欢迎访问《中国农学通报》,

中国农学通报 ›› 2026, Vol. 42 ›› Issue (11): 186-194.doi: 10.11924/j.issn.1000-6850.casb2025-0680

• 农业信息/科技教育 • 上一篇    下一篇

基于人工智能算法与气象数据的烟草单叶重可预报性研究

夏晓玲1,2(), 李想3(), 吴昌航1,4, 雷坤江1,5, 王星1,6, 王加敏1   

  1. 1 贵州新气象科技有限责任公司, 贵阳 550002
    2 贵州省气象服务中心, 贵阳 550002
    3 中国烟草总公司贵州公司, 贵阳 550005
    4 贵州省气象台, 贵阳 550002
    5 贵州省生态农业气象中心, 贵阳 550002,
    6 贵州省气候中心, 贵阳 550002
  • 收稿日期:2025-08-12 修回日期:2026-03-01 出版日期:2026-06-12 发布日期:2026-06-12
  • 通讯作者:
    李想,男,1982年出生,辽宁鞍山人,高级工程师,博士研究生,研究方向:烟草种植生产管理。通信地址:550004 贵州省贵阳市云岩区瑞金北路146号,Tel:0851-86830394,E-mail:
  • 作者简介:

    夏晓玲,女,1990年出生,湖北孝感人,高级工程师,硕士研究生,主要从事农业气象服务方面的研究。通信地址:550002 贵州省贵阳市南明区新华路翠微巷9号,Tel:0851-85507680,E-mail:

  • 基金资助:
    中国烟草公司重点研发项目“基于生态因子数字化的贵州省智慧烟田研究与应用”(2022XM12); 贵州省气象局省市联合科研基金项目“贵州省烤烟气象灾害预警与产量预测模型研究”(黔气科合SS[2023]12号); 贵州省科技计划项目“边界层及低空经济气象贵州省科技创新领军人才工作站”(黔科合平台KXJZ[2024]033); 贵州省科技计划2025 年度“三上”企业研发创新扶持及科技型企业培育项目“面向复杂山地的低空飞行器气象精准预报技术研发”(黔科合支撑(2025)一般186)

Research on Predictability of Tobacco Leaf Weight Based on Artificial Intelligence Algorithms and Meteorological Data

XIA Xiaoling1,2(), LI Xiang3(), WU Changhang1,4, LEI Kunjiang1,5, WANG Xing1,6, WANG Jiamin1   

  1. 1 Guizhou New Meteorological Technology Co., Ltd., Guiyang 550002
    2 Guizhou Provincial Meteorological Service Center, Guiyang 550002
    3 China National Tobacco Corporation Guizhou Company, Guiyang 550005
    4 Guizhou Provincial Meteorological Observatory, Guiyang 550002
    5 Guizhou Provincial Eco-agricultural Meteorological Center, Guiyang 550002
    6 Guizhou Provincial Climate Center, Guiyang 550002
  • Received:2025-08-12 Revised:2026-03-01 Published:2026-06-12 Online:2026-06-12

摘要:

本研究聚焦于气象要素对烟草单叶重的影响,旨在构建基于人工智能算法的烟草单叶重预测模型。研究涵盖2010—2024年贵州省50余个烟区的数据,包括气象数据和烟草单叶重实测数据。通过分析气象要素与烟草单叶重的相关性,筛选出显著相关的气象因子,并运用多种人工智能算法构建预测模型。研究得出,NuSVR和SVR算法在烟草单叶重预测中具有显著优势,其均方误差(MSE)较低,显示出良好的预测稳定性和适应性。不同叶位的预测误差存在差异,下部叶预测误差最低,中部叶次之,上部叶最高。4—8月预测误差整体呈下降趋势,且4—9月期间3个叶位的预报误差变化幅度不大,表明气象条件对烟草单叶重的影响具有持续性和稳定性。2020—2024年期间,各叶位预测误差逐年递减,反映出预报模型的不断优化。本研究发现运用气象数据和人工智能方法结合在6月前后就可以预测当年烟草单叶重,数据误差和9月基本一致,为烟草产业的精准化生产和智能化管理提供了有价值的参考。

关键词: 烟草单叶重, 气象要素, 人工智能算法, 预测模型, NuSVR, SVR

Abstract:

This study focuses on the impact of meteorological elements on flue-cured tobacco leaf weight and aims to develop a tobacco leaf weight prediction model based on artificial intelligence algorithms. The research covers data from over 50 tobacco-growing areas in Guizhou Province from 2010-2024, including meteorological and actual tobacco leaf weight data. It analyzes the correlation between meteorological factors and tobacco leaf weight, selects significantly correlated factors, and uses various AI algorithms to build prediction models. NuSVR and SVR algorithms show significant advantages in tobacco leaf weight prediction, with low mean squared error, high stability, and adaptability. Prediction errors vary by leaf position, being lowest in lower leaves, moderate in middle leaves, and highest in upper leaves. From April to August, errors show a downward trend, and during April-September, error fluctuations are small for all three positions, indicating sustained meteorological impacts. During 2020-2024, prediction errors decreased yearly, reflecting model optimization. The study shows that combining meteorological data with AI methods enables reliable June predictions of annual tobacco leaf weight with similar accuracy to September data, offering valuable insights for precision production and smart management in the tobacco industry.

Key words: tobacco leaf weight, meteorological elements, artificial intelligence algorithms, prediction models, NuSVR, SVR

中图分类号: