Estimation of Leaf Area Index of Winter Wheat Based on Hyperspectral Data of Unmanned Aerial Vehicles

2019 ◽  
Author(s):  
Riqiang Chen ◽  
Haikuan Feng ◽  
Fuqin Yang ◽  
Changchun Li ◽  
Guijun Yang ◽  
...  
Keyword(s):  
Winter Wheat ◽  
Leaf Area Index ◽  
Unmanned Aerial Vehicles ◽  
Leaf Area ◽  
Hyperspectral Data ◽  
Area Index ◽  
Aerial Vehicles

scholarly journals Leaf Area Index Estimation Model for UAV Image Hyperspectral Data Based on Wavelength Variable Selection and Machine Learning Methods

2020 ◽  
Author(s):  
Juanjuan Zhang ◽  
Tao Cheng ◽  
Wei Guo ◽  
Xin Xu ◽  
Xinming Ma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Winter Wheat ◽  
Leaf Area Index ◽  
Leaf Area ◽  
Hyperspectral Data ◽  
Learning Methods ◽  
Successive Projections Algorithm ◽  
Area Index ◽  
Machine Learning Methods ◽  
Successive Projections

Abstract Background In order to accurately estimate leaf area index (LAI) of winter wheat by using unmanned aerial vehicle (UAV) hyperspectral imagery.Methods The UAV hyperspectral imaging data, alternating slice-wise diagonalization (ASD) spectral data, and LAI were simultaneously obtained at main growth stages (jointing stage, booting stage, and filling stage) of various winter wheat varieties under various nitrogen fertilizer treatments.The characteristic bands related to LAI were extracted from UAV hyperspectral data with different algorithms including first derivative (FD), successive projections algorithm (SPA), competitive adaptive reweighed sampling (CARS), and competitive adaptive reweighed sampling combined with successive projections algorithm (CARS_SPA). Furthermore, three modeling machine learning methods including partial least squares regression (PLSR), support vector machine regression (SVR), and extreme gradient boosting (Xgboost) were used to build LAI estimation models.Results Our results show that the correlation coefficient between UAV and ASD hyperspectral data is greater than 0.99, indicating the UAV data can be used for estimation of wheat growth information.The LAI bands selected by using different algorithms were slightly different among the 15 models built in this study. The Xgboost model using nine consecutive characteristic bands selected by CARS_SPA algorithm as input was proved to have the best performance. This model yielded identical results of coefficient of determination (0.89) for both calibration set and validation set, indicating a high accuracy of this model.Conclusions The Xgboost modeling method in combine with CARS_SPA algorithm can reduce input variables and improve the efficiency of model operation. Our results provide reference and technical support for nondestructive and rapid estimation of winter wheat LAI by using UAV.

scholarly journals Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods

Plant Methods ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Juanjuan Zhang ◽  
Tao Cheng ◽  
Wei Guo ◽  
Xin Xu ◽  
Hongbo Qiao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Winter Wheat ◽  
Leaf Area Index ◽  
Leaf Area ◽  
Hyperspectral Data ◽  
Learning Methods ◽  
Successive Projections Algorithm ◽  
Area Index ◽  
Machine Learning Methods ◽  
Successive Projections

Abstract Background To accurately estimate winter wheat leaf area index (LAI) using unmanned aerial vehicle (UAV) hyperspectral imagery is crucial for crop growth monitoring, fertilization management, and development of precision agriculture. Methods The UAV hyperspectral imaging data, Analytical Spectral Devices (ASD) data, and LAI were simultaneously obtained at main growth stages (jointing stage, booting stage, and filling stage) of various winter wheat varieties under various nitrogen fertilizer treatments. The characteristic bands related to LAI were extracted from UAV hyperspectral data with different algorithms including first derivative (FD), successive projections algorithm (SPA), competitive adaptive reweighed sampling (CARS), and competitive adaptive reweighed sampling combined with successive projections algorithm (CARS_SPA). Furthermore, three modeling machine learning methods including partial least squares regression (PLSR), support vector machine regression (SVR), and extreme gradient boosting (Xgboost) were used to build LAI estimation models. Results The results show that the correlation coefficient between UAV and ASD hyperspectral data is greater than 0.99, indicating the UAV data can be used for estimation of wheat growth information. The LAI bands selected by using different algorithms were slightly different among the 15 models built in this study. The Xgboost model using nine consecutive characteristic bands selected by CARS_SPA algorithm as input was proved to have the best performance. This model yielded identical results of coefficient of determination (0.89) for both calibration set and validation set, indicating a high accuracy of this model. Conclusions The Xgboost modeling method in combine with CARS_SPA algorithm can reduce input variables and improve the efficiency of model operation. The results provide reference and technical support for nondestructive and rapid estimation of winter wheat LAI by using UAV.

scholarly journals Mapping leaf area index in a mixed temperate forest using Fenix airborne hyperspectral data and Gaussian processes regression

2021 ◽  
Vol 95 ◽  
pp. 102242 ◽  
Author(s):  
Rui Xie ◽  
Roshanak Darvishzadeh ◽  
Andrew K. Skidmore ◽  
Marco Heurich ◽  
Stefanie Holzwarth ◽  
...  
Keyword(s):  
Leaf Area Index ◽  
Leaf Area ◽  
Gaussian Processes ◽  
Temperate Forest ◽  
Hyperspectral Data ◽  
Area Index

scholarly journals Representing winter wheat in the Community Land Model (version 4.5)

2017 ◽  
Vol 10 (5) ◽  
pp. 1873-1888 ◽  
Author(s):  
Yaqiong Lu ◽  
Ian N. Williams ◽  
Justin E. Bagley ◽  
Margaret S. Torn ◽  
Lara M. Kueppers
Keyword(s):  
Heat Flux ◽  
Winter Wheat ◽  
Leaf Area Index ◽  
Leaf Area ◽  
Latent Heat Flux ◽  
Carbon Allocation ◽  
Net Ecosystem Exchange ◽  
Area Index ◽  
Community Land Model ◽  
The Us

Abstract. Winter wheat is a staple crop for global food security, and is the dominant vegetation cover for a significant fraction of Earth's croplands. As such, it plays an important role in carbon cycling and land–atmosphere interactions in these key regions. Accurate simulation of winter wheat growth is not only crucial for future yield prediction under a changing climate, but also for accurately predicting the energy and water cycles for winter wheat dominated regions. We modified the winter wheat model in the Community Land Model (CLM) to better simulate winter wheat leaf area index, latent heat flux, net ecosystem exchange of CO2, and grain yield. These included schemes to represent vernalization as well as frost tolerance and damage. We calibrated three key parameters (minimum planting temperature, maximum crop growth days, and initial value of leaf carbon allocation coefficient) and modified the grain carbon allocation algorithm for simulations at the US Southern Great Plains ARM site (US-ARM), and validated the model performance at eight additional sites across North America. We found that the new winter wheat model improved the prediction of monthly variation in leaf area index, reduced latent heat flux, and net ecosystem exchange root mean square error (RMSE) by 41 and 35 % during the spring growing season. The model accurately simulated the interannual variation in yield at the US-ARM site, but underestimated yield at sites and in regions (northwestern and southeastern US) with historically greater yields by 35 %.

Spring top-dressings of ‘Nitro-Chalk’ and late sprays of a liquid N-fertilizer and a broad spectrum fungicide for consecutive crops of winter wheat at Saxmundham, Suffolk

1978 ◽  
Vol 90 (3) ◽  
pp. 509-516 ◽  
Author(s):  
A. Penny ◽  
F. V. Widdowson ◽  
J. F. Jenkyn
Keyword(s):  
Calcium Carbonate ◽  
Winter Wheat ◽  
Leaf Area Index ◽  
Ammonium Nitrate ◽  
Leaf Area ◽  
Broad Spectrum ◽  
N Fertilizer ◽  
N Content ◽  
Area Index ◽  
Liquid Fertilizer

SummaryAn experiment at Saxmundham, Suffolk, during 1974–6, tested late sprays of a liquid N-fertilizer (ammonium nitrate/urea) supplying 50 kg N/ha, and a broad spectrum fungicide (benomyl and maneb with mancozeb) on winter wheat given, 0, 50, 100 or 150 kg N/ha as ‘Nitro-Chalk’ (ammonium nitrate/calcium carbonate) in springMildew (Erysiphe graminisf. sp. tritici) was most severe in 1974. It was increased by N and decreased by the fungicide in both 1974 and 1975, but was negligible in 1976. Septoria (S. nodorum) was very slight in 1974 and none was observed in 1976. It was much more severe in 1975, but was unaffected by the fungicide perhaps because this was applied too late.Yield and N content, number of ears and leaf area index were determined during summer on samples taken from all plots given 100 or 150 kg N/ha in spring; each was larger with 150 than with 100 kg N/ha. The effects of the liquid N-fertilizer on yield and N content varied, but leaf area index was consistently increased. None was affected consistently by the fungicide.Yields, percentages of N in, and amounts of N removed by grain and straw were greatly and consistently increased by each increment of ‘Nitro-Chalk’. Yields of grain were increased (average, 9%) by the liquid fertilizer in 1974 and 1975, and most where most ‘Nitro-Chalk’ had been given, but not in 1976 when the wheat ripened in July; however, both the percentage of N in and the amount of N removed by the grain were increased by the liquid fertilizer each year. The fungicide increased the response to the liquid N-fertilizer in 1974, but not in 1975 when Septoria was not controlled, nor in 1976 when leaf diseases were virtually absent.The weight of 1000 grains was increased by each increment of ‘Nitro-Chalk’ in 1975 but only by the first one (50 kg N/ha) in 1974 and 1976; it was very slightly increased by the liquid fertilizer and by fungicide each year.

Sign in / Sign up

Export Citation Format

Share Document