Ecological environment detection method and device based on multi-source data and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to an ecological environment detection method and device based on multi-source data and a storage medium, and the method comprises the steps: collecting spatial distribution parameters and environmental stress parameters; constructing an intrusion space index based on the target plaque area and the target plaque boundary perimeter; constructing a habitat stress index according to the daily average submerging duration and the soil salinity of the root system layer; constructing a diffusion risk factor according to the plaque area of the associated region of the target plaque, constructing a risk index based on the diffusion risk factor, the intrusion space index and the habitat stress index, and constructing a plaque treatment priority; and constructing an adjustment coefficient according to the canopy temperature daily difference, constructing an update coefficient according to the seed removal rate and the adjustment coefficient, and updating the plaque treatment priority based on the update coefficient and the target plaque area. According to the method, accurate diagnosis, risk early warning and scientific sorting of treatment priorities of the spartina alterniflora invasion situation are realized.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an ecological environment monitoring method, device, and storage medium based on multi-source data. Background Technology

[0002] Currently, there are significant limitations in the monitoring and management of invasive alien plants (such as Spartina alterniflora) in estuarine wetlands.

[0003] Traditional methods rely primarily on periodic manual field surveys and subsequent remote sensing interpretation, which are not only inefficient and have limited coverage, but also struggle to accurately quantify invasion dynamics. Their assessment indicators are often singular, limited to area changes, failing to provide insights into invasion mechanisms and control potential from multiple dimensions such as habitat suitability, biological interactions, and plant physiological states. This results in management decisions heavily reliant on subjective experience, lacking objective data support, and exhibiting significant delays in evaluating control effectiveness.

[0004] This passive, one-sided, and lagging management model is unable to meet the urgent need of highly dynamic wetland ecosystems for precise prevention and control of invasive species through "early detection, early warning, early decision-making, and early treatment," and it restricts the optimal allocation of governance resources and the improvement of overall prevention and control effectiveness. Summary of the Invention

[0005] The purpose of this invention is to provide an ecological environment monitoring method, device, and storage medium based on multi-source data, so as to solve at least one of the problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] An ecological environment monitoring method based on multi-source data includes:

[0008] Collect spatial distribution parameters and environmental stress parameters;

[0009] An intrusion space index is constructed based on the target patch area and the target patch boundary perimeter.

[0010] A habitat stress index was constructed based on the average daily flooding duration and root zone soil salinity.

[0011] A diffusion risk factor is constructed based on the patch area of ​​the associated region of the target patch, and a risk index is constructed based on the diffusion risk factor, the invasion space index and the habitat stress index. At the same time, a patch governance priority is constructed.

[0012] An adjustment coefficient is constructed based on the diurnal temperature range of the canopy, and an update coefficient is constructed based on the seed removal rate and the adjustment coefficient. The priority of patch management is then updated based on the update coefficient and the target patch area.

[0013] Furthermore, the target patch area A and the target patch boundary perimeter P within the monitoring period are fused to construct the target patch shape index SI, SI = 4 × π × A / P 2 ;

[0014] An invasion space index F is constructed based on the target patch shape index SI and the target patch area A. F is set as F = lg(A / a0+1) / lg2 + 0.3×(1-SI), where a0 is the first preset area threshold.

[0015] Furthermore, the average daily inundation duration during the monitoring period is calculated and denoted as Ts, and the average root zone soil salinity during the monitoring period is calculated and denoted as Si.

[0016] The first stress factor is determined based on Ts and the preset daily average flooding duration T0. The expression for the first stress factor is: Z1 = 1 - exp(-|Ts-T0| / T0), where Z1 is the first stress factor.

[0017] The second stress factor is determined based on Si and the preset salinity S0. The expression for the second stress factor is: Z2 = |Si-S0| / S0, where Z2 is the second stress factor.

[0018] A habitat stress index is constructed based on the first stress factor Z1 and the second stress factor Z2. The expression for the habitat stress index is as follows:

[0019] H = w1 × Z1 + w2 × Z2;

[0020] Where w1 is the first stress weight, w2 is the second stress weight, w1+w2=1, and H is the habitat stress index.

[0021] Furthermore, a diffusion risk factor is constructed based on the patch area of ​​the associated region of the target patch:

[0022] The area of ​​the associated region of the target patch is denoted as Ct, and a diffusion risk factor D is constructed based on Ct, where D = ln(Ct / Cs+1) / ln2, and Cs is the area of ​​the associated region of the target patch.

[0023] Furthermore, a risk index Y is constructed based on the diffusion risk factor, the invasion space index, and the habitat stress index, where Y = α1 × F + α2 × H + α3 × D, α1 is the spatial index weight, α2 is the habitat suitability weight, α3 is the diffusion risk weight, and α1 + α2 + α3 = 1.

[0024] The risk index Y is compared with a preset risk threshold y0 to provide users with risk warnings.

[0025] When Y≤y0, no risk warning is issued to the user; otherwise, a risk warning is issued to the user.

[0026] The risk index of the target patches that will be given risk warnings to users will be sorted, and the sorting results will be output to users as the priority of patch governance.

[0027] Furthermore, the average daily temperature range of the canopy during the monitoring period is calculated and denoted as ΔT. ΔT is then compared with each preset temperature threshold to construct an adjustment coefficient.

[0028] When ΔT is less than the first preset temperature threshold t1, the adjustment coefficient is set to η×(t1-ΔT) / t1, where η is the preset correction coefficient;

[0029] When ΔT is greater than or equal to the first preset temperature threshold t1 and less than or equal to the second preset temperature threshold t2, the adjustment coefficient is set to 0;

[0030] When ΔT is greater than the second preset temperature threshold t2, the adjustment coefficient is set to -η×tanh(ΔT-t2) / t2.

[0031] Furthermore, the average seed removal rate over the monitoring period is calculated and denoted as R. This R is then compared to a preset removal rate r1 to determine the predation pressure factor.

[0032] When R is less than the preset removal rate r1, the predation pressure factor is set to ln[3×(r1-R) / r1+1] / ln4;

[0033] When R is greater than or equal to the preset removal rate r1, the predation pressure factor is set to 0.

[0034] Furthermore, an update coefficient is constructed based on the predation pressure factor and the adjustment coefficient, where the update coefficient = predation pressure factor × (1 + adjustment coefficient);

[0035] Update patch remediation priorities based on target patch area and update coefficient:

[0036] If the area of ​​the target patch is less than or equal to the second preset area threshold, the risk index of the target patch is updated to (1 + 0.1 × update coefficient) times the original risk index. If the area of ​​the target patch is greater than the second preset area threshold, the risk index of the target patch is not updated.

[0037] According to another aspect of this application, an ecological environment monitoring device based on multi-source data is also provided, applied to the aforementioned ecological environment monitoring method based on multi-source data, comprising:

[0038] The data acquisition unit is used to collect spatial distribution parameters and environmental stress parameters;

[0039] The intrusion analysis unit is used to construct an intrusion spatial index based on the target patch area and the target patch boundary perimeter.

[0040] The habitat analysis unit is used to construct a habitat stress index based on the average daily flooding duration and root zone soil salinity.

[0041] The monitoring unit is used to construct a diffusion risk factor based on the patch area of ​​the associated region of the target patch, and to construct a risk index based on the diffusion risk factor, the invasion space index and the habitat stress index, while also constructing a patch governance priority.

[0042] The priority update unit is used to construct an adjustment coefficient based on the diurnal variation of canopy temperature, construct an update coefficient based on the seed removal rate and the adjustment coefficient, and update the priority of patch treatment based on the update coefficient and the target patch area.

[0043] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, wherein the computer program is used to control the electronic device on which the computer-readable storage medium is located to perform the ecological environment detection method based on multi-source data during runtime.

[0044] The beneficial effects of this invention are as follows: By constructing an intelligent sensing and decision-making system that deeply integrates multi-source data from "space, environment, biology, and physiology," this invention achieves a three-dimensional diagnosis of the ecological status of invasive plants in wetlands and adaptive optimization of management priorities. The solution comprehensively utilizes remote sensing, in-situ sensing, and ecological experimental methods to accurately quantify multiple dimensions, including the spatial pattern of invasive patches, water and salt stress, seed predation pressure, and plant water physiology, breaking through the limitations of traditional methods that rely solely on area indicators. By introducing dynamic weight adjustment and a closed-loop feedback mechanism, the system can keenly identify high-risk patches and key management nodes, and transform theoretical risk assessments into management sequences that are both operationally feasible. Its ultimate advantage lies in transforming the management model from reactive post-event handling to pre-event precise early warning and in-event intelligent decision-making, forming a complete closed loop integrating perception, diagnosis, decision-making, and optimization, significantly improving the scientific rigor, foresight, and resource utilization efficiency of invasive plant control. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the ecological environment monitoring method based on multi-source data in this embodiment.

[0047] Figure 2 This is a flowchart illustrating the plaque risk and priority construction method of this embodiment.

[0048] Figure 3 This is a flowchart illustrating the method for updating the priority of plaque treatment in this embodiment.

[0049] Figure 4 This is a schematic diagram of the ecological environment monitoring device based on multi-source data in this embodiment. Detailed Implementation

[0050] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0051] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0052] Specifically, this embodiment addresses the challenge of controlling the invasion of the alien species Spartina alterniflora in estuarine salt marsh wetland ecosystems by providing a precise management solution. Traditional methods rely on manual inspections and subjective judgment, making it difficult to quantify invasion dynamics and achieve early warning and accurate decision-making. This solution integrates multi-source data, including spatial distribution, environmental stress, biological interactions, and plant physiology, to construct a data-driven, closed-loop feedback, and adaptive optimization intelligent monitoring and decision-making system. This system aims to achieve accurate diagnosis of Spartina alterniflora invasion trends, risk warning, and scientific prioritization of management efforts.

[0053] Please see Figure 1 As shown, this is a flowchart illustrating the ecological environment monitoring method based on multi-source data in this embodiment. The method includes:

[0054] Step S101: Collect spatial distribution parameters and environmental stress parameters. The spatial distribution parameters include the target patch area and the perimeter of the target patch boundary. The environmental stress parameters include the average daily inundation duration and the root layer soil salinity. The Spartina alterniflora patch area is the projected area of ​​a single continuous distribution area of ​​Spartina alterniflora vegetation. The average daily inundation duration is the average number of hours the water level gauge is submerged by tides within a complete tidal cycle (24 hours). The root layer soil salinity is the soil pore water salinity of the main root distribution layer (depth 20cm) of the target. The target is Spartina alterniflora.

[0055] For example, in this embodiment, images can be collected by a drone equipped with a hyperspectral camera. The area of ​​the target patch can be automatically extracted and calculated using image recognition and segmentation algorithms (such as the U-Net model). Synchronously with the area A, the perimeter of the target patch boundary can be automatically extracted and calculated using the drone images through image recognition algorithms. The average daily flooding duration can be obtained by a pressure water level gauge deployed in the monitoring area. The soil salinity of the root zone can be obtained by a buried soil salinity sensor. In this embodiment, no specific limitation is made on the data collection method. Those skilled in the art can set it freely according to their needs.

[0056] For example, in this embodiment, a drone equipped with a hyperspectral camera is used to conduct aerial photography of the target wetland area according to a preset gridded flight path, acquiring hyperspectral image data with a spatial resolution better than 0.1 meters. The acquired raw images, after preprocessing such as radiometric calibration and atmospheric correction, are input into a pre-trained U-Net deep learning semantic segmentation model. This model is trained based on a large number of labeled wetland vegetation samples (including Spartina alterniflora, native vegetation, bare land, and water bodies, etc.), and can perform pixel-level classification of the input images, automatically identifying and segmenting connected regions where Spartina alterniflora is distributed. For each Spartina alterniflora segmented region output by the model, the system automatically calculates its projected plane area using GIS (Geographic Information System) components; this value is the target patch area A. Simultaneously, the system extracts the contour boundary of each segmented region using a boundary tracing algorithm and accurately calculates the total length of the contour; this value is the target patch boundary perimeter P. This embodiment does not specifically limit the above settings; those skilled in the art can freely set them according to their needs.

[0057] Specifically, by collaboratively utilizing remote sensing technology and in-situ sensor networks, key physical parameters reflecting the spatial patterns and living environments of invasive plants were systematically captured. This laid a unified and reliable data foundation for the entire analysis process, ensuring that all subsequent diagnoses and decisions were based on objective, real-time on-site perception.

[0058] Please continue reading. Figure 1 As shown, the ecological environment monitoring method based on multi-source data also includes:

[0059] Step S102: Construct an invasion space index based on the target patch area and the target patch boundary perimeter.

[0060] Specifically, the area A of the target patch and the perimeter P of the target patch boundary within the monitoring period are fused to construct the target patch shape index SI, SI = 4 × π × A / P 2 ;

[0061] An invasion space index F is constructed based on the target patch shape index SI and the target patch area A. F is set as F = lg(A / a0+1) / lg2 + 0.3×(1-SI), where a0 is the first preset area threshold.

[0062] Specifically, the optimal range for the first preset area threshold is 30-60m. 2 In this embodiment, the value is taken as 50m. 2 .

[0063] Specifically, in this embodiment, the monitoring period is 7 days.

[0064] Specifically, the geometric characteristics of patches are transformed into quantifiable spatial invasiveness indicators, taking into account not only the scale of expansion but also the aggressiveness and stability implied by their boundary morphology. This enables the system to accurately identify core patches with greater potential for spread and a higher risk of consolidation in a spatial dimension.

[0065] Please continue reading. Figure 1 As shown, the ecological environment monitoring method based on multi-source data also includes:

[0066] Step S103: Construct a habitat stress index based on the average daily flooding duration and root zone soil salinity.

[0067] Specifically, the average daily inundation duration during the monitoring period is calculated and denoted as Ts, and the average root zone soil salinity during the monitoring period is calculated and denoted as Si.

[0068] The first stress factor is determined based on Ts and the preset daily average flooding duration T0. The expression for the first stress factor is: Z1 = 1 - exp(-|Ts-T0| / T0), where Z1 is the first stress factor.

[0069] The second stress factor is determined based on Si and the preset salinity S0. The expression for the second stress factor is: Z2 = |Si-S0| / S0, where Z2 is the second stress factor.

[0070] A habitat stress index is constructed based on the first stress factor Z1 and the second stress factor Z2. The expression for the habitat stress index is as follows:

[0071] H = w1 × Z1 + w2 × Z2;

[0072] Where w1 is the first stress weight, w2 is the second stress weight, w1+w2=1, and H is the habitat stress index.

[0073] Specifically, the optimal range for the preset average daily flooding duration is 3-5 h / d, and in this embodiment, it is set to 4 h / d. The optimal range for the preset salinity is 10-20 psu, and in this embodiment, it is set to 15 psu.

[0074] Specifically, in this embodiment, the first coercion weight is 0.6 and the second coercion weight is 0.4.

[0075] Specifically, by analyzing the deviation of environmental parameters from the species' optimal habitat, complex water and salinity conditions are transformed into an intuitive assessment of stress levels. This step reveals the inhibitory or promoting effect of environmental pressure on invasion processes, providing crucial evidence for predicting the natural evolutionary trend of patches.

[0076] Please continue reading. Figure 1 As shown, the ecological environment monitoring method based on multi-source data also includes:

[0077] Step S104: Construct a diffusion risk factor based on the patch area of ​​the associated region of the target patch, and construct a risk index based on the diffusion risk factor, invasion space index and habitat stress index, while constructing a patch governance priority.

[0078] Specifically, the associated region of the target patch is a buffer zone with a radius of 50m centered on the target patch. The patch area of ​​the associated region of the target patch is the total area of ​​all other Spartina alterniflora patches within the buffer zone, which can be automatically calculated through buffer analysis and overlay statistics using GIS software.

[0079] Specifically, by integrating spatial invasiveness, environmental stress, and the risk of spread to neighboring areas, a comprehensive diagnosis of the ecological harm level of a single patch is achieved. The risk warnings triggered by this can quickly focus management attention on truly high-risk targets and generate preliminary action sequences.

[0080] Please see Figure 2 As shown, the plaque risk and priority construction method includes:

[0081] Step S201: Construct a diffusion risk factor based on the patch area of ​​the associated region of the target patch.

[0082] Specifically, the area of ​​the associated region of the target patch is denoted as Ct, and a diffusion risk factor D is constructed based on Ct, where D = ln(Ct / Cs+1) / ln2, and Cs is the area of ​​the associated region of the target patch.

[0083] Specifically, by focusing on the spatial correlation of patches, the potential risk of them serving as intrusion "stepping stones" was quantified. This effectively prevents the underestimation of the danger of patches that appear isolated but are actually located at critical network nodes.

[0084] Please continue reading. Figure 2 As shown, the plaque risk and priority construction method further includes:

[0085] Step S202: Construct a risk index based on diffusion risk factors, invasion space index and habitat stress index, and issue risk warnings to users.

[0086] Specifically, a risk index Y is constructed based on the diffusion risk factor, the invasion space index, and the habitat stress index, where Y = α1 × F + α2 × H + α3 × D, α1 is the weight of the spatial index, α2 is the weight of the habitat suitability, α3 is the weight of the diffusion risk, and α1 + α2 + α3 = 1.

[0087] The risk index Y is compared with a preset risk threshold y0 to provide users with risk warnings.

[0088] When Y≤y0, no risk warning is issued to the user; otherwise, a risk warning is issued to the user.

[0089] Specifically, the optimal range for the preset risk threshold is 0.2-0.4, and in this embodiment, the preset risk threshold is 0.3.

[0090] Specifically, in this embodiment, the spatial index weight is 0.4, the habitat suitability weight is 0.3, and the diffusion risk weight is 0.3.

[0091] Specifically, risk indicators from different dimensions are combined into a unified comprehensive evaluation, and clear early warning thresholds are set. This transforms complex multi-source information into concise and actionable decision signals, achieving a seamless connection from data analysis to management intervention.

[0092] Please continue reading. Figure 2 As shown, the plaque risk and priority construction method further includes:

[0093] Step S203: Construct a priority list for patch remediation based on the risk index and risk warning results.

[0094] Specifically, the risk index of the target patches that will be given risk warnings to users will be ranked, and the ranking results will be output to users as the priority of patch governance.

[0095] Specifically, ranking patches based on risk indices ensures that limited governance resources are always prioritized for areas facing the greatest and most serious threats.

[0096] Please continue reading. Figure 1 As shown, the ecological environment monitoring method based on multi-source data also includes:

[0097] Step S105: Construct an adjustment coefficient based on the daily variation of canopy temperature, construct an update coefficient based on the seed removal rate and the adjustment coefficient, and update the priority of patch management based on the update coefficient and the target patch area.

[0098] Specifically, the seed removal rate is the proportion of Spartina alterniflora seeds that have been consumed or removed by organisms within 24 hours relative to the initially placed seeds. This can be calculated by setting up seed stations in representative areas of the wetland, placing 50 stained seeds at each station, checking with ultraviolet light after 24 hours, and counting the number of remaining seeds.

[0099] Specifically, the diurnal temperature variation of the canopy is the difference between the highest and lowest temperatures on the canopy surface of the same patch within a day (e.g., 9:00 AM and 2:00 PM). This can be achieved by using a drone equipped with a thermal infrared camera to take aerial photos, extracting the temperature values ​​of the same patch, and then calculating the difference. In this embodiment, no specific limitation is made on the data acquisition method, and those skilled in the art can set it freely according to their needs.

[0100] Please see Figure 2 As shown, the method for updating the plaque remediation priority includes:

[0101] Step S301: Construct an adjustment coefficient based on the daily variation of canopy temperature within the monitoring period.

[0102] Specifically, the average daily temperature range of the canopy during the monitoring period is calculated and denoted as ΔT. ΔT is then compared with each preset temperature threshold to construct an adjustment coefficient.

[0103] When ΔT is less than the first preset temperature threshold t1, the adjustment coefficient is set to η×(t1-ΔT) / t1, where η is the preset correction coefficient;

[0104] When ΔT is greater than or equal to the first preset temperature threshold t1 and less than or equal to the second preset temperature threshold t2, the adjustment coefficient is set to 0;

[0105] When ΔT is greater than the second preset temperature threshold t2, the adjustment coefficient is set to -η×tanh(ΔT-t2) / t2.

[0106] Specifically, the optimal range for the first preset temperature threshold is 4-6℃, and the optimal range for the second preset temperature threshold is 7-9℃. In this embodiment, the first preset temperature threshold is 5℃ and the second preset temperature threshold is 8℃.

[0107] Specifically, the preset correction factor is the intensity adjustment factor of the adjustment coefficient, and the optimal value range is 0.1-0.3. In this embodiment, the value is 0.2.

[0108] Specifically, the diurnal temperature range of the canopy is used as an indirect physiological indicator to sensitively capture the water stress status of plants. The resulting adjustment coefficient can dynamically reflect the degree of inhibition of natural growth in patches, providing a physiological basis for flexible adjustment of priorities.

[0109] Please continue reading. Figure 2 As shown, the method for updating the plaque remediation priority further includes:

[0110] Step S302: Construct update coefficients based on seed removal rate and adjustment coefficients, and update patch governance priority based on update coefficients and target patch area.

[0111] Specifically, the average seed removal rate over the monitoring period is calculated and denoted as R. This R is then compared to a preset removal rate r1 to determine the predation pressure factor.

[0112] When R is less than the preset removal rate r1, the predation pressure factor is set to ln[3×(r1-R) / r1+1] / ln4;

[0113] When R is greater than or equal to the preset removal rate r1, the predation pressure factor is set to 0;

[0114] An update coefficient is constructed based on the predation pressure factor and the adjustment coefficient. The update coefficient = predation pressure factor × (1 + adjustment coefficient).

[0115] Update patch remediation priorities based on target patch area and update coefficient:

[0116] If the area of ​​the target patch is less than or equal to the second preset area threshold, the risk index of the target patch is updated to (1 + 0.1 × update coefficient) times the original risk index. If the area of ​​the target patch is greater than the second preset area threshold, the risk index of the target patch is not updated.

[0117] Specifically, the optimal range for the preset removal rate is 0.2-0.4, and in this embodiment it is 0.3. The optimal range for the second preset area threshold is 5-15m. 2 In this implementation, the value is taken as 10m. 2 .

[0118] Specifically, by integrating biological control effects with plant physiological states, the priority of small patch treatment is finely adjusted. This mechanism reflects the system's intelligent adaptation to ecological interactions and the plant's intrinsic physiological responses, making the final treatment sequence both scientific and ecologically sound.

[0119] Please see Figure 4 As shown, this is a schematic diagram of the structure of the ecological environment monitoring device based on multi-source data in this embodiment, including:

[0120] The data acquisition unit is used to collect spatial distribution parameters and environmental stress parameters;

[0121] The intrusion analysis unit is used to construct an intrusion spatial index based on the target patch area and the target patch boundary perimeter.

[0122] The habitat analysis unit is used to construct a habitat stress index based on the average daily flooding duration and root zone soil salinity.

[0123] The monitoring unit is used to construct a diffusion risk factor based on the patch area of ​​the associated region of the target patch, and to construct a risk index based on the diffusion risk factor, the invasion space index and the habitat stress index, while also constructing a patch governance priority.

[0124] The priority update unit is used to construct an adjustment coefficient based on the diurnal variation of canopy temperature, construct an update coefficient based on the seed removal rate and the adjustment coefficient, and update the priority of patch treatment based on the update coefficient and the target patch area.

[0125] The ecological environment monitoring device based on multi-source data provided in this application can execute the ecological environment monitoring method based on multi-source data provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

[0126] This application also provides a computer-readable storage medium, which is a tangible physical storage medium that can store the aforementioned computer program and various types of data used in the program; the physical storage medium includes, but is not limited to, existing physical storage media or combinations thereof, such as random access memory, read-only memory, optical disk, and hard disk.

[0127] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable programs, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable programs, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0128] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all the implementation methods here. All obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A method for ecological environment detection based on multi-source data, characterized in that, The method comprises the following steps: Collecting spatial distribution parameters and environmental stress parameters; Constructing an invasion space index based on the target patch area and the target patch boundary perimeter; Constructing a habitat stress index according to the average daily submergence time and the root layer soil salinity; Constructing a diffusion risk factor based on the patch area of the associated region of the target patch, and constructing a risk index based on the diffusion risk factor, the invasion space index and the habitat stress index, and constructing a patch management priority; Constructing an adjustment coefficient based on the daily temperature range of the canopy layer, constructing an update coefficient based on the seed removal rate and the adjustment coefficient, and updating the patch management priority based on the update coefficient and the target patch area. 2.The method of claim 1, wherein, The target plaque area A in the monitoring period is fused with the target plaque boundary perimeter P to construct a target plaque shape index SI, SI = 4 x π x A / P 2 ; Based on the target patch shape index SI and the target patch area A, an invasion space index F is constructed, and F = lg (A / a0 + 1) / lg2 + 0.3 × (1-SI) is set, where a0 is a first preset area threshold. 3.The method of claim 2, wherein, Calculate the average value of the average daily submergence time in the monitoring period, denoted as Ts, and calculate the average value of the root layer soil salinity in the monitoring period, denoted as Si; Determine a first stress factor according to Ts and a preset average daily submergence time T0, and the expression of the first stress factor is Z1 = 1-exp (-|Ts-T0| / T0), where Z1 is the first stress factor; Determine a second stress factor according to Si and a preset salinity S0, and the expression of the second stress factor is Z2 = |Si-S0| / S0, where Z2 is the second stress factor; Construct a habitat stress index based on the first stress factor Z1 and the second stress factor Z2, and the expression of the habitat stress index is H = w1 × Z1 + w2 × Z2, where w1 is a first stress weight, w2 is a second stress weight, w1 + w2 = 1, and H is the habitat stress index. Construct a diffusion risk factor based on the patch area of the associated region of the target patch: Record the patch area of the associated region of the target patch as Ct, and construct a diffusion risk factor D based on Ct, D = ln (Ct / Cs + 1) / ln2, where Cs is the area of the associated region of the target patch.

4. The ecological environment detection method based on multi-source data according to claim 3, characterized in that, Construct a risk index Y according to the diffusion risk factor, the invasion space index and the habitat stress index, Y = α1 × F + α2 × H + α3 × D, where α1 is a space index weight, α2 is a habitat suitability weight, and α3 is a diffusion risk weight, α1 + α2 + α3 = 1; Compare the risk index Y with a preset risk threshold y0 to perform risk warning to the user:

5. The ecological environment detection method based on multi-source data according to claim 4, characterized in that, If Y ≤ y0, no risk warning is performed to the user, otherwise, risk warning is performed to the user; Sort the risk indexes of the target patches for which risk warning is performed to the user, and output the sorting result as the patch management priority to the user. Calculate the average value of the daily temperature range of the canopy layer in the monitoring period, denoted as ΔT, and compare ΔT with each preset temperature threshold to construct an adjustment coefficient: When ΔT is less than a first preset temperature threshold t1, set the adjustment coefficient to η × (t1-△T) / t1, where η is a preset correction coefficient; 6. The ecological environment detection method based on multi-source data according to claim 5, characterized in that, When ΔT is greater than or equal to the first preset temperature threshold t1 and less than or equal to a second preset temperature threshold t2, set the adjustment coefficient to 0; ​ ​ When △T is greater than a second preset temperature threshold t2, the adjustment coefficient is set as -η×tanh(△T-t2) / t2.

7. The ecological environment detection method based on multi-source data according to claim 6, characterized in that, An average value of the seed removal rate in the monitoring period is calculated and recorded as R, and R is compared with a preset removal rate r1 to determine a predation pressure factor: When R is less than the preset removal rate r1, the predation pressure factor is set as ln[3×(r1-R) / r1+1] / ln4; When R is greater than or equal to the preset removal rate r1, the predation pressure factor is set as 0. 8.The method of claim 7, wherein, An update coefficient is constructed based on the predation pressure factor and the adjustment coefficient, and the update coefficient = predation pressure factor × (1+ adjustment coefficient); The patch management priority is updated based on the target patch area and the update coefficient: If the target patch area is less than or equal to a second preset area threshold, the risk index of the target patch is updated as (1+0.1×update coefficient) times of the original risk index, and if the target patch area is greater than the second preset area threshold, the risk index of the target patch is not updated.

9. An ecological environment detection device based on multi-source data, applied to the ecological environment detection method based on multi-source data according to any one of claims 1-8, characterized in that, The method comprises: a data acquisition unit configured to acquire spatial distribution parameters and environmental stress parameters; an invasion analysis unit configured to construct an invasion space index based on the target patch area and the target patch boundary perimeter; a habitat analysis unit configured to construct a habitat stress index according to the daily average submergence time and the root layer soil salinity; a monitoring unit configured to construct a diffusion risk factor according to the patch area of the associated area of the target patch, and construct a risk index based on the diffusion risk factor, the invasion space index and the habitat stress index, and construct a patch management priority; a priority updating unit configured to construct an adjustment coefficient according to the daily difference of canopy layer temperature, construct an update coefficient according to the seed removal rate and the adjustment coefficient, and update the patch management priority based on the update coefficient and the target patch area.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer readable storage medium is located to execute the ecological environment detection method based on multi-source data in any one of claims 1-8 when running. The computer readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer readable storage medium is located to execute the ecological environment detection method based on multi-source data in any one of claims 1-8 when running.

Images