| |
|
|
 | Acceso al texto completo restringido a Biblioteca INIA Las Brujas. Por información adicional contacte bibliolb@inia.org.uy. |
|
Registro completo
|
|
Biblioteca (s) : |
INIA Las Brujas. |
|
Fecha : |
23/02/2024 |
|
Actualizado : |
23/02/2024 |
|
Tipo de producción científica : |
Artículos en Revistas Indexadas Internacionales |
|
Autor : |
PARUELO, J.; TEXEIRA, M.; TOMASEL, F. |
|
Afiliación : |
JOSÉ PARUELO, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; IFEVA, Universidad de Buenos Aires, CONICET, Facultad de Agronomía, Buenos Aires, Argentina; IECA, Facultad de Ciencias, Universidad de la República, Montevideo, Uruguay; MARCOS TEXEIRA, IFEVA, Universidad de Buenos Aires, CONICET, Facultad de Agronomía, Buenos Aires, Argentina; FERNANDO TOMASEL, Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, United States. |
|
Título : |
Hybrid modeling for grassland productivity prediction: A parametric and machine learning technique for grazing management with applicability to digital twin decision systems. |
|
Fecha de publicación : |
2024 |
|
Fuente / Imprenta : |
Agricultural Systems. 2024. Volume 214, article 103847. https://doi.org/10.1016/j.agsy.2023.103847 |
|
ISSN : |
0308-521X |
|
DOI : |
10.1016/j.agsy.2023.103847 |
|
Idioma : |
Inglés |
|
Notas : |
Article history: Received 1 August 2023; Received in revised form 5 December 2023; Accepted 18 December 2023; Available online 28 December 2023. -- Correspondence: Paruelo, J.M.; Instituto Nacional de Investigación Agropecuaria, INIA, La Estanzuela, Ruta 50 km 11, Colonia, Uruguay; email:jparuelo@inia.org.uy -- Funding: This work was supported by grants from ANII (Uruguay. FSDA_1_2018_1_154773 and IA_2021_1_04 and IA_2021_1_1010784), CSIC-Universidad de la República - Uruguay (Programa I + D Grupos 2018-433), Universidad de Buenos Aires (Argentina) and CONICET (2021-2024. PIP-2021. 11220200100956CO01). -- Supplementary data: https://doi.org/10.1016/j.agsy.2023.103847 -- |
|
Contenido : |
ABSTRACT.- CONTEXT: Monitoring Aboveground Net Primary Production (ANPP) is critical to assess not only the current ecosystem status but also its long-term dynamics. In rangelands, the seasonal dynamics of ANPP determines forage availability, stock density, and livestock productivity. OBJECTIVE: To develop a hybrid model to be used as a prediction engine for ANPP in the native grasslands of Uruguay. The model combines a parametric component based on the seasonal dynamics of ANPP, and an artificial neural network (ANN) component used to model the remaining non-linearities, which are mainly related to precipitation and temperature variability. The output of hybrid model is proposed as the "virtual entity" of a digital twin support decision system where the "physical entity" is characterized by a collection of bi-weekly (fortnight) ANPP estimates. METHODS: Fortnight ANPP data were calculated from MODIS EVI for the 2001-2020 period. A sigmoidal functional response, having three parameters with an explicit biological interpretation, was fitted to the accumulated ANPP as a function of time. Forecasts were generated by extrapolating the sigmoidal functional response fit up to four fortnights ahead. From these fits, we obtained the fortnight ANPP values by differentiating the accumulated fortnight ANPP. Predictions (up to four fortnights) were generated for each fortnight and year. The residuals from these fits were modeled using a multilayer perceptron trained by backpropagation using climate variables as independent variables. RESULTS AND CONCLUSIONS: The sigmoidal functional response model fit was highly significant for the accumulated ANPP profile. This model also had a high explanatory power for the accumulated ANPP curve. The median of the percentage absolute residuals for forecasts made 1 to 4 fortnights ahead ranged from 17% to 18%. The ANN significantly reduced this unexplained variability in ANPP, showing a median reduction in residuals of 35%, 31%, 30%, and 30% for 1 to 4 fortnights ahead forecasts, respectively, when compared to predictions from the sigmoidal functional response fit. SIGNIFICANCE: By integrating both parametric and machine learning techniques, the hybrid model developed can make accurate predictions in a way that is both efficient and dependable. The hybrid model not only represents an advantage in terms of predictive power, but it also allows for a deeper understanding of the basic ecological processes involved in forage production. © 2023 MenosABSTRACT.- CONTEXT: Monitoring Aboveground Net Primary Production (ANPP) is critical to assess not only the current ecosystem status but also its long-term dynamics. In rangelands, the seasonal dynamics of ANPP determines forage availability, stock density, and livestock productivity. OBJECTIVE: To develop a hybrid model to be used as a prediction engine for ANPP in the native grasslands of Uruguay. The model combines a parametric component based on the seasonal dynamics of ANPP, and an artificial neural network (ANN) component used to model the remaining non-linearities, which are mainly related to precipitation and temperature variability. The output of hybrid model is proposed as the "virtual entity" of a digital twin support decision system where the "physical entity" is characterized by a collection of bi-weekly (fortnight) ANPP estimates. METHODS: Fortnight ANPP data were calculated from MODIS EVI for the 2001-2020 period. A sigmoidal functional response, having three parameters with an explicit biological interpretation, was fitted to the accumulated ANPP as a function of time. Forecasts were generated by extrapolating the sigmoidal functional response fit up to four fortnights ahead. From these fits, we obtained the fortnight ANPP values by differentiating the accumulated fortnight ANPP. Predictions (up to four fortnights) were generated for each fortnight and year. The residuals from these fits were modeled using a multilayer perceptron trained by backpropagation us... Presentar Todo |
|
Palabras claves : |
Agroecological transitions; ANPP; Artificial neural networks; Grasslands; Remote sensing; Uruguay. |
|
Asunto categoría : |
-- |
|
Marc : |
LEADER 04040naa a2200253 a 4500
001 1064472
005 2024-02-23
008 2024 bl uuuu u00u1 u #d
022 $a0308-521X
024 7 $a10.1016/j.agsy.2023.103847$2DOI
100 1 $aPARUELO, J.
245 $aHybrid modeling for grassland productivity prediction$bA parametric and machine learning technique for grazing management with applicability to digital twin decision systems.$h[electronic resource]
260 $c2024
500 $aArticle history: Received 1 August 2023; Received in revised form 5 December 2023; Accepted 18 December 2023; Available online 28 December 2023. -- Correspondence: Paruelo, J.M.; Instituto Nacional de Investigación Agropecuaria, INIA, La Estanzuela, Ruta 50 km 11, Colonia, Uruguay; email:jparuelo@inia.org.uy -- Funding: This work was supported by grants from ANII (Uruguay. FSDA_1_2018_1_154773 and IA_2021_1_04 and IA_2021_1_1010784), CSIC-Universidad de la República - Uruguay (Programa I + D Grupos 2018-433), Universidad de Buenos Aires (Argentina) and CONICET (2021-2024. PIP-2021. 11220200100956CO01). -- Supplementary data: https://doi.org/10.1016/j.agsy.2023.103847 --
520 $aABSTRACT.- CONTEXT: Monitoring Aboveground Net Primary Production (ANPP) is critical to assess not only the current ecosystem status but also its long-term dynamics. In rangelands, the seasonal dynamics of ANPP determines forage availability, stock density, and livestock productivity. OBJECTIVE: To develop a hybrid model to be used as a prediction engine for ANPP in the native grasslands of Uruguay. The model combines a parametric component based on the seasonal dynamics of ANPP, and an artificial neural network (ANN) component used to model the remaining non-linearities, which are mainly related to precipitation and temperature variability. The output of hybrid model is proposed as the "virtual entity" of a digital twin support decision system where the "physical entity" is characterized by a collection of bi-weekly (fortnight) ANPP estimates. METHODS: Fortnight ANPP data were calculated from MODIS EVI for the 2001-2020 period. A sigmoidal functional response, having three parameters with an explicit biological interpretation, was fitted to the accumulated ANPP as a function of time. Forecasts were generated by extrapolating the sigmoidal functional response fit up to four fortnights ahead. From these fits, we obtained the fortnight ANPP values by differentiating the accumulated fortnight ANPP. Predictions (up to four fortnights) were generated for each fortnight and year. The residuals from these fits were modeled using a multilayer perceptron trained by backpropagation using climate variables as independent variables. RESULTS AND CONCLUSIONS: The sigmoidal functional response model fit was highly significant for the accumulated ANPP profile. This model also had a high explanatory power for the accumulated ANPP curve. The median of the percentage absolute residuals for forecasts made 1 to 4 fortnights ahead ranged from 17% to 18%. The ANN significantly reduced this unexplained variability in ANPP, showing a median reduction in residuals of 35%, 31%, 30%, and 30% for 1 to 4 fortnights ahead forecasts, respectively, when compared to predictions from the sigmoidal functional response fit. SIGNIFICANCE: By integrating both parametric and machine learning techniques, the hybrid model developed can make accurate predictions in a way that is both efficient and dependable. The hybrid model not only represents an advantage in terms of predictive power, but it also allows for a deeper understanding of the basic ecological processes involved in forage production. © 2023
653 $aAgroecological transitions
653 $aANPP
653 $aArtificial neural networks
653 $aGrasslands
653 $aRemote sensing
653 $aUruguay
700 1 $aTEXEIRA, M.
700 1 $aTOMASEL, F.
773 $tAgricultural Systems. 2024. Volume 214, article 103847. https://doi.org/10.1016/j.agsy.2023.103847
Descargar
Esconder MarcPresentar Marc Completo |
|
Registro original : |
INIA Las Brujas (LB) |
|
|
Biblioteca
|
Identificación
|
Origen
|
Tipo / Formato
|
Clasificación
|
Cutter
|
Registro
|
Volumen
|
Estado
|
Volver
|
|
|
| Registros recuperados : 1 | |
| Registros recuperados : 1 | |
|
| Expresión de búsqueda válido. Check! |
|
|
