Agrivoltaic systems, combining solar energy generation with agricultural activities, offer a sustainable approach to maximising land efficiency. However, these systems can present challenges, such as potential shading effects that may impact fruit quality or crop yields. This study evaluated the impact of overhead agrivoltaic systems on apple (Malus domestica L. cv. Gala) ripening and maturation patterns in a temperate orchard near Lake Constance, Germany. Experiments compared apples grown under conventional conditions (control) with those under agrivoltaic setups equipped with semi-transparent photovoltaic panels utilizing spatially distributed cells for 40% light transparency installed with a 70% ground-coverage ratio. Key metrics, including fruit diameter, length, volume, and BBCH phenology stages, were monitored throughout the 2024 growing season. An IoT-based monitoring workflow was developed, combining fixed RGB image acquisition, automatic apple detection, colour-based ripening quantification, and time-series analysis to monitor visible maturation dynamics under field conditions. Results indicated that apples under agrivoltaic conditions showed delayed visible red-colour development, reaching comparable image-derived colour-maturity thresholds approximately 10–12 days later than the control group. On September 13 (harvest), no significant differences were found in mean length, while the diameter of agrivoltaic apples was significantly smaller (65.59 mm versus 70.98 mm), indicating slightly smaller dimensions under shaded conditions. Fruit volume and weight were approximately 16% lower under agrivoltaic conditions, averaging 161.16 cm3 (138.6 g) versus 191.58 cm3 (164.8 g) in the control. The delayed visible maturation was consistent with reduced light availability under the solar panels, although fruit-level light availability and physiological maturity indicators were not directly measured. These findings suggest that overhead agrivoltaic systems can significantly delay apple phenology and fruit maturation. Depending on the agricultural goals, the desired harvest timing and the cultivar, this may be challenging or beneficial, e.g., if it adapts the crop against climate change impacts or other factors such as local climate conditions, latitude and geographic region, and market demand. Integrating IoT-based monitoring with machine learning enhances the precision of agricultural assessments, providing valuable data for managing the effects of agrivoltaic systems on crop development.
