• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Hydrology >Spatial-temporal characteristics analysis of water resource system resilience in irrigation areas based on a support vector machine model optimized by the modified gray wolf algorithm
【24h】

Spatial-temporal characteristics analysis of water resource system resilience in irrigation areas based on a support vector machine model optimized by the modified gray wolf algorithm

机译：基于经修改灰狼算法优化的支持向量机模型的灌区水资源系统恢复空间特性分析

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This study aims to address a series of problems with agricultural irrigation water shortages and the poor efficiency of irrigation water use in severely colder irrigation areas in China. For this purpose, a support vector machine model based on the improved gray wolf optimization algorithm (IGWO-SVM) was proposed to improve the accuracy of the evaluation of the resilience of the water resource system in the irrigation areas. The results showed that the overall resilience of the selected irrigation areas was U-shaped from 2007 to 2016. From a spatial perspective, the results revealed that the resilience level of the western Songnen Plain irrigation area was less robust than that of the eastern Sanjiang Plain irrigation area. A comparison with the SVM model and SVM models optimized by the gray wolf optimization algorithm (GWO-SVM) and the gravity search algorithm (GSA-SVM) showed that the mean square error of the IGWO-SVM model was reduced by 7.69%, 12.19%, and 25%; the R-2 was 0.33%, 1.11% and 2.73%; and the accuracy was 2.32%, 4.74% and 16.03%, respectively. The running time of IGWO-SVM was 278.42 s, 498.63 s faster than those of GWO-SVM and GSA-SVM on average, respectively. The improvement in the results suggested that the IGWO-SVM model was stable and could be used to evaluate water resource system resilience.
机译：本研究旨在解决中国严寒地区农业灌溉用水短缺和灌溉用水效率低下的一系列问题。为此，提出了一种基于改进的灰狼优化算法（IGWO-SVM）的支持向量机模型，以提高灌区水资源系统恢复力评价的准确性。结果表明，从2007年到2016年，选定灌区的总体恢复力呈U型。结果表明，从空间角度来看，西部松嫩平原灌区的恢复力水平不如东部三江平原灌区。通过与支持向量机模型、灰太狼优化算法（GWO-SVM）和重力搜索算法（GSA-SVM）优化的支持向量机模型的比较，IGWO-SVM模型的均方误差分别降低了7.69%、12.19%和25%；R-2分别为0.33%、1.11%和2.73%；准确率分别为2.32%、4.74%和16.03%。IGWO-SVM的平均运行时间分别比GWO-SVM和GSA-SVM快278.42秒和498.63秒。结果表明，IGWO-SVM模型是稳定的，可用于评价水资源系统的恢复力。

著录项

  • 来源
    《Journal of Hydrology》 |2021年第1期|共14页
  • 作者

    Liu Dong; Li Maoxun; Ji Yi; Fu Qiang; Li Mo; Faiz Muhammad Abrar; Ali Shoaib; Li Tianxiao; Cui Song; Khan Muhammad Imran;

  • 作者单位

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Northeast Agr Univ Sch Water Conservancy &

    Civil Engn Harbin 150030 Heilongjiang Peoples R China;

    Univ Agr Faisalabad Dept Irrigat &

    Drainage Faisalabad Pakistan;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 水文科学（水界物理学）;
  • 关键词

    Sustainable development; Irrigation area; Resilience; SVM; China;

    机译：可持续发展;灌溉面积;弹性;SVM;中国;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号