04040naa a2200253 a 450000100080000000500110000800800410001902200140006002400360007410000160011024502020012626000090032850006860033752025110102365300310353465300090356565300310357465300150360565300190362065300120363970000160365170000160366777301030368310644722024-02-23       2024    bl uuuu     u00u1 u    #d  a0308-521X7 a10.1016/j.agsy.2023.1038472DOI1 aPARUELO, J.  aHybrid modeling for grassland productivity predictionbA parametric and machine learning technique for grazing management with applicability to digital twin decision systems.h[electronic resource]  c2024  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  --  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  aAgroecological transitions  aANPP  aArtificial neural networks  aGrasslands  aRemote sensing  aUruguay1 aTEXEIRA, M.1 aTOMASEL, F.  tAgricultural Systems. 2024. Volume 214, article 103847. https://doi.org/10.1016/j.agsy.2023.103847