| |
|
|
| Registros recuperados : 2 | |
| 1. |  | LOURENÇO, I. T.; FRAGOSO, R. R.; ROCHA, T. L.; GROSSI DE SÁ, M. F. Construção de vetores para transformação genética de algodoeiro visando resistência a insetos-praga. In: WORKSHOP INTERAÇÃO MOLECULAR PLANTA-PRAGAS, 2., 2007, Brasília, DF. II Workshop Interação Molecular Planta-Praga. Brasília, DF: Embrapa Recursos Genéticos e Biotecnologia, 2007. p. 96-101. (Embrapa Recursos Genéticos e Biotecnologia. Documentos, 229).| Biblioteca(s): Embrapa Recursos Genéticos e Biotecnologia. |
|    |
| Registros recuperados : 2 | |
|
|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Solos. |
|
Data corrente: |
17/12/2019 |
|
Data da última atualização: |
27/04/2022 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
A - 2 |
|
Autoria: |
KOTLAR, A. M.; LIER, Q. de J. van; BARROS, A. H. C.; IVERSEN, B. V.; VEREECKEN, H. |
|
Afiliação: |
ALI MEHMANDOOST KOTLAR, CENA/USP; QUIRIJN DE JONG VAN LIER, CENA/USP; ALEXANDRE HUGO CEZAR BARROS, CNPS; BO V. IVERSEN, AARHUS UNIV., DENMARK; HARRY VEREECKEN, INSTITUTE OF BIO- AND GEOSCIENCES (IBG-3), AGROSPHERE, FORSCHUNGSZENTRUM JULICH, GERMANY. |
|
Título: |
Development and uncertainty assessment of pedotransfer functions for predicting water contents at specific pressure heads. |
|
Ano de publicação: |
2019 |
|
Fonte/Imprenta: |
Vadose Zone Journal, v. 18, n. 1, 190063, 2019. |
|
DOI: |
10.2136/vzj2019.06.0063 |
|
Idioma: |
Inglês |
|
Conteúdo: |
There has been much effort to improve the performance of pedotransfer functions (PTFs) using intelligent algorithms, but the issue of covariate shift, i.e., different probability distributions in training and testing datasets, and its impact on prediction uncertainty of PTFs has been rarely addressed. The common practice in PTF generation is to randomly separate the dataset into training and testing subsets, and the outcomes of this random selection may be different if the process is subject to covariate shift. We evaluated the impact of covariate shift generated by data shuffling and detected by Kolmogorov-Smirnov test for the prediction of water contents using soil databases from Denmark and Brazil. The soil water contents at different pressure heads were predicted by developing linear and stepwise regression besides machine learning based PTFs including Gaussian process regression and ensemble method. Regression based PTFs for the Brazilian dataset resulted in better predictions compared with machine learning methods, which in their turn estimated high water contents in Danish soils more accurately. One hundred PTFs were developed for water content at specific pressure heads by data shuffling. From these, 100 sets of fitted van Genuchten parameters were obtained representing the generated uncertainty. Data shuffling led to covariate shift, resulting in uncertainty in water content prediction by the PTFs. Inherent variability of data may lead to increased prediction uncertainty. For correlated data, simple regression models performed as good as sophisticated machine learning methods. Using PTF-predicted water contents for van Genuchten retention parameter fitting may lead to a high uncertainty. MenosThere has been much effort to improve the performance of pedotransfer functions (PTFs) using intelligent algorithms, but the issue of covariate shift, i.e., different probability distributions in training and testing datasets, and its impact on prediction uncertainty of PTFs has been rarely addressed. The common practice in PTF generation is to randomly separate the dataset into training and testing subsets, and the outcomes of this random selection may be different if the process is subject to covariate shift. We evaluated the impact of covariate shift generated by data shuffling and detected by Kolmogorov-Smirnov test for the prediction of water contents using soil databases from Denmark and Brazil. The soil water contents at different pressure heads were predicted by developing linear and stepwise regression besides machine learning based PTFs including Gaussian process regression and ensemble method. Regression based PTFs for the Brazilian dataset resulted in better predictions compared with machine learning methods, which in their turn estimated high water contents in Danish soils more accurately. One hundred PTFs were developed for water content at specific pressure heads by data shuffling. From these, 100 sets of fitted van Genuchten parameters were obtained representing the generated uncertainty. Data shuffling led to covariate shift, resulting in uncertainty in water content prediction by the PTFs. Inherent variability of data may lead to increased prediction uncert... Mostrar Tudo |
|
Palavras-Chave: |
Funções de pedotransferência. |
|
Thesagro: |
Condutividade Hidráulica; Retenção de Água no Solo. |
|
Thesaurus NAL: |
Hydraulic conductivity; Pedotransfer functions; Soil water retention. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/207273/1/Development-and-uncertainty-assessment-of-pedotransfer-functions-2019.pdf
|
|
Marc: |
LEADER 02564naa a2200253 a 4500
001 2117100
005 2022-04-27
008 2019 bl uuuu u00u1 u #d
024 7 $a10.2136/vzj2019.06.0063$2DOI
100 1 $aKOTLAR, A. M.
245 $aDevelopment and uncertainty assessment of pedotransfer functions for predicting water contents at specific pressure heads.$h[electronic resource]
260 $c2019
520 $aThere has been much effort to improve the performance of pedotransfer functions (PTFs) using intelligent algorithms, but the issue of covariate shift, i.e., different probability distributions in training and testing datasets, and its impact on prediction uncertainty of PTFs has been rarely addressed. The common practice in PTF generation is to randomly separate the dataset into training and testing subsets, and the outcomes of this random selection may be different if the process is subject to covariate shift. We evaluated the impact of covariate shift generated by data shuffling and detected by Kolmogorov-Smirnov test for the prediction of water contents using soil databases from Denmark and Brazil. The soil water contents at different pressure heads were predicted by developing linear and stepwise regression besides machine learning based PTFs including Gaussian process regression and ensemble method. Regression based PTFs for the Brazilian dataset resulted in better predictions compared with machine learning methods, which in their turn estimated high water contents in Danish soils more accurately. One hundred PTFs were developed for water content at specific pressure heads by data shuffling. From these, 100 sets of fitted van Genuchten parameters were obtained representing the generated uncertainty. Data shuffling led to covariate shift, resulting in uncertainty in water content prediction by the PTFs. Inherent variability of data may lead to increased prediction uncertainty. For correlated data, simple regression models performed as good as sophisticated machine learning methods. Using PTF-predicted water contents for van Genuchten retention parameter fitting may lead to a high uncertainty.
650 $aHydraulic conductivity
650 $aPedotransfer functions
650 $aSoil water retention
650 $aCondutividade Hidráulica
650 $aRetenção de Água no Solo
653 $aFunções de pedotransferência
700 1 $aLIER, Q. de J. van
700 1 $aBARROS, A. H. C.
700 1 $aIVERSEN, B. V.
700 1 $aVEREECKEN, H.
773 $tVadose Zone Journal$gv. 18, n. 1, 190063, 2019.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Solos (CNPS) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
