欢迎访问《农学学报》，
农学学报

农学学报 ›› 2022, Vol. 12 ›› Issue (6): 50-54.doi: 10.11923/j.issn.2095-4050.cjas20200300085

所属专题： 生物技术； 水产渔业； 农业气象

• 畜牧/兽医/水产 • 上一篇    下一篇

基于江苏省河蟹主产区气象因子的产量BP神经网络预测

金武1(), 何奇2, 杜兴伟2, 朱新艳2, 闻海波1, 马学艳1, 何义进1, 邴旭文1()   

  1. 1中国水产科学研究院淡水渔业研究中心,江苏无锡 214081
    2常熟市水产技术推广站,江苏常熟 215500
  • 收稿日期:2020-03-27 修回日期:2020-06-18 出版日期:2022-06-20 发布日期:2022-07-08
  • 通讯作者: 邴旭文 E-mail:jinw@ffrc.cn;bingxw@ffrc.cn
  • 作者简介:金武,男,1984年出生,江苏如皋人,助理研究员,博士,主要从事水产动物种质资源与遗传育种。通信地址：214081 江苏省无锡市滨湖区山水东路9号 中国水产科学研究院淡水渔业研究中心,E-mail： jinw@ffrc.cn。
  • 基金资助:
    苏州市科技计划（农业科技创新）项目“梨形环棱螺规模化繁育研究与虾蟹池套养净水技术示范推广”(SNG201930);中国水产科学研究院淡水渔业研究中心基本科研业务费“梨形环棱螺遗传参数估算”(2017JBFM11)

Prediction of Crab Yield by BP Neural Network Based on Meteorological Factors of Crab Producing Areas in Jiangsu

JIN Wu1(), HE Qi2, DU Xingwei2, ZHU Xinyan2, WEN Haibo1, MA Xueyan1, HE Yijin1, BING Xuwen1()   

  1. 1Freshwater Fisheries Research Center, Chinese Academy of Fishery Sciences, Wuxi 214081, Jiangsu, China
    2Changshu Fishery Technical Extension Station, Changshu 215500, Jiangsu, China
  • Received:2020-03-27 Revised:2020-06-18 Online:2022-06-20 Published:2022-07-08
  • Contact: BING Xuwen E-mail:jinw@ffrc.cn;bingxw@ffrc.cn

RichHTML

5

PDF (PC)

153

摘要：

为提高江苏河蟹主产区产量预测能力,以此为基础制定科学合理的河蟹养殖发展规划,本研究对河蟹主产区附近设立的7个观测台站2013—2017年的气象数据和该区产量数据进行了采集,利用插值法补足少量缺失值,通过主成分分析选取了最能代表江苏省河蟹主产区特点的5个主成分作为研究对象建立BP神经网络,探索其用于江苏省河蟹主产区产量随气象因子变化的规律。结果表明,通过PCA主成分分析降维处理后数据的大部分特点能被BP神经网络学习到,预测值与真实之间的相关系数为0.82267,具备一定的模拟气象因子数据与产量之间的关系的能力。

关键词: 气象因子, BP神经网络, 河蟹产量, 短期预测

Abstract:

To improve the prediction ability of the crab production in Jiangsu and make a scientific and reasonable plan for crab culture to reduce disordered competition and unbalanced supply and demand, meteorological data in seven observation stations near the crab producing areas from 2013 to 2017 and crab yield data of the region were collected. The interpolation method was used to make up for some missing values. The principal component analysis (PCA) was used to select the five principal components that best represented the characteristics of data. Back propagation (BP) neural network was used to explore its feasibility for predicting the changing trend of meteorological data in these areas. After dimensionality reduction processing by PCA, the results show that most of the characteristics of the data can be learned by the BP neural network. The correlation coefficient between the predicted value and the true value of yield is 0.82267, which means the BP neural network has a certain simulated relationship capacity between weather factor data and the yield.

Key words: meteorological factor, back propagation (BP) neural network, yield of crab, short-term prediction