
Application of Support Vector Machine Model Based on GA Optimization in Water Consumption Prediction of Green Peppers
Jing-ran LIU, Xin LIU, Hai-xia WU, Hao DENG, Zao-peng LI
Application of Support Vector Machine Model Based on GA Optimization in Water Consumption Prediction of Green Peppers
In order to save irrigation water, the planting technology of furrow rainwater harvesting combined with drip irrigation (MFR-DI) was adopted, and the crop water consumption of green peppers in this technology was predicted. Based on years of meteorological data, canopy temperature and daily crop water consumption of green peppers, the GA-SVM model for predicting daily crop water consumption of green peppers in MFR-DI planting mode was constructed with canopy temperature and meteorological factors as input factors. The model was tested with data of 2017. The results showed that when the same meteorological factors were input, GA-SVM1 (RMSE=0.901 0 mm/d, MAE=0.673 5 mm/d, NS=0.971 8) model had higher precision performance than SVM (RMSE=0.960 7 mm/d,MAE=0.769 1 mm/d,NS=0.968 0) model. In addition, under the same number of input factors, when canopy temperature was introduced as one of the input factors of GA-SVM, the prediction accuracy was higher than that of GA-SVM model with only meteorological factor. The RMSE, MAE and NS of GA-SVM with canopy temperature being introduced were 0.781 7 mm/d, 0.583 8 mm/d and 0.978 8, respectively. The results show that GA can improve the convergence speed of SVM model and make the prediction model more accurate. In addition, introducing canopy temperature into crop water consumption prediction model can improve the prediction accuracy of the model and provide reference for realizing efficient and intelligent water saving.
support vector machine / Genetic Algorithm (GA) / prediction of crop water consumption / canopy temperature / green peppers {{custom_keyword}} /
Tab. 1 Parameter setting of Genetic Algorithm表1 遗传算法参数设置 |
参数 | 种群大小 | 迭代次数 | 交叉概率 | 变异概率 |
---|---|---|---|---|
取值 | 100 | 100 | 0.8 | 0.01 |
Tab. 2 Summary of input combinations for SVM prediction model in MFR-DI表2 MFR-DI种植模式下基于SVM预测模型的输入组合 |
预测模型 | 气象数据 | 作物数据 | ||||
---|---|---|---|---|---|---|
T | RH | Ph | u2 | Rs | Tc | |
SVM | √ | √ | √ | √ | √ | |
GA-SVM1 | √ | √ | √ | √ | √ | |
GA-SVM2 | √ | √ | √ | √ | √ |
Fig. 5 Comparative analysis of the crop water consumption of green peppers predicted by SVM and GA-SVM1 models图5 SVM与GA-SVM1模型预测青椒作物需水量的比较分析 |
Tab. 3 Performance comparison of ET prediction models表3 ET预测模型的性能对比 |
预测模型 | RMSE (mm·d-1) | MAE (mm·d-1) | NS |
---|---|---|---|
SVM | 0.960 7 | 0.769 1 | 0.968 0 |
GA-SVM1 | 0.901 0 | 0.673 5 | 0.971 8 |
GA-SVM2 | 0.781 7 | 0.583 8 | 0.978 8 |
1 |
包志炎,郑高安,王 萱,等. 基于模糊数据挖掘的灌区水资源配置研究[J].农业机械学报,2020(8):1-9.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
崔丙健,高 峰,胡 超,等. 非常规水资源农业利用现状及研究进展[J].灌溉排水学报,2019,38(7):60-68.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
中华人民共和国水利部. 2018年中国水资源公报[R].2018.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
沈莹莹,陈梦婷,崔 静,等. 农田灌溉用水量统计工作中的样点灌区选取方法研究[J].中国农村水利水电,2020(3):112-115.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
杨会娟,粟晓玲,郭 静. 基于支持向量机的干旱区月潜在蒸散发的模拟[J].中国农村水利水电,2016(7):6-10.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
李志新,赖志琴,龙云墨. 基于GA-Elman神经网络的参考作物需水量预测[J].节水灌溉,2019(2):117-120.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
孟 玮,孙西欢,郭向红,等. 基于人工蜂群径向基神经网络预测参考作物需水量[J].节水灌溉,2018(9):6-11.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
邓 皓,李文竹,刘婧然,等. 基于MIV-MEA-Elman神经网络的核桃果实膨大期需水量预测[J].节水灌溉,2020(4):68-72.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
彭世彰,魏 征,徐俊增,等. 参考作物腾发量支持向量回归机实时预报模型[J].农业工程学报,2009,25(10):45-49.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
郭淑海,杨国靖,李清峰,等. 新疆阿克苏河上游高寒草甸蒸散发观测与估算[J].冰川冻土,2015,37(1):241-248.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
POU A,
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
刘婧然,程东娟,王丽玄,等. 起垄微沟滴灌土壤水分入渗规律试验研究[J].节水灌溉,2018(9):6-11.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
周旭姣,王 琦,张登奎,等. 垄沟集雨种植对土壤水热效应及紫花苜蓿产量的影响[J].草业学报,2019,28(11):60-74.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
尹鑫卫,王 琦,李晓玲,等. 半干旱区垄沟集雨系统点尺度土壤水分动态随机模拟[J].生态学报,2019,39(1):321-332.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
21 |
ALI S,
{{custom_citation.content}}
{{custom_citation.annotation}}
|
22 |
梅四卫,朱涵珍,王 术,等. 不同覆盖方式对土壤水肥热状况以及玉米产量影响[J].灌溉排水学报,2020,39(4):69-73.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
23 |
钱玉平,田慧慧,程宏波,等. 秸秆覆盖及播种方式对马铃薯耗水特性和产量的影响[J].中国生态农业学报,2020,28(6):826-834.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
24 |
李 康,王 魏,林少涵. 基于GA-SVR的海水养殖过程软测量建模[J].控制工程,2019,26(11):2 047-2 051.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
25 |
王晨晖,刘立申,任 佳,等. 主成分分析法和遗传算法优化的支持向量机模型在地震伤亡人数预测中的应用[J]. 地震,2020,40(3):143-152.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
26 |
马 创,吕孝飞,梁炎明. 基于GA-SVM的农产品质量分类[J].计算机科学,2020,47(6):517-520.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |