Eucalyptus growth recognition using machine learning methods and spectral variables

Oliveira, Bruno Rodrigues de; Silva, Arlindo Ananias Pereira da; Teodoro, Larissa Pereira Ribeiro; Azevedo, Gileno Brito de; Azevedo, Glauce Táıs de Oliveira Sousa; Baio, Fábio Henrique Rojo; Sobrinho, Renato Lustosa; Silva, Carlos Antônio da; Teodoro, Paulo Eduardo

doi:10.1016/j.foreco.2021.119496

Cited by 13 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify which variables are most important, we first need to select the best hyperparameters of this algorithm for the available experimental data. Other works have recommended the use of machine learning in the solution of problems associated with the selection of genotypes with superior performance under stress conditions (Gava et al, 2022; Naik et al, 2017; Oliveira et al, 2021, 2022; Sharma et al, 2020, 2021; Teodoro et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of soybean genotypes during the seedling stage in controlled drought and salt stress environments using the decision tree algorithm

Oliveira¹,

Zuffo

Steiner

et al. 2023

J Agronomy Crop Science

Self Cite

View full text Add to dashboard Cite

Soybean is one of the most important oilseed crops grown worldwide. However, abiotic stresses such as drought and salinity can seriously affect soybean production, especially in tropical climate conditions. To evaluate the adaptability and stability of soybean genotypes under abiotic stress conditions, some studies have proposed a multitrait tool to select stress‐tolerant soybean genotypes through a multitrait stability index (MTSI). This index can be used under stressful environmental conditions to quantify the genotypic stability of soybean cultivars. Our study is based on an unprecedented approach, where we propose to use a machine learning algorithm called ‘Random Forest’ to obtain a classification model based on a decision tree algorithm. The decision tree data structure can be used even by nonexperts facilitating the decision‐making process for genotype selection. The proposed model evaluated the importance of six shoot and root morphological variables and predicted from which controlled growth environment the soybean plants originated. Using this model more than 73% of the genotypic patterns were learned correctly. Besides that, this model can also predict and rank the most critical variables in the development of soybean genotypes, having obtained results very similar to recent field research. The research is important for plant breeders who seek an early selection of soybean seedlings for drought and saline stresses.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In this work, we present a new method to study the importance of morphological variables of genotypes subject to different salt and water stress environments. This method is based on a machine Naik et al, 2017;Oliveira et al, 2021Oliveira et al, , 2022Sharma et al, 2020Sharma et al, , 2021Teodoro et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Classification of soybean genotypes during the seedling stage in controlled drought and salt stress environments using the decision tree algorithm

Oliveira¹,

Zuffo

Steiner

et al. 2023

J Agronomy Crop Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this, it was necessary to model the obtained data in a 7-dimensional vector. We chose the Manhattan distance to calculate the similarity between the samples because it presents better results in high-dimensional vector spaces [ 18 , 20 , 21 , 22 , 25 ]. Since the genotypes show different responses in saline and drought-stressed environments, we also included the TOPSIS method to select the one with the greatest similarity in both environments.…”

Section: Discussionmentioning

confidence: 99%

“…In other words, the closer two objects are, the more similar they are. Classic machine learning algorithms, such as a k-nearest neighbor, k-means, support vector machine, and others, use distance metrics to measure similarity [ 20 , 21 ]. There are several ways to calculate the distances between vectors.…”

Section: Introductionmentioning

confidence: 99%

Selection of Soybean Genotypes under Drought and Saline Stress Conditions Using Manhattan Distance and TOPSIS

Oliveira¹,

Zuffo

Aguilera³

et al. 2022

Plants

Self Cite

View full text Add to dashboard Cite

The search for soybean genotypes more adapted to abiotic stress conditions is essential to boost the development and yield of the crop in Brazil and worldwide. In this research, we propose a new approach using the concept of distance (or similarity) in a vector space that can quantify changes in the morphological traits of soybean seedlings exposed to stressful environments. Thus, this study was conducted to select soybean genotypes exposed to stressful environments (saline or drought) using similarity based on Manhattan distance and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. TOPSIS is a multi-criteria decision method for selecting the best alternative using the concept of distance. The use of TOPSIS is essential because the genotypes are not absolutely similar in both treatments. That is, just the distance measure is not enough to select the best genotype simultaneously in the two stress environments. Drought and saline stresses were induced by exposing seeds of 70 soybean genotypes to −0.20 MPa iso-osmotic solutions with polyethylene glycol–PEG 6000 (119.6 g L−1) or NaCl (2.36 g L−1) for 14 days at 25 °C. The germination rate, seedling length, and seedling dry matter were measured. We showed here how the genotypic stability of soybean plants could be quantified by TOPSIS when comparing drought and salinity conditions to a non-stressful environment (control) and how this method can be employed under different conditions. Based on the TOPSIS method, we can select the best soybean genotypes for environments with multiple abiotic stresses. Among the 70 tested soybean genotypes, RK 6813 RR, ST 777 IPRO, RK 7214 IPRO, TMG 2165 IPRO, 5G 830 RR, 98R35 IPRO, 98R31 IPRO, RK 8317 IPRO, CG 7464 RR, and LG 60177 IPRO are the 10 most stable genotypes under drought and saline stress conditions. Owing to high stability and gains with selection verified for these genotypes under salinity and drought conditions, they can be used as genitors in breeding programs to obtain offspring with higher resistance to antibiotic stresses.

show abstract

“…The RF integrates all the classified voting results and designates the category with the most votes as the final output. Compared to other non-parametric classifiers, RF has a faster calculation speed and lower cost [64]. RF can deal with > JSTARS-2021-01904.R2 < high-dimensional data, has strong anti-interference ability and strong anti-over-fitting ability [65].…”

Section: E Rf Classifiermentioning

confidence: 99%

Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images

Shi

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Maize crop lodging is a recurrent phenomenon which results in significant reduction of grain yield and quality in addition to the impediment of mechanical harvesting. The large-scale monitoring of maize crop lodging is important for production policy adjustment and agricultural insurance compensation. In this study, we derived a variety of features from multi-temporal GaoFen-1(GF-1) images before and after maize crop lodging. We screened the most sensitive features of the spectrum, texture, and vegetation index to monitor maize crop lodging. The recursive feature elimination method based on cross-validation (RFECV) and Mutual information (MI) were compared to obtain the optimal feature combination for monitoring the lodging extents of maize crop. The random forest (RF) classifier was used to classify the lodging extents. The results showed that the most sensitive features of the spectrum, texture, and vegetation indices of lodging extents included the difference of reflectance in blue, green and red bands, the difference of normalized difference vegetation index, the difference of ratio vegetation index, the difference of enhanced vegetation index difference, the difference of mean value of blue band, the difference of mean value of green band, and the difference of mean value of red band. The total accuracy of lodging extents classification was 87.50%, and the Kappa coefficient was 0.83 for testing samples. Based on multiple features derived from GF-1 images before and after lodging, the lodging extents of maize crop can be monitored on a large scale.

show abstract

Eucalyptus growth recognition using machine learning methods and spectral variables

Cited by 13 publications

References 42 publications

Classification of soybean genotypes during the seedling stage in controlled drought and salt stress environments using the decision tree algorithm

Classification of soybean genotypes during the seedling stage in controlled drought and salt stress environments using the decision tree algorithm

Selection of Soybean Genotypes under Drought and Saline Stress Conditions Using Manhattan Distance and TOPSIS

Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images

Contact Info

Product

Resources

About