CN118095112A - Marine floating facility environment influence analysis and quantification method - Google Patents
Marine floating facility environment influence analysis and quantification method Download PDFInfo
- Publication number
- CN118095112A CN118095112A CN202410524125.8A CN202410524125A CN118095112A CN 118095112 A CN118095112 A CN 118095112A CN 202410524125 A CN202410524125 A CN 202410524125A CN 118095112 A CN118095112 A CN 118095112A
- Authority
- CN
- China
- Prior art keywords
- marine
- influence
- model
- floating facility
- facility
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007667 floating Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000011002 quantification Methods 0.000 title claims abstract description 7
- 230000007613 environmental effect Effects 0.000 claims abstract description 66
- 230000008859 change Effects 0.000 claims abstract description 57
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 238000013461 design Methods 0.000 claims abstract description 18
- 230000007774 longterm Effects 0.000 claims abstract description 15
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 230000020477 pH reduction Effects 0.000 claims abstract description 9
- 230000003993 interaction Effects 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 38
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 36
- 238000011156 evaluation Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 18
- 230000004913 activation Effects 0.000 claims description 15
- 238000004088 simulation Methods 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 239000000126 substance Substances 0.000 claims description 11
- 241000894007 species Species 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 239000013535 sea water Substances 0.000 claims description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 229910052799 carbon Inorganic materials 0.000 claims description 5
- 238000002790 cross-validation Methods 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 5
- 239000002699 waste material Substances 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 4
- 230000008713 feedback mechanism Effects 0.000 claims description 4
- 239000012530 fluid Substances 0.000 claims description 4
- 241000251468 Actinopterygii Species 0.000 claims description 3
- 239000002028 Biomass Substances 0.000 claims description 3
- 241000283153 Cetacea Species 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 229930002875 chlorophyll Natural products 0.000 claims description 3
- 235000019804 chlorophyll Nutrition 0.000 claims description 3
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 239000000356 contaminant Substances 0.000 claims description 3
- 230000006378 damage Effects 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 235000015097 nutrients Nutrition 0.000 claims description 3
- 231100000719 pollutant Toxicity 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 150000003839 salts Chemical class 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000000547 structure data Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000013523 data management Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 231100000290 environmental risk assessment Toxicity 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis and management, in particular to an environmental impact analysis and quantification method for an offshore floating facility, which comprises the following steps: evaluating the design, position and operation mode of the offshore floating facility, and determining the type of direct and indirect influence of the offshore floating facility on the marine ecosystem; establishing a marine ecological environment baseline model by using a remote sensing technology and marine environment monitoring data; predicting the influence of the floating facility on the marine environment by simulating the operation of the floating facility on the sea and comparing and analyzing the floating facility with a baseline model; the method for evaluating the service value of the ecological system is applied to quantify the influence of the operation of the offshore floating facility on the service of the marine ecological system; and establishing a dynamic prediction analysis model to dynamically evaluate the environmental influence of the offshore floating facility by combining the climate change and the long-term environmental change factors of ocean acidification. The invention can provide scientific basis for the adaptability management of offshore facilities, thereby optimizing the design and operation of the facilities and reducing the negative influence on the marine ecological system.
Description
Technical Field
The invention relates to the technical field of data analysis and management, in particular to an environmental impact analysis and quantification method for an offshore floating facility.
Background
In the process of exploring and utilizing marine resources, there is an increasing use of offshore floating facilities such as drilling platforms, wind power plants and other offshore structures. These facilities play an important role in the fields of energy acquisition, scientific research, environmental monitoring and the like. However, as offshore activities increase, the impact of these floating facilities on the marine environment has also attracted considerable attention, particularly their potential impact on water quality, marine biodiversity, and overall marine ecosystem balance.
Traditional environmental impact assessment methods focus on land construction projects, while environmental impact assessment techniques for offshore floating facilities are still in the development stage, these assessments are usually based on static models and assumptions, and it is difficult to accurately predict long-term and complex environmental changes, especially when considering the effects of global problems such as climate change and ocean acidification. In addition, the existing methods often ignore complex interactions between various elements in the marine environment, such as water flow dynamics, biological community variation, acoustic interference, and other factors, which are important factors that cannot be ignored in assessing the environmental impact of the offshore floating facility.
Therefore, there is an urgent need to develop a new environmental impact assessment method that can dynamically and comprehensively assess the environmental impact of an offshore floating facility while taking into account long-term environmental changes and complex interactions within the marine ecosystem.
Disclosure of Invention
Based on the above objects, the present invention provides a method for analyzing and quantifying the environmental impact of an offshore floating facility.
The method for analyzing and quantifying the environmental impact of the offshore floating facility comprises the following steps:
S1: evaluating the design, position and operation mode of the offshore floating facility, and determining the type of direct and indirect influence of the offshore floating facility on the marine ecosystem;
s2: establishing a marine ecological environment baseline model by using a remote sensing technology and marine environment monitoring data;
S3: predicting the influence of the marine floating facility on the marine environment by simulating the operation of the marine floating facility and comparing and analyzing the marine floating facility with a baseline model, wherein the influence comprises water quality change, biological community structure change and acoustic interference;
S4: the method for evaluating the service value of the ecological system is applied to quantify the influence of the operation of the offshore floating facility on the service of the marine ecological system;
s5: and establishing a dynamic prediction analysis model to dynamically evaluate the environmental influence of the offshore floating facility by combining the climate change and the long-term environmental change factors of ocean acidification.
Further, the S1 specifically includes:
S11, design analysis: analyzing design parameters of the offshore floating facility, including the size, shape, materials, buoyancy characteristics and stability of the facility, to determine how the design parameters affect the physical contact area, resistance and potential benthonic habitat destruction of the facility with seawater;
S12, position selection evaluation: based on the GIS system and the marine topography data, estimating marine ecological characteristics of the preset position, including water depth, water flow, tide pattern and biodiversity hot spots, so as to predict the influence of the facility position on the local ecological system;
S13, operation mode analysis: examining a predetermined operating mode of the facility, including energy demand, waste emission, supply of materials, personnel variation, and evaluating how the operating mode indirectly affects the marine ecosystem, in particular by sound, vibration, light pollution and chemical pollution;
s14, direct impact quantization: combining the analysis results of S11 and S12, and quantifying the direct physical and chemical influence of the design and the position of facilities on the marine ecological system by using numerical simulation software (OpenFOAM), wherein the direct physical and chemical influence comprises the ecological environment change, the local water flow mode change and the pollutant diffusion caused by the artificial structure;
S15, indirect influence prediction: based on the operation mode analysis of S13, a system dynamics model (Vensim) is constructed to simulate interaction and feedback mechanisms among elements in the marine ecological system, including change of a food network structure, transition of species distribution and adjustment of an ecological competition mode;
S16, comprehensive evaluation: according to the influence degree of direct and indirect influence on the marine ecological system, different weights are distributed, various influences are comprehensively considered by utilizing a multi-index decision analysis method, comprehensive evaluation is carried out, and the overall environmental influence of the marine floating facility is evaluated, wherein the influence evaluation of an ecological sensitive area and potential long-term ecological consequences are included;
S17, influence type judgment: based on the comprehensive evaluation result, setting thresholds of various influences according to the resistance and restoring force of the ecological system, comparing the comprehensive evaluation result with the thresholds, and determining influence types including biodiversity influence, ecological service function influence and species habitat influence.
Further, the step S2 specifically includes:
S21, data collection and integration: collecting multi-time-sequence remote sensing images covering the preset position of the offshore floating facility and the surrounding sea areas by utilizing a satellite remote sensing technology, wherein the multi-time-sequence remote sensing images comprise a spectrum image, a temperature distribution map, a sea surface height map and a chlorophyll concentration distribution map; in combination with on-site marine environmental monitoring data, including water quality parameters (such as temperature, salinity, dissolved oxygen content), submarine geologic structures, and biodiversity survey results (including the distribution and quantity of plankton, benthos, and large marine organisms);
S22, constructing a baseline model: the method comprises the steps of applying a ground GIS (geographic information system) and Environmental Information System (EIS) technology to fuse remote sensing data and monitoring data, establishing a sea area space database, and simulating the natural state of a sea ecological system when the sea ecological system is not influenced by a sea floating facility by utilizing a sea ecological model (such as EcoSIM, ROMS and the like) and combining the sea area space database to construct a sea ecological environment baseline model, wherein the sea ecological environment baseline model can reflect the biological diversity, the ecological system structure and function and the natural variation range of a key ecological process in the sea;
S23, model verification and calibration: and verifying the accuracy and reliability of the model by comparing the output of the baseline model with the historical monitoring data, and adjusting and calibrating the model parameters according to the verification result.
Further, the step S3 specifically includes:
S31, facility operation simulation: simulating the influence of physical existence of the offshore floating facility on water flow, temperature distribution and illumination conditions of the surrounding sea area by using a computational fluid dynamics CFD model, and simulating water quality changes caused in the operation process of the facility by combining the operation parameters of the floating facility, wherein the water quality changes comprise changes of nutrient salt concentration and emission of harmful substances;
S32, biological community structure change simulation: based on a hydrodynamic CFD model, simulating the influence of facility operation on a marine organism community structure by combining with a marine ecological model, evaluating the variety of species, the variation of biomass and ecological niches, and evaluating the potential influence of the ecological environment variation (such as the influence of an artificial light source on plankton behaviors) caused by the facility operation on the biological community structure;
s33, acoustic interference assessment: using an acoustic model (RAM or Bellhop) to simulate the propagation of noise generated during operation of the facility in the marine environment, including the frequency, intensity and coverage of the noise, and evaluating the potential interference effect of the noise on marine mammals, fish and sound sensitive organisms;
s34, comparing and analyzing with a baseline model: comparing the facility operation simulation result with an established marine ecological environment baseline model, identifying and quantifying environmental changes caused by facility operation, and analyzing specific influences of facility operation on water quality, biological community structure and acoustic environment, including evaluation of positive and negative effects;
S35, comprehensive influence prediction: and (3) evaluating the overall influence of the operation of the offshore floating facility on the marine environment by combining simulation results of water quality change, biological community structure change and acoustic interference.
Further, the step S4 specifically includes:
S41, ecosystem service identification and classification: identifying and classifying ecosystem services affected by the marine floating facility according to characteristics of the marine ecosystem, including regulatory services (carbon recycling regulation, waste treatment), supply services (fishery production), and support services (e.g., biodiversity maintenance);
S42, baseline service value estimation: estimating the baseline value of each ecosystem service when unaffected by the offshore floating facility using an alternative cost method, e.g. for fishery production services, a market value method may be used, i.e. calculating the baseline value based on market price and throughput of the fishery product;
S43, calculating service value change: for each ecological service, the calculation formula defining the value change is as follows: Wherein/> Representing the variation of ecological service value,/>Representing the estimated value of the service after the operation of the offshore floating facility,/>Baseline service value, for regulatory service, using a surrogate cost approach, calculating the additional cost required to maintain the same carbon emission reduction level after facility operation as/>Is a function of the estimated value of (2);
S44, influence assessment and value quantification: predicting specific influence of the marine floating facility on various ecological service functions by using the marine ecological model and the simulation result of facility operation, and re-estimating the value of various services after the facility operation by adopting an economic method according to the prediction result And calculating the value variation/>, using the above formula；
S45, comprehensive value evaluation: value variation for all ecological servicesSummarizing to obtain the influence of the operation of the offshore floating facility on the overall service value of the marine ecosystem.
Further, the dynamic prediction analysis model in S5 specifically includes:
S51, data collection and pretreatment: collecting environmental impact data related to the offshore floating facility, including water quality parameters, biological community structure data, and acoustic data; collecting long-term environmental data related to climate change and ocean acidification, including global temperature, sea level, sea water pH;
S52, feature engineering: constructing time sequence features, namely, based on rolling standard deviation, capturing trend and seasonal change of the time sequence, and constructing environment feature interaction items, including interaction items of air temperature and pH value, so as to explore the compound influence of interaction among different environment factors on the marine environment;
S53, constructing a multi-layer LSTM network, wherein each layer comprises a plurality of LSTM units, and the stacked structure is used for capturing higher-order dependency relations in time sequence data;
S54, training and optimizing: selecting a loss function to evaluate the difference between the model predicted value and the actual environment influence index, and adopting an Adam optimizer to adjust model parameters so as to minimize the loss function, wherein the Adam optimizer combines the advantages of momentum and self-adaptive learning rate, thereby being beneficial to accelerating convergence and improving the training process;
S55, model evaluation and verification: a time sequence cross-validation method is adopted, a data set is divided into a training set and a testing set according to time sequence, and the performance of a model on unseen data is ensured;
S56, inputting the real-time environment monitoring data and the climate change parameters into a model for dynamic prediction so as to continuously evaluate the environmental influence of the offshore floating facility.
S57, utilizing LSTM weight analysis to explain a model prediction decision process, identifying the most important factors for marine environment influence prediction, firstly, extracting the weight of each LSTM unit from a trained LSTM model, including the weights of an input gate, a forgetting gate, an output gate and a cell state, carrying out statistical analysis on the extracted weights, wherein the input features with high weight have greater influence on the model prediction result, and displaying the weights corresponding to different input features through a visualization technology to help identify which features are most important for model prediction.
Further, the multilayer LSTM network specifically includes:
input layer: designing an input layer to accept a multi-dimensional feature vector, the multi-dimensional feature vector including environmental monitoring data and climate change parameters;
Hidden layer: setting a plurality of LSTM layers, the number of units in each layer being adjusted based on the experiment to obtain optimal performance, the LSTM units in the LSTM layers comprising an input gate, a forgetting gate, an output gate and a cell state, expressed as:
；
；
；
；
；
；
Wherein, 、/>、/>The activation values of the forget gate, the input gate and the output gate are respectively,/>Is in the state of cells,/>For the output of the current moment,/>For the current input,/>And/>For weight matrix and bias term,/>For sigmoid activation function, tanh is hyperbolic tangent activation function;
output layer-the output layer is a fully connected layer for converting the output of the LSTM layer into a final predicted environmental impact indicator, including concentration changes of specific contaminants.
Further, the loss function selects a mean square error MSE to evaluate the difference between the model predicted value and the actual environmental impact indicator, where MSE is defined as: Wherein/> Is the number of samples,/>Is/>Actual value of individual samples,/>Is a model predictive value.
Further, the training and optimizing in S54 further includes reducing overfitting by using a dropout technique to improve the generalization ability of the model, which specifically includes:
Dropout is added after LSTM layer: adding a Dropout layer behind each LSTM layer for preventing overfitting between LSTM layers;
Dropout is added before the output layer: adding a Dropout layer between the last LSTM layer and the output layer helps to reduce overfitting before the model makes the final prediction;
the super parameter Dropout rate (i.e. the discarded connection ratio) is 0.2-0.5, which is determined by experimental methods such as cross-validation.
Furthermore, in order to enable the LSTM unit to process feature interaction terms, when computing gating signals and updating cell states, an additional step is added to the computation to combine the original input features and their interaction terms, and the custom LSTM unit specifically includes:
Defining a feature interaction function The function accepts the original input/>As input, and outputs a combination of original features and interaction features: as input, and outputs a combination of original features and interaction features: /(I)，Generated by a polynomial feature generator: /(I)；
In custom LSTM cells, useTo calculate gating signals and cell status updates for each time stepThe update formula of the LSTM unit is as follows:
Forgetting the door: ；
An input door: ；
cell state candidate value: ；
Cell status update: ；
Output door: ；
Output value: Wherein/> Representing the input processed by the feature interaction function, and comprising the original features and interaction items thereof.
The invention has the beneficial effects that:
According to the invention, by combining a long-term memory network (LSTM) and an environment characteristic interaction mechanism, the long-term influence of the marine floating facility on the marine environment can be dynamically predicted and estimated, including the aspects of water quality change, biological community structure change, acoustic interference and the like, and by considering the long-term environment change factors such as climate change and marine acidification, the method can provide scientific basis for the adaptive management of the marine facility, thereby optimizing the facility design and operation and reducing the negative influence on the marine ecological system.
According to the invention, by introducing the Dropout technology and the feature engineering preprocessing, including manually created feature interaction items, the model can more accurately capture the complex mode and long-term dependency relationship in the environmental data, so that the generalization capability of the model is enhanced, the risk of overfitting is reduced, and the accuracy of prediction is improved. Therefore, the method can provide more reliable decision support for environmental protection policy establishment, operation management of offshore floating facilities and environmental risk assessment.
According to the invention, through LSTM weight analysis and feature importance evaluation, the most important factors for marine environment influence prediction can be identified and explained, and the interpretation is not only helpful for understanding the decision making process of the model and improving the transparency of the model, but also provides new insights for environmental science research, such as revealing how certain environmental factors are related to the health and stability of a marine ecological system.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method according to an embodiment of the invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1, the method for analyzing and quantifying the environmental impact of the offshore floating facility comprises the following steps:
S1: evaluating the design, position and operation mode of the offshore floating facility, and determining the type of direct and indirect influence of the offshore floating facility on the marine ecosystem;
s2: establishing a marine ecological environment baseline model by using a remote sensing technology and marine environment monitoring data;
S3: predicting the influence of the marine floating facility on the marine environment by simulating the operation of the marine floating facility and comparing and analyzing the marine floating facility with a baseline model, wherein the influence comprises water quality change, biological community structure change and acoustic interference;
S4: the method for evaluating the service value of the ecological system is applied to quantify the influence of the operation of the offshore floating facility on the service of the marine ecological system;
s5: and establishing a dynamic prediction analysis model to dynamically evaluate the environmental influence of the offshore floating facility by combining the climate change and the long-term environmental change factors of ocean acidification.
S1 specifically comprises:
S11, design analysis: analyzing design parameters of the offshore floating facility, including the size, shape, materials, buoyancy characteristics and stability of the facility, to determine how the design parameters affect the physical contact area, resistance and potential benthonic habitat destruction of the facility with seawater;
S12, position selection evaluation: based on the GIS system and the marine topography data, estimating marine ecological characteristics of the preset position, including water depth, water flow, tide pattern and biodiversity hot spots, so as to predict the influence of the facility position on the local ecological system;
S13, operation mode analysis: examining a predetermined operating mode of the facility, including energy demand, waste emission, supply of materials, personnel variation, and evaluating how the operating mode indirectly affects the marine ecosystem, in particular by sound, vibration, light pollution and chemical pollution;
s14, direct impact quantization: combining the analysis results of S11 and S12, and quantifying the direct physical and chemical influence of the design and the position of facilities on the marine ecological system by using numerical simulation software (OpenFOAM), wherein the direct physical and chemical influence comprises the ecological environment change, the local water flow mode change and the pollutant diffusion caused by the artificial structure;
S15, indirect influence prediction: based on the operation mode analysis of S13, a system dynamics model (Vensim) is constructed to simulate interaction and feedback mechanisms among elements in the marine ecological system, including change of a food network structure, transition of species distribution and adjustment of an ecological competition mode;
S16, comprehensive evaluation: according to the influence degree of direct and indirect influence on the marine ecological system, different weights are distributed, various influences are comprehensively considered by utilizing a multi-index decision analysis method, comprehensive evaluation is carried out, and the overall environmental influence of the marine floating facility is evaluated, wherein the influence evaluation of an ecological sensitive area and potential long-term ecological consequences are included;
S17, influence type judgment: based on the comprehensive evaluation result, setting thresholds of various influences according to the resistance and restoring force of the ecological system, comparing the comprehensive evaluation result with the thresholds, and determining influence types including biodiversity influence, ecological service function influence and species habitat influence.
S2 specifically comprises:
S21, data collection and integration: collecting multi-time-sequence remote sensing images covering the preset position of the offshore floating facility and the surrounding sea areas by utilizing a satellite remote sensing technology, wherein the multi-time-sequence remote sensing images comprise a spectrum image, a temperature distribution map, a sea surface height map and a chlorophyll concentration distribution map; in combination with on-site marine environmental monitoring data, including water quality parameters (such as temperature, salinity, dissolved oxygen content), submarine geologic structures, and biodiversity survey results (including the distribution and quantity of plankton, benthos, and large marine organisms);
S22, constructing a baseline model: the method comprises the steps of applying a ground GIS (geographic information system) and Environmental Information System (EIS) technology to fuse remote sensing data and monitoring data, establishing a sea area space database, and simulating the natural state of a sea ecological system when the sea ecological system is not influenced by a sea floating facility by utilizing a sea ecological model (such as EcoSIM, ROMS and the like) and combining the sea area space database to construct a sea ecological environment baseline model, wherein the sea ecological environment baseline model can reflect the biological diversity, the ecological system structure and function and the natural variation range of a key ecological process in the sea;
S23, model verification and calibration: and verifying the accuracy and reliability of the model by comparing the output of the baseline model with the historical monitoring data, and adjusting and calibrating the model parameters according to the verification result.
S3 specifically comprises:
S31, facility operation simulation: simulating the influence of physical existence of the offshore floating facility on water flow, temperature distribution and illumination conditions of the surrounding sea area by using a computational fluid dynamics CFD model, and simulating water quality changes caused in the operation process of the facility by combining the operation parameters of the floating facility, wherein the water quality changes comprise changes of nutrient salt concentration and emission of harmful substances;
S32, biological community structure change simulation: based on a hydrodynamic CFD model, simulating the influence of facility operation on a marine organism community structure by combining with a marine ecological model, evaluating the variety of species, the variation of biomass and ecological niches, and evaluating the potential influence of the ecological environment variation (such as the influence of an artificial light source on plankton behaviors) caused by the facility operation on the biological community structure;
s33, acoustic interference assessment: using an acoustic model (RAM or Bellhop) to simulate the propagation of noise generated during operation of the facility in the marine environment, including the frequency, intensity and coverage of the noise, and evaluating the potential interference effect of the noise on marine mammals, fish and sound sensitive organisms;
s34, comparing and analyzing with a baseline model: comparing the facility operation simulation result with an established marine ecological environment baseline model, identifying and quantifying environmental changes caused by facility operation, and analyzing specific influences of facility operation on water quality, biological community structure and acoustic environment, including evaluation of positive and negative effects;
S35, comprehensive influence prediction: and (3) evaluating the overall influence of the operation of the offshore floating facility on the marine environment by combining simulation results of water quality change, biological community structure change and acoustic interference.
S4 specifically comprises the following steps:
S41, ecosystem service identification and classification: identifying and classifying ecosystem services affected by the marine floating facility according to characteristics of the marine ecosystem, including regulatory services (carbon recycling regulation, waste treatment), supply services (fishery production), and support services (e.g., biodiversity maintenance);
S42, baseline service value estimation: estimating the baseline value of each ecosystem service when unaffected by the offshore floating facility using an alternative cost method, e.g. for fishery production services, a market value method may be used, i.e. calculating the baseline value based on market price and throughput of the fishery product;
S43, calculating service value change: for each ecological service, the calculation formula defining the value change is as follows: Wherein/> Representing the variation of ecological service value,/>Representing the estimated value of the service after the operation of the offshore floating facility,/>For baseline service value, for regulatory service, an alternative cost approach is employed to calculate the additional cost required to maintain the same carbon emission reduction level after facility operation as/>Is a function of the estimated value of (2);
S44, influence assessment and value quantification: predicting specific influence of the marine floating facility on various ecological service functions by using the marine ecological model and the simulation result of facility operation, and re-estimating the value of various services after the facility operation by adopting an economic method according to the prediction result And calculating the value variation/>, using the above formula；
S45, comprehensive value evaluation: value variation for all ecological servicesSummarizing to obtain the influence of the operation of the offshore floating facility on the overall service value of the marine ecosystem.
The dynamic prediction analysis model in S5 specifically includes:
S51, data collection and pretreatment: collecting environmental impact data related to the offshore floating facility, including water quality parameters, biological community structure data, and acoustic data; collecting long-term environmental data related to climate change and ocean acidification, including global temperature, sea level, sea water pH;
S52, feature engineering: constructing time sequence features, namely, based on rolling standard deviation, capturing trend and seasonal change of the time sequence, and constructing environment feature interaction items, including interaction items of air temperature and pH value, so as to explore the compound influence of interaction among different environment factors on the marine environment;
S53, constructing a multi-layer LSTM network, wherein each layer comprises a plurality of LSTM units, and the stacked structure is used for capturing higher-order dependency relations in time sequence data;
S54, training and optimizing: selecting a loss function to evaluate the difference between the model predicted value and the actual environment influence index, and adopting an Adam optimizer to adjust model parameters so as to minimize the loss function, wherein the Adam optimizer combines the advantages of momentum and self-adaptive learning rate, thereby being beneficial to accelerating convergence and improving the training process;
S55, model evaluation and verification: a time sequence cross-validation method is adopted, a data set is divided into a training set and a testing set according to time sequence, and the performance of a model on unseen data is ensured;
S56, inputting the real-time environment monitoring data and the climate change parameters into a model for dynamic prediction so as to continuously evaluate the environmental influence of the offshore floating facility.
S57, utilizing LSTM weight analysis to explain a model prediction decision process, identifying the most important factors for marine environment influence prediction, firstly, extracting the weight of each LSTM unit from a trained LSTM model, including the weights of an input gate, a forgetting gate, an output gate and a cell state, carrying out statistical analysis on the extracted weights, wherein the input features with high weight have greater influence on the model prediction result, and displaying the weights corresponding to different input features through a visualization technology to help identify which features are most important for model prediction.
By analyzing and visualizing the weights of the LSTM layers, the most important factors for marine environmental impact prediction can be identified. For example, if the characteristic weight associated with a temperature change is significantly higher than other characteristics, this indicates that the temperature change is of higher importance for prediction of marine environmental impact. The analysis not only can improve the transparency of the model, but also can provide important insight for environmental science research and policy formulation.
The multilayer LSTM network specifically comprises:
input layer: designing an input layer to accept a multi-dimensional feature vector, the multi-dimensional feature vector including environmental monitoring data and climate change parameters;
Hidden layer: setting a plurality of LSTM layers, the number of units in each layer being adjusted based on the experiment to obtain optimal performance, the LSTM units in the LSTM layers comprising an input gate, a forgetting gate, an output gate and a cell state, expressed as:
；
；
；
；
；
；
Wherein, 、/>、/>The activation values of the forget gate, the input gate and the output gate are respectively,/>Is in the state of cells,/>For the output of the current moment,/>For the current input,/>And/>For weight matrix and bias term,/>For sigmoid activation function, tanh is hyperbolic tangent activation function;
output layer-the output layer is a fully connected layer for converting the output of the LSTM layer into a final predicted environmental impact indicator, including concentration changes of specific contaminants.
The LSTM specific parameters are defined as follows:
1. input door Control of the current input/>Which parts of (a) need to update the internal state:
: an input gate activation value for the current time step; /(I) : Sigmoid activation function, mapping values to/>In range, for door control; /(I): Inputting a weight matrix of the gate; /(I)Outputting the previous time step; /(I)Inputting the current time step; /(I)Inputting a bias term of the gate.
2. Forgetting doorDeciding which information to discard from the cell state:
Forgetting the door activation value in the current time step; /(I) A weight matrix of forgetting gate; /(I)Forget the bias term of the door.
3. Cell state candidatesCreating a candidate value to update the cell state:
cell state candidate values of the current time step; /(I) A weight matrix of cell state candidates; /(I)Bias term of cell state candidate; /(I)Hyperbolic tangent activation function mapping/>Within the range.
4. Cell status update: Updating the cell state, partially preserving the old state and adding the new candidate state:
the cell state of the current time step; /(I) : Cell status of the last time step.
5. Output doorDetermining an output value according to the cell state:
Outputting a gate activation value of the current time step; /(I) Outputting a weight matrix of the gate; /(I)Outputting the bias item of the gate.
6. Output valueThe final output value is the output gate activation value and the/>, of the cell stateProduct of values: /(I): The output value of the current time step.
The loss function selects the mean square error MSE to evaluate the difference between the model predicted value and the actual environmental impact indicator, the MSE being defined as: Wherein/> Is the number of samples,/>Is/>Actual value of individual samples,/>Is a model predictive value.
Training and optimizing in S54 further includes reducing overfitting by dropout techniques to improve generalization ability of the model, including:
Dropout is added after LSTM layer: adding a Dropout layer behind each LSTM layer for preventing overfitting between LSTM layers;
Dropout is added before the output layer: adding a Dropout layer between the last LSTM layer and the output layer helps to reduce overfitting before the model makes the final prediction;
the super parameter Dropout rate (i.e. the discarded connection ratio) is 0.2-0.5, which is determined by experimental methods such as cross-validation.
In order to enable the LSTM unit to process feature interaction terms, when computing gating signals and updating cell states, adding an operation of feature interaction, adding an additional step in the computation, for combining original input features and their interaction terms, the custom LSTM unit specifically includes:
Defining a feature interaction function The function accepts the original input/>As input, and outputs a combination of original features and interaction features: as input, and outputs a combination of original features and interaction features: /(I)，Generated by a polynomial feature generator: /(I)；
In custom LSTM cells, useTo calculate gating signals and cell status updates for each time stepThe update formula of the LSTM unit is as follows:
Forgetting the door: ；
An input door: ；
cell state candidate value: ；
Cell status update: ；
Output door: ；
Output value: Wherein/> Representing the input processed by the feature interaction function, and comprising the original features and interaction items thereof.
In implementing the custom LSTM unit described above, an underlying APIs in a deep learning framework (e.g., tensorFlow or PyTorch) may be used, for example, in TensorFlow, to create a custom LSTM layer by inheriting the tf.keras.layers.layer class and implementing custom logic.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (10)
1. The method for analyzing and quantifying the environmental impact of the offshore floating facility is characterized by comprising the following steps:
S1: evaluating the design, position and operation mode of the offshore floating facility, and determining the type of direct and indirect influence of the offshore floating facility on the marine ecosystem;
s2: establishing a marine ecological environment baseline model by using a remote sensing technology and marine environment monitoring data;
S3: predicting the influence of the marine floating facility on the marine environment by simulating the operation of the marine floating facility and comparing and analyzing the marine floating facility with a baseline model, wherein the influence comprises water quality change, biological community structure change and acoustic interference;
S4: the method for evaluating the service value of the ecological system is applied to quantify the influence of the operation of the offshore floating facility on the service of the marine ecological system;
s5: and establishing a dynamic prediction analysis model to dynamically evaluate the environmental influence of the offshore floating facility by combining the climate change and the long-term environmental change factors of ocean acidification.
2. The method for analyzing and quantifying the environmental impact of a marine floating facility according to claim 1, wherein S1 specifically comprises:
S11, design analysis: analyzing design parameters of the offshore floating facility, including the size, shape, materials, buoyancy characteristics and stability of the facility, to determine how the design parameters affect the physical contact area, resistance and potential benthonic habitat destruction of the facility with seawater;
S12, position selection evaluation: based on the GIS system and the marine topography data, estimating marine ecological characteristics of the preset position, including water depth, water flow, tide pattern and biodiversity hot spots, so as to predict the influence of the facility position on the local ecological system;
S13, operation mode analysis: examining a predetermined operation mode of the facility, including energy demand, waste discharge, material replenishment, personnel variation, and evaluating how the operation mode indirectly affects the marine ecosystem;
S14, direct impact quantization: combining the analysis results of S11 and S12, and quantifying the direct physical and chemical influence of the design and the position of facilities on the marine ecological system by using numerical simulation software, wherein the direct physical and chemical influence comprises the ecological environment change, the local water flow mode change and the pollutant diffusion caused by the artificial structure;
S15, indirect influence prediction: based on the operation mode analysis of S13, a system dynamics model is constructed, and interaction and feedback mechanisms among elements in the marine ecological system are simulated, wherein the interaction and feedback mechanisms comprise change of a food network structure, transition of species distribution and adjustment of an ecological competition mode;
S16, comprehensive evaluation: according to the influence degree of direct and indirect influence on the marine ecological system, different weights are distributed, various influences are comprehensively considered by utilizing a multi-index decision analysis method, comprehensive evaluation is carried out, and the overall environmental influence of the marine floating facility is evaluated, wherein the influence evaluation of an ecological sensitive area and potential long-term ecological consequences are included;
S17, influence type judgment: based on the comprehensive evaluation result, setting thresholds of various influences according to the resistance and restoring force of the ecological system, comparing the comprehensive evaluation result with the thresholds, and determining influence types including biodiversity influence, ecological service function influence and species habitat influence.
3. The method for analyzing and quantifying environmental impact of an offshore floating facility according to claim 1, wherein S2 specifically comprises:
S21, data collection and integration: collecting multi-time-sequence remote sensing images covering the preset position of the offshore floating facility and the surrounding sea areas by utilizing a satellite remote sensing technology, wherein the multi-time-sequence remote sensing images comprise a spectrum image, a temperature distribution map, a sea surface height map and a chlorophyll concentration distribution map; combining on-site marine environment monitoring data, including water quality parameters, submarine geological structures and biodiversity investigation results;
S22, constructing a baseline model: the method comprises the steps of applying a ground GIS (geographic information system) and environmental information system technology to fuse remote sensing data and monitoring data, establishing a sea area space database, simulating the natural state of a marine ecological system when the marine ecological system is not influenced by a marine floating facility by utilizing a marine ecological model and combining the sea area space database, and establishing a marine ecological environment baseline model which can reflect the biological diversity, the ecological system structure and function and the natural variation range of a key ecological process in the sea area;
S23, model verification and calibration: and verifying the accuracy and reliability of the model by comparing the output of the baseline model with the historical monitoring data, and adjusting and calibrating the model parameters according to the verification result.
4. The method for analyzing and quantifying environmental impact of an offshore floating facility according to claim 1, wherein S3 specifically comprises:
S31, facility operation simulation: simulating the influence of physical existence of the offshore floating facility on water flow, temperature distribution and illumination conditions of the surrounding sea area by using a computational fluid dynamics CFD model, and simulating water quality changes caused in the operation process of the facility by combining the operation parameters of the floating facility, wherein the water quality changes comprise changes of nutrient salt concentration and emission of harmful substances;
S32, biological community structure change simulation: based on the fluid dynamics CFD model, combining with a marine ecological model, simulating the influence of facility operation on a marine biological community structure, evaluating the variety of species, the variation of biomass and ecological niches, and evaluating the potential influence of the ecological environment variation caused by the facility operation on the biological community structure;
S33, acoustic interference assessment: applying an acoustic model to simulate the propagation condition of noise generated in the operation process of facilities in the marine environment, including the frequency, the intensity and the coverage range of the noise, and evaluating the potential interference effect of the noise on marine mammals, fish and sound sensitive organisms;
s34, comparing and analyzing with a baseline model: comparing the facility operation simulation result with an established marine ecological environment baseline model, identifying and quantifying environmental changes caused by facility operation, and analyzing specific influences of facility operation on water quality, biological community structure and acoustic environment, including evaluation of positive and negative effects;
S35, comprehensive influence prediction: and (3) evaluating the overall influence of the operation of the offshore floating facility on the marine environment by combining simulation results of water quality change, biological community structure change and acoustic interference.
5. The method for analyzing and quantifying environmental impact of an offshore floating facility according to claim 1, wherein S4 specifically comprises:
S41, ecosystem service identification and classification: identifying and classifying ecosystem services affected by the offshore floating facility, including regulatory services, provisioning services, and support services, according to characteristics of the marine ecosystem;
s42, baseline service value estimation: estimating a baseline value of each ecosystem service when the ecosystem service is not affected by the offshore floating facility by adopting a replacement cost method;
S43, calculating service value change: for each ecological service, the calculation formula defining the value change is as follows: Wherein/> Representing the variation of ecological service value,/>Representing the estimated value of the service after the operation of the offshore floating facility,/>For baseline service value, for regulatory service, an alternative cost approach is employed to calculate the additional cost required to maintain the same carbon emission reduction level after facility operation as/>Is a function of the estimated value of (2);
S44, influence assessment and value quantification: predicting specific influence of the marine floating facility on various ecological service functions by using the marine ecological model and the simulation result of facility operation, and re-estimating the value of various services after the facility operation by adopting an economic method according to the prediction result And calculating the value variation/>, using the above formula；
S45, comprehensive value evaluation: value variation for all ecological servicesSummarizing to obtain the influence of the operation of the offshore floating facility on the overall service value of the marine ecosystem.
6. The method for analyzing and quantifying environmental impact of a marine floating facility according to claim 5, wherein the dynamic predictive analysis model in S5 specifically comprises:
S51, data collection and pretreatment: collecting environmental impact data related to the offshore floating facility, including water quality parameters, biological community structure data, and acoustic data; collecting long-term environmental data related to climate change and ocean acidification, including global temperature, sea level, sea water pH;
S52, feature engineering: constructing time sequence features, namely, based on rolling standard deviation, capturing trend and seasonal change of the time sequence, and constructing environment feature interaction items, including interaction items of air temperature and pH value, so as to explore the compound influence of interaction among different environment factors on the marine environment;
S53, constructing a multi-layer LSTM network, wherein each layer comprises a plurality of LSTM units, and the stacked structure is used for capturing higher-order dependency relations in time sequence data;
S54, training and optimizing: selecting a loss function to evaluate the difference between the model predicted value and the actual environment influence index, and adopting an Adam optimizer to adjust model parameters so as to minimize the loss function, wherein the Adam optimizer combines the advantages of momentum and self-adaptive learning rate, thereby being beneficial to accelerating convergence and improving the training process;
S55, model evaluation and verification: a time sequence cross-validation method is adopted, a data set is divided into a training set and a testing set according to time sequence, and the performance of a model on unseen data is ensured;
s56, inputting real-time environment monitoring data and climate change parameters into a model for dynamic prediction so as to continuously evaluate the environmental influence of the offshore floating facility;
S57, utilizing LSTM weight analysis to explain a model prediction decision process, identifying the most important factors for marine environment influence prediction, firstly, extracting the weight of each LSTM unit from a trained LSTM model, including the weights of an input gate, a forgetting gate, an output gate and a cell state, carrying out statistical analysis on the extracted weights, wherein the input features with high weight have greater influence on the model prediction result, and displaying the weights corresponding to different input features through a visualization technology to help identify which features are most important for model prediction.
7. The method for analyzing and quantifying the environmental impact of an offshore floating facility according to claim 6, wherein said multi-layered LSTM network specifically comprises:
input layer: designing an input layer to accept a multi-dimensional feature vector, the multi-dimensional feature vector including environmental monitoring data and climate change parameters;
Hidden layer: setting a plurality of LSTM layers, the number of units in each layer being adjusted based on the experiment to obtain optimal performance, the LSTM units in the LSTM layers comprising an input gate, a forgetting gate, an output gate and a cell state, expressed as:
；
；
；
；
；
；
Wherein, 、/>、/>The activation values of the forget gate, the input gate and the output gate are respectively,/>Is in the state of cells,/>For the output of the current moment,/>For the current input,/>And/>For weight matrix and bias term,/>For sigmoid activation function, tanh is hyperbolic tangent activation function;
output layer-the output layer is a fully connected layer for converting the output of the LSTM layer into a final predicted environmental impact indicator, including concentration changes of specific contaminants.
8. The method of claim 7, wherein the loss function selects a mean square error MSE to evaluate the difference between the model predicted value and the actual environmental impact indicator, the MSE being defined as: Wherein/> Is the number of samples,/>Is/>Actual value of individual samples,/>Is a model predictive value.
9. The method of analyzing and quantifying environmental impact of an offshore floating facility according to claim 8, wherein the training and optimizing in S54 further comprises reducing overfitting using dropout techniques to improve generalization ability of the model, in particular comprising:
Dropout is added after LSTM layer: adding a Dropout layer behind each LSTM layer for preventing overfitting between LSTM layers;
Dropout is added before the output layer: adding a Dropout layer between the last LSTM layer and the output layer helps to reduce overfitting before the model makes the final prediction;
the super-parameter Dropout rate is 0.2-0.5.
10. The method of analyzing and quantifying the environmental impact of an offshore floating facility according to claim 8, wherein to enable the LSTM unit to process the feature interactions, adding the feature interactions to the calculation of gating signals and cell status updates, adding an additional step to the calculation for combining the original input features and their interactions, the custom LSTM unit specifically comprises:
Defining a feature interaction function The function accepts the original input/>As input, and outputs a combination of original features and interaction features: as input, and outputs a combination of original features and interaction features: /(I)，Generated by a polynomial feature generator: /(I)；
In custom LSTM cells, useTo calculate gating signals and cell status updates for each time step/>The update formula of the LSTM unit is as follows:
Forgetting the door: ；
An input door: ；
cell state candidate value: ；
Cell status update: ；
Output door: ；
Output value: Wherein/> Representing the input processed by the feature interaction function, and comprising the original features and interaction items thereof.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524125.8A CN118095112A (en) | 2024-04-29 | 2024-04-29 | Marine floating facility environment influence analysis and quantification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524125.8A CN118095112A (en) | 2024-04-29 | 2024-04-29 | Marine floating facility environment influence analysis and quantification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118095112A true CN118095112A (en) | 2024-05-28 |
Family
ID=91146148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410524125.8A Pending CN118095112A (en) | 2024-04-29 | 2024-04-29 | Marine floating facility environment influence analysis and quantification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118095112A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2726128C1 (en) * | 2019-12-12 | 2020-07-09 | Общество с ограниченной ответственностью "Научно-исследовательский институт проблем Каспийского моря" | Method of organizing ecological studies of the marine environment using a system of stationary biostations within the framework of industrial environmental monitoring |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN117745103A (en) * | 2023-12-27 | 2024-03-22 | 上海勘测设计研究院有限公司 | Marine wind farm marine ecological environment influence evaluation method based on index system method |
-
2024
- 2024-04-29 CN CN202410524125.8A patent/CN118095112A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2726128C1 (en) * | 2019-12-12 | 2020-07-09 | Общество с ограниченной ответственностью "Научно-исследовательский институт проблем Каспийского моря" | Method of organizing ecological studies of the marine environment using a system of stationary biostations within the framework of industrial environmental monitoring |
| CN113297801A (en) * | 2021-06-15 | 2021-08-24 | 哈尔滨工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| JP7175415B1 (en) * | 2021-06-15 | 2022-11-18 | 哈爾濱工程大学 | Marine environment element prediction method based on STEOF-LSTM |
| CN117745103A (en) * | 2023-12-27 | 2024-03-22 | 上海勘测设计研究院有限公司 | Marine wind farm marine ecological environment influence evaluation method based on index system method |
Non-Patent Citations (2)
| Title |
|---|
| 朱贵重;胡松;: "基于LSTM-RNN的海水表面温度模型研究", 应用海洋学学报, no. 02, 15 May 2019 (2019-05-15) * |
| 武慧超;李志伟;: "集约用海对曹妃甸及邻近海域生态环境的影响评估", 河北渔业, no. 05, 20 May 2019 (2019-05-20) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Izadyar et al. | Appraisal of the support vector machine to forecast residential heating demand for the District Heating System based on the monthly overall natural gas consumption | |
| Yin et al. | Bayesian set pair analysis and machine learning based ensemble surrogates for optimal multi-aquifer system remediation design | |
| Heydari et al. | Coupled quantity-quality simulation-optimization model for conjunctive surface-groundwater use | |
| CN117116382B (en) | Water quality space-time prediction method and system for water-bearing lake under influence of diversion engineering | |
| Chatterjee et al. | Hybrid non-dominated sorting genetic algorithm: II-neural network approach | |
| Bhagat et al. | Integrative artificial intelligence models for Australian coastal sediment lead prediction: An investigation of in-situ measurements and meteorological parameters effects | |
| KR102229213B1 (en) | Prediction system of changes in marine benthic communities including benthic habitat map | |
| Kayhomayoon et al. | How does a combination of numerical modeling, clustering, artificial intelligence, and evolutionary algorithms perform to predict regional groundwater levels? | |
| Wu et al. | Simulating urban expansion by coupling a stochastic cellular automata model and socioeconomic indicators | |
| Yu et al. | Adaptative DNN emulator-enabled multi-objective optimization to manage aquifer− sea flux interactions in a regional coastal aquifer | |
| Huang et al. | Improvement of two-dimensional flow-depth prediction based on neural network models by preprocessing hydrological and geomorphological data | |
| KR101635623B1 (en) | Prediction system of changes in marine benthic communities | |
| Moayedi et al. | A novel problem-solving method by multi-computational optimisation of artificial neural network for modelling and prediction of the flow erosion processes | |
| CN117808214A (en) | Hydraulic engineering data analysis system | |
| Mirakhorlo et al. | Integration of SimWeight and Markov Chain to Predict Land Use of Lavasanat Basin | |
| CN117350146A (en) | GA-BP neural network-based drainage pipe network health evaluation method | |
| CN118095112A (en) | Marine floating facility environment influence analysis and quantification method | |
| Ran et al. | Improved runoff forecasting based on time-varying model averaging method and deep learning | |
| Wang | Application of carbon emission prediction based on a combined neural algorithm in the control of coastal environmental pollution in China | |
| McKenna Jr et al. | Habitat characterization and species distribution model of the only large‐lake population of the endangered Silver Chub (Macrhybopsis storeriana, Kirtland 1844) | |
| Zhou et al. | Predicting and explaining karst spring dissolved oxygen using interpretable deep learning approach | |
| CN112260870B (en) | Network security prediction method based on dynamic fuzzy clustering and grey neural network | |
| Fatema et al. | Detection of estuarine benthic macroinvertebrates communities using artificial neural network | |
| Moayedi et al. | Validation of four optimization evolutionary algorithms combined with artificial neural network (ANN) for landslide susceptibility mapping: A case study of Gilan, Iran | |
| Misra et al. | Statistical downscaling of high-resolution precipitation in India using convolutional long short-term memory networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |