EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic perspectives into tropical fruit production: a review of modeling techniques

Daniel Mancero-Castillo, Yoansy Garcia, Maritza Aguirre-Munizaga, Daniel Ponce de Leon, Diego Portalanza, Jorge Avila-Santamaria

Frontiers in Agronomy · 20.12.2024 · 6

DOI: 10.3389/fagro.2024.1482893 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Agronomy, online erschienen am 20.12.2024. Verfasst von Daniel Mancero-Castillo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 214 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling the intricate interactions between fruit trees, their environments, soils, and economic factors continues to be a significant challenge in agricultural research globally, requiring a multidisciplinary approach. Despite advances in agricultural technology and algorithms, significant knowledge gaps persist in understanding and modeling these interactions. This review explores basic concepts related to modeling for tropical fruit production. It explains modeling development from sensor technologies, image analysis, databases, and algorithms for decision support systems while considering climate changes or edaphoclimatic limitations. We report the current fruit modeling tendencies showing a significant increase in publications on these topics starting in 2021, driven by the need for sustainable solutions and access to large agricultural databases. This study emphasizes inherent challenges in tropical fruit modeling, such as fruit tree cycles, costly and time-consuming experimentation, and the lack of standardized data. These limitations are evident in tropical fruit, where few models have been reported or validated for cocoa, avocado, durian, dragonfruit, banana, mango, or passion fruit. This study analyzes the classification of the algorithms related to tropical fruit into three main categories: supervised, unsupervised, and reinforcement learning, each with specific applications in agricultural management optimization. Crop classification and yield prediction use supervised models like neural networks and decision trees. Unsupervised models, like K-Means clustering, allow pattern identification without prior labels, which is useful for area segmentation and pest detection. Automation of irrigation and fertilization systems employs reinforcement learning algorithms to maximize efficiency. This multidisciplinary review discusses recent approaches to 1) Modeling Soil health and plant-soil interaction, 2) Yield prediction in tropical fruit orchards, 3) Integrating meteorological models for enhanced tropical fruit production, and 4) Economics of tropical fruit business through modeling. Furthermore, this review illustrates the complexity and multidisciplinary research on models for tropical fruit and platforms using agricultural models. Further opportunities to advance fruit modeling frameworks are indicated, requiring technical knowledge about the fruit crop requirements with user-friendly platforms to collect and access fruit tree data and site-specific agroecological conditions.

Zitieren

APA

Mancero-Castillo, D., Garcia, Y., Aguirre-Munizaga, M., Leon, D. P. D., Portalanza, D., & Avila-Santamaria, J. (2024). Dynamic perspectives into tropical fruit production: a review of modeling techniques. Frontiers in Agronomy, 6. https://doi.org/10.3389/fagro.2024.1482893

Vancouver

Mancero-Castillo D, Garcia Y, Aguirre-Munizaga M, Leon DPD, Portalanza D, Avila-Santamaria J. Dynamic perspectives into tropical fruit production: a review of modeling techniques. Frontiers in Agronomy. 2024;6. doi:10.3389/fagro.2024.1482893

BibTeX
@article{ManceroCastillo2024,
  author = {Mancero-Castillo, Daniel and Garcia, Yoansy and Aguirre-Munizaga, Maritza and Leon, Daniel Ponce de and Portalanza, Diego and Avila-Santamaria, Jorge},
  title = {Dynamic perspectives into tropical fruit production: a review of modeling techniques},
  journal = {Frontiers in Agronomy},
  year = {2024},
  volume = {6},
  doi = {10.3389/fagro.2024.1482893}
}
Kostenlos starten →