Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods
Brazil is home to 30% of the world’s <i>Eucalyptus</i> trees. The seedlings are fertilized at plantation to support biomass production until canopy closure. Thereafter, fertilization is guided by state standards that may not apply at the local scale where myriads of growth factors intera...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/9/8/1049 |
| _version_ | 1797557335044915200 |
|---|---|
| author | Betania Vahl de Paula Wagner Squizani Arruda Léon Etienne Parent Elias Frank de Araujo Gustavo Brunetto |
| author_facet | Betania Vahl de Paula Wagner Squizani Arruda Léon Etienne Parent Elias Frank de Araujo Gustavo Brunetto |
| author_sort | Betania Vahl de Paula |
| collection | DOAJ |
| description | Brazil is home to 30% of the world’s <i>Eucalyptus</i> trees. The seedlings are fertilized at plantation to support biomass production until canopy closure. Thereafter, fertilization is guided by state standards that may not apply at the local scale where myriads of growth factors interact. Our objective was to customize the nutrient diagnosis of young <i>Eucalyptus</i> trees down to factor-specific levels. We collected 1861 observations across eight clones, 48 soil types, and 148 locations in southern Brazil. Cutoff diameter between low- and high-yielding specimens at breast height was set at 4.3 cm. The random forest classification model returned a relatively uninformative area under the curve (AUC) of 0.63 using tissue compositions only, and an informative AUC of 0.78 after adding local features. Compared to nutrient levels from quartile compatibility intervals of nutritionally balanced specimens at high-yield level, state guidelines appeared to be too high for Mg, B, Mn, and Fe and too low for Cu and Zn. Moreover, diagnosis using concentration ranges collapsed in the multivariate Euclidean hyper-space by denying nutrient interactions. Factor-specific diagnosis detected nutrient imbalance by computing the Euclidean distance between centered log-ratio transformed compositions of defective and successful neighbors at a local scale. Downscaling regional nutrient standards may thus fail to account for factor interactions at a local scale. Documenting factors at a local scale requires large datasets through close collaboration between stakeholders. |
| first_indexed | 2024-03-10T17:15:42Z |
| format | Article |
| id | doaj.art-d46bea5d6be647bca6d1e637731b364f |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-10T17:15:42Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-d46bea5d6be647bca6d1e637731b364f2023-11-20T10:32:14ZengMDPI AGPlants2223-77472020-08-0198104910.3390/plants9081049Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional MethodsBetania Vahl de Paula0Wagner Squizani Arruda1Léon Etienne Parent2Elias Frank de Araujo3Gustavo Brunetto4Departemento dos Solos, Universidade Federal de Santa Maria, Av. Roraima, 1000-Camobi, Santa Maria-RS 97105-900, BrazilDepartemento dos Solos, Universidade Federal de Santa Maria, Av. Roraima, 1000-Camobi, Santa Maria-RS 97105-900, BrazilDepartemento dos Solos, Universidade Federal de Santa Maria, Av. Roraima, 1000-Camobi, Santa Maria-RS 97105-900, BrazilSoil and Management Researcher of CMPC-Cellulose Rio Grandense, Rua São Geraldo 1680-Guaíba–RS, BrazilDepartemento dos Solos, Universidade Federal de Santa Maria, Av. Roraima, 1000-Camobi, Santa Maria-RS 97105-900, BrazilBrazil is home to 30% of the world’s <i>Eucalyptus</i> trees. The seedlings are fertilized at plantation to support biomass production until canopy closure. Thereafter, fertilization is guided by state standards that may not apply at the local scale where myriads of growth factors interact. Our objective was to customize the nutrient diagnosis of young <i>Eucalyptus</i> trees down to factor-specific levels. We collected 1861 observations across eight clones, 48 soil types, and 148 locations in southern Brazil. Cutoff diameter between low- and high-yielding specimens at breast height was set at 4.3 cm. The random forest classification model returned a relatively uninformative area under the curve (AUC) of 0.63 using tissue compositions only, and an informative AUC of 0.78 after adding local features. Compared to nutrient levels from quartile compatibility intervals of nutritionally balanced specimens at high-yield level, state guidelines appeared to be too high for Mg, B, Mn, and Fe and too low for Cu and Zn. Moreover, diagnosis using concentration ranges collapsed in the multivariate Euclidean hyper-space by denying nutrient interactions. Factor-specific diagnosis detected nutrient imbalance by computing the Euclidean distance between centered log-ratio transformed compositions of defective and successful neighbors at a local scale. Downscaling regional nutrient standards may thus fail to account for factor interactions at a local scale. Documenting factors at a local scale requires large datasets through close collaboration between stakeholders.https://www.mdpi.com/2223-7747/9/8/1049compatibility intervalsEuclidean distanceHumboldtian locicentered log ratiosmachine learning |
| spellingShingle | Betania Vahl de Paula Wagner Squizani Arruda Léon Etienne Parent Elias Frank de Araujo Gustavo Brunetto Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods Plants compatibility intervals Euclidean distance Humboldtian loci centered log ratios machine learning |
| title | Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods |
| title_full | Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods |
| title_fullStr | Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods |
| title_full_unstemmed | Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods |
| title_short | Nutrient Diagnosis of <i>Eucalyptus</i> at the Factor-Specific Level Using Machine Learning and Compositional Methods |
| title_sort | nutrient diagnosis of i eucalyptus i at the factor specific level using machine learning and compositional methods |
| topic | compatibility intervals Euclidean distance Humboldtian loci centered log ratios machine learning |
| url | https://www.mdpi.com/2223-7747/9/8/1049 |
| work_keys_str_mv | AT betaniavahldepaula nutrientdiagnosisofieucalyptusiatthefactorspecificlevelusingmachinelearningandcompositionalmethods AT wagnersquizaniarruda nutrientdiagnosisofieucalyptusiatthefactorspecificlevelusingmachinelearningandcompositionalmethods AT leonetienneparent nutrientdiagnosisofieucalyptusiatthefactorspecificlevelusingmachinelearningandcompositionalmethods AT eliasfrankdearaujo nutrientdiagnosisofieucalyptusiatthefactorspecificlevelusingmachinelearningandcompositionalmethods AT gustavobrunetto nutrientdiagnosisofieucalyptusiatthefactorspecificlevelusingmachinelearningandcompositionalmethods |