Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach
Crop seed yield modeling and prediction can act as a key approach in the precision agriculture industry, enabling the reliable assessment of the effectiveness of agro-traits. Here, multiple machine learning (ML) techniques are employed to predict sesame (<i>Sesamum indicum</i> L.) seed y...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Agriculture |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0472/12/10/1739 |
_version_ | 1797476209833017344 |
---|---|
author | Mahdieh Parsaeian Mohammad Rahimi Abbas Rohani Shaneka S. Lawson |
author_facet | Mahdieh Parsaeian Mohammad Rahimi Abbas Rohani Shaneka S. Lawson |
author_sort | Mahdieh Parsaeian |
collection | DOAJ |
description | Crop seed yield modeling and prediction can act as a key approach in the precision agriculture industry, enabling the reliable assessment of the effectiveness of agro-traits. Here, multiple machine learning (ML) techniques are employed to predict sesame (<i>Sesamum indicum</i> L.) seed yields (SSY) using agro-morphological features. Various ML models were applied, coupled with the PCA (principal component analysis) method to compare them with the original ML models, in order to evaluate the prediction efficiency. The Gaussian process regression (GPR) and radial basis function neural network (RBF-NN) models exhibited the most accurate SSY predictions, with determination coefficients, or <i>R<sup>2</sup></i> values, of 0.99 and 0.91, respectfully. The root-mean-square error (RMSE) obtained using the ML models ranged between 0 and 0.30 t/ha (metric tons/hectare) for the varied modeling process phases. The estimation of the sesame seed yield with the coupled PCA-ML models improved the performance accuracy. According to the k-fold process, we utilized the datasets with the lowest error rates to ensure the continued accuracy of the GPR and RBF models. The sensitivity analysis revealed that the capsule number per plant (CPP), seed number per capsule (SPC), and 1000-seed weight (TSW) were the most significant seed yield determinants. |
first_indexed | 2024-03-09T20:55:43Z |
format | Article |
id | doaj.art-ab91d9a1fb9841ac8fb28fdf2286d09f |
institution | Directory Open Access Journal |
issn | 2077-0472 |
language | English |
last_indexed | 2024-03-09T20:55:43Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Agriculture |
spelling | doaj.art-ab91d9a1fb9841ac8fb28fdf2286d09f2023-11-23T22:23:27ZengMDPI AGAgriculture2077-04722022-10-011210173910.3390/agriculture12101739Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning ApproachMahdieh Parsaeian0Mohammad Rahimi1Abbas Rohani2Shaneka S. Lawson3Department of Agronomy and Plant Breeding, Shahrood University of Technology, Shahrood 3619995161, IranDepartment of Biosystems Engineering, Ferdowsi University of Mashhad, Mashhad 9177948974, IranDepartment of Biosystems Engineering, Ferdowsi University of Mashhad, Mashhad 9177948974, IranUSDA Forest Service, Northern Research Station, Hardwood Tree Improvement and Regeneration Center (HTIRC), Department of Forestry and Natural Resources, Purdue University, 715 West State Street, West Lafayette, IN 47906, USACrop seed yield modeling and prediction can act as a key approach in the precision agriculture industry, enabling the reliable assessment of the effectiveness of agro-traits. Here, multiple machine learning (ML) techniques are employed to predict sesame (<i>Sesamum indicum</i> L.) seed yields (SSY) using agro-morphological features. Various ML models were applied, coupled with the PCA (principal component analysis) method to compare them with the original ML models, in order to evaluate the prediction efficiency. The Gaussian process regression (GPR) and radial basis function neural network (RBF-NN) models exhibited the most accurate SSY predictions, with determination coefficients, or <i>R<sup>2</sup></i> values, of 0.99 and 0.91, respectfully. The root-mean-square error (RMSE) obtained using the ML models ranged between 0 and 0.30 t/ha (metric tons/hectare) for the varied modeling process phases. The estimation of the sesame seed yield with the coupled PCA-ML models improved the performance accuracy. According to the k-fold process, we utilized the datasets with the lowest error rates to ensure the continued accuracy of the GPR and RBF models. The sensitivity analysis revealed that the capsule number per plant (CPP), seed number per capsule (SPC), and 1000-seed weight (TSW) were the most significant seed yield determinants.https://www.mdpi.com/2077-0472/12/10/1739agro-morphologicaldata-drivenmachine learningseed yieldsensitivity analysis |
spellingShingle | Mahdieh Parsaeian Mohammad Rahimi Abbas Rohani Shaneka S. Lawson Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach Agriculture agro-morphological data-driven machine learning seed yield sensitivity analysis |
title | Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach |
title_full | Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach |
title_fullStr | Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach |
title_full_unstemmed | Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach |
title_short | Towards the Modeling and Prediction of the Yield of Oilseed Crops: A Multi-Machine Learning Approach |
title_sort | towards the modeling and prediction of the yield of oilseed crops a multi machine learning approach |
topic | agro-morphological data-driven machine learning seed yield sensitivity analysis |
url | https://www.mdpi.com/2077-0472/12/10/1739 |
work_keys_str_mv | AT mahdiehparsaeian towardsthemodelingandpredictionoftheyieldofoilseedcropsamultimachinelearningapproach AT mohammadrahimi towardsthemodelingandpredictionoftheyieldofoilseedcropsamultimachinelearningapproach AT abbasrohani towardsthemodelingandpredictionoftheyieldofoilseedcropsamultimachinelearningapproach AT shanekaslawson towardsthemodelingandpredictionoftheyieldofoilseedcropsamultimachinelearningapproach |