Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Hybrid forest models in the age of abundant monitoring data and powerful data-driven algorithms: back to the future

  • Lo, Yueh-Hsin
  • Blanco Vaca, Juan Antonio
Forests are entering an era in which future climate, disturbance regimes, and management conditions may have no close historical analogues, while society increasingly demands the simultaneous provision of timber, carbon sequestration, biodiversity conservation, and other ecosystem services. Supporting sustainable, climate-smart forest management therefore requires predictive tools capable of anticipating ecosystem responses under novel environmental conditions. Recent advances in artificial intelligence (AI), remote sensing, and large forest databases have revolutionized forest monitoring and prediction. The rapid expansion of satellite observations, sensor networks, forest inventories, and automated monitoring programs has generated unprecedented volumes of data, allowing AI to greatly improve pattern recognition, forecasting, and decision support within historically observed, data-rich domains. However, the principal limitation of purely data-driven models lies in their limited transferability to environmental conditions beyond those represented in the training data. As forests experience novel combinations of climate, disturbances, species interactions, and management practices, statistical relationships derived from historical observations may no longer remain valid, compromising extrapolative predictions. Alternatively, process-based models (PBMs) provide a complementary approach by explicitly representing the physiological and ecological mechanisms governing forest dynamics, making them better suited for exploring future scenarios outside the historical record. Therefore, integrating these mechanistic models with AI tools and Internet of Things (IoT) technologies offers a promising pathway toward next-generation hybrid models and forest Digital Twins that combine pattern-recognition capabilities with causal ecological understanding. Achieving this vision will require continued development of process-based models, improved hybrid model architectures, standardized datasets, and rigorous uncertainty analysis to support robust, climate-smart, multi-objective forest management., Funding for this research has been provided by the Spanish Ministry of Economy and Competitiveness. Open access support provided by the Library of the Public University of Navarre. Project grant TED2021-131081B-C21 funded by MICIU/AEI /10.13039/501100011033 and the European Union NextGenerationEU/ PRTR.
Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
Publicación Artículo científico (JournalArticle)

Sensitivity of long-term productivity estimations in mixed forests to uncertain parameters related to fine roots.

  • Yeste Yeste, Antonio
  • Seely, Brad
  • Imbert Rodríguez, Bosco
  • Blanco Vaca, Juan Antonio
Forest growth models are increasingly being used in forestry and ecology research as predictive tools to help developing practical guidelines and to improve understanding of the drivers of forest ecosystem functioning. Models are usually calibrated using parameters directly obtained or estimated from empirical field observation, and hence are subject to uncertainty. Thus, output accuracy depends on input parameters precision and on how influential is each parameter on model behaviour. Hence, it is important to analyse parameter-related uncertainty and its effects on model outputs. This can be done by performing sensitivity analyses, which allow to explore the influence of one or several calibration parameters on model outputs. As studies on tree root parameters are particularly scarce, the aim of the present work was to evaluate the influence of parameters related to fine roots on estimations of long-term forest growth patterns in pure and mixed forests, using FORECAST (a hybrid forest growth model) as a virtual lab. The fine root parameters assessed were biomass, turnover rate, and nitrogen content. The analysis was performed by simulating monospecific stands of two contrasting species (Pinus sylvestris L. and Fagus sylvatica L.), and mixed stands formed by both species. In all cases, FORECAST showed good capability to contain uncertainty propagation during the first and middle stages of stand development (<40 years). After that moment, model output uncertainty steadily increased, but it reached different maximum uncertainty levels depending on stand type. Simulations of the less nutrient demanding P. sylvestris manifested very little sensitivity when growing in monospecific stands. However, F. sylvatica monospecific stands showed intermediate sensitivity, but significant species interactions occurred in mixed stands that determined the biggest impact detected of uncertainty related to fine root parameters over model outputs. All things considered, FORECAST displayed an interesting capability to capture some of the interspecific interactions that are key in mixed forests functioning. Our results suggest an acceptable model performance under uncertain parameterization but also caution against expecting accurate quantitative estimations of forest growth, especially when considering long-term scenarios in complex mixed stands., This research was funded by the Spanish Ministry of Economy and Competitiveness (grant AGL2016-76463-P TIMENUTRIENT) and the Spanish Ministry of Science and Innovation (grant TED2021-131081BC21). A.Y. was funded through a Spanish Predoctoral Research Grant (BES-2017-080326).