Method, device and equipment for evaluating influence of offshore wind plant on survival of dolphin population

Abstract

The invention relates to the technical field of marine ecological environment monitoring, and discloses a method, device and equipment for evaluating the influence of an offshore wind plant on dolphin population survival, and the method comprises the steps: obtaining population number change index data, a habitat suitability index, a behavior interference index and a breeding success rate of a target sea area in a first time period; inputting the population quantity change index data, the habitat suitability index, the behavior interference index and the breeding success rate of the first time period into a pre-constructed long-term dynamic evaluation model, the long-term dynamic evaluation model outputs population quantity change index data, a habitat suitability index, a behavior interference index and a breeding success rate in a second time period, and the second time period is later than the first time period; and evaluating the influence of the offshore wind plant on the survival of the dolphin population based on the population quantity change index data, the habitat suitability index, the behavior interference index and the breeding success rate in the second time period to obtain an evaluation result.

Description

Technical Field

[0001] This invention relates to the field of marine ecological environment monitoring technology, specifically to methods, devices, and equipment for assessing the impact of offshore wind farms on dolphin population survival. Background Technology

[0002] Dolphins, as flagship species in marine ecosystems, play a vital role in maintaining marine biodiversity and ecological balance. In recent years, with the increasing demand for clean energy, large-scale construction of offshore wind farms has quietly emerged, subtly altering the original ecological environment of nearshore waters, which are precisely the habitats of dolphins. The impact of offshore wind farms on dolphin populations includes not only underwater noise generated throughout their lifespan, but also changes in water temperature and quality due to climate change, and the impact of human activities (such as the influence of passing ships and wind farm maintenance vessels). Current research on the impact of wind farms on dolphins mainly focuses on the single factor of underwater noise during the construction phase, neglecting the potential impacts after the farms are put into operation and other related factors. This results in problems such as a single assessment indicator and a lack of dynamic tracking, leading to inaccurate and unpredictable assessment results, and thus failing to provide sufficient reference for developing targeted conservation strategies. Summary of the Invention

[0003] This invention provides a method, apparatus, and equipment for assessing the impact of offshore wind farms on dolphin population survival, in order to solve the problem that the assessment of the impact of wind farms on dolphins by using underwater noise as a single factor in related technologies leads to a lack of accuracy and predictability in the assessment results.

[0004] In a first aspect, the present invention provides a method for assessing the impact of offshore wind farms on dolphin population survival. The method includes: acquiring population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for a target sea area in a first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavioral monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data; inputting the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the first time period into a pre-constructed long-term dynamic assessment model, so that the long-term dynamic assessment model outputs the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for a second time period. The long-term dynamic assessment model is a time-series-based prediction model, and the second time period is later than the first time period; assessing the impact of offshore wind farms on dolphin population survival based on the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the second time period, and obtaining the assessment results.

[0005] The method for assessing the impact of offshore wind farms on dolphin population survival provided by this invention comprehensively covers the key dimensions of dolphin population survival by constructing a four-core indicator system encompassing population size change data, habitat suitability index, behavioral disturbance index, and reproductive success rate. This system includes not only population size changes that directly reflect population stability, but also environmental adaptability supporting survival, the degree of disturbance to immediate activities, and reproductive potential that determines population continuation. Furthermore, the data sources for each indicator are fully linked to multiple influencing factors throughout the entire life cycle of the wind farm, such as underwater noise, water temperature and quality changes caused by climate warming, and human activities brought by passing ships and maintenance vessels, rather than being limited to construction-phase noise. This completely compensates for the one-sidedness of related technical assessments, making the characterization of the impact on dolphin population survival more systematic and closer to real ecological scenarios. Secondly, by acquiring the data of the four major indicators in the first period and inputting them into a pre-built long-term dynamic assessment model, the indicators for the second period, which is later than the first period, can be predicted. This dynamic analysis method based on time series data can capture the long-term correlation between the changes in influencing factors at different stages of wind farm operation and the survival status of dolphin populations. It breaks through the limitations of static assessment of a certain stage by related technologies, makes the assessment results predictable, can identify potential risks in advance, and avoids the problem of delayed protection measures due to the inability of related technologies to predict subsequent impacts.

[0006] In one optional implementation, the population change index data includes a first population change rate and a second population change rate. These two rates are used to characterize population changes from different monitoring dimensions. The first population change rate is determined based on dolphin population change data obtained from underwater acoustic monitoring, and the second population change rate is determined based on image data acquired by an image acquisition device. The steps of acquiring population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the target sea area during the first time period include: acquiring first dolphin population change data, second dolphin population change data, survival suitability assessment data for multiple environmental factors, and dolphin vocalization abnormalities during the first time period. The following data were used to determine the population changes of dolphins in the first period: normal frequency, total vocal frequency, frequency of abnormal behavior, frequency of total observed behavior, number of pregnant females, and number of surviving calves. The first set of dolphin population change data was determined through underwater acoustic monitoring, while the second set was determined through image data acquired by image acquisition equipment. Based on the first set of dolphin population change data, the first population change rate for the first period was determined; based on the second set of dolphin population change data, the second population change rate for the first period was determined; based on the survival suitability assessment data of multiple environmental factors, the habitat suitability index for the first period was determined; based on the abnormal vocal frequency, total vocal frequency, frequency of abnormal behavior, and frequency of total observed behavior, the behavioral disturbance index for the first period was determined; and based on the number of pregnant females and the number of surviving calves, the reproductive success rate for the first period was determined.

[0007] In one optional implementation, the long-term dynamic assessment model is constructed through the following steps: acquiring time-series data of assessment indicators for the target sea area within a preset time period, wherein the time-series data of assessment indicators are used to characterize the changes in population size change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate over time; using a first time period as a sliding window, dividing the time-series data of assessment indicators using a preset sliding step size to obtain first training data; using a second time period as a sliding window, dividing the time-series data of assessment indicators using a preset sliding step size to obtain second training data; associating the first training data and the second training data according to prediction requirements to construct a dataset; training a preset neural network model based on the dataset until the model accuracy meets the preset requirements to obtain the long-term dynamic assessment model.

[0008] In one optional implementation, the step of assessing the impact of offshore wind farms on dolphin population survival based on population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period, and obtaining the assessment results, includes: obtaining the warning thresholds corresponding to the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period; comparing the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period with the corresponding warning thresholds to obtain comparison results; and assessing the impact of offshore wind farms on dolphin population survival based on the comparison results to obtain the assessment results.

[0009] In one optional implementation, the first dolphin population change data and the second dolphin population change data are determined through the following steps: acquiring underwater acoustic signals collected by multiple underwater acoustic monitoring devices and image data collected by image acquisition devices; determining the first number of dolphins at a first moment and the second number at a second moment based on the underwater acoustic signals; determining the first dolphin population change data based on the first number and the second number; performing image recognition based on the image data to determine the third number of dolphins at the first moment and the fourth number at the second moment; and determining the second dolphin population change data based on the third number and the fourth number.

[0010] In one optional implementation, the survival suitability assessment data of multiple environmental factors are determined through the following steps: acquiring parameter data of multiple environmental factors collected by environmental monitoring equipment; assessing the degree of impact of the corresponding environmental factor on the suitability of the Indo-Pacific humpback dolphin habitat based on the parameter data of each environmental factor, thereby obtaining the survival suitability assessment data of the corresponding environmental factor.

[0011] Secondly, the present invention provides an assessment device for the impact of offshore wind farms on dolphin population survival. The device includes: an acquisition module for acquiring population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate of a target sea area in a first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavioral monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data; a determination module for inputting the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate of the first time period into a pre-constructed long-term dynamic assessment model, so that the long-term dynamic assessment model outputs the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate of a second time period. The long-term dynamic assessment model is a time-series-based prediction model, and the second time period is later than the first time period; and an assessment module for assessing the impact of offshore wind farms on dolphin population survival based on the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate of the second time period, and obtaining the assessment results.

[0012] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for assessing the impact of offshore wind farms on dolphin population survival as described in the first aspect or any corresponding embodiment.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for assessing the impact of offshore wind farms on dolphin population survival as described in the first aspect or any corresponding embodiment.

[0014] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for assessing the impact of offshore wind farms on dolphin population survival as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of an assessment method for the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the second process for assessing the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the method for assessing the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention. Figure 5 This is a structural block diagram of an assessment device for the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0020] As an optional application scenario of this invention, the specific application environment architecture or specific hardware architecture on which the method for assessing the impact of offshore wind farms on dolphin population survival depends is described here. For example... Figure 1 As shown, the architecture system may include at least one terminal device and at least one server. Figure 1The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0021] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0022] With the increasing demand for clean energy, large-scale construction of offshore wind farms has quietly emerged, subtly altering the original ecological environment of nearshore waters, which are also the habitats of dolphins. The impact of offshore wind farms on dolphin populations includes not only underwater noise generated throughout their lifespan, but also changes in water temperature and quality due to climate change, and the influence of human activities (such as the impact of passing ships and wind farm maintenance vessels). Current research on the impact of wind farms on dolphins mainly focuses on the single factor of underwater noise during the construction phase, neglecting the potential impacts of later operation and other related factors. This results in problems such as a single assessment indicator and a lack of dynamic tracking, leading to inaccurate and unpredictable assessment results, and thus failing to provide sufficient reference for developing targeted protection strategies.

[0023] In view of this, this application provides a method for assessing the impact of offshore wind farms on dolphin population survival. This method can be applied to a single server to assess the impact of offshore wind farms on dolphin population survival. The "impact of offshore wind farms on dolphin population survival" includes the comprehensive impact on dolphin population size, habitat, behavior, and reproductive status during the construction, operation, and maintenance phases of the wind farm. The method provided in this application constructs a comprehensive indicator system covering four core indicators: population size change data, habitat suitability index, behavioral disturbance index, and reproductive success rate. This system comprehensively covers the key dimensions of dolphin population survival, including population changes that directly reflect population stability, environmental adaptability supporting survival, the degree of immediate activity disturbance, and reproductive potential that determines population continuation. Furthermore, the data sources for each indicator are fully correlated with multiple influencing factors throughout the wind farm's lifecycle, such as underwater noise, water temperature and quality changes due to climate change, and human activities from passing vessels and maintenance ships, rather than being limited to construction-phase noise. This completely overcomes the limitations of related technical assessments, making the characterization of the impact on dolphin population survival more systematic and closer to real-world ecological scenarios. Secondly, by acquiring the data of the four major indicators in the first period and inputting them into a pre-built long-term dynamic assessment model, the indicators for the second period, which is later than the first period, can be predicted. This dynamic analysis method based on time series data can capture the long-term correlation between the changes in influencing factors at different stages of wind farm operation and the survival status of dolphin populations. It breaks through the limitations of static assessment of a certain stage by related technologies, makes the assessment results predictable, can identify potential risks in advance, and avoids the problem of delayed protection measures due to the inability of related technologies to predict subsequent impacts.

[0024] According to an embodiment of the present invention, an embodiment of a method for assessing the impact of offshore wind farms on dolphin population survival is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] This embodiment provides a method for assessing the impact of offshore wind farms on dolphin population survival, which can be used in the aforementioned server. Figure 2 This is a flowchart of a method for assessing the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain population change index, habitat suitability index, behavioral disturbance index and reproductive success rate of the target sea area in the first time period.

[0026] For example, the first time period refers to the baseline or historical time period for collecting basic data. This application does not limit the specific content of the first time period. Those skilled in the art can determine the population change index data based on their needs, which refers to the increase or decrease in the total number of dolphins within the first time period. The core is to quantify the stability of the population size; it is not the number at a single point in time, but rather a comparison of the numbers at two key nodes within the first time period. Dolphins may include, but are not limited to, the Indo-Pacific humpback dolphin. The population change index data is determined based on dolphin population change data, which refers to data obtained through scientific monitoring methods from the start to the end of the first time period, reflecting the increase or decrease in the total number of Indo-Pacific humpback dolphins in the target sea area. The dolphin population change data is not obtained from a single source, but through dual-source cross-validation of acoustic and image data, avoiding blind spots from a single monitoring method. Acoustic data refers to the continuous collection of signals such as whistles and pulses unique to Indo-Pacific humpback dolphins using underwater acoustic monitoring equipment deployed in the target sea area. Acoustic positioning algorithms, combined with the time difference of signals received by multiple devices, are used to determine the location and group distribution of dolphins. Simultaneously, by identifying signal frequency and intensity characteristics, group size can be statistically analyzed, making it particularly suitable for underwater scenarios with obstructed visibility, compensating for the limitations of image monitoring. Image data refers to image data collected periodically by shore-based high-definition cameras or high-definition video equipment mounted on drones during patrols of target sea areas. After image capture, the images undergo preprocessing and are then processed using deep learning-based target detection algorithms to accurately identify the number of individual Indo-Pacific humpback dolphins in the image, directly obtaining intuitive individual count data, suitable for scenarios with clear visibility at sea surface. The habitat suitability index characterizes the degree to which the environmental conditions of the target sea area are suitable for the survival of Indo-Pacific humpback dolphins, its core being the quantification of the quality of the dolphin's living environment. The habitat suitability index is determined based on environmental assessment data of the target sea area, which characterizes the objectively measured and standardized descriptive information of the environmental conditions required for dolphin survival. The behavioral disturbance index refers to the severity of external disturbances (such as wind farm noise and ship activity) affecting the natural behaviors of Indo-Pacific humpback dolphins (swimming, hunting, resting, communication, etc.). The behavioral disturbance index is determined based on dolphin behavioral monitoring data, including vocal anomaly data captured by underwater acoustic equipment and behavioral anomaly data captured by imaging equipment. Reproductive success rate refers to the proportion of Indo-Pacific humpback dolphins that successfully reproduce and raise their offspring to survival. Its core function is to quantify the long-term sustainability of the population, directly impacting its future survival. The reproductive success rate is determined based on dolphin reproductive monitoring data.

[0027] Step S202: Input the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the first time period into the pre-constructed long-term dynamic assessment model so that the long-term dynamic assessment model outputs the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period. The long-term dynamic assessment model is a time series-based prediction model, and the second time period is later than the first time period.

[0028] For example, the second time period can be the next time period after the first time period. This application embodiment does not limit the specific content of the second time period, as long as it is reasonable. In this application embodiment, the second time period is the period for which assessment indicator data prediction is required. The assessment indicator data includes population change indicator data, habitat suitability index, behavioral disturbance index, and reproductive success rate. The long-term dynamic assessment model uses a Long Short-Term Memory (LSTM) network model from machine learning, taking the assessment indicator data of the first time period as input, and outputting the predicted values ​​of each assessment indicator in the second time period.

[0029] Step S203: Based on the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period, assess the impact of offshore wind farms on dolphin population survival and obtain the assessment results.

[0030] For example, using population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period as the core criteria, first examine the values ​​of each indicator (e.g., whether they are close to or exceed warning thresholds, which can be set based on historical monitoring data, industry experience, or management needs) and their trends (e.g., whether the decline in population size is narrowing, or whether habitat suitability continues to deteriorate); combine the correlation between the indicators and wind farm-related influencing factors (noise, ship activity, etc.) to determine whether these changes are caused by wind farm operations; finally, clarify whether the impact of the wind farm is positive or negative, short-term or long-term, minor or major, and simultaneously identify the main factors. To identify interfering factors, an assessment result is ultimately formed that includes impact assessment, risk level, and targeted recommendations. Furthermore, using the predicted values ​​of the wind farm at different operational stages output by the long-term dynamic assessment model, the trend of the impact of offshore wind farms on the survival of the Indo-Pacific humpback dolphin population at different stages of operation is analyzed. For example, by comparing the predicted values ​​of the habitat suitability index at different time periods, it is determined whether the habitat environment is improving or deteriorating; the correlation between the behavioral disturbance index and the intensity of human activities is analyzed, thereby identifying the main interfering factors. In this embodiment, the navigation trajectory and speed v of ships within the wind farm area are obtained through the Automatic Identification System (AIS). s Quantity n s By collecting data on the frequency, timing, and scope of wind farm operation and maintenance activities, the intensity of human activity can be quantified.

[0031] The assessment method for the impact of offshore wind farms on dolphin population survival provided in this embodiment comprehensively covers the key dimensions of dolphin population survival by constructing a four-core indicator system encompassing population size change data, habitat suitability index, behavioral disturbance index, and reproductive success rate. This system includes not only population size changes that directly reflect population stability, but also environmental adaptability that supports survival, the degree of disturbance to immediate activities, and reproductive potential that determines population continuation. Furthermore, the data sources for each indicator are fully linked to multiple influencing factors throughout the wind farm's life cycle, such as underwater noise, water temperature and quality changes caused by climate warming, and human activities brought by passing vessels and maintenance ships, rather than being limited to construction-phase noise. This completely compensates for the one-sidedness of related technical assessments, making the characterization of the impact on dolphin population survival more systematic and closer to real ecological scenarios. Secondly, by acquiring the data of the four major indicators in the first period and inputting them into a pre-built long-term dynamic assessment model, the indicators for the second period, which is later than the first period, can be predicted. This dynamic analysis method based on time series data can capture the long-term correlation between the changes in influencing factors at different stages of wind farm operation and the survival status of dolphin populations. It breaks through the limitations of static assessment of a certain stage by related technologies, makes the assessment results predictable, can identify potential risks in advance, and avoids the problem of delayed protection measures due to the inability of related technologies to predict subsequent impacts.

[0032] This embodiment provides a method for assessing the impact of offshore wind farms on dolphin population survival, which can be used in the aforementioned server. Figure 3 This is a flowchart of a method for assessing the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the target sea area in the first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavior monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data.

[0033] Specifically, the population change index data includes a first population change rate and a second population change rate. These two rates are used to characterize population changes from different monitoring dimensions. The first population change rate is determined based on dolphin population change data obtained from underwater acoustic monitoring, and the second population change rate is determined based on image data acquired by image acquisition equipment. Step S301 includes: Step S3011: Obtain the first dolphin population change data, the second dolphin population change data, the survival suitability evaluation data of multiple environmental factors, the abnormal vocalization frequency of dolphins, the total vocalization frequency, the frequency of abnormal behavior, the total frequency of observed behavior, the number of pregnant female dolphins, and the number of surviving calves in the target sea area during the first time period. The first dolphin population change data is determined by underwater acoustic monitoring, and the second dolphin population change data is determined by image data collected by image acquisition equipment.

[0034] For example, the first dolphin population change data is determined by sound signals collected by underwater acoustic monitoring equipment, and the second dolphin population change data is determined based on image data collected by shore-based / UAV high-definition camera equipment. The survival suitability evaluation data for each environmental factor is obtained by comparing the measured data of the corresponding environmental factor with the suitable living environment range of the Indo-Pacific humpback dolphin. In this embodiment of the application, marine hydrological monitoring devices such as underwater mooring buoys or submersibles are deployed in the wind farm area to collect environmental parameters such as seawater temperature (T), salinity (S), dissolved oxygen (DO), pH, and water flow velocity (v) and direction in real time. Then, sensor network technology is used to transmit the collected data to the data processing center in real time. The abnormal frequency and total frequency of dolphin vocalizations can be obtained by underwater acoustic monitoring equipment. The underwater acoustic monitoring equipment can obtain information such as the frequency, intensity, duration, and location of vocalizations by identifying and analyzing the unique whistles and pulse sounds of the Indo-Pacific humpback dolphin. The frequency of abnormal behavior and the total frequency of observed behavior can be obtained by monitoring with video equipment.

[0035] Step S3012: Determine the population change rate of the first species in the first time period based on the first dolphin population change data.

[0036] For example, in an embodiment of this application, the rate of change of the first population can be calculated using the following formula:

[0037] in, This represents the rate of change in the population size of the first species. express The number of individual Indo-Pacific humpback dolphins is constantly being counted. express The number of individual Indo-Pacific humpback dolphins is constantly being counted. and These represent two key time points in the first time period. In this embodiment, the key time points may include, but are not limited to, the start and end times of the first time period.

[0038] Step S3013: Determine the second population change rate for the first time period based on the second dolphin population change data. For example, the formula for calculating the second population change rate is the same as the formula for calculating the first population change rate, and will not be repeated here.

[0039] In some optional implementations, the first dolphin population change data and the second dolphin population change data are determined through the following steps: Step a1: Acquire underwater acoustic signals collected by multiple underwater acoustic monitoring devices and image data collected by image acquisition devices.

[0040] For example, in this embodiment of the application, multiple underwater acoustic monitoring devices (such as self-contained recorders) are evenly deployed in the target sea area to continuously collect underwater sounds at fixed intervals. The devices will accurately capture the unique "whistles" (used for communication) and "pulse sounds" (used for positioning) of the Indo-Pacific humpback dolphin, while filtering out ship noise, wave sounds, and sounds of other marine life (such as fish calls).

[0041] Step a2: Determine the first number of dolphins at the first moment and the second number at the second moment based on underwater acoustic signals.

[0042] For example, the first moment can be the start time of the first time period, and the second moment can be the end time of the first time period. In this embodiment, the characteristics of the underwater acoustic signal are analyzed by an algorithm: ① By comparing the frequency range and duration of the whistle and pulse sound of the Indo-Pacific humpback dolphin, the target of the sound is confirmed to be the Indo-Pacific humpback dolphin; ② Based on the spatial distribution of the signal (located by the time difference of reception of multiple acoustic devices), the number of sound sources is determined, and synchronous sound signals at different locations correspond to different groups of Indo-Pacific humpback dolphins. Using an acoustic positioning algorithm, the location of the Indo-Pacific humpback dolphin is determined by the time difference of signals received by multiple monitoring devices. The calculation formula is as follows:

[0043] in, This indicates the coordinates of the Indo-Pacific humpback dolphin's location. and Indicates the coordinates of the two acoustic monitoring devices. Indicates the speed of sound. This indicates the time difference between the signals received by the two acoustic monitoring devices.

[0044] The number of individuals is estimated by correlating vocalization intensity with group size to obtain the first and second numbers of Indo-Pacific humpback dolphins. The specific steps include: ① When a single individual vocalizes, the signal intensity is relatively stable, and a correspondence model between signal intensity and number of individuals can be established using historical data (e.g., a certain intensity range corresponds to 1-2 individuals); ② When a group vocalizes, the number of individuals in each group is estimated by combining the superimposed intensity of the signal, the frequency of vocalization, and the known distribution pattern of Indo-Pacific humpback dolphin group size (e.g., common groups are 3-5 individuals, 10-20 individuals); ③ The estimated numbers of all groups are summarized to obtain the "individual number range" for acoustic monitoring (e.g., 25-30 individuals).

[0045] Step a3: Determine the first dolphin number change data based on the first and second quantities.

[0046] Step a4: Perform image recognition based on image data to determine the third number of dolphins at the first moment and the fourth number at the second moment.

[0047] For example, in the embodiments of this application, a deep learning target detection algorithm can be used to detect and recognize the image data to determine the number of Chinese white dolphins at the first and second time moments.

[0048] Step a4: Determine the dolphin population change data based on the first and second population change information.

[0049] In some alternative implementations, survival suitability assessment data for multiple environmental factors are determined through the following steps: Step b1: Obtain parameter data of multiple environmental factors collected by environmental monitoring equipment.

[0050] For example, in this embodiment of the application, marine hydrological monitoring devices such as underwater mooring buoys or buoys are deployed in the wind farm area to collect parameter data of environmental factors such as seawater temperature (T), salinity (S), dissolved oxygen (DO), pH, and water flow velocity (v) and direction in real time.

[0051] Step b2: Based on the parameter data of each environmental factor, assess the degree of impact of the corresponding environmental factor on the suitability of the Indo-Pacific humpback dolphin habitat, and obtain the survival suitability evaluation data of the corresponding environmental factor.

[0052] For example, suitability assessments can be performed on the parameter data of each environmental factor according to preset evaluation rules to obtain survival suitability assessment data. In this embodiment of the application, the survival suitability assessment data for each environmental factor... The score can be obtained by comparing parameter data with the suitable habitat range of the Indo-Pacific humpback dolphin.

[0053] Step S3014: Determine the habitat suitability index for the first time period based on the survival suitability assessment data of multiple environmental factors.

[0054] For example, in this embodiment of the application, the habitat suitability index can be calculated by the following formula:

[0055] in, Indicates the habitat suitability index. Indicates the first The weight of each environmental factor Indicates the first Suitability assessment data for each environmental factor. Weights of each environmental factor. It was determined using the Analytic Hierarchy Process (AHP).

[0056] Step S3015: Determine the behavioral interference index for the first time period based on the abnormal vocalization frequency, total vocalization frequency, abnormal behavior frequency, and total observed behavior frequency of dolphins.

[0057] For example, in this embodiment of the application, the behavioral interference index can be calculated by the following formula:

[0058] in, Indicates the behavioral interference index. , Indicates the weighting coefficient. This indicates the abnormal frequencies of vocalization detected by acoustic equipment in the Indo-Pacific humpback dolphins. Indicates the total frequency of sound. This indicates the frequency of abnormal behaviors (avoidance, agitation, etc.) detected by the video equipment. This indicates the total frequency of observed behaviors.

[0059] Step S3016: Determine the reproductive success rate for the first period based on the number of pregnant female piglets and the number of surviving calves.

[0060] For example, in this embodiment of the application, the reproductive success rate can be calculated using the following formula:

[0061] in, Indicates the reproductive success rate. This indicates the number of surviving calves.

[0062] Step S302 involves inputting the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate from the first time period into a pre-constructed long-term dynamic assessment model. This allows the long-term dynamic assessment model to output the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the second time period. The long-term dynamic assessment model is a time-series-based prediction model, and the second time period is later than the first time period. For details, please refer to [link to details]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0063] In some alternative implementations, the long-term dynamic evaluation model is constructed through the following steps: Step c1: Obtain time series data of assessment indicators for the target sea area within a preset time period. The time series data of assessment indicators are used to characterize the changes in population size, habitat suitability index, behavioral disturbance index, and reproductive success rate over time.

[0064] For example, the time series data of the evaluation indicators within the preset time period can be historical monitoring data from the past 5-10 years.

[0065] Step c2: Using the first time period as a sliding window, the time series data of the evaluation index is divided using a preset sliding step size to obtain the first training data.

[0066] For example, the first time period may include, but is not limited to, one year, and the preset activity step size can be determined according to actual needs.

[0067] Step c3: Using the second time period as a sliding window, the time series data of the evaluation index is divided using a preset sliding step size to obtain the second training data.

[0068] For example, the second time period may include, but is not limited to, one year.

[0069] Step c4: Associate the first training data and the second training data according to the prediction requirements to construct a dataset.

[0070] For example, demand forecasting can be based on the previous year's assessment indicator data to predict the next year's assessment indicator data. In this embodiment, the specific content of the association method is not limited, and those skilled in the art can determine it according to their needs.

[0071] Step c5: Train the preset neural network model based on the dataset until the model accuracy meets the preset requirements, and obtain the long-term dynamic evaluation model.

[0072] For example, in this embodiment of the application, the preset neural network model may include, but is not limited to, a Long Short-Term Memory (LSTM) model. The input layer of the LSTM model receives data on indicators such as population change rate, habitat suitability index, behavioral disturbance index, and reproductive success rate at different time steps; the hidden layer of the model learns the long-term dependencies in the data through LSTM units (that is, when the model makes predictions, it can fully consider the impact of historical data on the future and accurately predict the survival status of the Indo-Pacific humpback dolphin population in the future); the output layer of the model outputs the predicted values ​​of various evaluation indicators for a future period of time (such as 1 year, 2 years, etc.).

[0073] Historical monitoring data from the past 5-10 years was collected as the training set, divided into a 70% training set, 20% validation set, and 10% test set. Model performance was evaluated using metrics such as Mean Squared Error (MSE) and Mean Absolute Error (MAE). Model parameters (such as the number of hidden layer nodes, learning rate, and number of iterations) were continuously adjusted to achieve good prediction results on the validation set. For example, when the MSE is less than a set threshold (e.g., 0.05), the model is considered successfully trained (a reasonable threshold needs to be set based on actual research requirements). The formulas for Mean Squared Error (MSE) and Mean Absolute Error (MAE) are as follows:

[0074]

[0075] in, Indicates the first The true value of each sample Indicates the first The predicted value for each sample, Indicates the number of samples.

[0076] Step S303 assesses the impact of offshore wind farms on dolphin population survival based on population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate during the second time period, obtaining the assessment results. For details, please refer to... Figure 3 Step S203 of the illustrated embodiment will not be described again here.

[0077] This embodiment provides a method for assessing the impact of offshore wind farms on dolphin population survival, which can be used in the aforementioned server. Figure 4 This is a flowchart of a method for assessing the impact of offshore wind farms on dolphin population survival according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Obtain population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the target sea area during the first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavior monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0078] Step S402 involves inputting the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate from the first time period into a pre-built long-term dynamic assessment model. This allows the long-term dynamic assessment model to output the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate for the second time period. The long-term dynamic assessment model is a time-series-based prediction model, and the second time period is later than the first time period. For details, please refer to [link to details]. Figure 2 Step S302 of the illustrated embodiment will not be described again here.

[0079] Step S403: Based on the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period, assess the impact of offshore wind farms on dolphin population survival and obtain the assessment results.

[0080] Specifically, step S403 includes: Step S4031: Obtain the early warning thresholds corresponding to population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate.

[0081] For example, in this embodiment of the application, it is necessary to set a warning threshold for each evaluation indicator. The specific content of the warning threshold can be determined according to actual needs, and this embodiment of the application does not make specific limitations.

[0082] Step S4032: Compare the population change index, habitat suitability index, behavioral disturbance index, and reproductive success rate of the second time period with the corresponding warning thresholds to obtain the comparison results.

[0083] Step S4033: Based on the comparison results, assess the impact of offshore wind farms on dolphin population survival and obtain the assessment results.

[0084] For example, in this embodiment of the application, a system warning is triggered when the predicted value of an indicator exceeds the threshold range. For instance, if the population change rate is below -5% for two consecutive years, the habitat suitability index is below 0.6, the behavioral disturbance index is above 0.3, and the reproductive success rate is below 40%, the assessment system will automatically send warning information to relevant management departments, research institutions, and wind farm operators to remind them to take appropriate protective measures in a timely manner.

[0085] Based on the predicted values ​​output by the assessment model, the trend of the impact of offshore wind farms on the survival of the Indo-Pacific humpback dolphin population at different stages of operation is analyzed. For example, by comparing the predicted values ​​of habitat suitability index at different time periods, it is determined whether the habitat environment is improving or deteriorating; the correlation between behavioral disturbance index and intensity of human activities is analyzed, thereby identifying the main disturbance factors.

[0086] The following specific embodiments illustrate the assessment method for the impact of offshore wind farms on dolphin population survival provided in this application.

[0087] Example 1: The method for assessing the impact of offshore wind farms on dolphin population survival provided in this application embodiment can be applied to an assessment system. The assessment system includes a data acquisition module, a data processing module, an index calculation and model operation module, and a result display and early warning module. The data acquisition module is primarily responsible for collecting various types of data. This module consists of underwater acoustic monitoring equipment, shore-based cameras / UAV aerial cameras, environmental monitoring sensors, and an AIS data receiving device. It collects various types of data in real time at a set frequency and transmits the data to the data processing module via wireless or wired transmission.

[0088] The data processing module is mainly responsible for cleaning the collected data, removing outliers and noisy data, converting formats, unifying the diverse data formats collected from different devices, and then storing the processed data in the database for subsequent analysis.

[0089] The index calculation and model operation module mainly involves retrieving data from the database to calculate the values ​​of various indicators based on the constructed evaluation index system; inputting the index values ​​into the pre-trained LSTM evaluation model for prediction calculation; and outputting the evaluation results. Furthermore, the model needs to be updated and trained regularly using newly collected data to ensure its timeliness and accuracy.

[0090] The results display and early warning module primarily presents the system's assessment results in a visual format. It uses line graphs to show population change trends, bar charts to display habitat suitability in different regions, and scatter plots to show the correlation between influencing factors and assessment indicators. When the assessment results trigger early warning conditions, the system sends warning information to relevant personnel via SMS, email, and system pop-ups, and generates a detailed assessment report, including an analysis of the current population survival status, key influencing factors, future trend predictions, and conservation recommendations.

[0091] Example 2: This application provides a comprehensive, accurate, and dynamically trackable assessment method that enables long-term monitoring and analysis of the impact of operational offshore wind farms on the survival of the Indo-Pacific humpback dolphin population from multiple dimensions, providing strong support for the protection and management of relevant departments. The method includes the following steps: Step 1, Multi-source data collection and integration: (1) Acoustic data acquisition: In the offshore wind farm and the surrounding sea area where the Chinese white dolphin is mainly active, multiple underwater acoustic monitoring devices (such as self-contained underwater acoustic recorders) are deployed to continuously collect underwater acoustic signals at fixed time intervals (such as every 10 minutes). By identifying and analyzing the unique whistles, pulse sounds and other signals of the Chinese white dolphin, information such as its sound frequency, intensity, sound time and location is obtained. (2) Image Data Acquisition: Using shore-based high-definition cameras / high-definition video equipment mounted on drones, regular (e.g., weekly) patrols and filming are conducted on the wind farm and surrounding sea areas (mainly to obtain image data of Indo-Pacific humpback dolphins). Deep learning-based target detection algorithms are used to identify the number of individual Indo-Pacific humpback dolphins, group size, and behavioral status (swimming, feeding, resting, etc.) in the captured images. Preprocessing of the captured images is necessary, including noise reduction and contrast enhancement, to improve recognition accuracy.

[0092] (3) Environmental data acquisition: Deploy marine hydrological monitoring devices such as underwater mooring buoys or buoys in the wind farm area to collect environmental parameters such as seawater temperature T, salinity S, dissolved oxygen DO, pH, water flow velocity v and direction in real time, and then use sensor network technology to transmit the collected data to the data processing center in real time.

[0093] (4) Human activity data collection: The navigation trajectory, speed vs, and number ns of ships in the wind farm area are obtained through the Automatic Identification System (AIS). The frequency, time and scope of wind farm operation and maintenance activities are statistically analyzed, and the intensity of human activities is then quantified.

[0094] (5) Data integration: Establish a unified data format and timestamp, and integrate different types of data into a relational database. For example, the location information of Indo-Pacific humpback dolphins obtained by acoustic positioning is linked and stored with hydrological environmental data and human activity data at the same time to facilitate subsequent comprehensive analysis.

[0095] Step 2, construct the evaluation indicator system: (1) Population change index: The population change rate is calculated by comparing the number of Chinese white dolphins identified by image recognition and acoustic monitoring statistics in different time periods.

[0096] (2) Habitat suitability index: The Habitat Suitability Index (HSI) model was constructed to comprehensively consider the impact of various environmental factors on the habitat suitability of the Chinese white dolphin.

[0097] (3) Behavioral interference index: The behavioral interference index is calculated based on the abnormal frequency of vocalization of Chinese white dolphins monitored by acoustic equipment (such as long-term high-frequency vocalization, abnormal vocalization interval, etc.) and the frequency of abnormal behaviors (avoidance, agitation, etc.) monitored by video equipment.

[0098] (4) Reproductive success rate index: The reproductive success rate is calculated by long-term tracking and observation of the number of pregnant female pigs and the number of surviving piglets.

[0099] Step 3: Establish a long-term dynamic evaluation model: (1) Model Construction: The Long Short-Term Memory (LSTM) network model in machine learning is used to predict the future survival status of the Indo-Pacific humpback dolphin population by taking time series evaluation index data as input. The input layer of the model receives index data such as population change rate, habitat suitability index, behavioral disturbance index, and reproductive success rate at different time steps; the hidden layer of the model learns the long-term dependencies in the data through LSTM units (that is, when the model makes predictions, it can fully consider the impact of historical data on the future and accurately predict the survival status of the Indo-Pacific humpback dolphin population in the future); the output layer of the model outputs the predicted values ​​of each evaluation index for a future period of time (such as 1 year, 2 years, etc.).

[0100] (2) Model Training and Validation: Collect historical monitoring data from the past 5-10 years as the training set, dividing the data into a 70% training set, 20% validation set, and 10% test set. Use metrics such as mean squared error (MSE) and mean absolute error (MAE) to evaluate model performance, and continuously adjust model parameters (such as the number of hidden layer nodes, learning rate, number of iterations, etc.) to achieve good prediction results on the validation set. For example, when the MSE is less than a set threshold (such as 0.05), the model is considered to have been successfully trained (a reasonable threshold needs to be set according to the actual research requirements).

[0101] Step 4, Analysis and Early Warning of Evaluation Results: (1) Results analysis: Based on the predicted values ​​output by the evaluation model, the trend of the impact of offshore wind farms on the survival of the Indo-Pacific humpback dolphin population at different stages during the operation period was analyzed. For example, by comparing the predicted values ​​of habitat suitability index at different time periods, it was determined whether the habitat environment was improving or deteriorating, and the correlation between behavioral disturbance index and human activity intensity was analyzed to identify the main disturbance factors.

[0102] (2) Early warning mechanism: It is necessary to set early warning thresholds for each assessment indicator. When the predicted value of an indicator exceeds the threshold range, the system will trigger an early warning. For example, when the population change rate is below -5% for two consecutive years, the habitat suitability index is below 0.6, the behavioral disturbance index is above 0.3, and the reproductive success rate is below 40%, the assessment system will automatically send early warning information to relevant management departments, research institutions, and wind farm operators to remind them to take appropriate protective measures in a timely manner.

[0103] Example 3: Fifteen underwater acoustic monitoring devices were evenly deployed across a 50-square-kilometer area surrounding an offshore wind farm, collecting acoustic data every 10 minutes. Drones were used to conduct weekly patrols and photography of the area, each flight lasting one hour and covering the entire monitoring area. Simultaneously, ten water quality monitoring buoys and eight marine hydrological monitoring moorings were deployed to collect real-time seawater environmental parameters, with data updated every 30 minutes and transmitted to a data processing center. Through cooperation with maritime authorities and the wind farm operator, AIS data of vessels within the wind farm area was obtained and processed and stored hourly.

[0104] Calculating the population change rate: Assuming the population of Indo-Pacific humpback dolphins was 300 at the beginning of 2023 and 280 at the beginning of 2024, the population change rate is: However, low- and medium-frequency noise, changes in ocean hydrology, and increased human activities during the operation of offshore wind farms may lead to individual migration or death, directly affecting population size.

[0105] Calculating the Habitat Suitability Index: Assuming that seawater temperature is weighted using AHP (Adaptive Hierarchical Method). Salinity weight Dissolved oxygen weight Water depth weight Substrate type weight The weight of feed biomass, wprey = 0.2. The evaluation values ​​for each factor are S... T =0.8, S S =0.7, S DO =0.9, S d =0.8, S sed =0.6、S prey =0.7, then the habitat suitability index is:

[0106] Wind farm operations may reduce suitability by driving away white dolphins with noise, altering water flow leading to reduced food availability, or directly occupying habitats.

[0107] Calculating the behavioral interference index: If, after the wind farm begins operation, the dolphin avoidance behavior frequency is 8 times / hour and the background frequency is 1 time / hour, then the behavioral interference index is 8 / 1 = 8 (truncated to 1.0). Using a graded scoring method (e.g., scoring directly from 0 to 1), the value is taken as 0.8, combined with observed moderate-intensity interference (e.g., occasional avoidance, but not completely leaving the area). The change in the behavioral interference index may be due to the low-to-medium frequency noise from the wind farm and the presence of ships, which directly interfere with the sonar system of the Indo-Pacific humpback dolphins, thus affecting their positioning and communication.

[0108] Calculating reproductive success rate: If there are 10 breeding females in a wind farm area, and 5 calves survive within 1 year, then the reproductive success rate = 5 / 10 = 0.5. However, the reproductive success rate may be affected by habitat degradation and behavioral disturbances, leading to a decrease in female conception rate and a lower calf survival rate (e.g., the mother is unable to nurse her calves due to difficulty in finding food).

[0109] Monitoring data from 2015 to 2024 was collected and used as the training set for the model. An LSTM model was selected, and relevant parameters were set, such as 128 hidden layer nodes, a learning rate of 0.001, and 1000 iterations. During training, when the mean squared error (MSE) on the validation set gradually decreased to 0.04 (MSE ≤ 0.05), it was considered to have achieved good prediction results. The model was then validated using real-time monitoring data from the first half of 2025. The predicted population change rate for the next year was directly compared with the actual observed population change rate by the end of 2025 to verify the model's accuracy and reliability.

[0110] If the warning threshold for the population change rate of the Indo-Pacific humpback dolphin is set at -5%, a system warning will be triggered when the assessment model outputs a population change rate of -6% for the next year. The assessment system will immediately send SMS and email warning messages to relevant departments, and simultaneously display a warning pop-up window on the assessment system interface, reminding relevant departments to take appropriate countermeasures in a timely manner.

[0111] In addition, the assessment system will periodically (e.g., monthly / quarterly / semi-annually) generate assessment reports for the selected areas, visually displaying changes in the population size of Indo-Pacific humpback dolphins and habitat suitability through charts. If the report shows that the activity of wind farm maintenance vessels in the selected area has led to an increase in the disturbance index of Indo-Pacific humpback dolphins, relevant management departments can take management measures to restrict the speed and range of vessel navigation. At the same time, wind farm operators should also adjust their operation and maintenance plans to reduce disturbance to the Indo-Pacific humpback dolphins.

[0112] This embodiment also provides an assessment device for the impact of offshore wind farms on dolphin population survival. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0113] This embodiment provides an assessment device for the impact of offshore wind farms on dolphin population survival, such as... Figure 5 As shown, it includes: The acquisition module 501 is used to acquire population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the target sea area in the first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavior monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data. The determination module 502 is used to input the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the first time period into the pre-built long-term dynamic assessment model so that the long-term dynamic assessment model outputs the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period. The long-term dynamic assessment model is a time series-based prediction model, and the second time period is later than the first time period. Assessment module 503 is used to assess the impact of offshore wind farms on dolphin population survival based on population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period, and to obtain assessment results.

[0114] In some optional implementations, the population change index data includes a first population change rate and a second population change rate. The first and second population change rates are used to characterize population changes from different monitoring dimensions. The first population change rate is determined based on dolphin population change data obtained from underwater acoustic monitoring, and the second population change rate is determined based on image data acquired by an image acquisition device. The acquisition module 501 includes: The first acquisition submodule is used to acquire data on dolphin population changes in the target sea area during the first time period, survival suitability assessment data for multiple environmental factors, abnormal vocalization frequency of dolphins, total vocalization frequency, frequency of abnormal behavior, total frequency of observed behavior, number of pregnant female dolphins, and number of surviving calves. The first dolphin population change data is determined by underwater acoustic monitoring, and the second dolphin population change data is determined by image data acquired by image acquisition equipment. The first determining submodule is used to determine the first population change rate for the first time period based on the first dolphin population change data. The second determination submodule is used to determine the population change rate of the second species in the first time period based on the second dolphin population change data. The third determination submodule is used to determine the habitat suitability index for the first time period based on survival suitability assessment data of multiple environmental factors; The fourth submodule is used to determine the behavioral interference index for the first time period based on the abnormal vocalization frequency, total vocalization frequency, abnormal behavior frequency, and total observed behavior frequency of dolphins. The fifth determination submodule is used to determine the reproductive success rate of the first period based on the number of pregnant sows and the number of surviving calves.

[0115] In some alternative implementations, the long-term dynamic evaluation model is constructed through the following steps: Acquire time series data of assessment indicators for the target sea area within a preset time period. The time series data of assessment indicators are used to characterize the changes in population size, habitat suitability index, behavioral disturbance index and reproductive success rate over time. Using the first time period as a sliding window, the time series data of the evaluation index is divided using a preset sliding step size to obtain the first training data; The second time period is used as a sliding window, and the time series data of the evaluation index is divided using a preset sliding step size to obtain the second training data. The first and second training data are associated according to the prediction requirements to construct a dataset; The preset neural network model is trained based on the dataset until the model accuracy meets the preset requirements, thus obtaining a long-term dynamic evaluation model.

[0116] In some optional implementations, the evaluation module 503 includes: The second acquisition submodule is used to acquire data on population change indicators, habitat suitability index, behavioral disturbance index, and early warning thresholds corresponding to reproductive success rate. The comparison submodule is used to compare the population change index, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period with the corresponding warning thresholds to obtain the comparison results. The assessment submodule is used to evaluate the impact of offshore wind farms on dolphin population survival based on the comparison results, and obtain the assessment results.

[0117] In some optional implementations, the first dolphin population change data and the second dolphin population change data are determined through the following steps: Acquire underwater acoustic signals collected by multiple underwater acoustic monitoring devices and image data collected by image acquisition devices; The first number of dolphins at the first moment and the second number at the second moment were determined based on underwater acoustic signals. The first dolphin population change data is determined based on the first and second counts; Image recognition was performed based on image data to determine the third number of dolphins at the first moment and the fourth number at the second moment; The second dolphin population change data were determined based on the third and fourth counts.

[0118] In some alternative implementations, survival suitability assessment data for multiple environmental factors are determined through the following steps: Acquire parameter data of multiple environmental factors collected by environmental monitoring equipment; Based on the parameter data of each environmental factor, the impact of the corresponding environmental factor on the suitability of the Indo-Pacific humpback dolphin habitat is assessed, and survival suitability evaluation data of the corresponding environmental factor is obtained.

[0119] The device for assessing the impact of offshore wind farms on dolphin population survival provided in this embodiment of the invention can execute the assessment method for assessing the impact of offshore wind farms on dolphin population survival provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0120] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0121] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0122] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0123] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the method for assessing the impact of offshore wind farms on dolphin population survival according to embodiments of the present invention.

[0124] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0125] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for assessing the impact of offshore wind farms on dolphin population survival shown in the above embodiments is implemented.

[0126] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0127] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for assessing the impact of offshore wind farms on dolphin population survival, characterized in that, The method includes: Data on population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate of the target sea area in the first time period were obtained. The population change indicators were determined based on dolphin population change data, the habitat suitability index was determined based on environmental assessment data of the target sea area, the behavioral disturbance index was determined based on dolphin behavioral monitoring data, and the reproductive success rate was determined based on dolphin reproductive monitoring data. The population change index, habitat suitability index, behavioral disturbance index, and reproductive success rate of the first time period are input into a pre-constructed long-term dynamic assessment model so that the long-term dynamic assessment model outputs the population change index, habitat suitability index, behavioral disturbance index, and reproductive success rate of the second time period. The long-term dynamic assessment model is a time series-based prediction model, and the second time period is later than the first time period. The impact of offshore wind farms on dolphin population survival was assessed based on population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate data from the second time period. The assessment results were obtained.

2. The method according to claim 1, characterized in that, The population change index data includes a first population change rate and a second population change rate. These two rates are used to characterize population changes from different monitoring dimensions. The first population change rate is determined based on dolphin population change data obtained from underwater acoustic monitoring, and the second population change rate is determined based on image data acquired by image acquisition equipment. The step of acquiring the population change index data, habitat suitability index, behavioral disturbance index, and reproductive success rate of the target sea area within the first time period includes: The data obtained in the target sea area during the first time period included the first dolphin population change data, the second dolphin population change data, survival suitability assessment data for multiple environmental factors, abnormal vocalization frequency of dolphins, total vocalization frequency, frequency of abnormal behavior, total frequency of observed behavior, number of pregnant female dolphins, and number of surviving calves. The first dolphin population change data was determined by underwater acoustic monitoring, and the second dolphin population change data was determined by image data acquired by image acquisition equipment. The population change rate of the first species during the first time period is determined based on the first dolphin population change data. The population change rate of the second species during the first time period was determined based on the second dolphin population change data. The habitat suitability index for the first time period is determined based on the survival suitability assessment data of the aforementioned multiple environmental factors. The behavioral interference index for the first time period is determined based on the abnormal vocalization frequency, total vocalization frequency, abnormal behavior frequency, and total observed behavior frequency of the dolphins. The reproductive success rate for the first period is determined based on the number of pregnancies of the mother pigs and the number of surviving calves.

3. The method according to claim 1 or 2, characterized in that, The long-term dynamic evaluation model is constructed through the following steps: Acquire time series data of assessment indicators for the target sea area within a preset time period. The time series data of assessment indicators are used to characterize the changes in population size, habitat suitability index, behavioral disturbance index, and reproductive success rate over time. Using the first time period as a sliding window, the time series data of the evaluation index is divided using a preset sliding step size to obtain the first training data; Using the second time period as a sliding window, the time series data of the evaluation index is divided using a preset sliding step size to obtain the second training data; The first training data and the second training data are associated according to the prediction requirements to construct a dataset; The preset neural network model is trained based on the dataset until the model accuracy meets the preset requirements, thus obtaining the long-term dynamic evaluation model.

4. The method according to claim 1 or 2, characterized in that, The steps for assessing the impact of offshore wind farms on dolphin population survival based on population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period, and obtaining the assessment results, include: Acquire early warning thresholds for population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate; The population change index, habitat suitability index, behavioral disturbance index, and reproductive success rate for the second time period were compared with the corresponding warning thresholds to obtain the comparison results. The impact of offshore wind farms on dolphin population survival was assessed based on the comparison results, and the assessment results were obtained.

5. The method according to claim 2, characterized in that, The first dolphin population change data and the second dolphin population change data were determined through the following steps: Acquire underwater acoustic signals collected by multiple underwater acoustic monitoring devices and image data collected by image acquisition devices; The first number of dolphins at the first moment and the second number at the second moment are determined based on the underwater acoustic signals. The change data in the number of the first dolphins is determined based on the first quantity and the second quantity; Based on the image data, image recognition is performed to determine the third number of dolphins at the first moment and the fourth number at the second moment; The second dolphin population change data is determined based on the third and fourth quantities.

6. The method according to claim 2, characterized in that, The survival suitability assessment data for the aforementioned multiple environmental factors were determined through the following steps: Acquire parameter data of multiple environmental factors collected by environmental monitoring equipment; Based on the parameter data of each environmental factor, the degree of impact of the corresponding environmental factor on the habitat suitability of the Indo-Pacific humpback dolphin is assessed, and the survival suitability evaluation data of the corresponding environmental factor is obtained.

7. An assessment device for the impact of offshore wind farms on dolphin population survival, characterized in that, The device includes: The acquisition module is used to acquire population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the target sea area in the first time period. The population change index data is determined based on dolphin population change data, the habitat suitability index is determined based on environmental assessment data of the target sea area, the behavioral disturbance index is determined based on dolphin behavior monitoring data, and the reproductive success rate is determined based on dolphin reproductive monitoring data. The determination module is used to input the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the first time period into a pre-constructed long-term dynamic assessment model, so that the long-term dynamic assessment model outputs the population change index data, habitat suitability index, behavioral disturbance index and reproductive success rate of the second time period. The long-term dynamic assessment model is a time series-based prediction model, and the second time period is later than the first time period. The assessment module is used to evaluate the impact of offshore wind farms on dolphin population survival based on population change indicators, habitat suitability index, behavioral disturbance index, and reproductive success rate in the second time period, and to obtain assessment results.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the assessment method for the impact of offshore wind farms on dolphin population survival as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the assessment method for the impact of offshore wind farms on dolphin population survival as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the assessment method for the impact of offshore wind farms on dolphin population survival as described in any one of claims 1 to 6.

Images