CN111784034B - Screening and detecting method for key environmental factors affecting Chilean sea area American red squid fishing ground - Google Patents
Screening and detecting method for key environmental factors affecting Chilean sea area American red squid fishing ground Download PDFInfo
- Publication number
- CN111784034B CN111784034B CN202010576595.0A CN202010576595A CN111784034B CN 111784034 B CN111784034 B CN 111784034B CN 202010576595 A CN202010576595 A CN 202010576595A CN 111784034 B CN111784034 B CN 111784034B
- Authority
- CN
- China
- Prior art keywords
- key
- american red
- distribution
- month
- data
- 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.)
- Active
Links
- 230000007613 environmental effect Effects 0.000 title claims abstract description 98
- 241000238366 Cephalopoda Species 0.000 title claims abstract description 93
- 238000012216 screening Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 title claims description 30
- 238000009826 distribution Methods 0.000 claims abstract description 81
- 238000004088 simulation Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000000694 effects Effects 0.000 claims abstract description 4
- 241000894007 species Species 0.000 claims description 25
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 241000223600 Alternaria Species 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 235000002568 Capsicum frutescens Nutrition 0.000 abstract description 6
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000008859 change Effects 0.000 description 3
- 238000003306 harvesting Methods 0.000 description 2
- 241000739514 Dosidicus gigas Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The invention discloses a screening and detecting technology of key environmental factors affecting a Chili sea area American red squid fishing ground, which comprises the following steps: s1, processing fishery fishing data of the Chilean sea area American red squid, wherein the data comprise operation time, operation position, fishing yield and fishing effort, S2, verifying simulation effects, S3, comparing and analyzing contribution conditions of different environmental variables of each month to distribution of the American red squid fishing ground, S4, matching the actual fishery data of each month with key environmental factor data of the American red squid fishing ground, S5, drawing the potential distribution of the American red squid fishing ground by taking the key environmental variables as horizontal coordinates, S6, reestablishing a MaxEnt model, and selecting key environmental factors of each month to evaluate and predict the Chilean sea area American red squid fishing ground. The invention considers the sensitivity difference of the biological characteristics of the American red squid to the environment, so that the environment variable selected in the future prediction of the Chilean sea area American red squid fishing ground is more reasonable and scientific, and the reliability of the prediction model is enhanced.
Description
Technical Field
The invention relates to an environmental impact assessment and fishing ground prediction method for space-time distribution of a American red squid fishing ground, in particular to a method for screening and detecting key environmental factors of the American red squid fishing ground in the Chilean sea area based on a maximum entropy model.
Background
The American red squid (Dosidicusgigas) is a commercially developed cephalopod type which is widely distributed in the Tongnan Pacific sea area, the fishing yield is extremely high, the proportion of the total fishing yield of the cephalopod type is high, the currently developed fishing ground is provided with Chilean, peruvian, equator and the like, and the Chilean fishing ground is one of the most important fishing grounds for fishing the American red squid in China. The red squid is a annual short life cycle species, the population of the red squid is very sensitive to environmental changes, so that when the environment in the range of the habitat of the red squid changes, the population of the red squid is caused to react rapidly, the abundance and the spatial distribution of resources can change rapidly in a short time, the fishing yield of the red squid is obviously influenced by the environment, and the yield fluctuation is obvious and has obvious annual and monthly differences. In response researches on resource abundance and fishery distribution of the American red squid to environmental change, numerous analysis results neglect the inter-month change of the environment, and in fact, the environmental factors in different months have different influence degrees on the American red squid, namely, key environmental factors with higher influence degrees and non-key environmental factors with lower influence degrees exist. Therefore, a relation model for screening key environmental factors of the Chilean sea area American red squid fishing ground is established, and the American red squid fishing ground in the sea area is evaluated and predicted, so that the method has important guiding significance for the ocean squid fishing industry in the east-south Pacific sea area of China.
At present, a plurality of methods and models for detecting the fishing ground of the Chilean sea area American red squid exist, and the methods and models do not consider whether the selected environment variable is a key environment variable in the research time, so that the accuracy of the model or the method for detecting the fishing ground is not high. The method is based on 12 environmental data such as different water layer water temperatures (including 0m,25m,50m,100m,150m,200m,300m,400m,500 m), sea surface height, sea surface salinity, mixed layer depth and the like, and the key environmental factors are screened on the premise of fully considering influence differences of the factors in different time periods, so that the prediction performance of the Chili sea area American red squid fishing ground is improved, and the model method can be used for accurately detecting the fishing ground of the Chili sea area in the Tongnan Pacific ocean of China.
Disclosure of Invention
In order to solve the problems, the invention explores the influence degree of 12 environmental data such as water temperatures (including 0m,25m,50m,100m,150m,200m,300m,400m,500 m) of different water layers under different time conditions, sea surface height, sea surface salinity, mixed layer depth and the like on the distribution of potential fishing ground of the American red squid, and provides a screening and detecting method of key environmental factors influencing the American red squid fishing ground in the Chilean sea area.
The invention is realized by the following technical scheme:
A screening and detecting method for key environmental factors affecting a Chili sea area Alaska sleeve-fish fishing ground comprises the following steps:
s1, processing fishery fishing data of Chilean sea area American red squid, wherein the data comprise working time (year and month), working position (longitude and latitude), fishing yield (unit: ton), fishing effort (calculated by working times), processing all environmental data into image layer data by ArcGis10.2 software, simulating potential fishing ground distribution of Chilean sea area American red squid by combining the processed fishery data and the environmental data by using MaxEnt model,
S2, visualizing and classifying the distribution result of the Alternaria americana in each month by using ArcGis 10.2 software, classifying the Alternaria americana in different colors, defining the Alternaria americana existence probability as a Habitat Suitability Index (HSI), representing potential fishing field distribution, superposing the Alternaria americana with actual fishery distribution data, verifying a simulation effect, taking the size of an AUC value in a model simulation result as an index for measuring model precision,
S3, comparing and analyzing the contribution condition of different environmental variables in each month to the distribution of the American red squid fishing ground, selecting the variable with the contribution rate being higher than that of the first three in arrangement as a key environmental factor affecting the space-time distribution of the American red squid fishing ground in the month according to the contribution rate,
S4, matching the actual fishery data of each month with the key environment factor data thereof, defining the operation times as the fishing effort, drawing a frequency distribution diagram taking the key environment variable as an abscissa and the fishing effort as an ordinate by using a frequency distribution method, calculating the proper range of the key environment variable when the American red squid is actually distributed,
S5, drawing a response curve graph taking the key environment variable as an abscissa and the adaptive probability of the American red squid as an ordinate under the single environment variable condition, calculating the appropriate range of the corresponding key environment variable with the adaptive probability of more than 0.4 under the simulation condition, comparing the appropriate range of the corresponding key environment variable with the appropriate range of the corresponding environment variable in the actual distribution,
S6, selecting fishery data and environment data of different years, reestablishing a MaxEnt model to simulate potential distribution of the American red squid fishing ground, and selecting key environment factors of each month to evaluate and predict the Chilean sea area American red squid fishing ground.
Preferably, the step S2 defines the probability of presence of the american red squid as a habitat suitability index (Habitat Suitability Index, HSI).
Preferably, in the step S2, the probability of occurrence of the american red squid is that the model combines all environmental variables and screens out key factors according to the contribution rate of each variable to perform fishing ground simulation and verification.
Preferably, the step S2 uses an area value (area less than or equal to undercurve, AUC) under a subject working characteristic curve (ReceiverOperatingCharacteristic Curve, ROC) automatically generated during the model running process as an index for measuring the accuracy of the model, specifically: when the potential distribution of the simulated American red squid does not coincide with the actual distribution of the simulated American red squid, the AUC value is 0; when the model simulates that the potential distribution and the actual distribution completely coincide, namely in an ideal state, the AUC value is 1; and judging the model accuracy according to the AUC value automatically generated by the model.
Preferably, in the step S3, the number of the environmental variables is not limited, and the first three variables with the highest contribution rate are selected as the key environmental factors of the month according to the contribution of each environmental variable to the species distribution in different time periods.
Preferably, in the step S3, the key environmental factors of each month are selected by sequentially selecting the first three variables of the sorting row as the key environmental factors of each month according to the order of the contribution rate of the environmental variables of each month from big to small, and the key environmental factors of each month have differences.
Preferably, the fishing effort in the step S4 is defined as the number of operations.
Preferably, in the step S5, the environment variable range corresponding to the case where the probability of the amenity of the american red squid is greater than 0.4 is regarded as the suitable environment range of the american red squid.
Preferably, when the response curve of the probability of occurrence of the american red squid to the key environmental variable is drawn in the step S5, in order to avoid the influence of other environmental variables, a single environmental variable is selected, and the rationality of the selection of the key environmental factors is verified by combining the frequency distribution diagram of the key environmental variable and the fishing effort in the step S4.
The principle of the invention is as follows: the method comprises the steps of simulating potential fishing field distribution of the American red squid by combining fishery fishing data of the American red squid with environmental data such as water temperatures of different water layers, sea surface heights, sea surface salinity, mixed layer depths and the like through a maximum entropy model, superposing a simulated fishing field distribution result with actual fishery data, selecting key environmental factors influencing the fishing field distribution of the American red squid through contribution rates of different environmental variables in each month, comparing and analyzing proper ranges of the key environmental factors under simulation and actual distribution conditions of the American red squid, and selecting different years of fishery data and environmental data to conduct fishing field prediction analysis based on the screened key environmental factors.
The invention has the beneficial effects that:
(1) Aiming at the traditional research of space-time distribution and environmental association of the America red squid fishing ground, most of the traditional research is to analyze environmental factors set by 2-3 persons, the invention fully considers the difference and contribution rate of 12 different environmental variables to the America red squid fishing ground distribution in different time periods, explores the response rule and inter-month difference of America red squid to different environmental factors, screens out key environmental factors and evaluates the preference range of America red squid.
(2) The method screens out key environmental factors affecting distribution of the American red squid fishing ground based on factors with little influence on the contribution rate, and models and predicts the factors, fully considers biological characteristics of the American red squid and sensitivity differences of the biological characteristics to the environment, enables environmental variables selected in future prediction of the American red squid fishing ground in the Chilean sea area to be more reasonable and scientific, and enhances reliability of a prediction model.
Drawings
FIG. 1 is a diagram of the latest MaxEnt software 3.4.1 running interface in an embodiment of the present invention.
Fig. 2 is a graph showing the superposition distribution of the probability of occurrence of MaxEnt model simulation 2011-2017 in summer (12 months, 1 month, 2 months) and autumn (3 months, 4 months, 5 months) and the actual operation position in an embodiment of the present invention.
FIG. 3 is a graph showing the frequency of actual harvesting efforts of the America red squid under key environmental variable conditions of summer months in an embodiment of the present invention.
FIG. 4 is a graph showing the frequency of actual harvesting efforts of Alternaria americana under key environmental variables of autumn and each month in an embodiment of the invention.
FIG. 5 is a graph showing the probability of the adaptive probability of the America squid modeling with only a single key environmental variable in summer according to one embodiment of the present invention.
FIG. 6 is a graph showing the probability of fit of the America squid when modeling only a single key environmental variable in autumn according to one embodiment of the present invention.
Fig. 7 is a graph showing the actual distribution of the probability of occurrence (or HSI) of 12-5 months of american red squid in 2011 predicted by the MaxEnt model in an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the attached drawings: the present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are provided, but the protection scope of the present invention is not limited to the following embodiments.
A screening and detecting method for key environmental factors affecting a Chili sea area Alaska sleeve-fish fishing ground comprises the following steps:
s1, processing fishery fishing data of Chilean sea area American red squid, wherein the data comprise working time (year and month), working position (longitude and latitude), fishing yield (unit: ton), fishing effort (calculated by working times), processing all environmental data into image layer data by ArcGis10.2 software, simulating potential fishing ground distribution of Chilean sea area American red squid by combining the processed fishery data and the environmental data by using MaxEnt model,
S2, visualizing and classifying the distribution result of the Alternaria americana in each month by using ArcGis 10.2 software, classifying the Alternaria americana in different colors, defining the Alternaria americana existence probability as a Habitat Suitability Index (HSI), representing potential fishing field distribution, superposing the Alternaria americana with actual fishery distribution data, verifying a simulation effect, taking the size of an AUC value in a model simulation result as an index for measuring model precision,
S3, comparing and analyzing the contribution condition of different environmental variables in each month to the distribution of the American red squid fishing ground, selecting the variable with the contribution rate being higher than that of the first three in arrangement as a key environmental factor affecting the space-time distribution of the American red squid fishing ground in the month according to the contribution rate,
S4, matching the actual fishery data of each month with the key environment factor data thereof, defining the operation times as the fishing effort, drawing a frequency distribution diagram taking the key environment variable as an abscissa and the fishing effort as an ordinate by using a frequency distribution method, calculating the proper range of the key environment variable when the American red squid is actually distributed,
S5, drawing a response curve graph taking the key environment variable as an abscissa and the adaptive probability of the American red squid as an ordinate under the single environment variable condition, calculating the appropriate range of the corresponding key environment variable with the adaptive probability of more than 0.4 under the simulation condition, comparing the appropriate range of the corresponding key environment variable with the appropriate range of the corresponding environment variable in the actual distribution,
S6, selecting fishery data and environment data of different years, reestablishing a MaxEnt model to simulate potential distribution of the American red squid fishing ground, and selecting key environment factors of each month to evaluate and predict the Chilean sea area American red squid fishing ground.
The step S2 defines the probability of presence of the America squid as a habitat suitability index (Habitat Suitability Index, HSI). And in the step S2, the existence probability of the America squid is that the model combines all environment variables and screens out key factors according to the contribution rate of each variable to perform fishing ground simulation and verification. The step S2 takes an area value (area is less than or equal to undercurve, AUC) under a subject working characteristic curve (ReceiverOperatingCharacteristic Curve, ROC) automatically generated in the running process of the model as an index for measuring the accuracy of the model, and specifically refers to: when the potential distribution of the simulated American red squid does not coincide with the actual distribution of the simulated American red squid, the AUC value is 0; when the model simulates that the potential distribution and the actual distribution completely coincide, namely in an ideal state, the AUC value is 1; and judging the model accuracy according to the AUC value automatically generated by the model.
In the step S3, the number of the environment variables is not limited, the first three variables with the highest contribution rate are selected as key environment factors of the month according to the contribution conditions of the environment variables to species distribution in different time periods, and compared with the prior study, the method fully considers the influence degree of the environment variables on the space-time distribution of the America red squid in different time periods, reflects the high migration and the biological characteristics of environmental sensitivity of the America red squid, and enables the study result to be more scientific. In the step S3, the key environmental factors of each month are selected by sequentially selecting the first three variables of the sorting row as the key environmental factors of each month according to the order of the contribution rate of the environmental variables of each month from big to small, and the key environmental factors of each month have differences. The fishing effort in step S4 is defined as the number of operations.
And in the step S5, the environment variable range corresponding to the adaptive probability of the Heterosleeve-like America is regarded as the suitable environment range of the Heterosleeve-like America when the adaptive probability of the Heterosleeve-like America is larger than 0.4. When the response curve of the probability of the presence of the American red squid to the key environment variable is drawn in the step S5, a single environment variable is selected to avoid the influence of other environment variables, and the rationality of the selection of the key environment factors is verified by combining the frequency distribution diagram of the key environment variable and the fishing effort in the step S4.
Examples: as shown in fig. 1 to 7, evaluation and prediction of the american red squid fishing ground in summer (12 to 2 months) and autumn (3 to 5 months) in the chile sea area 2011 to 2017 are selected as implementation cases, wherein the spatial resolution is 0.5 degrees x 0.5 degrees, and the coverage range is 70 to 97 degrees W and 20 to 47 degrees S.
1. Model construction
The maximum entropy model (Maximum Entropy, maxEnt) in the present application is to select the distribution with the highest probability of species existence, i.e. entropy, as the optimal distribution of potential habitats in accordance with the constraint conditions, based on the species existence data and the environmental data of the whole research area. Assuming that the environment area of species distribution is M, M is composed of a limited number of spatial grids x i; y represents the presence of a species in a certain grid, i.e. y has a value of 1 when the species is present and 0 when the species is absent. Defining the probability of target species distribution in each grid as pi (x) based on the presence of species
π(x)＝Pr(x∣y＝1) (1)
And Σpi (x) =1; the distribution probability H (pi) of species under environmental condition constraints is calculated as follows:
The model operation uses the latest MaxEnt software 3.4.1 (http:// bioodiends information ics.amnh. Org/open_source/MaxEnt /), and the running interface is shown in FIG. 1. Species existence data of a sample input layer (Samples) are data of fishing each fishing boat in a daily operation position of a fishing month and removing fishing to be 0, the data are derived from a China ocean fishery data center of Shanghai university, the Chili sea area American red squid fishery fishing data in 2011-2017 are selected, the time resolution is month, the spatial resolution is 0.5 degrees multiplied by 0.5 degrees, the input form is species name, longitude and latitude, and the data are stored in a csv format. The environmental input layer (Environmental layer) data are the average value of 12 environmental data such as water temperatures (including 0m,25m,50m,100m,150m,200m,300m,400m,500 m), sea surface height, sea surface salinity, mixed layer depth and the like of different water layers in a research area of each month, the data are obtained from a Asian data research center (http:// apdrc.soest.hawaii.edu/las_ ofes/v6/DATASETCATITEM =71), and the time resolution is month. The spatial resolution was 0.5 ° x 0.5 °, and it was converted into ASCII format by ArcGis 10.2 software for storage. Before the MaxEnt model is operated, 75% of species distribution data is used as training data, the remaining 25% is test data, in order to eliminate randomness and repetition number, the number of repeated operation of the model is set to 10, namely sample data are equally divided into 10 parts, in the operation process, the 10 equal parts of species distribution data are operated in a cross-validation mode, regularization multipliers and iteration numbers default to automatic optimal setting of software, and operation results are output in a Logistic mode.
2. Result verification
The invention uses a subject work characteristic curve (Receiver Operating Characteristic Curve, ROC) automatically generated by a MaxEnt model to evaluate model experimental performance. The judgment of the model on the prediction result threshold value can generate different classification modes such as correct estimation, overestimation, underestimation and the like. The correct estimation is that in M area space grids, the model correctly predicts the actual grid number of the species, also called true positive, and the true positive rate is the rate at which the species existence is correctly predicted; overestimation is that the species is not actually present in the M-region spatial grid, but the model predicts the number of grids in which it is present, also called false positives, and the false positive rate is the rate at which the species is not actually present but is predicted to be present; under-estimation is that the species in the M area space grid actually exists, but the model predicts the grid number of the species which does not exist and becomes false negative. The ROC curve is drawn by taking the false positive rate as an abscissa and the true positive rate as an ordinate, the size of a curve area value (AUC) enclosed by the false positive rate and the abscissa is used as a measurement index of model accuracy, the value range is [0,1], namely, when the potential distribution of the model simulation species does not coincide with the actual distribution at all, the AUC value is 0; when the two completely agree, the AUC value is 1. Will be Defined as model predictive failure, poor, general, good, and excellent. The simulation sample size, the simulation precision and the standard deviation of the model of each month are summarized as shown in table 1, and the simulation precision of each month is more than 0.9, which indicates that the simulation result is excellent.
Table 1 summary of simulation of Alaska and autumn Hei
The output existence probability distribution result format of the model is ASCII, which is required to be imported into ArcGis10.2 software for visual analysis. Firstly, converting ASCII format data into a grid format (Raster format), loading a world map file for 'extraction analysis' so as to obtain a distribution diagram of the American red squid in a research area; the probability of existence is defined as Habitat Suitability Index (HSI) and is in accordance with(Unsuitable habitat),/>(Generally suitable for habitat),(More suitable habitat),/>(Optimum habitat) to "Reclassify (RECLASSIFY)", giving each category a different colour; the statistical data of the actual production of the Chilean sea area American red squid is overlapped with the simulated probability distribution map, as shown in fig. 2, the actual fishing force in 2011-2017 is mostly concentrated in the most suitable area, which indicates that the matching degree of the simulated species distribution of the model and the actual distribution of the model is very high.
3. Critical environmental factor selection
In the model operation process, the model gain is increased by changing the characteristic coefficient of a certain environment variable, meanwhile, the increment of the model gain is given to the environment variable, and the increment of the gain is converted into a percentage at the end of the model operation process, so that the contribution rate of the environment variable of each month can be obtained, as shown in table 2. According to the contribution rate of the environmental variables of each month, the first three variables with higher contribution rate are selected as the key environmental factors of the month according to the order from the big contribution rate to the small contribution rate (the thickened environmental variables in the table 2 are the key environmental factors screened out by each month).
Table 2 2011-2017 environmental factor contribution rates of summer, autumn and each month
Matching the selected key environment factor data of each month with fishery data, drawing a frequency distribution map with key environment variables as horizontal coordinates and fishing effort as vertical coordinates by using a frequency step method, and estimating the proper range of each key environment variable, as shown in fig. 3 and 4; and drawing a response curve graph taking the key environment variable as an abscissa and taking the output amethystoides adaptive probability as an ordinate when modeling is performed by using a single key environment variable, calculating the appropriate range of the key environment variable under the condition that the adaptive probability is larger than 0.4 as shown in fig. 5 and 6, and comparing the calculated adaptive range with the appropriate range of the corresponding key environment variable in the frequency distribution graph to verify the rationality of the selected key environment factor, wherein the appropriate range of the key environment variable under the simulation condition is consistent with the appropriate range of the key environment variable when the key environment variable is actually distributed as shown in table 3.
Table 3 suitable ranges of key environmental factors for each month in summer and autumn
4. Predictive analysis
According to the key environmental factors of the screened Chilean sea area American red squid habitat and the technical method for detecting the fishing ground, the processed 2012-2017 summer (12-2 months) and autumn (3-5 months) fishery data and the environmental data of a research area are selected, the time resolution is month, the spatial resolution is 0.5 degrees multiplied by 0.5 degrees, the key environmental factors of each month are reselected by using a MaxEnt model, as shown in table 4, the key environmental factors selected by each month are combined with the processed 2011 corresponding month corresponding environmental variable data, the 2011 corresponding month American red squid potential fishing ground is predicted, and the actual fishery distribution data are superimposed, as shown in fig. 7, most of the 2011 fishing forces predicted according to the key environmental factors selected by the model simulation 2012-2017 are concentrated in the area with high HSI value, so that the key environmental factors selected by the method can be well estimated and predicted.
Table 4 contribution rates of environmental factors of summer, autumn and each month in 2012-2017
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. The screening and detecting method for the key environmental factors affecting the Chilean sea area Alaska sleeve-fish fishing ground is characterized by comprising the following steps:
S1, processing fishery fishing data of Chilean sea area Heterosleeve-fish, wherein the data comprise working time, working position, fishing yield and fishing effort, processing all environmental data into image layer data by ArcGis10.2 software, simulating potential fishing field distribution of Chilean sea area Heterosleeve-fish by combining the processed fishery data with the environmental data by using a MaxEnt model,
S2, visualizing and classifying the distribution result of the Alternaria americana in each month by using ArcGis 10.2 software, distinguishing the categories with different colors, defining the Alternaria americana existence probability as a habitat suitability index, representing potential fishery distribution, superposing the Alternaria americana with actual fishery distribution data, verifying the simulation effect, taking the magnitude of an AUC value in the model simulation result as an index for measuring the model precision,
S3, comparing and analyzing the contribution condition of different environmental variables in each month to the distribution of the American red squid fishing ground, selecting the first three variables with contribution rate ranking as key environmental factors affecting the space-time distribution of the American red squid fishing ground in the month according to the contribution rate,
S4, matching the actual fishery data of each month with the key environment factor data thereof, defining the operation times as the fishing effort, drawing a frequency distribution diagram taking the key environment variable as an abscissa and the fishing effort as an ordinate by using a frequency distribution method, calculating the proper range of the key environment variable when the American red squid is actually distributed,
S5, drawing a response curve graph taking the key environment variable as an abscissa and the adaptive probability of the American red squid as an ordinate under the single environment variable condition, calculating the appropriate range of the corresponding key environment variable with the adaptive probability of more than 0.4 under the simulation condition, comparing the appropriate range of the corresponding key environment variable with the appropriate range of the corresponding environment variable in the actual distribution,
S6, selecting fishery data and environmental data of different years, reestablishing a MaxEnt model to simulate potential distribution of the American red squid fishing ground, selecting key environmental factors of each month to evaluate and predict the Chilean sea area American red squid fishing ground,
The probability of the occurrence of the American red squid in the step S2 is that the model combines all environment variables and screens out key factors according to the contribution rate of each variable to perform fishing ground simulation and verification,
Step S2 takes an area value under a subject working characteristic curve automatically generated in the model running process as an index for measuring the model accuracy, specifically: when the potential distribution of the simulated American red squid does not coincide with the actual distribution of the simulated American red squid, the AUC value is 0; when the model simulates that the potential distribution and the actual distribution completely coincide, namely in an ideal state, the AUC value is 1; judging the model accuracy according to the AUC value automatically generated by the model,
In the step S3, the number of the environmental variables is not limited, the first three variables with the highest contribution rate are selected as the key environmental factors of the month according to the contribution conditions of the environmental variables to the species distribution in different time periods,
The key environmental factors of each month in the step S3 are selected by sequentially selecting the first three variables of the sorting row as the key environmental factors of each month according to the order of the contribution rate of the environmental variables of each month from big to small, the key environmental factors of each month have differences,
In the step S5, the environment variable range corresponding to the adaptive probability of the America squid being larger than 0.4 is regarded as the suitable environment range of the America squid,
When the response curve of the probability of the presence of the American red squid to the key environment variable is drawn in the step S5, a single environment variable is selected to avoid the influence of other environment variables, and the rationality of the selection of the key environment factors is verified by combining the frequency distribution diagram of the key environment variable and the fishing effort in the step S4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576595.0A CN111784034B (en) | 2020-06-22 | Screening and detecting method for key environmental factors affecting Chilean sea area American red squid fishing ground |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576595.0A CN111784034B (en) | 2020-06-22 | Screening and detecting method for key environmental factors affecting Chilean sea area American red squid fishing ground |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111784034A CN111784034A (en) | 2020-10-16 |
| CN111784034B true CN111784034B (en) | 2024-06-11 |
Family
ID=
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204313A (en) * | 2016-07-22 | 2016-12-07 | 上海海洋大学 | A kind of method predicting jumbo flying squid resources spatial distribution |
| CN106651616A (en) * | 2016-12-26 | 2017-05-10 | 上海海洋大学 | Method for predicting access fishing of western and central pacific ocean katsuwonuspelamis purse seine fishery |
| CN106845699A (en) * | 2017-01-05 | 2017-06-13 | 南昌大学 | A kind of method for predicting oil tea normal region |
| CN107944590A (en) * | 2016-10-13 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of fishing condition analysis and forecasting |
| CN109584098A (en) * | 2018-12-20 | 2019-04-05 | 上海海洋大学 | A kind of prediction technique and device of fishing ground catch per unit effort |
| CN109767040A (en) * | 2019-01-15 | 2019-05-17 | 上海海洋大学 | Saury cental fishing ground prediction technique based on habitat suitability index |
| CN109902761A (en) * | 2019-03-18 | 2019-06-18 | 上海海洋大学 | A kind of fishing feelings prediction technique based on marine environment Factor Fusion and deep learning |
| WO2020088615A1 (en) * | 2018-11-02 | 2020-05-07 | 上海海洋大学 | Todarodes pacificus resource abundance prediction method and application based on pacific decadal oscillation |
| CN111222748A (en) * | 2019-11-27 | 2020-06-02 | 上海海洋大学 | Tuna habitat quantitative evaluation method |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204313A (en) * | 2016-07-22 | 2016-12-07 | 上海海洋大学 | A kind of method predicting jumbo flying squid resources spatial distribution |
| CN107944590A (en) * | 2016-10-13 | 2018-04-20 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus of fishing condition analysis and forecasting |
| CN106651616A (en) * | 2016-12-26 | 2017-05-10 | 上海海洋大学 | Method for predicting access fishing of western and central pacific ocean katsuwonuspelamis purse seine fishery |
| CN106845699A (en) * | 2017-01-05 | 2017-06-13 | 南昌大学 | A kind of method for predicting oil tea normal region |
| WO2020088615A1 (en) * | 2018-11-02 | 2020-05-07 | 上海海洋大学 | Todarodes pacificus resource abundance prediction method and application based on pacific decadal oscillation |
| CN109584098A (en) * | 2018-12-20 | 2019-04-05 | 上海海洋大学 | A kind of prediction technique and device of fishing ground catch per unit effort |
| CN109767040A (en) * | 2019-01-15 | 2019-05-17 | 上海海洋大学 | Saury cental fishing ground prediction technique based on habitat suitability index |
| CN109902761A (en) * | 2019-03-18 | 2019-06-18 | 上海海洋大学 | A kind of fishing feelings prediction technique based on marine environment Factor Fusion and deep learning |
| CN111222748A (en) * | 2019-11-27 | 2020-06-02 | 上海海洋大学 | Tuna habitat quantitative evaluation method |
Non-Patent Citations (3)
| Title |
|---|
| 基于MAXENT模型预测西北太平洋秋刀鱼潜在渔场;张孝民;石永闯;李凡;朱明明;魏振华;;上海海洋大学学报;20190911(第02期);全文 * |
| 基于最大熵模型模拟西北太平洋柔鱼潜在栖息地分布;龚彩霞;陈新军;高峰;;中国水产科学;20200313(第03期);全文 * |
| 基于最大熵模型的南太平洋长鳍金枪鱼栖息地预测;张嘉容;杨晓明;田思泉;;中国水产科学;20200401(第10期);全文 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633255B (en) | Rock lithology automatic identification and classification method under deep learning mode | |
| WO2018001338A1 (en) | Grey system-based pelagic squid resource richness forecasting method | |
| CN111680844B (en) | Technical method for evaluating and predicting habitat of Atlantic Argentina sliding flexible fish in southwest based on water temperature vertical structure | |
| CN111199270A (en) | Regional wave height forecasting method and terminal based on deep learning | |
| CN104239712B (en) | Real-time evaluation method for anti-interference performance of radar | |
| CN109902761B (en) | Fishing situation prediction method based on marine environment factor fusion and deep learning | |
| CN113516228B (en) | Network anomaly detection method based on deep neural network | |
| CN113487600A (en) | Characteristic enhancement scale self-adaptive sensing ship detection method | |
| Chiffard et al. | Adaptive niche-based sampling to improve ability to find rare and elusive species: Simulations and field tests | |
| CN115408925A (en) | Rock mass parameter prediction method and device for tunnel construction | |
| CN112084860A (en) | Target object detection method and device and thermal power plant detection method and device | |
| CN111079783A (en) | Method for identifying stratum lithology parameters based on multi-core ensemble learning | |
| CN114612260A (en) | South-sea fishery resource assessment system modeling method and system based on machine learning | |
| CN113343123B (en) | Training method and detection method for generating confrontation multiple relation graph network | |
| CN111784034B (en) | Screening and detecting method for key environmental factors affecting Chilean sea area American red squid fishing ground | |
| CN113627657A (en) | Sandstone-type uranium mineralization interest area prediction method using machine learning model | |
| Noor et al. | Prediction map of rainfall classification using random forest and inverse distance weighted (IDW) | |
| CN109636194B (en) | Multi-source cooperative detection method and system for major change of power transmission and transformation project | |
| CN115272798B (en) | Method and system for predicting training positive sample by using information quantity to expand ore formation | |
| Shi et al. | Construction of CPUE standardization model and its simulation testing for chub mackerel (Scomber japonicus) in the Northwest Pacific Ocean | |
| CN114021445B (en) | Ocean vortex mixing non-locality prediction method based on random forest model | |
| CN111784034A (en) | Screening and detecting technology of key environmental factors influencing Chilo squid fishery in Chili sea area | |
| CN112330029A (en) | Fishing ground prediction calculation method based on multilayer convLSTM | |
| Yang et al. | Research on intelligent identification technology of lithology wireless remote transmission based on element measurement | |
| CN113033908B (en) | Optimization method for submarine resource detection station |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |