Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods
Abstract While onion cultivars, irrigation and soil and crop management have been given much attention in Brazil to boost onion yields, nutrient management at field scale is still challenging due to large dosage uncertainty. Our objective was to develop an accurate feature-based fertilization model...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-55647-9 |
| _version_ | 1797259357733257216 |
|---|---|
| author | Leandro Hahn Claudinei Kurtz Betania Vahl de Paula Anderson Luiz Feltrim Fábio Satoshi Higashikawa Camila Moreira Danilo Eduardo Rozane Gustavo Brunetto Léon-Étienne Parent |
| author_facet | Leandro Hahn Claudinei Kurtz Betania Vahl de Paula Anderson Luiz Feltrim Fábio Satoshi Higashikawa Camila Moreira Danilo Eduardo Rozane Gustavo Brunetto Léon-Étienne Parent |
| author_sort | Leandro Hahn |
| collection | DOAJ |
| description | Abstract While onion cultivars, irrigation and soil and crop management have been given much attention in Brazil to boost onion yields, nutrient management at field scale is still challenging due to large dosage uncertainty. Our objective was to develop an accurate feature-based fertilization model for onion crops. We assembled climatic, edaphic, and managerial features as well as tissue tests into a database of 1182 observations from multi-environment fertilizer trials conducted during 13 years in southern Brazil. The complexity of onion cropping systems was captured by machine learning (ML) methods. The RReliefF ranking algorithm showed that the split-N dosage and soil tests for micronutrients and S were the most relevant features to predict bulb yield. The decision-tree random forest and extreme gradient boosting models were accurate to predict bulb yield from the relevant predictors (R2 > 90%). As shown by the gain ratio, foliar nutrient standards for nutritionally balanced and high-yielding specimens producing > 50 Mg bulb ha−1 set apart by the ML classification models differed among cultivars. Cultivar × environment interactions support documenting local nutrient diagnosis. The split-N dosage was the most relevant controllable feature to run future universality tests set to assess models’ ability to generalize to growers’ fields. |
| first_indexed | 2024-04-24T23:08:09Z |
| format | Article |
| id | doaj.art-6c3e1ecba0ca409aa8a99c96217c4b1d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T23:08:09Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6c3e1ecba0ca409aa8a99c96217c4b1d2024-03-17T12:21:52ZengNature PortfolioScientific Reports2045-23222024-03-0114111210.1038/s41598-024-55647-9Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methodsLeandro Hahn0Claudinei Kurtz1Betania Vahl de Paula2Anderson Luiz Feltrim3Fábio Satoshi Higashikawa4Camila Moreira5Danilo Eduardo Rozane6Gustavo Brunetto7Léon-Étienne Parent8Caçador Experimental Station, Research and Rural Extension of Santa Catarina (Epagri), EpagriItuporanga Experimental Station, Research and Rural Extension of Santa Catarina (Epagri), EpagriDepartment of Soil, Federal University of Santa MariaCaçador Experimental Station, Research and Rural Extension of Santa Catarina (Epagri), EpagriItuporanga Experimental Station, Research and Rural Extension of Santa Catarina (Epagri), EpagriUniversity Alto Vale do Rio do Peixe, UniarpState University Paulista “Julio Mesquita Filho”Department of Soil, Federal University of Santa MariaDepartment of Soil, Federal University of Santa MariaAbstract While onion cultivars, irrigation and soil and crop management have been given much attention in Brazil to boost onion yields, nutrient management at field scale is still challenging due to large dosage uncertainty. Our objective was to develop an accurate feature-based fertilization model for onion crops. We assembled climatic, edaphic, and managerial features as well as tissue tests into a database of 1182 observations from multi-environment fertilizer trials conducted during 13 years in southern Brazil. The complexity of onion cropping systems was captured by machine learning (ML) methods. The RReliefF ranking algorithm showed that the split-N dosage and soil tests for micronutrients and S were the most relevant features to predict bulb yield. The decision-tree random forest and extreme gradient boosting models were accurate to predict bulb yield from the relevant predictors (R2 > 90%). As shown by the gain ratio, foliar nutrient standards for nutritionally balanced and high-yielding specimens producing > 50 Mg bulb ha−1 set apart by the ML classification models differed among cultivars. Cultivar × environment interactions support documenting local nutrient diagnosis. The split-N dosage was the most relevant controllable feature to run future universality tests set to assess models’ ability to generalize to growers’ fields.https://doi.org/10.1038/s41598-024-55647-9 |
| spellingShingle | Leandro Hahn Claudinei Kurtz Betania Vahl de Paula Anderson Luiz Feltrim Fábio Satoshi Higashikawa Camila Moreira Danilo Eduardo Rozane Gustavo Brunetto Léon-Étienne Parent Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods Scientific Reports |
| title | Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods |
| title_full | Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods |
| title_fullStr | Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods |
| title_full_unstemmed | Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods |
| title_short | Feature-specific nutrient management of onion (Allium cepa) using machine learning and compositional methods |
| title_sort | feature specific nutrient management of onion allium cepa using machine learning and compositional methods |
| url | https://doi.org/10.1038/s41598-024-55647-9 |
| work_keys_str_mv | AT leandrohahn featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT claudineikurtz featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT betaniavahldepaula featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT andersonluizfeltrim featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT fabiosatoshihigashikawa featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT camilamoreira featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT daniloeduardorozane featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT gustavobrunetto featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods AT leonetienneparent featurespecificnutrientmanagementofonionalliumcepausingmachinelearningandcompositionalmethods |