Grapevine Phenology Prediction: A Comparison of Physical and Machine Learning Models

被引：2

作者：

Lacueva-Perez, Francisco J. ^{[1
]}

Ilarri, Sergio ^{[2
]}

Barriuso, Juan J. ^{[3
]}

Balduque, Joaquin ^{[3
]}

Labata, Gorka ^{[1
]}

del-Hoyo, Rafael ^{[1
]}

机构：

[1] Inst Tecnol Aragon, Zaragoza 50018, Spain

[2] Univ Zaragoza, Dept Comp Sci & Syst Engn, I3A, Zaragoza 50018, Spain

[3] Univ Zaragoza, Dept Agr & Nat Environm Sci, Zaragoza 50018, Spain

来源：

BIG DATA ANALYTICS AND KNOWLEDGE DISCOVERY, DAWAK 2022 | 2022年 / 13428卷

关键词：

Grapevine; Phenology prediction; Machine learning; IoT; BIG DATA;

D O I：

10.1007/978-3-031-12670-3_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The reduction of plant pest treatments contributes to a more sustainable agriculture. However, to be effective, the application of these treatments must be performed at the correct phenological stage of the plants. In this paper, we present the comparison of physical and ML models to predict the phenological stage of vineyards. The performance of both shows an average R-2 above 0.94. However, the physical models do not generalize well and they cannot be easily improved by the inclusion of new datasets as ML models do.

引用

页码：263 / 269

页数：7

共 24 条

[1] Optuna: A Next-generation Hyperparameter Optimization Framework [J].