Carbon dioxide (CO₂) concentrations play an important role in plant production, as they have a direct impact on both plant growth and yield. Therefore, the objectives of this study were to predict CO₂ concentrations in the greenhouse by applying time series models using five datasets. To estimate the CO₂ concentrations, this study was conducted over a four-month period from 1 December 2023 to 31 March 2024, in a strawberry-cultivating greenhouse. Fifteen sensors (MCH-383SD, Lutron, Taiwan) were installed inside the greenhouse to measure CO₂ concentration at 1-min intervals. Finally, the dataset was transformed into intervals of 1, 5, 10, 30, and 60 min. The time-series data were analyzed using the autoregressive integrated moving average (ARIMA) and the Prophet Forecasting Model (PFM), with performance assessed through root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²). The evaluation indicated that the best model performance was achieved with data collected at 1-min intervals, while model performance declined with longer intervals, with the lowest performance observed at 60-min intervals. Specifically, the ARIMA model outperformed across all data collection intervals while comparing with the PFM. The ARIMA model, with data collected at 1-min intervals, achieved an R² of 0.928, RMSE of 7.359, and MAE of 2.832. However, both ARIMA and PFM exhibited poorer performances as the interval of data collection increased, with the lowest performance at 60-min intervals where ARIMA had an R² of 0.762, RMSE of 19.469, and MAE of 11.48. This research underscores the importance of frequent data collection for precise environmental control in greenhouse agriculture, emphasizing the critical role of short-interval data collection for accurate predictive modeling.

Accurate localization of picking points and depth estimation is critical for implementing a robotic strawberry harvesting system. Due to the delicate nature of strawberries, harvesting must be performed without bruising or damage, typically by grasping and cutting the peduncle of the ripe strawberry. However, accurately detecting and localizing the thin peduncle in a cluttered environment is a significant challenge. This study proposed depth fused Mask R-CNN (DF-Mask R-CNN), which integrates depth information of the scene with the RGB image to enhance the detection, localization, and segmentation of strawberries and their peduncles in a greenhouse environment. To generate a dense depth map, a cutting-edge monocular depth estimator, ZoeDepth was used. The proposed DF-Mask R-CNN with ResNet101-FPN exhibited superior instance segmentation performance, with an overall mAP of 81.9%, with mAP_small at 33.3%, mAP_medium at 78.79%, mAP_large at 88.8 and AP^IOU=0.5 at 98.1%. In tests with 300 ripe strawberry samples, the method demonstrated a robust picking point detection, with a mean absolute error and root mean square error of 1.98 cm and 2.12 cm, respectively. These results highlight the effectiveness of the DF-Mask R-CNN model combined with the ZoeDepth estimator in enhancing the detection, localization, and segmentation of strawberries and their peduncles. This approach enables precise picking point localization and depth estimation for efficient vision systems for robotic strawberry harvesting.

Accurate fruit counting is crucial for data-driven decision-making in modern precision agriculture. In strawberry cultivation, a labor-intensive sector, automated, scalable yield estimation is especially critical. However, dense foliage, variable lighting, visual ambiguity of ripeness stages, and fruit clustering pose significant challenges. To overcome these, we developed a real-time multi-stage framework for strawberry detection and counting by optimizing a YOLOv8s detector and integrating a class-aware tracking system. The detector was enhanced with a lightweight C3x module, an additional detection head for small objects, and the Wise-IOU (WIoU) loss function, thereby improving performance against occlusion. Our final model achieved a 92.5% mAP@0.5, outperforming the baseline while reducing the number of parameters by 27.9%. This detector was integrated with the ByteTrack multiple object tracking (MOT) algorithm. Our system enabled accurate, automated fruit counting in complex greenhouse environments. When validated on video data, results showed a strong correlation with ground-truth counts (R² = 0.914) and a low mean absolute percentage error (MAPE) of 9.52%. Counting accuracy was highest for ripe strawberries (R² = 0.950), confirming the value for harvest-ready estimation. This work delivers an efficient, accurate, and resource-conscious solution for automated yield monitoring in commercial strawberry production.

Vertical farming or vertical growing systems, a subset of controlled environment agriculture (CEA), integrates smart and precision agriculture to optimize crop production in stacked environments within a greenhouse, utilizing Internet of Things (IoT) sensors, automation, and advanced lighting. However, vertical farming can be carried out in the open, but the advantages of a closed system are sacrificed. This review examines recent advancements, including precision irrigation (hydroponics, aeroponics, and aquaponics), LED spectral optimization, robotics, and machine learning (ML) for enhanced resource efficiency. Case studies from Singapore, Japan, and the Netherlands demonstrate yield increases of 200-300% and energy savings of 30-50% compared to traditional methods. By integrating robotics, ML, and IoT, yields can be maximized, resource utilization can be optimized, and environmental impact can be reduced. Case studies from Singapore, Japan, and the Netherlands demonstrate the potential, with kale yields of 300 t•ha-1 , strawberry production at 200 t•ha-1 , and dual basil fish outputs achieved through 98% water recycling. Challenges such as high costs, energy demands, and technical complexity persist, particularly in developing regions. Future directions propose the integration of renewable energy, can offset energy reliance, cutting costs by 50%, low-cost sensors that broaden access and simplify IoT deployment, and modular designs that enhance scalability and offer hope for adaptation. This manuscript synthesizes quantitative metrics, comparative analyses, and implementation challenges, providing engineers and researchers with a detailed framework to advance sustainable urban agriculture through technology-driven solutions.

This study quantitatively evaluated the disinfection performance of a low-pressure mercury UV-C system against the pathogenic bacterium Agrobacterium rhizogenes by analyzing the effect of different combinations of lamp power consumption and flow rate. Agricultural water samples were collected from three commercial farms (Sources A, B, and C) in Sacheon-si, Gyeongsangnam-do, for the first experiment, and Source D in Gunbuk-myeon, Haman-gun, Republic of Korea, for the second experiment. All water samples were artificially inoculated with A. rhizogenes prior to treatment. The experiment tested nine combinations of three lamp power consumption levels (40, 75, and 105 W) and three flow rates (10, 15, and 30 L/min). Among these, samples #10, #20, and #30 were inoculated but not UV-treated, serving as the corresponding pre-disinfection controls. In the second experiment, a fixed power of 75 W was applied under high-flow conditions (60 and 120 L/min), with samples #37 and #38 serving as the corresponding untreated controls. In all tested conditions, absence of detectable bacteria was confirmed, except for sample #33 (75 W, 60 L/min), in which viable cells were detected at 2.0×10 2 CFU/mL. However, this represented approximately a 4.9 log reduction compared to its control (#37, 1.6×10⁷ CFU/mL), indicating substantial bactericidal efficacy. These findings suggest that effective disinfection can be achieved even under high-flow conditions, provided that sufficient UV dose is delivered. The results underscore the practical applicability of low-pressure UV-C systems in agricultural water treatment through the optimal configuration of operating parameters.