Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area
Leaf area is an important parameter in plant growth, physiology, and productive potential studies. However, its measurement using traditional methods can be limited. The search for non-destructive approaches based on leaf dimensions is essential, and machine learning offers promising alternatives fo...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11108270/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849763037582458880 |
|---|---|
| author | Joao Everthon da Silva Ribeiro Antonio Gideilson Correia da Silva Pablo Henrique de Almeida Oliveira Josiana Micarla da Silva Oliveira Alessandra Nunes da Silva John Victor Lucas Lima Ivan Euzebio da Silva Ester Dos Santos Coelho Isaque de Oliveira Leite Elania Freire da Silva Toshik Iarley da Silva Lindomar Maria da Silveira Aurelio Paes Barros Junior |
| author_facet | Joao Everthon da Silva Ribeiro Antonio Gideilson Correia da Silva Pablo Henrique de Almeida Oliveira Josiana Micarla da Silva Oliveira Alessandra Nunes da Silva John Victor Lucas Lima Ivan Euzebio da Silva Ester Dos Santos Coelho Isaque de Oliveira Leite Elania Freire da Silva Toshik Iarley da Silva Lindomar Maria da Silveira Aurelio Paes Barros Junior |
| author_sort | Joao Everthon da Silva Ribeiro |
| collection | DOAJ |
| description | Leaf area is an important parameter in plant growth, physiology, and productive potential studies. However, its measurement using traditional methods can be limited. The search for non-destructive approaches based on leaf dimensions is essential, and machine learning offers promising alternatives for accurate estimation. Therefore, the present study aimed to develop and compare linear regression models and machine learning algorithms for the non-destructive prediction of leaf area in four sunflower cultivars (BRS 323, Altis 99, Sany 66, and BRS 442). The best-performing model was also made available through an interactive and freely accessible web interface. Models based on artificial neural networks (ANN), random forest, and linear regression were developed using leaf length and width as input variables, and leaf area as the output. Model performance was evaluated using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and Willmott’s agreement index (d). The ANN model with a 2-4-1 architecture showed the highest accuracy (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9937$ </tex-math></inline-formula>; RMSE =1.1060; MAE =0.7851; MAPE =4.7916; <inline-formula> <tex-math notation="LaTeX">$d =0.9984$ </tex-math></inline-formula>), outperforming the other models. This ANN model was subsequently implemented in the web interface, offering an efficient, non-destructive tool for estimating sunflower leaf area based on linear dimensions. |
| format | Article |
| id | doaj-art-32bd672144d84201bf5226a4552d1e01 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-32bd672144d84201bf5226a4552d1e012025-08-20T03:05:33ZengIEEEIEEE Access2169-35362025-01-011313776113777210.1109/ACCESS.2025.359515311108270Machine Learning for Non-Destructive Prediction of Sunflower Leaf AreaJoao Everthon da Silva Ribeiro0https://orcid.org/0000-0002-1937-0066Antonio Gideilson Correia da Silva1https://orcid.org/0000-0002-6403-5507Pablo Henrique de Almeida Oliveira2Josiana Micarla da Silva Oliveira3https://orcid.org/0009-0003-6148-7289Alessandra Nunes da Silva4John Victor Lucas Lima5Ivan Euzebio da Silva6https://orcid.org/0000-0002-8176-3821Ester Dos Santos Coelho7https://orcid.org/0000-0002-5541-1937Isaque de Oliveira Leite8https://orcid.org/0000-0001-8878-6623Elania Freire da Silva9Toshik Iarley da Silva10https://orcid.org/0000-0003-0704-2046Lindomar Maria da Silveira11Aurelio Paes Barros Junior12https://orcid.org/0000-0002-6983-8245Center of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agricultural and Environmental Sciences, Federal University of Recôncavo of Bahia, Cruz das Almas, Bahia, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilCenter of Agrarian Sciences, Federal Rural University of the Semi-Arid Region, Mossoró, Rio Grande do Norte, BrazilLeaf area is an important parameter in plant growth, physiology, and productive potential studies. However, its measurement using traditional methods can be limited. The search for non-destructive approaches based on leaf dimensions is essential, and machine learning offers promising alternatives for accurate estimation. Therefore, the present study aimed to develop and compare linear regression models and machine learning algorithms for the non-destructive prediction of leaf area in four sunflower cultivars (BRS 323, Altis 99, Sany 66, and BRS 442). The best-performing model was also made available through an interactive and freely accessible web interface. Models based on artificial neural networks (ANN), random forest, and linear regression were developed using leaf length and width as input variables, and leaf area as the output. Model performance was evaluated using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and Willmott’s agreement index (d). The ANN model with a 2-4-1 architecture showed the highest accuracy (<inline-formula> <tex-math notation="LaTeX">$\text{R}^{2} =0.9937$ </tex-math></inline-formula>; RMSE =1.1060; MAE =0.7851; MAPE =4.7916; <inline-formula> <tex-math notation="LaTeX">$d =0.9984$ </tex-math></inline-formula>), outperforming the other models. This ANN model was subsequently implemented in the web interface, offering an efficient, non-destructive tool for estimating sunflower leaf area based on linear dimensions.https://ieeexplore.ieee.org/document/11108270/Helianthus annuus L.artificial neural networksregression modelsalometric modelsprecision agriculture |
| spellingShingle | Joao Everthon da Silva Ribeiro Antonio Gideilson Correia da Silva Pablo Henrique de Almeida Oliveira Josiana Micarla da Silva Oliveira Alessandra Nunes da Silva John Victor Lucas Lima Ivan Euzebio da Silva Ester Dos Santos Coelho Isaque de Oliveira Leite Elania Freire da Silva Toshik Iarley da Silva Lindomar Maria da Silveira Aurelio Paes Barros Junior Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area IEEE Access Helianthus annuus L. artificial neural networks regression models alometric models precision agriculture |
| title | Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area |
| title_full | Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area |
| title_fullStr | Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area |
| title_full_unstemmed | Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area |
| title_short | Machine Learning for Non-Destructive Prediction of Sunflower Leaf Area |
| title_sort | machine learning for non destructive prediction of sunflower leaf area |
| topic | Helianthus annuus L. artificial neural networks regression models alometric models precision agriculture |
| url | https://ieeexplore.ieee.org/document/11108270/ |
| work_keys_str_mv | AT joaoeverthondasilvaribeiro machinelearningfornondestructivepredictionofsunflowerleafarea AT antoniogideilsoncorreiadasilva machinelearningfornondestructivepredictionofsunflowerleafarea AT pablohenriquedealmeidaoliveira machinelearningfornondestructivepredictionofsunflowerleafarea AT josianamicarladasilvaoliveira machinelearningfornondestructivepredictionofsunflowerleafarea AT alessandranunesdasilva machinelearningfornondestructivepredictionofsunflowerleafarea AT johnvictorlucaslima machinelearningfornondestructivepredictionofsunflowerleafarea AT ivaneuzebiodasilva machinelearningfornondestructivepredictionofsunflowerleafarea AT esterdossantoscoelho machinelearningfornondestructivepredictionofsunflowerleafarea AT isaquedeoliveiraleite machinelearningfornondestructivepredictionofsunflowerleafarea AT elaniafreiredasilva machinelearningfornondestructivepredictionofsunflowerleafarea AT toshikiarleydasilva machinelearningfornondestructivepredictionofsunflowerleafarea AT lindomarmariadasilveira machinelearningfornondestructivepredictionofsunflowerleafarea AT aureliopaesbarrosjunior machinelearningfornondestructivepredictionofsunflowerleafarea |