|
|
| 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
|
|
Registro completo
|
Biblioteca (s) : |
INIA Las Brujas. |
Fecha actual : |
19/04/2017 |
Actualizado : |
09/01/2018 |
Tipo de producción científica : |
Informes Agroclimáticos |
Autor : |
GIMÉNEZ, A.; CASTAÑO, J.; CAL, A.; TISCORNIA, G.; SCHIAVI, C.; WADSWORTH, C. |
Afiliación : |
AGUSTIN EDUARDO GIMÉNEZ FUREST, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; JOSE PEDRO CASTAÑO SANCHEZ, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; ADRIAN TABARE CAL ALVAREZ, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; GUADALUPE TISCORNIA TOSAR, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; CARLOS IGNACIO SCHIAVI RAMPELBERG, INIA (Instituto Nacional de Investigación Agropecuaria), Uruguay; CRISTINE WADSWORTH, INIA (Instituto Nacional de Investigación Agropecuaria). |
Título : |
Informe agroclimático 2017 - Situación a Marzo. |
Fecha de publicación : |
2017 |
Fuente / Imprenta : |
Montevideo (Uruguay): INIA, 2017. |
Páginas : |
4 p. |
Idioma : |
Español |
Palabras claves : |
AGROCLIMA; AGROCLIMATOLOGÍA; BOLETIN AGROCLIMÁTICO; CARACTERIZACIÓN AGROCLIMÁTICA; DIRECCION VIENTO; ESTACIONES AGROMETEOROLOGICAS; ESTACIONES AUTOMATICAS; ESTACIONES INIA; ESTADO DEL TIEMPO; ESTRÉS HÍDRICO; GRAFICAS AGROCLIMATICOS; GRAS; HELIOFANOGRAFO; INFORMACION SATELITAL; INFORME AGROCLIMÁTICO 2017; INUNDACIONES; LLUVIAS DIARIAS; MAXIMA; MEDIA; MINIMA; PANEL SOLAR; PERSPECTIVAS CLIMATICAS; PLUVIOMETRO; PRECIPITACION NACIONAL; PREVENCION HELADAS; PRONOSTICO; SENSOR; SIMETRICO; TANQUE A; TERMOCUPLAS; TERMOHIDROGRAFO; VARIABLES AGROCLIMATICAS; VELETA. |
Thesagro : |
AGROCLIMATOLOGIA; CAMBIO CLIMATICO; CLIMA; CLIMATOLOGIA; ESTACIONES METEOROLOGICAS; ESTRES HIDRICO; EVAPORACION; EVAPOTRANSPIRACION; HUMEDAD; HUMEDAD RELATIVA; LLUVIA; METEOROLOGIA; PERSPECTIVAS; PLUVIOMETROS; PRONOSTICO DEL TIEMPO; SENSORES; SISTEMAS; SISTEMAS DE INFORMACION; SUELO; TEMPERATURA; TERMOMETROS. |
Asunto categoría : |
-- |
URL : |
http://www.ainfo.inia.uy/digital/bitstream/item/6712/1/Informe-agroclimatico-INIA-GRAS-Marzo-de-2017.pdf
|
Marc : |
LEADER 02139nam a2200817 a 4500 001 1057103 005 2018-01-09 008 2017 bl uuuu u0uu1 u #d 100 1 $aGIMÉNEZ, A. 245 $aInforme agroclimático 2017 - Situación a Marzo.$h[electronic resource] 260 $aMontevideo (Uruguay): INIA$c2017 300 $a4 p. 650 $aAGROCLIMATOLOGIA 650 $aCAMBIO CLIMATICO 650 $aCLIMA 650 $aCLIMATOLOGIA 650 $aESTACIONES METEOROLOGICAS 650 $aESTRES HIDRICO 650 $aEVAPORACION 650 $aEVAPOTRANSPIRACION 650 $aHUMEDAD 650 $aHUMEDAD RELATIVA 650 $aLLUVIA 650 $aMETEOROLOGIA 650 $aPERSPECTIVAS 650 $aPLUVIOMETROS 650 $aPRONOSTICO DEL TIEMPO 650 $aSENSORES 650 $aSISTEMAS 650 $aSISTEMAS DE INFORMACION 650 $aSUELO 650 $aTEMPERATURA 650 $aTERMOMETROS 653 $aAGROCLIMA 653 $aAGROCLIMATOLOGÍA 653 $aBOLETIN AGROCLIMÁTICO 653 $aCARACTERIZACIÓN AGROCLIMÁTICA 653 $aDIRECCION VIENTO 653 $aESTACIONES AGROMETEOROLOGICAS 653 $aESTACIONES AUTOMATICAS 653 $aESTACIONES INIA 653 $aESTADO DEL TIEMPO 653 $aESTRÉS HÍDRICO 653 $aGRAFICAS AGROCLIMATICOS 653 $aGRAS 653 $aHELIOFANOGRAFO 653 $aINFORMACION SATELITAL 653 $aINFORME AGROCLIMÁTICO 2017 653 $aINUNDACIONES 653 $aLLUVIAS DIARIAS 653 $aMAXIMA 653 $aMEDIA 653 $aMINIMA 653 $aPANEL SOLAR 653 $aPERSPECTIVAS CLIMATICAS 653 $aPLUVIOMETRO 653 $aPRECIPITACION NACIONAL 653 $aPREVENCION HELADAS 653 $aPRONOSTICO 653 $aSENSOR 653 $aSIMETRICO 653 $aTANQUE A 653 $aTERMOCUPLAS 653 $aTERMOHIDROGRAFO 653 $aVARIABLES AGROCLIMATICAS 653 $aVELETA 700 1 $aCASTAÑO, J. 700 1 $aCAL, A. 700 1 $aTISCORNIA, G. 700 1 $aSCHIAVI, C. 700 1 $aWADSWORTH, C.
Descargar
Esconder MarcPresentar Marc Completo |
Registro original : |
INIA Las Brujas (LB) |
|
Biblioteca
|
Identificación
|
Origen
|
Tipo / Formato
|
Clasificación
|
Cutter
|
Registro
|
Volumen
|
Estado
|
Volver
|
Expresión de búsqueda válido. Check! |
|
|