Detecting coffee leaf rust with UAV-based vegetation indices and decision tree machine learning models

Marin, Diego Bedin; Ferraz, Gabriel Araújo e Silva; Santana, Lucas Santos; Barbosa, Brenon Diennevan Souza; Barata, Rafael Alexandre Pena; Osco, Lucas Prado; Ramos, Ana Paula Marques; Guimarães, Paulo Henrique Sales

doi:10.1016/j.compag.2021.106476

Cited by 33 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Narrow bands in the visible and near-infrared hyperspectral images are sensitive to the subtle changes of plants caused by diseases, providing the possibility for disease identification and diagnosis ( Yuan et al., 2019 ; Lin et al., 2020 ). Screening important bands related to target tasks as features (such as calculating vegetation index) is effective to reduce redundant data in hyperspectral bands ( Marin et al., 2021 ; Zhang et al., 2021 ). There are also related researches on constructing new indices for disease detection by screening sensitive bands.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

Bai

Zhou²,

Feng³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Hyperspectral imaging technique combined with machine learning is a powerful tool for the evaluation of disease phenotype in rice disease-resistant breeding. However, the current studies are almost carried out in the lab environment, which is difficult to apply to the field environment. In this paper, we used visible/near-infrared hyperspectral images to analysis the severity of rice bacterial blight (BB) and proposed a novel disease index construction strategy (NDSCI) for field application. A designed long short-term memory network with attention mechanism could evaluate the BB severity robustly, and the attention block could filter important wavelengths. Best results were obtained based on the fusion of important wavelengths and color features with an accuracy of 0.94. Then, NSDCI was constructed based on the important wavelength and color feature related to BB severity. The correlation coefficient of NDSCI extended to the field data reached -0.84, showing good scalability. This work overcomes the limitations of environmental conditions and sheds new light on the rapid measurement of phenotype in disease-resistant breeding.

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

Bai

Zhou²,

Feng³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…(3) The RF algorithm was trained and accuracy validated by multispectral image sample data for Sentinel-2 image classification and compared with four classification algorithms, spectral angle matching (SAM) (Kruse et al, 1993), support vector machine (SVM) (Pujari et al, 2016), decision tree (DT) (Marin et al, 2021) and BP neural network (Xu et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…The main work of this study is as follows: (1) Based on the multitemporal Sentinel-2 satellite data, the cotton area in the study area was extracted by using the supervised classification algorithm and vegetation index (VI) threshold method to remove unnecessary disturbing factors for the classification of aphid infestation severity; (2) The DRS algorithm was used to process and analyze the ground hyperspectral data, ground hyperspectral resampling data and Sentinel-2 multispectral image sampling point data. The sensitive bands associated with aphid infestation were extracted by Pearson correlation analysis, and the effectiveness of the DRS algorithm was verified; (3) The RF algorithm was trained and accuracy validated by multispectral image sample data for Sentinel-2 image classification and compared with four classification algorithms, spectral angle matching (SAM) ( Kruse et al., 1993 ), support vector machine (SVM) ( Pujari et al., 2016 ), decision tree (DT) ( Marin et al., 2021 ) and BP neural network ( Xu et al., 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Cotton aphid infestation monitoring using Sentinel-2 MSI imagery coupled with derivative of ratio spectroscopy and random forest algorithm

Zhao

Song

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Aphids are one of the main pests of cotton and have been an important disaster limiting cotton yield. It is important to use satellite multispectral data to monitor the severity of cotton aphids in a timely and accurate manner on regional scale. Based on the combination of derivative of ratio spectra (DRS) and random forest (RF) algorithm, this study researched the quantitative monitoring model of cotton aphid severity based on Sentinel-2 data. First, the cotton area was extracted by using a supervised classification algorithm and the vegetation index threshold method. Then, the DRS algorithm was used to analyze the spectral characteristics of cotton aphids from three scales, and the Pearson correlation analysis algorithm was used to extract the bands significantly related to aphid infestation. Finally, the RF model was trained by ground sampling points and its accuracy was evaluated. The optimal model results were selected by the cross-validation method, and the accuracy was compared with the four classical classification algorithms. The results showed that (1) the canopy spectral reflectance curves at different grades of cotton aphid infestation were significantly different, with a significant positive correlation between cotton aphid grade and spectral reflectance in the visible band range and a negative correlation in the near-infrared band range; (2) The DRS algorithm could effectively remove the interference of the background endmember of satellite multispectral image pixels and enhance the aphid spectral features. The analysis results from three different scales and the evaluation results demonstrate the effectiveness of the algorithm in processing satellite multispectral data; (3) After the DRS processing, Sentinel-2 multispectral images could effectively classify the severity of cotton aphid infestation by the RF model with an overall classification accuracy of 80% and a kappa coefficient of 0.73. Compared with the results of four classical classification algorithms, the proposed algorithm has the best accuracy, which proves the superiority of RF. Based on satellite multispectral data, the DRS and RF can be combined to monitor the severity of cotton aphids on a regional scale, and the accuracy can meet the actual need.

show abstract

“…RPA has been successfully used to evaluate different conditions of coffee plants, such as nitrogen content [8,9], disease [10], biophysical parameters [11], planting errors [12] and fruit detection and maturation [13,14]. However, assessing frost damage, there is still a considerable gap to be filled.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Potential of Remote Piloted Aircraft in the Detection of Damage by Frost in Coffee Plants

Sayenko

Ferraz

Schwerz

et al. 2022

2022 8th International Engineering, Sciences and Technology Conference (IESTEC)

Self Cite

View full text Add to dashboard Cite

The current methods for monitoring and evaluating the frost damage of coffee plants are not only costly but also impractical in areas of extensive cultivation. Therefore, remote sensing using Remotely Piloted Aircraft (RPA) can be a feasible alternative, providing coffee producers with a fast, continuous, and accessible method to identify and evaluate the frost damage in coffee plants. Therefore, the objective of this study was to evaluate the frost damage in coffee plantations using multispectral images obtained from RPA. For the analysis of frost on the coffee plants, 18 sampling points were selected in the field. Each sampling point consisted of 5 plants, 1 central plant and 2 sets of 2 plants in the east-west direction from the main plant. The evaluations of the frost damage were performed visually through scores. Subsequently, 3 levels were defined according to the percentage of damage to the plant. The images were obtained with a multispectral camera coupled to an RPA with rotating wings. The spectral signatures of each of the 3 levels of frost damage were determined. The spatial distribution of the frost damage on the plantation allowed the identification of the plantation regions most susceptible to the effects of frost. The spectral signatures made it possible to differentiate coffee plants with different levels of frost damage. The Modified Photochemical Reflectance Index (MPRI) showed the most significant variation in the different levels of frost damage, during the Green Normalized Difference Vegetation Index (GNDVI) had the slightest deviation..

show abstract

Detecting coffee leaf rust with UAV-based vegetation indices and decision tree machine learning models

Cited by 33 publications

References 36 publications

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

Cotton aphid infestation monitoring using Sentinel-2 MSI imagery coupled with derivative of ratio spectroscopy and random forest algorithm

Analysis of the Potential of Remote Piloted Aircraft in the Detection of Damage by Frost in Coffee Plants

Contact Info

Product

Resources

About