Comparison of Multi-Methods for Identifying Maize Phenology Using PhenoCams

Guo, Yahui; Chen, Shouzhi; Fu, Yongshuo H.; Xiao, Yi; Wu, Wenxiang; Wang, Hanxi; Beurs, Kirsten M. de

doi:10.3390/rs14020244

Cited by 12 publications

(8 citation statements)

References 121 publications

(122 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phenological data is fundamental to agricultural disaster prevention and mitigation, and the richness and accuracy of phenological data is critical to accurate monitoring and early warning of agro‐meteorological disasters. Current sources of phenological data for maize are mainly based on manual records at agro‐meteorological stations and remote sensing (Guo et al., 2022; Niu et al., 2022). However, phenological data is relatively lacking due to the flawed construction of such stations, the potential presence of human biases within manual recording, and the susceptibility of remote sensing monitoring to various factors such as atmospheric conditions, cloud coverage and the phenological stage of the plants.…”

Section: Discussionmentioning

confidence: 99%

“…Phenological data is fundamental to agricultural disaster prevention and mitigation, and the richness and accuracy of phenological data is critical to accurate monitoring and early warning of agrometeorological disasters. Current sources of phenological data for maize are mainly based on manual records at agro-meteorological stations and remote sensing (Guo et al, 2022;Niu et al, 2022). the varying meteorological conditions in different years, which also affect the growth process of maize to some extent.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Drought risk assessment for early maize growth in Northeast China based on a reconstructed phenological dataset

Wang,

Li,

et al. 2024

J Agronomy Crop Science

View full text Add to dashboard Cite

Drought is one of the meteorological disasters to which maize is most vulnerable during its seedling stage in Northeast China. The absence of phenological data impedes the precise evaluation of the likelihood of drought during this phase. In response to these issues, this study develops a phenology model and reconstructing the data. Furthermore, it effectively assessed drought risk at the site scale by utilizing drought indicators. Using reconstructed phenological data from 217 sites from 1981 to 2015, we analysed the duration and trends of each phenological period and assessed the spatial and temporal distribution of drought frequency at each growth stage. The study demonstrated that the average date ranges for the sowing, emergence, three‐leaf, and seven‐leaf stages annually were 115–138 days, 130–151 days, 135–160 days, and 150–180 days, respectively. Additionally, there was a significant trend towards earlier dates in all phenological stages. Our research reveals notable fluctuations in drought frequency during various growth stages of early maize in Northeast China. Particularly, the period from the three‐leaf to the seven‐leaf stages emerges as the most drought‐prone, while the initial emergence to three‐leaf stage also shows considerable vulnerability. On average, the frequency of drought events during the critical three‐ to seven‐leaf stage stands at 35%. This average is surpassed in regions like Heilongjiang, northwest Jilin, northern Inner Mongolia, and southwest Liaoning, indicating a heightened risk in these areas. The early maize growth stage drought types are mainly light and moderate drought, with the three‐leaf to seven‐leaf stage, and Heilongjiang and Inner Mongolia, as the key stages and regions of concern, respectively. Identifying the principal types of drought and their occurrence in distinct regions and growth stages is pivotal for averting and reducing disasters.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Phenological data is fundamental to agricultural disaster prevention and mitigation, and the richness and accuracy of phenological data is critical to accurate monitoring and early warning of agrometeorological disasters. Current sources of phenological data for maize are mainly based on manual records at agro-meteorological stations and remote sensing (Guo et al, 2022;Niu et al, 2022). the varying meteorological conditions in different years, which also affect the growth process of maize to some extent.…”

Section: Discussionmentioning

confidence: 99%

Drought risk assessment for early maize growth in Northeast China based on a reconstructed phenological dataset

Wang,

Li,

et al. 2024

J Agronomy Crop Science

View full text Add to dashboard Cite

show abstract

“…According to the relevant literature on estimating biomass by GLCM (Guo et al, 2022; Jiang et al, 2021; Lu et al, 2021; Maimaitijiang, Sagan, Sidike, Hartling, et al, 2020; Zheng et al, 2019), the GLCM texture features of wheat plants (leaves and spikes) were expressed by angular second moment (also known as energy feature) (SEM), entropy (ENT), contrast (CON), correlation (COR), and homogeneity (HOM; Fink et al, 2001; Haralick et al, 1973). The formulas used are as follows:

SEM goodbreak= \sum_{i, j} p {(i, j)}^{2}

ENT goodbreak= goodbreak- \sum_{i, j} p ()(, i, j) \log p ()(, i, j)

CON goodbreak= \sum_{i, j} {(i - j)}^{2} p ()(, i, j)

COR goodbreak= \sum_{i, j} \frac{()(, i goodbreak- μ_{i}) ()(, j goodbreak- μ_{j}) italicpP ()(, i, j)}{σ_{i} σ_{j}}

HOM goodbreak= \sum_{i, j} \frac{p ()(, i, j)}{1 + (||, i goodbreak- j)}

Where i and j represent the length and width of an image, and p is the number of gray‐level co‐occurrence matrix.…”

Section: Methodsmentioning

confidence: 99%

“…According to the relevant literature on estimating biomass by GLCM (Guo et al, 2022;Jiang et al, 2021;Lu et al, 2021;Maimaitijiang, Sagan, Sidike, Hartling, et al, 2020;Zheng et al, 2019), the GLCM texture features of wheat plants (leaves and spikes) were expressed by angular second moment (also known as energy feature) (SEM), entropy (ENT), contrast (CON), correlation (COR), and homogeneity (HOM; Fink et al, 2001;Haralick et al, 1973). The formulas used are as follows:…”

Section: Texture Features Extractionmentioning

confidence: 99%

Estimation of grain yield in wheat using source–sink datasets derived from RGB and thermal infrared imaging

Wang

Zhu

et al. 2022

Food and Energy Security

View full text Add to dashboard Cite

Timely and efficient monitoring of crop aboveground biomass (AGB) and grain yield (GY) forecasting before harvesting are critical for improving crop yields and ensuring food security in precision agriculture. The purpose of this study is to explore the potential of fusing source–sink‐level color, texture, and temperature values extracted from RGB images and thermal images based on proximal sensing technology to improve grain yield prediction. High‐quality images of wheat from flowering to maturity under different treatments of nitrogen application were collected using proximal sensing technology over a 2‐year trial. Numerous variables based on source and sink organs were extracted from the acquired subsample images, including 30 color features, 10 texture features, and two temperature values. The principal component analysis (PCA), least absolute shrinkage and selection operator (LASSO), and recursive feature elimination (RFE) were used to screen variables. Support vector regression (SVR) and random forest (RF) were applied to establish AGB estimation models, and the GY prediction models were built by RF. The source dataset and sink dataset performed differently on AGB and GY estimation, but the combined source–sink dataset performed best for estimating both AGB and GY. Based on the source–sink dataset, the LASSO‐RF model was the best combination for predicting AGB and GY, with the coefficient of determination (R2) of 0.85 and 0.86, root mean square error (RMSE) of 1179.09 and 609.61 kg ha−1, and the ratio of performance to deviation (RPD) of 2.10 and 2.45, respectively. This study demonstrates that the multivariate eigenvalues of both source and sink organs have the potential to predict wheat yield and that the combination of machine learning models and variable selection methods can significantly affect the accuracy of yield prediction models and achieve effective monitoring of crop growth at late reproductive stages.

show abstract

“…However, the growing variety of near-surface remote sensing technologies makes it easier to acquire data with high spatiotemporal resolution. Near-surface remote sensing techniques, which might successfully compensate for deficiencies in spatiotemporal resolution, represent a new approach to multiscale-based water quality monitoring [16][17][18]. Unmanned aerial vehicles (UAVs) have huge advantages in monitoring water pollution in small areas because of the simplicity of their operation and their affordability, flexibility, and nonsusceptibility to interference by clouds; moreover, they can acquire near-real-time high-resolution imagery [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

UAV Multispectral Image-Based Urban River Water Quality Monitoring Using Stacked Ensemble Machine Learning Algorithms—A Case Study of the Zhanghe River, China

et al. 2022

Self Cite

View full text Add to dashboard Cite

Timely monitoring of inland water quality using unmanned aerial vehicle (UAV) remote sensing is critical for water environmental conservation and management. In this study, two UAV flights were conducted (one in February and the other in December 2021) to acquire images of the Zhanghe River (China), and a total of 45 water samples were collected concurrently with the image acquisition. Machine learning (ML) methods comprising Multiple Linear Regression, the Least Absolute Shrinkage and Selection Operator, a Backpropagation Neural Network (BP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) were applied to retrieve four water quality parameters: chlorophyll-a (Chl-a), total nitrogen (TN), total phosphors (TP), and permanganate index (CODMn). Then, ML models based on the stacking approach were developed. Results show that stacked ML models could achieve higher accuracy than a single ML model; the optimal methods for Chl-a, TN, TP, and CODMn were RF-XGB, BP-RF, RF, and BP-RF, respectively. For the testing dataset, the R2 values of the best inversion models for Chl-a, TN, TP, and CODMn were 0.504, 0.839, 0.432, and 0.272, the root mean square errors were 1.770 μg L−1, 0.189 mg L−1, 0.053 mg L−1, and 0.767 mg L−1, and the mean absolute errors were 1.272 μg L−1, 0.632 mg L−1, 0.045 mg L−1, and 0.674 mg L−1, respectively. This study demonstrated the great potential of combined UAV remote sensing and stacked ML algorithms for water quality monitoring.

show abstract

Comparison of Multi-Methods for Identifying Maize Phenology Using PhenoCams

Cited by 12 publications

References 121 publications

Drought risk assessment for early maize growth in Northeast China based on a reconstructed phenological dataset

Drought risk assessment for early maize growth in Northeast China based on a reconstructed phenological dataset

Estimation of grain yield in wheat using source–sink datasets derived from RGB and thermal infrared imaging

UAV Multispectral Image-Based Urban River Water Quality Monitoring Using Stacked Ensemble Machine Learning Algorithms—A Case Study of the Zhanghe River, China

Contact Info

Product

Resources

About