CN106251006A - A kind of Argentina squid resource magnitude of recruitment Forecasting Methodology - Google Patents

Abstract

A method for predicting the replenishment of Argentine squid resources, which is characterized in that it uses the correlation between the time series values of the marine environment factors in the feeding field in the month of hunting and the CPUE time series of this year, and selects the marine environmental factors in sea areas with high correlations as the fishing habitat Factors related to the impact of the environment on the replenishment of squid resources in Argentina; using the correlation between the time series values of the spawning ground marine environmental factors in the spawning month and the CPUE time series in the next year, the marine environmental factors in sea areas with high correlation were selected as the spawning habitat Factors related to the impact of the environment on resource replenishment; using the proportion of the suitable surface water temperature range of the spawning ground in the spawning month to the total area, and the proportion of the suitable surface water temperature range of the feeding ground in the feeding month to the total area, expressed in _PS and _PF The suitable degree of habitat environment for spawning grounds and feeding grounds; use selected environmental factors and different combinations of _PS and _PF to establish BP network structure prediction models, and select the optimal model for medium and long-term fish forecasting.

Description

A Method for Predicting the Replenishment of Argentine Squid Resources

technical field

The invention relates to a method for mid- and long-term forecasting of fishery conditions, in particular to a method for forecasting the replenishment of Argentine squid resources.

Background technique

The forecast of resource replenishment is one of the medium and long-term forecasts of fishery situation. Accurate forecasting of resource replenishment is the key to scientific management and rational development of fishery. Argentine squid is a species with a short life cycle. Although it has a strong self-regulation ability, it can respond to changes in the marine environment in a short period of time and quickly adapt to such changes. The impact is still significant. Existing studies have shown that the most important factor affecting the replenishment of squid resources in Argentina is environmental factors. Therefore, the current forecast research on its resource replenishment is also based on this. However, the environmental factors selected in previous studies are relatively single, and the forecast models established are also simple linear models. In order to understand the influence of marine environmental factors on the replenishment of Argentine squid resources, find out the marine environmental factors that have the most significant impact on the replenishment of Argentine squid resources. On this basis, establish a resource replenishment prediction model and analyze the reasons.

Contents of the invention

The present invention studies and understands the impact of marine environmental factors on the replenishment of Argentine squid resources, finds out the most significant marine environmental factors affecting the replenishment of Argentine squid resources, and aims to establish a method for predicting the replenishment of Argentine squid resources on this basis, using In the medium and long-term fishery forecast.

The technical scheme of the present invention comprises selecting marine environment factor and setting up BP network structure predictive model, it is characterized in that the time series value that utilizes the time series value that the marine environment factor of the baiting field of Argentine squid baiting field is formed and the correlation of this year's CPUE time series, The marine environmental factors in sea areas with high correlation were selected as the relevant factors of the impact of the bait habitat on the replenishment of Argentine squid resources; the time series values of the marine environmental factors of the spawning grounds of Argentine squid during the spawning period and the CPUE time series of the next year were used Correlation of the correlation, select the marine environmental factors of high correlation sea areas as the relevant factors of the impact of the spawning habitat environment on the replenishment of Argentine squid resources; use the proportion of the suitable surface water temperature range of the spawning ground of the Argentine squid spawning month to the total area P _S , The proportion _{P F} of the suitable surface water temperature range of the feeding field to the total area in the feeding month, and the suitability of the Argentine squid spawning ground and feeding field habitat are expressed by PS and _PF ; the correlation coefficient adopts the Pearson correlation coefficient, and the formula is as follows :

$\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}{\sqrt{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}$

Among them, x and y represent environmental factors, including marine environmental factors of spawning grounds and feeding grounds, and a series of values composed of PS, _PF and _CPUE of each month's environment;

Using the selected environmental factors and different combinations of _{PS and PF as} the input factors of the BP prediction model, the BP network structure prediction models were respectively established, and then compared to obtain the optimal model for medium and long-term fish forecasting.

The present invention utilizes the influence of marine environmental factors on the replenishment of Argentine squid resources, finds out the marine environmental factors that have the most significant impact on the replenishment of Argentine squid resources, and establishes a method for predicting the replenishment of Argentine squid resources. The prediction accuracy is above 90%. Compared with the traditional multivariate linear model, the forecast accuracy is significantly improved.

Description of drawings

Figure 1 is the simulation results of different neural network models.

detailed description

The replenishment of Argentine squid resources is closely related to the habitats of its spawning grounds and feeding grounds. Therefore, it is possible to calculate the correlation between the time series values of the marine environmental factors of the Argentine squid in the feeding month and the CPUE time series of this year, and select the marine environmental factors in sea areas with high correlations as the habitat for Argentine squid. The impact of resource replenishment; calculate the correlation between the time series value of the marine environmental factors in the spawning ground of Argentine squid in the spawning month and the CPUE time series in the next year, and select the marine environmental factors in sea areas with high correlation as the spawning habitat environment pair 2010. Effects of recruitment on squid stocks in Argentina.

The proportion of the optimum surface water temperature range of spawning grounds and baiting grounds to the total area is one of the indicators to measure the quality of Argentine squid habitat environment. Calculate the proportion of the suitable surface water temperature range of the spawning ground to the total area in the spawning month (expressed by PS), and the proportion of the suitable surface water temperature range of the feeding ground in the feeding month to the total area _{(expressed by P F )} , and use PS, _{P F} expresses the suitability of the habitat environment in the spawning grounds and feeding grounds of squid resources in Argentina.

The correlation coefficient adopts the Pearson correlation coefficient, and the formula is as follows:

$\mathrm{<span\; class="notranslate">\; r</span>}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}{\sqrt{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}$

Among them, x and y represent the series of values composed of environment and CPUE respectively.

According to the selected correlation factors, the multivariate linear model or BP neural network model between the significant correlation factors affecting the replenishment of Argentine squid resources and CPUE was established.

The annual CPUE standardized by the GLBM model was used as the abundance index of Argentine squid resources in the Southwest Atlantic.

Studies have shown that the 30°S-45°S, 40°W-65°W sea areas are generally considered to be the spawning grounds of Argentine squid in the Southwest Atlantic. In the spawning month (June to August), calculate and analyze the correlation between the time series value composed of SST and SSTA at each point and the time series value composed of CPUE in the coming year, and select SST and SSTA in sea areas with high correlation as the supplementary quantity of Argentine squid. Impact factor.

The SST of 16-18°C was defined as the optimum surface temperature of the spawning ground, Ps was selected as the influencing factor of Argentine squid recruitment, and the correlation between the time series value of Ps composition and the time series value of CPUE composition in the coming year was calculated.

Table 1 Correlation analysis parameters between SST in key regions in June and CPUE in the next year

Table 2 Correlation analysis parameters of optimal surface temperature in spawning grounds divided into Ps and next year CPUE

A multivariate linear model is established by using samples composed of the selected month’s regional surface temperature and the next year’s CPUE (t/d), and its equation is CPUE=0.152SST _Area1 +0.17SST _Area2 +0.58SST _Area3 -5.8, and its correlation coefficient R is 0.943 ( P=0.007<0.05).

Using the different combinations of regional surface temperature and Ps in the selected month as the input factors of the EBP prediction model, a variety of EBP prediction models are constructed, which are:

Scheme 1: Select the three factors of area 1 surface temperature, area 3 surface temperature, and Ps as the input layer to construct a 3:4:1 EBP network structure.

Scheme 2: Select the three factors of surface temperature in area 2, surface temperature in area 3, and Ps as the input layer, and construct a 3:4:1 EBP grid structure.

Scheme 3: Select the four factors of surface temperature in area 1, surface temperature in area 2, surface temperature in area 3, and Ps as the input layer to construct a 4:5:1 EBP network structure.

Using matlab to calculate, the mean square error of the three schemes is obtained, the mean square error of scheme 3 is the smallest, and its accuracy rate is 96.4%.

Claims (1)

1. an Argentinian squid resource magnitude of recruitment Forecasting Methodology, including selecting the marine environment factor and to set up BP network structure pre- Survey model, it is characterized in that utilizing the time sequential value of the marine environment factor composition in Argentina squid forage month feeding ground and this The dependency of year CPUE seasonal effect in time series, selects the marine environment factor in dependency height marine site as forage habitat to Ah root The correlation factor of court of a feudal ruler squid resource magnitude of recruitment impact；Utilize Argentina squid in the marine environment factor set in month spawning ground of laying eggs The time sequential value become and next year CPUE seasonal effect in time series dependency, select the marine environment factor in dependency height marine site as product The ovum habitat correlation factor on Argentina's squid resource magnitude of recruitment impact；Utilize Argentina squid lay eggs month spawning ground fit Preferably surface temperature scope accounts for ratio P of the gross area_S, forage month feeding ground suitable surface temperature scope account for ratio P of the gross area_F, Use P_S、P_FExpress the suitable degree of Argentina's feeding ground, squid resource spawning ground habitat；Relative coefficient uses Pearson Correlation coefficient, formula is as follows:

$r=\frac{{\mathrm{\&Sigma;}}_i^n\left(x_i-\stackrel{\&OverBar;}{x}\right)\left(y_i-\stackrel{\&OverBar;}{y}\right)}{\sqrt{{\mathrm{\&Sigma;}}_i^n{\left(x_i-\stackrel{\&OverBar;}{x}\right)}^2{\mathrm{\&Sigma;}}_i^n{\left(y_i-\stackrel{\&OverBar;}{y}\right)}^2}}$

Wherein x, y represent envirment factor respectively, including the marine environment factor in spawning ground and feeding ground, and each month environment P_SAnd P_F, CPUE composition series of values；

Utilize selected envirment factor and P_S、P_FVarious combination as the input factor of BP forecast model, set up BP net respectively Network structure prediction model, then comparing acquisition most has model, for medium-term and long-term fishery forescast.