface without being affected by weather conditions (cloudy days, fog, etc.), which is especially suitable for monitoring the structure of terrain, oceans and vegetation-covered areas.

[0022] Remote sensing data can obtain surface information of a large area at one time, unlike traditional ground observations that can only obtain limited and scattered point data. For example, it can quickly obtain information such as vegetation distribution and land use in the entire province or even the entire country, which is convenient for macro-ecological environment analysis and resource management. Different remote sensing platforms have their own revisit cycles (which will be explained in detail when introducing the observation cycle later). The same area can be observed again after a certain time interval, so as to facilitate the acquisition of time series data for analyzing the dynamic changes of surface objects, such as monitoring the growth changes of crops at different stages of the growing season, the expansion process of cities, etc. It can provide data in multiple bands, and different bands reflect different physical and chemical properties of surface objects. By comprehensively analyzing these band information, it is possible to more accurately identify the type of objects and estimate related ecological parameters (such as the use of different bands to calculate vegetation coverage and estimate biomass, etc.).

[0023] The observation period refers to the time arrangement for the remote sensing platform to repeatedly observe the same target area at a certain time interval, which is often called the revisit period. It is mainly affected by factors such as the orbit design of the remote sensing platform itself and the mission requirements. For example, the observation period is 1 day, 15 days, 1 month, or 1 year, which also needs to be determined in combination with the actual operation of the satellite.

[0024] For example, the Landsat 8 satellite has a revisit period of approximately 16 days, which means that under ideal conditions, it can obtain image data for the same geographic location again every 16 days; the Sentinel-2 satellite has a shorter revisit period of approximately 5 days (a shorter revisit period can be achieved when multiple satellites are networked for collaborative observation), which enables it to observe surface changes more frequently, which is very beneficial for monitoring rapidly changing objects (such as vegetation damage in areas affected by sudden natural disasters, growth changes caused by short-term crop diseases and insect pests, etc.).

[0025] Some high-orbit meteorological satellites, such as the Fengyun-3 series satellites, are mainly used to obtain global meteorological data. Their observation period is relatively long and they may conduct global observations in hours. The focus is on continuously monitoring the dynamic changes of meteorological elements such as atmospheric temperature, humidity, and cloud cover.

[0026] In one embodiment, the vegetation coverage is calculated using the normalized vegetation index in remote sensing data; The aboveground biomass is calculated using a random forest model using remote sensing data and MODIS red, blue, near-infrared bands and NDVI, DVI, SAVI, RVI, and EVI vegetation indices; The net primary productivity is calculated from photosynthetically active radiation and actual light energy utilization efficiency, wherein the photosynthetically active radiation is calculated based on the absorption ratio of total solar radiation and photosynthetically active radiation; The evapotranspiration includes the amount of water evaporated from vegetation and land surface.

[0027] Among them, vegetation coverage is a comprehensive quantitative indicator of the surface coverage of plant communities and an important parameter for describing vegetation communities and ecosystems. There is a close relationship between vegetation coverage and grassland degradation. High vegetation coverage usually means that vegetation is lush, while low vegetation coverage means that vegetation is sparse or degraded. Grassland degradation is negatively correlated with vegetation coverage.

[0028] Vegetation coverage is obtained by inverting remote sensing data. First, NDVI is calculated, and then the relationship between vegetation coverage and NDVI is used to calculate vegetation coverage using the following formula.

[0029] ; Where NDVI represents the NDVI value of the mixed pixel, and are the NDVI values ​​of pure vegetation and bare soil pixels, respectively.

[0030] Aboveground biomass refers to the biological mass of plants per unit area, which is usually used to measure the growth status and productivity of vegetation. Aboveground biomass can well describe the growth of surface plants, and aboveground biomass has a negative correlation with grassland degradation. This study used ground-measured data, combined with the red, blue, and near-infrared bands of MODIS, and five vegetation indices including NDVI, DVI, SAVI, RVI, and EVI, and used a random forest model to invert the aboveground biomass of Xilin Gol League.

[0031] Net Primary Production (NPP) refers to the amount of organic matter accumulated by green plants per unit area and per unit time, and is an important indicator of vegetation productivity. It directly reflects the production capacity of vegetation itself and the community under natural conditions, and is a reference for judging carbon cycles and pathways. Grassland degradation may lead to a decrease in vegetation coverage, a decrease in vegetation biomass, and a decrease in productivity, which in turn affects the level of NPP. Therefore, NPP is a key indicator for evaluating grassland vegetation growth and grassland degradation.

[0032] The CASA model is a light energy utilization model that fully considers environmental factors and vegetation characteristics and is widely used in NPP estimation. Photosynthetically active radiation (APAR) and actual light energy utilization rate (ɛ) are the two decisive variables of the CASA model. The calculation formula of the CASA model is as follows: ; Where APAR (x, t) and ɛ (x, t) represent the photosynthetically active radiation and actual light energy utilization efficiency of pixel x in month t, respectively. APAR is determined by the total solar radiation (SOL) and the photosynthetically active radiation absorption ratio (FPAR): ; SOL (x, t) and FPAR (x, t) represent the absorption ratio of total solar radiation and photosynthetically active radiation of x pixel in month t, respectively. Solar radiation is the direct energy source for NPP through photosynthesis. In alpine areas, the shielding effect of terrain on solar radiation leads to spatial differences in light and thermal conditions. The visible light that can be absorbed and utilized by plants accounts for about 50%, so 0.5 is used as the ratio of photosynthetically active radiation to total solar radiation. ɛ is determined by the temperature stress coefficient (T ɛ1 , T ɛ2 ) and the water stress coefficient (W ɛ )Decide: ; in, The maximum light energy utilization efficiency of vegetation is an important parameter in the CASA model. Different vegetation types have different maximum light energy utilization efficiencies. Temperature and moisture stress coefficient and The three parameters jointly determine the actual light energy utilization.

[0033] Evapotranspiration is an important parameter of surface water and heat balance, which indicates the amount of water evaporated from vegetation and land surface. Grassland degradation refers to the process in which the structure and function of vegetation in grassland ecosystems deteriorate due to human or natural factors. When evapotranspiration decreases, the moisture content on the land surface may increase, leading to changes in soil moisture, which in turn affects the growth and recovery capacity of grassland vegetation.

[0034] In one embodiment, the vegetation coverage change trend is determined using the following formula: ; Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

[0035] In one embodiment, the aboveground biomass variation trend is determined using the following formula: ; Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

[0036] The trend of vegetation coverage and aboveground biomass reflects the evolution of regional vegetation and can identify whether there are signs of gradual decline or degradation of vegetation. It is an important indicator for assessing grassland health and degradation. The univariate linear regression prediction method can be used to analyze the linear relationship between the time series as the dependent variable and each pixel corresponding to the time series as the independent variable, and can be used to predict the trend of vegetation coverage and aboveground biomass of grassland over a period of time.

[0037] Vegetation cover change trend The calculation formula is: ; In the formula: n is the statistical year number, i is the statistical year; is the average vegetation coverage of the grid cell in year i; is the vegetation coverage change trend of a single pixel, which is the overall change trend simulated by the univariate linear regression of the average vegetation coverage value of the pixel for n consecutive years. , it means that the change of vegetation cover in n years has an increasing trend, otherwise it has a decreasing trend.

[0038] Trend of aboveground biomass The calculation formula is: ; In the formula: n is the statistical year number, i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

[0039] In one embodiment, the net primary productivity change trend is determined using the following formula: ; Where n is the statistical year number and i is the statistical year; is the average net primary productivity of the grid cell in year i, is the changing trend of net primary productivity of a single pixel.

[0040] In one embodiment, the evapotranspiration variation trend is determined using the following formula: ; Where n is the statistical year number and i is the statistical year; is the average evapotranspiration of the grid cell in year i; is the changing trend of evapotranspiration of a single pixel.

[0041] Monitoring the changing trends of NPP and ET can effectively reflect grassland degradation. NPP is an important indicator for measuring vegetation growth and carbon fixation capacity. Grassland degradation is often accompanied by a significant decline in NPP, indicating that grassland vegetation has slowed down its growth rate, deteriorated its health, and reduced its biomass. ET includes plant transpiration and soil evaporation, and is an important indicator reflecting vegetation and water use efficiency. Grassland degradation usually leads to a decrease in vegetation cover, which in turn leads to a decrease in ET. In the process of judging grassland degradation, the joint decline of NPP and ET can provide strong evidence to indicate the degradation trend of the ecosystem. The continuous decline in NPP indicates that vegetation growth has been suppressed for a long time, while the decline in ET reflects the reduction in vegetation cover and the reduction in water use efficiency. Combining the changing trends of the two, the degree of grassland degradation and ecological impact can be comprehensively assessed, providing a scientific basis for grassland protection and restoration.

[0042] NPP Trends The calculation formula is: ; In the formula: n is the statistical year number, i is the statistical year; is the average net primary productivity of the grid cell in year i, is the NPP variation trend of a single pixel.

[0043] ET change trend The calculation formula is: ; In the formula: n is the statistical year number, i is the statistical year; is the average evapotranspiration of the grid cell in year i; is the changing trend of evapotranspiration of a single pixel.

[0044] After establishing the grassland degradation risk indicator system, remote sensing is used to extract relevant indicators, and the Bayesian model is used to train and model these indicators.

[0045] S120, inputting the input data into a pre-built Bayesian model, and outputting an estimated result of the grassland degradation risk level through the Bayesian model.

[0046] Bayesian network is a modeling method that uses mathematical statistics knowledge to solve uncertain problems in complex systems. It effectively integrates expert prior knowledge and various objective evidence, and can perform quantitative risk prediction and assessment. Bayesian network is a complex system, including network structures such as naive Bayes, weighted Bayes, and hierarchical Bayes, and these networks all follow Bayes' theorem. The principle of classification is to use the Bayesian formula to calculate the posterior probability of an object through the prior probability of the object, that is, the probability that the object belongs to a certain class, and select the class with the largest posterior probability as the class to which the object belongs.

[0047] Naive Bayes is a classification algorithm based on Bayes' theorem. Its basic idea is to infer the category of new data based on training data of known categories. In Naive Bayes, the data to be classified is taken as a vector, and each element in the vector represents a feature or attribute. Naive Bayes includes Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, etc. Naive Bayes Classifier adopts the "attribute conditional independence assumption", that is, for known categories, it is assumed that all attributes are independent of each other. The steps of Naive Bayes Classifier are: ① Set the parameters, and assume that the sample attribute set is x{x1,x2,x3......x n}, n is the number, xi is the value; let c be the category set, divide the sample into a certain category, c={y1,y2,y3......y m}.

[0048] ②Calculate the posterior probability, the formula is as follows: ; in ...P , that is, each feature is independent of each other.

[0049] ③ Calculate the probability. Calculate the conditional probability of each partition It is the basic step of naive Bayes classification. When the feature attribute is a discrete value, it is very convenient to count the frequency of each division in each category in the training sample for estimation. When the feature attribute is a continuous value, it is usually assumed that its value follows a Gaussian distribution (also called a normal distribution). That is: ; As long as the mean and standard deviation of this feature item in each category in the training sample are calculated and substituted into the above formula, the required estimated value can be obtained.

[0050] The advantage of using Bayesian model for vegetation change risk assessment is that it not only considers the interrelationships between various indicators, but also effectively handles uncertainty and incomplete information. This method reveals the impact of different factors on vegetation change in a probabilistic way, enabling decision makers to have a more comprehensive understanding of vegetation health. In addition, the flexibility and portability of Bayesian model make it applicable to different ecosystems and geographical environments.

[0051] In one embodiment, the training process of the Bayesian model includes: Build an initial model; The data collected according to the preset period is used as sample data, and the initial model is used to conduct nonlinear quantitative risk assessment on the grassland degradation risk level of the target period; The nonlinear quantitative risk assessment is evaluated using data actually collected during the target period, and the parameters of the initial model are adjusted according to the evaluation results to obtain a Bayesian model with an accuracy rate that meets the requirements.

[0052] Among them, the initial model can be a Bayesian model without parameter adjustment. The data collected in the preset period can be ground remote sensing data collected by remote sensing technology in the preset period, including the above eight types of data. The preset period can be collected in units of years. The nonlinear quantitative risk assessment of the grassland degradation risk level of the target period can be an assessment of the grassland degradation risk level in the next year of the last actual data collection period, for example, using the data of 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 and 2010 to assess the grassland degradation risk level in 2011. After the assessment, the above eight types of data actually collected in 2011 can be obtained to actually calculate the current grassland degradation risk level, and compare the calculated results with the grassland degradation risk level obtained by the assessment, so as to adjust the parameters of the initial model in the presence of deviations, so that the adjusted model has a more accurate estimation ability, thereby obtaining an adjusted Bayesian model.

[0053] Through such a setting, this solution can obtain accurate model estimation results through Bayesian model training and provide accurate output data for subsequent estimation operations.

[0054] The technical solution provided in this embodiment uses remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; the input data is input into a pre-constructed Bayesian model, and the estimated result of the grassland degradation risk level is output through the Bayesian model. By adopting the technical solution provided by the present invention, the above-mentioned multiple data can be integrated, and the grassland degradation risk level can be objectively evaluated using the Bayesian model to obtain a unified evaluation result, which is convenient for providing a data basis for understanding and managing grassland degradation.

[0055] Figure 2a This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2010 provided in Example 1 of the present application. Figure 2b This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2015 provided in Example 1 of the present application. Figure 2c This is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2020 provided in Example 1 of the present application. Figure 2d 2 is a schematic diagram of the grassland degradation risk level assessment results for a certain region in 2022 provided in Example 1 of the present application. Figure 2a to Figure 2dAs shown, therefore, the present invention starts from the perspective of grassland characteristics and changing trends, and realizes nonlinear quantitative vegetation risk assessment of the region in 2010, 2015, 2020 and 2022 based on the Bayesian model. According to the grassland type in the region, the entire study area is divided into eastern, central and western regions, with meadow grassland being the main region in the east, typical grassland being the main region in the middle, and desert grassland being the main region in the west. The risk level in the region gradually decreases from west to east, which is consistent with the grassland type of Xilinguole League. From the perspective of spatial distribution, medium and high risks are mainly distributed in the western region of Xilinguole League. The distribution between 2010 and 2022 shows an overall downward trend, and the risk center of gravity has an obvious westward shift.

[0056] The technical solution provided in this embodiment adopts the "state + trend" method to select eight remote sensing parameters, including vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, and the corresponding change trends of the above four indicators, to construct a remote sensing assessment index system for grassland degradation risk. The Bayesian network model is introduced to diagnose grassland ecological degradation risks, realizing nonlinear assessment of grassland degradation risks.

[0057] Embodiment 2 Figure 3 Schematic diagram of the structure of the Bayesian model grassland degradation risk remote sensing diagnosis device provided in Example 2 of the present application. Figure 3 As shown, the device comprises: The input data acquisition module 310 is used to use remote sensing technology to acquire one or more of vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The prediction module 320 is used to input the input data into a pre-built Bayesian model, and output an estimated result of the grassland degradation risk level through the Bayesian model.

[0058] This device can execute the Bayesian model grassland degradation risk remote sensing diagnosis method provided by the above embodiments, and has corresponding functional units and beneficial effects, which will not be described in detail here.

[0059] Embodiment 3 The present application also provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a Bayesian model grassland degradation risk remote sensing diagnosis method when executed by a computer processor, the method comprising: Using remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The input data is input into a pre-built Bayesian model, and the estimated result of grassland degradation risk level is output through the Bayesian model.

[0060] Storage medium - any of various types of memory electronic devices or storage electronic devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0061] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application is not limited to the Bayesian model grassland degradation risk remote sensing diagnosis operations as described above, but can also execute related operations in the Bayesian model grassland degradation risk remote sensing diagnosis method provided in any embodiment of the present application.

[0062] Embodiment 4 The embodiment of the present application also provides a Bayesian model grassland degradation risk remote sensing diagnosis system, the remote sensing diagnosis system for grassland degradation risk based on the Bayesian model is used to execute a Bayesian model grassland degradation risk remote sensing diagnosis method, the method comprising: Using remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The input data is input into a pre-built Bayesian model, and the estimated result of grassland degradation risk level is output through the Bayesian model.

[0063] The technical solution provided in this embodiment uses remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; the input data is input into a pre-constructed Bayesian model, and the estimated result of the grassland degradation risk level is output through the Bayesian model. By adopting the technical solution provided by the present invention, the above-mentioned multiple data can be integrated, and the grassland degradation risk level can be objectively evaluated using the Bayesian model to obtain a unified evaluation result, which is convenient for providing a data basis for understanding and managing grassland degradation.

[0064] Embodiment 5 An embodiment of the present application provides an electronic device. Figure 4 Schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present application. Figure 4 As shown, this embodiment provides an electronic device 400, which includes: one or more processors 420; a storage device 410, which is used to store one or more programs. When the one or more programs are run by the one or more processors 420, the one or more processors 420 implement the Bayesian model grassland degradation risk remote sensing diagnosis method provided in the embodiment of the present application. The method includes: Using remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The input data is input into a pre-built Bayesian model, and the estimated result of grassland degradation risk level is output through the Bayesian model.

[0065] Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0066] like Figure 4 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processor 420 in the electronic device can be one or more. Figure 4 A processor 420 is taken as an example; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 4 The connection via bus 450 is taken as an example.

[0067] The storage device 410, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and module units, such as program instructions corresponding to the Bayesian model grassland degradation risk remote sensing diagnosis method in the embodiment of the present application.

[0068] The storage device 410 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the storage device 410 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 410 may further include a memory remotely arranged relative to the processor 420, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0069] The input device 430 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 440 may include electronic devices such as a display screen and a speaker.

[0070] The technical solution provided in this embodiment uses remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; the input data is input into a pre-constructed Bayesian model, and the estimated result of the grassland degradation risk level is output through the Bayesian model. By adopting the technical solution provided by the present invention, the above-mentioned multiple data can be integrated, and the grassland degradation risk level can be objectively evaluated using the Bayesian model to obtain a unified evaluation result, which is convenient for providing a data basis for understanding and managing grassland degradation.

[0071] Those skilled in the art will appreciate that the embodiments of the present application may provide methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0072] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A Bayesian model grassland degradation risk remote sensing diagnosis method, characterized in that: The method comprises: Using remote sensing technology to obtain one or more of the vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The input data is input into a pre-built Bayesian model, and the estimated result of grassland degradation risk level is output through the Bayesian model.

2. The method according to claim 1, characterized in that The training process of the Bayesian model includes: Build an initial model; The data collected according to the preset period is used as sample data, and the initial model is used to conduct nonlinear quantitative risk assessment on the grassland degradation risk level of the target period; The nonlinear quantitative risk assessment is evaluated using data actually collected during the target period, and the parameters of the initial model are adjusted according to the evaluation results to obtain a Bayesian model with an accuracy rate that meets the requirements.

3. The method according to claim 1, characterized in that: The vegetation coverage is calculated using the normalized vegetation index in remote sensing data; The aboveground biomass is calculated using a random forest model using remote sensing data and MODIS red, blue, near-infrared bands and NDVI, DVI, SAVI, RVI, and EVI vegetation indices; The net primary productivity is calculated from photosynthetically active radiation and actual light energy utilization efficiency, wherein the photosynthetically active radiation is calculated based on the absorption ratio of total solar radiation and photosynthetically active radiation; The evapotranspiration includes the amount of water evaporated from vegetation and land surface.

4. The method according to claim 1, characterized in that: The vegetation coverage change trend is determined by the following formula: ； Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

5. The method according to claim 1, characterized in that The aboveground biomass change trend is determined by the following formula: ； Where n is the statistical year number and i is the statistical year; is the average vegetation coverage of the grid cell in year i; It is the vegetation coverage change trend of a single pixel.

6. The method according to claim 1, characterized in that The net primary productivity change trend is determined by the following formula: ； Where n is the statistical year number and i is the statistical year; is the average net primary productivity of the grid cell in year i, is the changing trend of net primary productivity of a single pixel.

7. The method according to claim 1, characterized in that The evapotranspiration variation trend is determined by the following formula: ； Where n is the statistical year number and i is the statistical year; is the average evapotranspiration of the grid cell in year i; is the changing trend of evapotranspiration of a single pixel.

8. A remote sensing diagnostic device for grassland degradation risk using a Bayesian model, characterized in that: The device comprises: An input data acquisition module is used to use remote sensing technology to acquire one or more of vegetation coverage, aboveground biomass, net primary productivity, evapotranspiration, vegetation coverage change trend, aboveground biomass change trend, net primary productivity change trend and evapotranspiration change trend of the target area collected according to the observation period as input data; The prediction module is used to input the input data into a pre-built Bayesian model, and output an estimated result of the grassland degradation risk level through the Bayesian model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the Bayesian model grassland degradation risk remote sensing diagnosis method as described in any one of claims 1 to 7 is implemented.

10. A Bayesian model grassland degradation risk remote sensing diagnosis system, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the Bayesian model grassland degradation risk remote sensing diagnosis method as described in any one of claims 1 to 7 when executing the computer program.

Images