Comparative analysis of vegetation indices, non-parametric and physical retrieval methods for monitoring nitrogen in wheat using UAV-based multispectral imagery

2016 ◽  
Author(s):  
Yong Liu ◽  
Tao Cheng ◽  
Yan Zhu ◽  
Yongchao Tian ◽  
Weixing Cao ◽  
...  
Keyword(s):  
Comparative Analysis ◽  
Vegetation Indices ◽  
Multispectral Imagery ◽  
Non Parametric

Contrast-Enhanced MRI with Magnetization Transfer Effect in the Imaging of Brain Metastatic Lesions

2017 ◽  
pp. 8-17
Author(s):  
A. A. Ermakova ◽  
O. Yu. Borodin ◽  
M. Yu. Sannikov ◽  
S. D. Koval ◽  
V. Yu. Usov
Keyword(s):  
Comparative Analysis ◽  
Roc Analysis ◽  
Magnetization Transfer ◽  
Metastatic Lesion ◽  
Transfer Effect ◽  
Wilcoxon Test ◽  
Post Contrast ◽  
Metastatic Lesions ◽  
The Brain ◽  
Non Parametric

Purpose: to investigate the diagnostic opportunities of contrast  magnetic resonance imaging with the effect of magnetization transfer effect in the diagnosis of focal metastatic lesions in the brain.Materials and methods.Images of contrast MRI of the brain of 16  patients (mean age 49 ± 18.5 years) were analysed. Diagnosis of  the direction is focal brain lesion. All MRI studies were carried out  using the Toshiba Titan Octave with magnetic field of 1.5 T. The  contrast agent is “Magnevist” at concentration of 0.2 ml/kg was  used. After contrasting process two T1-weighted studies were  performed: without T1-SE magnetization transfer with parameters of pulse: TR = 540 ms, TE = 12 ms, DFOV = 24 sm, MX = 320 × 224  and with magnetization transfer – T1-SE-MTC with parameters of pulse: ΔF = −210 Hz, FA(МТС) = 600°, TR = 700 ms, TE = 10 ms,  DFOV = 23.9 sm, MX = 320 x 224. For each detected metastatic  lesion, a contrast-to-brain ratio (CBR) was calculated. Comparative  analysis of CBR values was carried out using a non-parametric  Wilcoxon test at a significance level p < 0.05. To evaluate the  sensitivity and specificity of the techniques in the detection of  metastatic foci (T1-SE and T1-SE-MTC), ROC analysis was used. The sample is divided into groups: 1 group is foci ≤5 mm in size, 2  group is foci from 6 to 10 mm, and 3 group is foci >10 mm. Results.Comparative analysis of CBR using non-parametric Wilcoxon test showed that the values of the CBR on T1-weighted  images with magnetization transfer are significantly higher (p  <0.001) that on T1-weighted images without magnetization transfer. According to the results of the ROC analysis, sensitivity in detecting  metastases (n = 90) in the brain on T1-SE-MTC and T1-SE was  91.7% and 81.6%, specificity was 100% and 97.6%, respectively.  The accuracy of the T1-SE-MTC is 10% higher in comparison with  the technique without magnetization transfer. Significant differences (p < 0.01) between the size of the foci detected in post-contrast T1- weighted images with magnetization transfer and in post-contrast  T1-weighted images without magnetization transfer, in particular for  foci ≤5 mm in size, were found. Conclusions1. Comparative analysis of CBR showed significant (p < 0.001)  increase of contrast between metastatic lesion and white matter on  T1-SE-MTC in comparison with T1-SE.2. The sensitivity, specificity and accuracy of the magnetization transfer program (T1-SE-MTC) in detecting foci of  metastatic lesions in the brain is significantly higher (p < 0.01), relative to T1-SE.3. The T1-SE-MTC program allows detecting more foci in comparison with T1-SE, in particular foci of ≤5 mm (96% and 86%, respectively, with p < 0.05).

scholarly journals Mapping Wheat Dry Matter and Nitrogen Content Dynamics and Estimation of Wheat Yield Using UAV Multispectral Imagery Machine Learning and a Variety-Based Approach: Case Study of Morocco

2021 ◽  
Vol 3 (1) ◽  
pp. 29-49
Author(s):  
Ghizlane Astaoui ◽  
Jamal Eddine Dadaiss ◽  
Imane Sebari ◽  
Samir Benmansour ◽  
Ettarid Mohamed
Keyword(s):  
Random Forest ◽  
Nitrogen Uptake ◽  
Dry Matter ◽  
Vegetation Indices ◽  
Wheat Yield ◽  
Wheat Crop ◽  
Multispectral Imagery ◽  
Biophysical Parameters ◽  
Phenological Stages ◽  
Wheat Varieties

Our work aims to monitor wheat crop using a variety-based approach by taking into consideration four different phenological stages of wheat crop development. In addition to highlighting the contribution of Red-Edge vegetation indices in mapping wheat dry matter and nitrogen content dynamics, as well as using Random Forest regressor in the estimation of wheat yield, dry matter and nitrogen uptake relying on UAV (Unmanned Aerial Vehicle) multispectral imagery. The study was conducted on an experimental platform with 12 wheat varieties located in Sidi Slimane (Morocco). Several flight missions were conducted using eBee UAV with MultiSpec4C camera according to phenological growth stages of wheat. The proposed methodology is subdivided into two approaches, the first aims to find the most suitable vegetation index for wheat’s biophysical parameters estimation and the second to establish a global model regardless of the varieties to estimate the biophysical parameters of wheat: Dry matter and nitrogen uptake. The two approaches were conducted according to six main steps: (1) UAV flight missions and in-situ data acquisition during four phenological stages of wheat development, (2) Processing of UAV multispectral images which enabled us to elaborate the vegetation indices maps (RTVI, MTVI2, NDVI, NDRE, GNDVI, GNDRE, SR-RE et SR-NIR), (3) Automatic extraction of plots by Object-based image analysis approach and creating a spatial database combining the spectral information and wheat’s biophysical parameters, (4) Monitoring wheat growth by generating dry biomass and wheat’s nitrogen uptake model using exponential, polynomial and linear regression for each variety this step resumes the varietal approach, (5) Engendering a global model employing both linear regression and Random Forest technique, (6) Wheat yield estimation. The proposed method has allowed to predict from 1 up to 21% difference between actual and estimated yield when using both RTVI index and Random Forest technique as well as mapping wheat’s dry biomass and nitrogen uptake along with the nitrogen nutrition index (NNI) and therefore facilitate a careful monitoring of the health and the growth of wheat crop. Nevertheless, some wheat varieties have shown a significant difference in yield between 2.6 and 3.3 t/ha.

scholarly journals A Comparative Assessment of Different Modeling Algorithms for Estimating Leaf Nitrogen Content in Winter Wheat Using Multispectral Images from an Unmanned Aerial Vehicle

2018 ◽  
Vol 10 (12) ◽  
pp. 2026 ◽  
Author(s):  
Hengbiao Zheng ◽  
Wei Li ◽  
Jiale Jiang ◽  
Yong Liu ◽  
Tao Cheng ◽  
...  
Keyword(s):  
Winter Wheat ◽  
Unmanned Aerial Vehicle ◽  
Processing Speed ◽  
Parametric Modeling ◽  
Comparative Assessment ◽  
Transfer Model ◽  
Leaf Nitrogen Content ◽  
Multispectral Imagery ◽  
Aerial Vehicle ◽  
Non Parametric

Unmanned aerial vehicle (UAV)-based remote sensing (RS) possesses the significant advantage of being able to efficiently collect images for precision agricultural applications. Although numerous methods have been proposed to monitor crop nitrogen (N) status in recent decades, just how to utilize an appropriate modeling algorithm to estimate crop leaf N content (LNC) remains poorly understood, especially based on UAV multispectral imagery. A comparative assessment of different modeling algorithms (i.e., simple and non-parametric modeling algorithms alongside the physical model retrieval method) for winter wheat LNC estimation is presented in this study. Experiments were conducted over two consecutive years and involved different winter wheat varieties, N rates, and planting densities. A five-band multispectral camera (i.e., 490 nm, 550 nm, 671 nm, 700 nm, and 800 nm) was mounted on a UAV to acquire canopy images across five critical growth stages. The results of this study showed that the best-performing vegetation index (VI) was the modified renormalized difference VI (RDVI), which had a determination coefficient (R2) of 0.73 and a root mean square error (RMSE) of 0.38. This method was also characterized by a high processing speed (0.03 s) for model calibration and validation. Among the 13 non-parametric modeling algorithms evaluated here, the random forest (RF) approach performed best, characterized by R2 and RMSE values of 0.79 and 0.33, respectively. This method also had the advantage of full optical spectrum utilization and enabled flexible, non-linear fitting with a fast processing speed (2.3 s). Compared to the other two methods assessed here, the use of a look up table (LUT)-based radiative transfer model (RTM) remained challenging with regard to LNC estimation because of low prediction accuracy (i.e., an R2 value of 0.62 and an RMSE value of 0.46) and slow processing speed. The RF approach is a fast and accurate technique for N estimation based on UAV multispectral imagery.

scholarly journals Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

Drones ◽  
2019 ◽  
Vol 3 (4) ◽  
pp. 80 ◽  
Author(s):  
Kaori Otsu ◽  
Magda Pla ◽  
Andrea Duane ◽  
Adrián Cardil ◽  
Lluís Brotons
Keyword(s):  
Random Forest ◽  
Large Scale ◽  
Vegetation Index ◽  
Vegetation Indices ◽  
Thaumetopoea Pityocampa ◽  
Multispectral Imagery ◽  
Mixed Stands ◽  
Crown Defoliation ◽  
Total Study Area ◽  
Pine Species

Periodical outbreaks of Thaumetopoea pityocampa feeding on pine needles may pose a threat to Mediterranean coniferous forests by causing severe tree defoliation, growth reduction, and eventually mortality. To cost–effectively monitor the temporal and spatial damages in pine–oak mixed stands using unmanned aerial systems (UASs) for multispectral imagery, we aimed at developing a simple thresholding classification tool for forest practitioners as an alternative method to complex classifiers such as Random Forest. The UAS flights were performed during winter 2017–2018 over four study areas in Catalonia, northeastern Spain. To detect defoliation and further distinguish pine species, we conducted nested histogram thresholding analyses with four UAS-derived vegetation indices (VIs) and evaluated classification accuracy. The normalized difference vegetation index (NDVI) and NDVI red edge performed the best for detecting defoliation with an overall accuracy of 95% in the total study area. For discriminating pine species, accuracy results of 93–96% were only achievable with green NDVI in the partial study area, where the Random Forest classification combined for defoliation and tree species resulted in 91–93%. Finally, we achieved to estimate the average thresholds of VIs for detecting defoliation over the total area, which may be applicable across similar Mediterranean pine stands for monitoring regional forest health on a large scale.

Sign in / Sign up

Export Citation Format

Share Document