2019
DOI: 10.1016/j.agrformet.2019.03.010
|View full text |Cite
|
Sign up to set email alerts
|

Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

26
249
1
2

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2

Relationship

1
8

Authors

Journals

citations
Cited by 410 publications
(278 citation statements)
references
References 92 publications
26
249
1
2
Order By: Relevance
“…Combining SIF with all environmental data (i.e., climate data, soil properties, and irrigation ratio) significantly improved the predicted R 2 s (ranging from 0.19 to 0.32) depending on the methods (Figure 8a). Moreover, the peak SIF consistently showed more contribution than the other two stages, which was in agreement with previous studies [17,29].…”
Section: The Spatial Patterns Of Predicted Yieldsupporting
confidence: 93%
See 1 more Smart Citation
“…Combining SIF with all environmental data (i.e., climate data, soil properties, and irrigation ratio) significantly improved the predicted R 2 s (ranging from 0.19 to 0.32) depending on the methods (Figure 8a). Moreover, the peak SIF consistently showed more contribution than the other two stages, which was in agreement with previous studies [17,29].…”
Section: The Spatial Patterns Of Predicted Yieldsupporting
confidence: 93%
“…In agreement with previous studies [17,64,65], we found both SIF and EVI were positively correlated with yield across AEZs, and the correlation coefficients at the peak stage for SIF were generally higher than that for EVI, illustrating SIF was more sensitive to a high photosynthesis rate. However, we noticed the predicted R 2 for two data sources were comparable on the national scale irrelative to methods.…”
Section: Comparing the Performances Of Evi And Sif In Predicting Cropsupporting
confidence: 92%
“…DCN provides the best estimation results with RMSE equals 0.82 Mg ha −1 as compared with LASSO and RF ( figure 4). LASSO provides the lowest estimation accuracy with RMSE equals 1.14 Mg ha −1 , agreeing with the discovery in previous study that linear methods are limited in simulating the relationship between crop yield and meteorological factors relative to nonlinear approaches (Cai et al 2018). RF provides a better result than LASSO with RMSE equals 1.05 Mg ha −1 .…”
Section: Performance Comparison Among Dcn Lasso and Rfsupporting
confidence: 89%
“…Recently, machine-learning (ML) has emerged as a powerful tool for environmental analysis (Chlingaryan et al 2018), as well as climate impact assessment on crop yield (Jeong et al 2016, Johnson et al 2016, Feng et al 2018, Cai et al 2019, Vogel et al 2019. ML often shows better performance compared to conventional linear regression models (Feng et al 2018), as it can capture non-linear relationships, handle the interactions among predictors and do not assume a certain shape of response function (e.g.…”
Section: Introductionmentioning
confidence: 99%