| 引用本文: | 高涛,袁日萍,郑丽萍,等.基于几种算法优化BP网络模拟白杨树ET0[J].灌溉排水学报,0,():-. |
| GAO Tao,YUAN Riping,ZHENG Liping,et al.基于几种算法优化BP网络模拟白杨树ET0[J].灌溉排水学报,0,():-. |
|
| 摘要: |
| 【目的】影响植被的ET0的环境因子是很多的,部分因子的获取还比较困难,难以用多元线性模型表达,因此寻找一种简易可行的方法模拟植被ET0对环境因子的响应过程,对定量分析高寒区典型植被生态需水量尤为重要。【方法】利用贵德县2022年1月至6月的气象数据资料,建立了不同算法优化下模拟植被ET0的BP网络模型,选取其中151组数据对模型进行训练,其余30组数据对模型测试验证。【结果】影响白杨树ET0的主要因素为平均温度,2m风速,饱和水汽压差,相对湿度,相关性从大到小依次为平均温度、饱和水汽压差、2m风速和相对湿度,采用不同算法优化后BP神经网络模型模拟白杨树ET0,模拟效果相较于传统的BP网络均有提升。【结论】其中EWOA-BP优化模型模拟结果最佳,可以作为预测高寒区白杨树ET0的首选模型。 |
| 关键词: 植被ET0;优化的BP神经网络;高寒区;气象数据 |
| DOI： |
| 分类号:S161.4 |
| 基金项目:清华大学水沙科学与水利水电工程国家重点实验室开放基金资助课题(sklhse-2022-A-04)；青海省重大科技专项(2021-SF-134)。 |
|
| Simulation of Poplar ET0 by Optimizing BP Network Based on Several Algorithms |
|
GAO Tao, YUAN Riping, ZHENG Liping, GAN Yongde, WANG Shangtao
|
|
Laboratory of Water Ecological Management and Protection in River Source Areas,Ministry of Water Resources/ Laboratory of Ecological Protection and High Quality Development in the Upper Yellow River/ School of Civil Engineering and Water Resources,Qinghai University
|
| Abstract: |
| 【Objective】There are many environmental factors that affect ET0 of vegetation, and it is difficult to obtain some of them, so it is difficult to express them by multivariate linear model. Therefore, it is particularly important to find a simple and feasible method to simulate the response process of vegetation ET0 to environmental factors for quantitative analysis of ecological water demand of typical vegetation in alpine region.【Method】Based on the meteorological data of Guide County from January to June, 2022, a BP network model for simulating vegetation ET0 under different algorithm optimization was established, 151 groups of data were selected to train the model, and the remaining 30 groups of data were tested and verified.【Result】The main factors affecting poplar ET0 are average temperature, 2m wind speed, saturated vapor pressure difference, relative humidity, and the correlation from large to small is average temperature, saturated vapor pressure difference, 2m wind speed and relative humidity. BP neural network model optimized by different algorithms is used to simulate poplar ET0, and the simulation effect is improved compared with the traditional BP network.【Conclusion】among which EWOA-BP optimization model has the best simulation result, which can be used as the first choice model to predict poplar ET0 in alpine region. |
| Key words: Vegetation ET0; optimized BP neural network; alpine region; meteorological data |
