Emergency prediction and early warning method for water oil spill and hazardous chemical substance leakage accidents

Abstract

The invention discloses an emergency prediction and early warning method for an overwater oil spill and hazardous chemical substance leakage accident. The method comprises the following steps: establishing an inland river basic database; constructing an environmental ecological effect model of the oil spill event; biological population changes under the influence of the oil spill event are identified; evaluating the influence of the oil spill event on the ecological system by using an eDNA macro stripe code technology; based on a biostatistics method, analyzing the relationship between the microbial community and the environmental elements; multi-dimensional real-time monitoring and early warning are carried out on an oil spill event; and a targeted sewage disposal scheme and ecological restoration measures are provided. According to the method, aerial remote sensing, ship and shore-based radar, video monitoring and buoy data are combined, multi-dimensional real-time monitoring and early warning of oil spill events are achieved through a multi-source data fusion technology, a traditional method usually only depends on a single data source, the monitoring accuracy and timeliness are improved, and the method is suitable for popularization and application. And after an oil spilling event occurs, a response can be made more quickly, and the damage of the accident to the environment and the economy is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of environmental management, and in particular to an emergency prediction and early warning method for oil spills and hazardous chemical leakage accidents on water. Background Art

[0002] In recent years, river water pollution caused by inland water transportation accidents and bridge and road traffic accidents has occurred frequently. Due to the narrow river channels, fast flow rates and complex terrain, it is very difficult to predict the drift of pollutants.

[0003] Many existing methods rely on the accuracy and timeliness of historical data and real-time monitoring data. If data is difficult to obtain or updated in a timely manner, the accuracy and practicality of the prediction model will be affected. In addition, oil spills on water are affected by a variety of environmental factors, such as hydrodynamics, topography, meteorological conditions, etc. Existing prediction models are difficult to maintain sufficient accuracy when considering these complex factors, especially under complex terrain or meteorological conditions. Summary of the invention

[0004] The purpose of the present invention is to provide an emergency prediction and early warning method for oil spills and hazardous chemical leakage accidents on water, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An emergency prediction and early warning method for oil spills and hazardous chemical leakage accidents on water, comprising the following steps:

[0007] Step S1, establishing a basic inland river database, including historical oil spill records, water quality monitoring data, biological population data and geographic information system data;

[0008] Step S2, integrating the functional modules and parameterization system of the oil spill trajectory model, and combining it with the inland river basic database to construct an environmental ecological effect model of the oil spill incident;

[0009] Step S3, applying artificial intelligence technologies, including image recognition, data mining and pattern recognition, to conduct real-time monitoring and data analysis of aquatic ecosystems to identify changes in biological populations affected by the oil spill;

[0010] Step S4, using eDNA macrobarcode technology to monitor the changes in microbial communities in the river after the pollution accident and evaluate the impact of the oil spill on the ecosystem;

[0011] Step S5, analyzing the relationship between microbial communities and environmental factors based on biostatistics methods to determine the ecological risk of the oil spill and the possible biodiversity loss;

[0012] Step S6, using multi-source sensor data fusion technology, combining aerial remote sensing, ship and shore-based radar, video surveillance and buoy data, to achieve multi-dimensional real-time monitoring and early warning of oil spill incidents;

[0013] Step S7, based on the model prediction results, propose targeted pollution cleanup plans and ecological restoration measures to minimize the impact of the oil spill on the ecological environment and social economy.

[0014] Furthermore, in step S1, the biological population includes but is not limited to juvenile fish, adult fish, aquatic plants, invertebrates and wild animals.

[0015] Furthermore, in step S2, the oil spill trajectory model has an accurate prediction of the impact on the spread of oil spills based on factors such as hydrodynamics, topography and meteorological conditions;

[0016] The Navier-Stokes equations describe the motion of fluids and are used to calculate the speed and direction of inland water flow: [\frac{\partial\mathbf{v}}{\partial t}+(\mathbf{v}\cdot\nabla)\mathbf{v}=

[0017] -\frac{1}{\rho}\nabla p+\nu\nabla^2\mathbf{v}+\mathbf{g}]

[0018] Among them, (\mathbf{v}) represents the fluid velocity vector, (p) represents the pressure, (\rho) represents the fluid density, (\nu) represents the dynamic viscosity, and (\mathbf{g}) represents the gravitational acceleration vector;

[0019] Digital elevation model (DEM) data is used to evaluate the impact of terrain on oil spill diffusion. The expression is as follows:

[0020] [h(x,y)]

[0021] where (h(x,y)) represents the height above ground or altitude as a function of the two-dimensional coordinates ((x,y));

[0022] Calculate the influence of wind speed, wind direction and precipitation on the oil spill diffusion path, the expression is as follows:

[0023] [\mathbf{V}_{wind}(t)=(v_x(t),v_y(t))]

[0024] Among them, (\mathbf{V}_{wind}(t)) represents the wind speed field, (v_x(t)) and (v_y(t)) are the wind speed components at time (t), respectively.

[0025] Furthermore, in step S3, the artificial intelligence technology includes an ecological monitoring data analysis system based on a machine learning algorithm.

[0026] Furthermore, the artificial intelligence technology further includes a deep learning model that realizes automatic identification and tracking of underwater biological communities by analyzing satellite images and underwater sonar data.

[0027] Furthermore, in step S4, the eDNA macrobarcode technology is used to identify and quantitatively assess the impact of the oil spill on the microbial diversity of the aquatic ecosystem;

[0028] Environmental DNA high-throughput sequencing methods were used to analyze changes in microbial community structure, and the expression is as follows:

[0029] [n_i=f(d_i)]

[0030] Among them, (n_i) represents the abundance or existence of the (i)th microorganism, (d_i) represents the environmental factor related to the microbial population (i), that is, the temporal or spatial changes after the oil spill, and (f) represents the functional relationship between the abundance (n_i) and the environmental factor (d_i).

[0031] Furthermore, in step S5, biostatistical methods are used to quantify the ecological risk assessment of oil spill incidents on different biological populations.

[0032] Furthermore, the biostatistics method uses any one of RDA or CCA to analyze the relationship between microbial communities and environmental factors and identify the main factors affecting changes in microbial communities;

[0033] The RDA method is used to analyze the relationship between biological populations and environmental factors. The expression is as follows:

[0034] [\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E}]

[0035] Among them, (\mathbf{Y}) represents the data matrix of biological populations, (\mathbf{X}) represents the data matrix of environmental factors, (\mathbf{B}) represents the regression coefficient matrix, which describes the impact of environmental factors on biological populations, and (\mathbf{E}) represents the residual matrix, which contains the biological population variation not explained by environmental factors.

[0036] Furthermore, in step S6, multi-source sensor data fusion technology is used to improve the accuracy and real-time performance of oil spill prediction and monitoring;

[0037] The aerial remote sensing data, ship and shore-based radar data, and video surveillance data are integrated for real-time monitoring and early warning of oil spills. The expression is as follows:

[0038] [\mathbf{M}{fusion}=g(\mathbf{M}{radar},\mathbf{M}{video},

[0039] \mathbf{M}{satellite})]

[0040] Among them, (\mathbf{M}_{fusion}) represents the fused data, including radar, video and satellite data, and (g) represents the fusion function, which integrates different sensor data into a single monitoring result.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention combines aerial remote sensing, ship and shore-based radar, video surveillance and buoy data, and uses multi-source data fusion technology to achieve multi-dimensional real-time monitoring and early warning of oil spill incidents. Traditional methods often only rely on a single data source. This method improves the accuracy and timeliness of monitoring, allowing for a faster response after an oil spill incident occurs, effectively reducing the damage to the environment and the economy caused by the accident.

[0043] 2. The present invention uses environmental DNA high-throughput sequencing methods to analyze changes in the structure of microbial communities. Through eDNA technology, the impact of oil spills on the microbial diversity of aquatic ecosystems can be assessed very accurately, which is much faster and more comprehensive than traditional biological monitoring methods.

[0044] 3. The present invention integrates the oil spill trajectory model with water flow dynamics, topography and meteorological conditions to construct an environmental ecological effect model of oil spill incidents. The integrated model can accurately predict the propagation path and impact range of oil spills in rivers or lakes, which not only helps to respond quickly to emergency situations, but also can evaluate the recovery needs of the ecosystem after the accident, thereby improving the scientificity and operability of the impact assessment of oil spill incidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The present invention is a flow chart of an emergency prediction and early warning method for oil spills and hazardous chemicals leakage accidents on water. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 , the present invention provides a technical solution:

[0048] An emergency prediction and early warning method for oil spills and hazardous chemical leakage accidents on water, comprising the following steps:

[0049] Step S1, establishing a basic inland river database, including historical oil spill records, water quality monitoring data, biological population data and geographic information system data;

[0050] Preferably, the biological population includes, but is not limited to, juvenile fish, adult fish, aquatic plants, invertebrates and wild animals;

[0051] In this step, historical oil spill data are collected, including event time, oil spill volume, and oil spill location; inland river water quality monitoring data are obtained, including the spatiotemporal changes in dissolved oxygen, ammonia nitrogen, and pH values; biological population data are collected, including the population density and distribution of different organisms; and geographic information system data are integrated, including terrain, landforms, and river flow geographic information.

[0052] Step S2, integrating the functional modules and parameterization system of the oil spill trajectory model, and combining it with the inland river basic database to construct an environmental ecological effect model of the oil spill incident;

[0053] Preferably, the oil spill trajectory model is based on factors such as hydrodynamics, topography and meteorological conditions, and has an accurate impact prediction on the spread of oil spills;

[0054] The Navier-Stokes equations describe the motion of fluids and are used to calculate the speed and direction of inland water flow: [\frac{\partial\mathbf{v}}{\partial t}+(\mathbf{v}\cdot\nabla)\mathbf{v}=

[0055] -\frac{1}{\rho}\nabla p+\nu\nabla^2\mathbf{v}+\mathbf{g}]

[0056] Among them, (\mathbf{v}) represents the fluid velocity vector, (p) represents the pressure, (\rho) represents the fluid density, (\nu) represents the dynamic viscosity, and (\mathbf{g}) represents the gravitational acceleration vector;

[0057] As can be understood, assuming that it is necessary to simulate the water flow speed and direction in an inland river to evaluate the path of oil spill diffusion, the Navier-Stokes equation is used to describe the motion behavior of the fluid, where the left side of the equation represents the acceleration of the fluid, the first term on the right side is the pressure gradient force, the second term is the viscous drag, and the third term is the external force, such as gravity;

[0058] Digital elevation model (DEM) data is used to evaluate the impact of terrain on oil spill diffusion. The expression is as follows:

[0059] [h(x,y)]

[0060] where (h(x,y)) represents the height above ground or altitude as a function of the two-dimensional coordinates ((x,y));

[0061] It can be understood that, assuming that it is necessary to simulate the impact of terrain on the oil spill diffusion path, the digital elevation model DEM is used to provide data on ground height or altitude. The height of the terrain is expressed as (h(x,y)), where ((x,y)) is the geographic coordinate. In the numerical simulation, the DEM data is combined with a spatial grid, such as an orthogonal grid, to obtain the terrain height information on each grid cell, which is used to calculate the changes in the oil spill path;

[0062] Calculate the influence of wind speed, wind direction and precipitation on the oil spill diffusion path, the expression is as follows:

[0063] [\mathbf{V}_{wind}(t)=(v_x(t),v_y(t))]

[0064] Where (\mathbf{V}_{wind}(t)) represents the wind speed field, (v_x(t)) and (v_y(t)) are the wind speed components at time (t);

[0065] It can be understood that, assuming that the effect of wind speed and wind direction on the spread of oil spill needs to be simulated, based on the meteorological data of wind speed and wind direction, the wind speed can be expressed as a two-dimensional vector (\mathbf{V}_{wind}(t)=(v_x(t),v_y(t))), where (v_x(t)) and (v_y(t)) are the wind speed components at time (t). In the simulation, the effect of wind on the surface fluid motion is considered by coupling with the fluid motion equation, for example, by accelerating or slowing down the spread of the oil spill;

[0066] In this step, the Navier-Stokes hydrodynamic model is used to describe the speed and direction of inland water flow, the terrain model is used, and the digital elevation model DEM data is used to evaluate the impact of terrain on oil spill diffusion, and the meteorological condition model, including wind speed, wind direction and precipitation, is used to predict the oil spill diffusion path.

[0067] The equations are discretized by the finite element method or the finite volume method in order to calculate the changes in the velocity field and the pressure field within a given time step.

[0068] Step S3, applying artificial intelligence technologies, including image recognition, data mining and pattern recognition, to conduct real-time monitoring and data analysis of aquatic ecosystems to identify changes in biological populations affected by the oil spill;

[0069] Preferably, the artificial intelligence technology includes an ecological monitoring data analysis system based on a machine learning algorithm;

[0070] Furthermore, the artificial intelligence technology further includes a deep learning model that automatically identifies and tracks underwater biomes by analyzing satellite imagery and underwater sonar data;

[0071] In this step, image recognition technology is used to analyze the monitored video data to identify changes in aquatic plant and fish populations affected by the oil spill. Data mining technology is used to analyze historical data and real-time monitoring data to assess the impact of the oil spill on wildlife populations such as birds and mammals. Pattern recognition technology is used to analyze changes in the structure and composition of microbial communities after the oil spill.

[0072] Step S4, using eDNA macrobarcode technology to monitor the changes in microbial communities in the river after the pollution accident and evaluate the impact of the oil spill on the ecosystem;

[0073] Preferably, the eDNA macrobarcode technology is used to identify and quantitatively assess the impact of oil spills on the microbial diversity of aquatic ecosystems;

[0074] Environmental DNA high-throughput sequencing methods were used to analyze changes in microbial community structure, and the expression is as follows:

[0075] [n_i=f(d_i)]

[0076] Wherein, (n_i) represents the abundance or presence of the (i)th microorganism, (d_i) represents the environmental factor related to the microbial population (i), i.e., the temporal or spatial changes after the oil spill, and (f) represents the functional relationship between the abundance (n_i) and the environmental factor (d_i);

[0077] It can be understood that the environmental DNA high-throughput sequencing technology is used to analyze the changes in microbial communities after oil spills. Assuming that eDNA data at multiple time points are collected, for the (i)th microbial population, its abundance (n_i) can be expressed as a function of the environmental factor (d_i), that is, (n_i = f(d_i)). By analyzing the eDNA data at different time points, it is possible to infer how environmental factors (d_i), such as the temporal or spatial changes of the oil spill, affect the abundance of the microbial community;

[0078] In this step, water samples are collected and environmental DNA is extracted. High-throughput sequencing technology is used to analyze changes in the microbial community structure, and based on the known microbial DNA sequence database, changes in specific microbial populations after the oil spill are identified.

[0079] Step S5, analyzing the relationship between microbial communities and environmental factors based on biostatistics methods to determine the ecological risk of the oil spill and the possible biodiversity loss;

[0080] Preferably, biostatistical methods are used to quantify the ecological risk assessment of oil spills to different biological populations.

[0081] Furthermore, the biostatistics method uses any one of RDA or CCA to analyze the relationship between microbial communities and environmental factors and identify the main factors affecting changes in microbial communities;

[0082] The RDA method is used to analyze the relationship between biological populations and environmental factors. The expression is as follows:

[0083] [\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E}]

[0084] Among them, (\mathbf{Y} represents the data matrix of biological populations, (\mathbf{X}) represents the data matrix of environmental factors, (\mathbf{B}) represents the regression coefficient matrix, describing the impact of environmental factors on biological populations, and (\mathbf{E}) represents the residual matrix, which contains the biological population variation not explained by environmental factors;

[0085] As can be understood, RDA is used to analyze the relationship between biological populations and environmental factors. Assuming there is a biological population data matrix (\mathbf{Y}) and an environmental factor data matrix (\mathbf{X}), RDA analysis calculates linear combinations (\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E}), where (\mathbf{B}) is the regression coefficient matrix, which describes the impact of environmental factors on biological populations. The residual matrix (\mathbf{E}) contains the biological population variation that is not explained by environmental factors. The impact of other unknown factors can be understood by analyzing the residuals.

[0086] In this step, the RDA method is used to analyze the relationship between biological populations and environmental factors, assess the impact of the oil spill on different components of the ecosystem, and quantify the loss of biodiversity and population density.

[0087] Step S6, using multi-source sensor data fusion technology, combining aerial remote sensing, ship and shore-based radar, video surveillance and buoy data, to achieve multi-dimensional real-time monitoring and early warning of oil spill incidents;

[0088] Preferably, multi-source sensor data fusion technology is used to improve the accuracy and real-time performance of oil spill prediction and monitoring;

[0089] The aerial remote sensing data, ship and shore-based radar data, and video surveillance data are integrated for real-time monitoring and early warning of oil spills. The expression is as follows:

[0090] [\mathbf{M}{fusion}=g(\mathbf{M}{radar},\mathbf{M}{video},

[0091] \mathbf{M}{satellite})]

[0092] Among them, (\mathbf{M}_{fusion}) represents the fused data, including radar, video and satellite data, (g) represents the fusion function, which integrates different sensor data into a single monitoring result;

[0093] It can be understood that real-time monitoring and early warning of oil spill incidents can be achieved by fusing data from different sensors. Assuming that there are monitoring data from multiple sensors such as radar, video and satellite (\mathbf{M}{radar},\mathbf{M}{video},\mathbf{M}_{satellite}), data fusion integrates the data from different sensors into a more comprehensive monitoring result by defining a fusion function (\mathbf{M}{fusion}=g(\mathbf{M}{radar},\mathbf{M}{video},\mathbf{M}{satellite})). The fusion algorithm uses weighted average or Kalman filtering to improve monitoring precision and accuracy.

[0094] In this step, aerial remote sensing data are integrated to obtain the spatial distribution and diffusion rate of the oil film on the surface of the inland river after the oil spill. Ship and shore-based radar data are used to monitor the water flow dynamics and pollution diffusion in the waters downstream of the oil spill. Video surveillance data is analyzed to evaluate the impact of the oil spill on the behavior of birds and mammals. Buoys and water quality sensors are deployed to monitor the direct impact of the oil spill on water quality and biological populations in real time.

[0095] Step S7, based on the model prediction results, propose targeted pollution cleanup plans and ecological restoration measures to minimize the impact of the oil spill on the ecological environment and social economy;

[0096] In this step, real-time monitoring data and model analysis results are combined to formulate a pollution cleanup plan, including pollution source control and pollutant removal measures, and propose an ecological restoration plan, focusing on protecting and restoring damaged ecosystem components and reducing the long-term impact of the oil spill on the ecosystem.

[0097] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0098] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for emergency prediction and early warning of oil spills and hazardous chemical leakage accidents on water, characterized in that: The following steps are involved: Step S1, establishing a basic inland river database, including historical oil spill records, water quality monitoring data, biological population data and geographic information system data; Step S2, integrating the functional modules and parameterization system of the oil spill trajectory model, and combining it with the inland river basic database to construct an environmental ecological effect model of the oil spill incident; Step S3, applying artificial intelligence technologies, including image recognition, data mining and pattern recognition, to conduct real-time monitoring and data analysis of aquatic ecosystems to identify changes in biological populations affected by the oil spill; Step S4, using eDNA macrobarcode technology to monitor the changes in microbial communities in the river after the pollution accident and evaluate the impact of the oil spill on the ecosystem; Step S5, analyzing the relationship between microbial communities and environmental factors based on biostatistics methods to determine the ecological risk of the oil spill and the possible biodiversity loss; Step S6, using multi-source sensor data fusion technology, combining aerial remote sensing, ship and shore-based radar, video surveillance and buoy data, to achieve multi-dimensional real-time monitoring and early warning of oil spill incidents; Step S7, based on the model prediction results, propose targeted pollution cleanup plans and ecological restoration measures to minimize the impact of the oil spill on the ecological environment and social economy.

2. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S1, the biological population includes but is not limited to young fish, adult fish, aquatic plants, invertebrates and wild animals.

3. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S2, the oil spill trajectory model has an accurate prediction of the impact on the spread of oil spills based on factors such as hydrodynamics, topography and meteorological conditions; The Navier-Stokes equations describe the motion of fluids and are used to calculate the speed and direction of inland water flow: [\frac{\partial\mathbf{v}}{\partial t}+(\mathbf{v}\cdot\nabla)\mathbf{v}= -\frac{1}{\rho}\nabla p+\nu\nabla^2\mathbf{v}+\mathbf{g}] Among them, (\mathbf{v}) represents the fluid velocity vector, (p) represents the pressure, (\rho) represents the fluid density, (\nu) represents the dynamic viscosity, and (\mathbf{g}) represents the gravitational acceleration vector; Digital elevation model (DEM) data is used to evaluate the impact of terrain on oil spill diffusion. The expression is as follows: [h(x,y)] where (h(x,y)) represents the height above ground or altitude as a function of the two-dimensional coordinates ((x,y)); Calculate the influence of wind speed, wind direction and precipitation on the oil spill diffusion path, the expression is as follows: [\mathbf{V}_{wind}(t)=(v_x(t),v_y(t))] Among them, (\mathbf{V}_{wind}(t)) represents the wind speed field, (v_x(t)) and (v_y(t)) are the wind speed components at time (t), respectively.

4. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S3, the artificial intelligence technology includes an ecological monitoring data analysis system based on a machine learning algorithm.

5. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 4, characterized in that: The artificial intelligence technology further includes a deep learning model that automatically identifies and tracks underwater biological communities by analyzing satellite imagery and underwater sonar data.

6. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S4, the eDNA macrobarcode technology is used to identify and quantitatively assess the impact of the oil spill on the microbial diversity of the aquatic ecosystem; Environmental DNA high-throughput sequencing methods were used to analyze changes in microbial community structure, and the expression is as follows: [n_i=f(d_i)] Among them, (n_i) represents the abundance or existence of the (i)th microorganism, (d_i) represents the environmental factor related to the microbial population (i), that is, the temporal or spatial changes after the oil spill, and (f) represents the functional relationship between the abundance (n_i) and the environmental factor (d_i).

7. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S5, biostatistics methods are used to quantify the ecological risk assessment of oil spill incidents on different biological populations.

8. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 7, characterized in that: The biostatistics method uses either RDA or CCA to analyze the relationship between microbial communities and environmental factors and identify the main factors affecting changes in microbial communities; The RDA method is used to analyze the relationship between biological populations and environmental factors. The expression is as follows: [\mathbf{Y}=\mathbf{X}\mathbf{B}+\mathbf{E}] Among them, (\mathbf{Y}) represents the data matrix of biological populations, (\mathbf{X}) represents the data matrix of environmental factors, (\mathbf{B}) represents the regression coefficient matrix, which describes the impact of environmental factors on biological populations, and (\mathbf{E}) represents the residual matrix, which contains the biological population variation not explained by environmental factors.

9. The method for emergency prediction and early warning of oil spills and hazardous chemicals leakage accidents on water according to claim 1, characterized in that: In step S6, multi-source sensor data fusion technology is used to improve the accuracy and real-time performance of oil spill prediction and monitoring; The aerial remote sensing data, ship and shore-based radar data, and video surveillance data are integrated for real-time monitoring and early warning of oil spills. The expression is as follows: [\mathbf{M}{fusion}=g(\mathbf{M}{radar},\mathbf{M}{video}, \mathbf{M}{satellite})] Among them, (\mathbf{M}_{fusion}) represents the fused data, including radar, video and satellite data, and (g) represents the fusion function, which integrates different sensor data into a single monitoring result.

Images