Identification of Maize Lodging: A Case Study Using a Remotely Piloted Aircraft System

Acorsi, Matheus Gabriel; Martello, Maurício; Angnes, Graciele

doi:10.1590/1809-4430-eng.agric.v39nep66-73/2019

Cited by 5 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D-CNN analysis of spatio-temporal models was applied to UAV remote sensing for only a limited number of traits and crops. The applicability of the 3D-CNN analysis of spatio-temporal data to predict yield [18] is consistent with yield being a product of compound growth and dynamic interactions with the environment over the entire growing season. However, the black-box nature of CNN analysis makes it hard to pinpoint which elements of the 3D-CNN and time course of imagery drive enhancements in performance.…”

Section: Discussionsupporting

confidence: 53%

“…However, such methods require intensive manual labor and are limited to small spatial areas. Lodging has been monitored using satellites [14] and aircraft [18], recently including UAVs [3]. Advanced data-based modeling techniques benefit from the increased resolution of spatial data collected by UAVs, as they are able to exploit these data to learn relevant features on a given task [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum

2022

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV)-based remote sensing is gaining momentum in a variety of agricultural and environmental applications. Very-high-resolution remote sensing image sets collected repeatedly throughout a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow for an improved estimation of crop traits, as well as the effects of genetics and the environment on these traits. Multispectral and geometric time series imagery was collected by UAV on 11 dates, along with ground-truth data, in a field trial of 866 genetically diverse biomass sorghum accessions. We compared the performance of Convolution Neural Network (CNN) architectures that used image data from single dates (two spatial dimensions, 2D) versus multiple dates (two spatial dimensions + temporal dimension, 3D) to estimate lodging detection and severity. Lodging was detected with 3D-CNN analysis of time series imagery with 0.88 accuracy, 0.92 precision, and 0.83 recall. This outperformed the best 2D-CNN on a single date with 0.85 accuracy, 0.84 precision, and 0.76 recall. The variation in lodging severity was estimated by the best 3D-CNN analysis with 9.4% mean absolute error (MAE), 11.9% root mean square error (RMSE), and goodness-of-fit (R2) of 0.76. This was a significant improvement over the best 2D-CNN analysis with 11.84% MAE, 14.91% RMSE, and 0.63 R2. The success of the improved 3D-CNN analysis approach depended on the inclusion of “before and after” data, i.e., images collected on dates before and after the lodging event. The integration of geometric and spectral features with 3D-CNN architecture was also key to the improved assessment of lodging severity, which is an important and difficult-to-assess phenomenon in bioenergy feedstocks such as biomass sorghum. This demonstrates that spatio-temporal CNN architectures based on UAV time series imagery have significant potential to enhance plant phenotyping capabilities in crop breeding and precision agriculture applications.

show abstract

Section: Discussionsupporting

confidence: 53%

Section: Introductionmentioning

confidence: 99%

Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum

2022

View full text Add to dashboard Cite

show abstract

“…3D-CNN analysis of spatio-temporal models has been applied to UAV remote sensing for only a limited number of traits and crops. The applicability of 3D-CNN analysis of spatio-temporal data to predict yield [16] is consistent with yield being a product of compound growth and dynamic interactions with the environment over the entire growing season. But, the black-box nature of CNN analysis makes it hard to pinpoint which elements of the 3D-CNN and time-course of imagery drives enhancements in performance.…”

Section: Discussionmentioning

confidence: 54%

“…But, such methods require intensive manual labor and are limited to small spatial areas. Lodging has been monitored using satellites [14] and aircraft [16], including recently UAVs [3]. Advanced data-based modeling techniques benefit from increased resolution of spatial data collected by UAVs, as they are able to exploit this to learn relevant features on a given task [17].…”

Section: Introductionmentioning

confidence: 99%

Implementing spatio-temporal 3D-convolution neural networks and UAV time series imagery to better predict lodging damage in sorghum.

Varela

Leakey

2022

agriRxiv

View full text Add to dashboard Cite

Unmanned aerial vehicle (UAV)-based remote sensing is gaining momentum in a variety of agricultural and environmental applications. Very high-resolution remote sensing image sets collected repeatedly across a crop growing season are becoming increasingly common. Analytical methods able to learn from both spatial and time dimensions of the data may allow improved estimation of crop traits, as well as the effects of genetics and the environment upon them. Multispectral and geometric time series imagery was collected by UAV on 11 dates, along with ground-truth data, in a field trial of 866 genetically diverse biomass sorghum accessions. We compared the performance of Convolution Neural Network (CNN) architectures that used image data from single dates (two spatial dimensions, 2D) versus multiple dates (two spatial dimensions + temporal dimension, 3D) to estimate lodging detection and severity. Lodging was detected with 3D-CNN analysis of time-series imagery with 0.88 accuracy, 0.92 precision, and 0.83 recall. This outperformed the best 2D-CNN on a single date with 0.85 accuracy, 0.84 precision, and 0.76 recall. Variation in lodging severity was estimated by the best 3D-CNN analysis with 9.4% mean absolute error (MAE), 11.9% root mean square error (RMSE), and goodness-of-fit (R2) of 0.76. This was a significant improvement over the best 2D-CNN analysis with 11.84% MAE, 14.91% RMSE, and 0.63 R2. Success of the improved 3D-CNN analysis approach depended on inclusion of before and after data i.e. images collected on dates before and after the lodging event. Integration of geometric and spectral features with 3D-CNN architecture was also key to improved assessment of lodging severity, which is an important and difficult to assess phenomenon in bioenergy feedstocks such as biomass sorghum. This demonstrates that spatio-temporal CNN architectures based on UAV time series imagery have significant potential to enhance plant phenotyping capabilities in crop breeding and precision agriculture applications.

show abstract

“…The maize growing season is from July to September every year. During this period, severe weather events such as strong winds and rainstorms occur frequently, and are the main cause of maize lodging [2,3]. Maize lodging seriously affects the normal progress of plant photosynthesis and nutrient transport.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Plant Height Changes of Lodged Maize Using UAV-LiDAR Data

Zhou

Cheng

et al. 2020

Agriculture

View full text Add to dashboard Cite

Lodging stress seriously affects the yield, quality, and mechanical harvesting of maize, and is a major natural disaster causing maize yield reduction. The aim of this study was to obtain light detection and ranging (LiDAR) data of lodged maize using an unmanned aerial vehicle (UAV) equipped with a RIEGL VUX-1UAV sensor to analyze changes in the vertical structure of maize plants with different degrees of lodging, and thus to use plant height to quantitatively study maize lodging. Based on the UAV-LiDAR data, the height of the maize canopy was retrieved using a canopy height model to determine the height of the lodged maize canopy at different times. The profiles were analyzed to assess changes in maize plant height with different degrees of lodging. The differences in plant height growth of maize with different degrees of lodging were evaluated to determine the plant height recovery ability of maize with different degrees of lodging. Furthermore, the correlation between plant heights measured on the ground and LiDAR-estimated plant heights was used to verify the accuracy of plant height estimation. The results show that UAV-LiDAR data can be used to achieve maize canopy height estimation, with plant height estimation accuracy parameters of R2 = 0.964, RMSE = 0.127, and nRMSE = 7.449%. Thus, it can reflect changes of plant height of lodging maize and the recovery ability of plant height of different lodging types. Plant height can be used to quantitatively evaluate the lodging degree of maize. Studies have shown that the use of UAV-LiDAR data can effectively estimate plant heights and confirm the feasibility of LiDAR data in crop lodging monitoring.

show abstract

Identification of Maize Lodging: A Case Study Using a Remotely Piloted Aircraft System

Cited by 5 publications

References 12 publications

Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum

Implementing Spatio-Temporal 3D-Convolution Neural Networks and UAV Time Series Imagery to Better Predict Lodging Damage in Sorghum

Implementing spatio-temporal 3D-convolution neural networks and UAV time series imagery to better predict lodging damage in sorghum.

Analysis of Plant Height Changes of Lodged Maize Using UAV-LiDAR Data

Contact Info

Product

Resources

About