| Acute hepatopancreatic necrosis disease（AHPND）of cultured shrimp has a wide prevalence,rapid onset,and high mortality,which is an important limiting factor to affect shrimp aquaculture development in recent years and bring massive economic losses to the industry in worldwide.Systematic study of which factors are significantly correlated with the occurrence of AHPND,and further establishment of a prediction model for the occurrence of shrimp AHPND are important for the prevention and control of the diseases.In this paper,the cultured Litopenaeus vannamei in ponds were preliminarily analyzed the coupling relationship between the occurrence and prevalence of AHPND in shrimps and pathogens,environmental and host autoimmune factors by collecting environmental factors,pathogen abundance,and the host health indicators under AHPND incidence,and to comprehensively analyze the relationship between the changes of each factor in the aquaculture system and the occurrence of diseases by potassium hydrogen sulfate（PMS）intervention.Finally,the mathematical early warning model of AHPND occurrence in pond cultured L.vannamei was constructed by Support Vector Machine and Deep Forest Algorithm,respectively,and the model calculus effect was compared and analyzed.The relevant research results provide basic data and technical support for shrimp AHPND disease prediction and health prevention and control,and lay a theoretical foundation for further establishment of aquaculture animal disease early warning theory.The main research contents of this paper are as follows:1.Correlation Analysis of AHPND Occurrence with Environment,Pathogen and Host Immune Factors in Pond Cultured L.vannameiIn order to explore the relationship between the occurrence of AHPND and environment,pathogen and shrimp immunity,the occurrence of AHPND and its environment,pathogen and shrimp immunity factors in pond cultured L.vannamei were continuously monitored.The results showed that air temperature,water temperature,dissolved oxygen（DO）,p H,salinity,ammonia nitrogen（NH4-N）and nitrite（NO2-N）fluctuated in the range of 21～29℃,24.8～31℃,1.4～8.32 mg/L,8～8.91,34～50‰,0.01～0.26 mg/L and 0.005～0.212 mg/L,respectively;the number of culturable bacteria and Vibrio in water ranged from 3×103 to 2.4×105 CFU/m L and2×102 to 1.8×104CFU/m Ll,respectively;the number of culturable bacteria and Vibrio in shrimp ranged from 9.8×104to 8.8×106CFU/g and 3.9×103 to 3.61×106 CFU/g,respectively;the 16S r DNA identification results showed that 20 vibrio species were detected,and the main vibrio species was Vibrio owensii、V.Campbellii、V.Neocaledonicus、V.parahaemolyticus、V.Alginolyticus and V.harveyi;the results showed that the activities of ACP,AKP,SOD,LZM and PO were 7.5～75 U/mg,1～8.5U/mg,2.4～11.07 U/mg and 1.3～43 U/mg,respectively 23～28 U/mg.2.Construction of Early Warning Mathematical Model of Pond Cultivated Litopenaeus vannamei AHPND Based on Support Vector Machine AlgorithmThrough the support vector machine algorithm function model,the parameter simulation prediction data based on the L.vannamei AHPND occurrence related factor sequence（environmental factor,microbial factor and shrimp health indicator）are constructed for the first time,the one-dimensional sequence is mapped into the three-dimensional space,different kernel functions are selected in combination with the actual classification problem to compare the model fitting accuracy,and the parameters in the model are optimized by the test algorithm.At the same time,the model is constructed and verified by strictly following the 9:1 ratio principle of training sample set and test sample set.The results show that the simulation results of SVM based on polynomial kernel function are the best.The input-output mapping was established in the early warning and prediction of L.vannamei AHPND based on the support vector machine algorithm by Python language programming,and the classification accuracy and prediction effect of different models were compared with six classification algorithms including multinomial native bayes,,k nearest neighbor classification algorithms,logistic regression analysis,random forest neighbors,decisiontree,and gradient ascending classification algorithm,and finally a6-dimensional vector parameter combination model for the early warning and prediction of L.vannamei AHPND was established,that is,the total number of culturable bacteria in shrimp,the proportion of Vibrios in shrimp,the proportion of Vibrio in water,ACP,AKP,and SOD parameters were used as predictors.The prediction accuracy is as high as 100.00%,but the SVM model of 6-dimensional vectors has the problems of overfitting and immune indicators that are difficult to collect in production.3.Construction of Early Warning Mathematical Model for Pond Cultivation of Litopenaeus vannamei AHPND Based on Deep Forest AlgorithmThe relationship between 18 parameters and the occurrence of AHPND in L.vannamei was analyzed by Pearson correlation,and the main influencing factors were further screened by pairwise analysis between the factors.The results showed that the occurrence of AHPND in L.vannamei was directly and significantly correlated with 7parameters including the total number of shrimp bacteria,the total number of shrimp Vibrios,LZM,the proportion of shrimp Vibrio,the total number of water bacteria,salinity,and water Vibrios.The prediction performance of three popular integrated learning method algorithms based on decision tree,deep forest,Light GBM,and XGBoost,was evaluated by Python language programming,and finally a4-dimensional vector early warning prediction model based on Deep Forest algorithm for the total number of shrimp bacteria,the proportion of Vibrio shrimp,water bacteria,and salinity was established（accuracy 89.00%）.Although the prediction performance of the deep forest model decreased somewhat compared with the support vector machine model（accuracy 100.00%）established in this study,the algorithm was gradually screened out based on the correlation relationship between factors,including the effects of all factors.It is proved that the deep forest model established in this study is the most ideal prediction model for predicting the occurrence of AHPND in L.vannamei among the ten algorithm models tried,and the superiority of the deep forest algorithm is also further verified.4.Analysis on the changes of water environment index and bacterial structure in shrimp aquaculture system under the intervention of potassium hydrogen persulfateThe effect of potassium monopersulfate（PMS）on water environment index and bacterial community were analyzed by water quality physical and chemical factors monitor,culturable bacteria detection in shrimp hepatopancreas and water,and bacterial community analysis.The results showed that:compared with the control,the water temperature,DO,p H,salinity,ammonia nitrogen（NH4-N）and nitrite（NO2-N）in the experimental and control group was similar,and with the fluctuation range of26.3～28.3℃,4.36～5.93 mg/L,8.39～8.74,40～45,0.02～0.16 mg/L and 0.01～0.21mg/L.PMS could improve the water quality physical and chemical factors.The number of culturable bacteria and Vibrios in hepatopancreas decreased from 3.13×106CFU/g and 1.98×106 CFU/g to 4.30×105 CFU/g and 1.09×105 CFU/g respectively,and the proportion of Vibrios decreased from 63.36%to 25.35%.The number of culturable bacteria and Vibrios in water decreased from 2.70×104 CFU·m L-1 and6.00×103 CFU/m L to 8.50×103 CFU/m L and 1.20×103 CFU/m L respectively,and the proportion of Vibrios decreased from 22.22%to 14.11%.PMS could significantly reduce the number of culturable bacterias,Vibrios and the proportion of Vibrios in hepatopancreas and pond water.Bacterial community analysis the water showed that the Actinobacteria,Bacteroidota,Cyanobacteria and Proteobacteria were the main dominant phylum.Compared with the variation trends of 3 days before and after PMS interference,the difference of bacterial community structure between PMS free groups was gradually increased,and reflected that the PMS has better stability in maintaining the bacterial structure of the aquaculture pond.The results provide data support for the prevention roles and scientific application of PMS in aquaculture. |
PDF Full Text Request