Improving water status prediction of winter wheat using multi-source data with machine learning

Shi, Bo; Yuan, Yifan; Zhuang, Tingxuan; Xu, Xuan; Schmidhalter, Urs; Ata-UI-Karim, Syed Tahir; Zhao, Ben; Liu, Xiaojun; Tian, Yongchao; Zhu, Yan; Cao, Weixing; Cao, Qiang

doi:10.1016/j.eja.2022.126548

Cited by 17 publications

(6 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, multi-source data related to environmental factors coupled with the spectral monitoring model of LWC has been successfully established in wheat plants to reduce the errors caused by environmental and physiological factors during the spectral monitoring process [ 16 ]. This study used the Pearson correlation coefficient method to analyze the physiological and ecological indicators related to LWC.…”

Section: Discussionmentioning

confidence: 99%

“…The band amplitude of the device ranged from 350 to 2500 nm. The measurements were conducted under clear and cloudless sky conditions between 10:00 and 14:00 [ 16 ]. After measuring 10 times for each sample, the average value was calculated, and the reference plate was used to correct the instrument every 15 min.…”

Section: Methodsmentioning

confidence: 99%

“…Finally, the four machine learning algorithms named decision tree regression (DT), random forest regression (RF), K-nearest neighbor regression (KNN), and gradient boosting decision tree regression (GBDT) were adopted in this study. The four selected methods were successfully applied on estimating various ecological parameters such as water content of wheat plants and soil moisture of wheat fields [ 16 , 33 ]. In addition, the scikit-learn packages of the four algorithms were from Python 3.8 software ( https://scikit-learn.org/stable/index.html ).…”

Section: Methodsmentioning

confidence: 99%

“…The neglected information could be the primary reason for the poor generalizability of existing vegetation index models in practical applications. Therefore, integrating the actors into the spectral monitoring models of LWC would be more high precision due to considering the potential effects of the growing environment and growth characteristics on LWC [ 16 , 17 ]. Qin et al [ 18 ] have recently improved crop nitrogen content prediction accuracy using a spectral model that combines image feature parameters and fluorescence parameters.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, machine learning algorithms allow the use of different classes of sample data as input variables, allowing multiple sources of data (physiological and ecological indicators and spectral information) to be effectively coupled and can effectively discriminate between differences in the contributions of the input variables, allowing the model’s parameters can be fully utilized. Therefore, we speculated that the monitoring capacities of vegetation index models integrating with multi-source data would also have significant advantages using machine learning algorithms when predicting the LWC of rice plants based on the results previous studies [ 16 , 26 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving the prediction performance of leaf water content by coupling multi-source data with machine learning in rice (Oryza sativa L.)

Zhang,

Xu,

She

et al. 2024

Plant Methods

View full text Add to dashboard Cite

Background Leaf water content (LWC) significantly affects rice growth and development. Real-time monitoring of rice leaf water status is essential to obtain high yield and water use efficiency of rice plants with precise irrigation regimes in rice fields. Hyperspectral remote sensing technology is widely used in monitoring crop water status because of its rapid, nondestructive, and real-time characteristics. Recently, multi-source data have been attempted to integrate into a monitored model of crop water status based on spectral indices. However, there are fewer studies using spectral index model coupled with multi-source data for monitoring LWC in rice plants. Therefore, 2-year field experiments were conducted with three irrigation regimes using four rice cultivars in this study. The multi-source data, including canopy ecological factors and physiological parameters, were incorporated into the vegetation index to accurately predict LWC in rice plants. Results The results presented that the model accuracy of rice LWC estimation after combining data from multiple sources improved by 6–44% compared to the accuracy of a single spectral index normalized difference index (ND). Additionally, the optimal prediction accuracy of rice LWC was produced using a machine algorithm of gradient boosted decision tree (GBDT) based on the combination of ND(1287,1673) and crop water stress index (CWSI) (R2 = 0.86, RMSE = 0.01). Conclusions The machine learning estimation model constructed based on multi-source data fully utilizes the spectral information and considers the environmental changes in the crop canopy after introducing multi-source data parameters, thus improving the performance of spectral technology for monitoring rice LWC. The findings may be helpful to the water status diagnosis and accurate irrigation management of rice plants.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%