PhenoMath 

Phenology is the science that studies the timing and duration of recurring life-cycle events in plants—such as budburst, flowering, and fruit ripening—in relation to environmental variables, particularly temperature. In agricultural contexts, phenological models enable the prediction of crop development under changing conditions and help adapt management practices to climate variability. For instance, in Phenological analysis through biomathematical models of three varieties of pear (Pyrus communis L.) in Mediterranean climate conditions, the authors developed monomolecular models to describe key stages such as budburst, flowering, and harvest for pear varieties under Mediterranean conditions (R² between 0.94 and 0.96). Similarly, in Development and validation of phenological models for eight varieties of sweet cherry (Prunus avium L.) growing under Mediterranean climate condition, the study designs and validates models based on growing degree days (GDD) for eight cherry varieties cultivated in the Maule region. The paper Biomathematical modeling and phenology in sweet cherry: addressing the challenges of climate change explores how phenological models can be adapted to face the impacts of climate change. Moreover, Digitalized biomathematical models for the dynamic analysis of gray mold caused by Botrytis cinerea in wine grapes: insights and applications links phenology with plant disease dynamics, integrating digitalized models to analyse how climate modulates Botrytis outbreaks in vineyards. 

Digital phenology monitoring integrates mathematical models with advanced imaging technology to understand and predict plant development under real environmental conditions. In this context, Basler industrial cameras play a crucial role, enabling the continuous and precise capture of high-resolution images that record key phenological stages such as budburst, flowering, and fruit ripening. These cameras generate quantitative data that can be processed and linked to biomathematical models, improving the calibration and validation of predictive functions based on temperature, light, or accumulated heat units (GDD). The integration between image acquisition and mathematical simulation allows researchers to analyse the dynamics of growth and stress with greater temporal precision, enhancing the capacity to monitor crops in real time. Thus, the synergy between mathematical modelling and digital vision systems represents a significant step toward the development of intelligent tools for sustainable agriculture and the adaptation of production systems to climate change. 

Furthermore, the use of Basler cameras facilitates the creation of automated observation networks that strengthen the connection between field data and computational analysis. By combining time-series image datasets with machine learning and mathematical modelling, it is possible to identify subtle phenological patterns and forecast developmental stages under different climatic scenarios.