Precision seed metering has evolved from mechanically optimized devices to sensor-based, digitally connected systems. However, research remains fragmented across metering mechanisms, sensing, data processing, communication, and control. This review examined monitoring and closed-loop control throughout the seed-delivery process, from pickup and release to tube passage, furrow placement, and crop emergence. This structured review synthesized 49 primary studies identified through Scopus and the Web of Science Core Collection, with supplementary searching using Google Scholar and literature coverage through 1 September 2026. Optical and photoelectric sensors provide the most direct evidence for seed-passage detection, whereas encoders, pressure, vacuum, motor-current, and vibration measurements primarily indicate machine or actuator conditions. Machine vision provides spatial information and can support independent reference measurements, but requires suitable imaging conditions and computational resources. Capacitive, acoustic, impact-based, and hybrid approaches remain less extensively validated. Reported performance cannot be directly compared across studies due to differences in seed characteristics, mechanisms, operating speeds, event definitions, disturbances, and reference methods. Most studies demonstrate monitoring, alarms, or open-loop optimization rather than complete sensor-to-actuator correction. An engineering framework is therefore proposed to connect measurement targets, evidence maturity, latency, actuator authority, and independent verification. Future research should prioritize standardized testing, disturbance robustness, synchronized multi-row field validation, and measured end-to-end delay. Transparent reporting of correction accuracy, stability, cost, power demand, and interoperability is also required to support deployment and defensible assessment of closed-loop seeding systems.

Vertical farming requires precise monitoring and control of environmental conditions to support consistent year-round crop production and efficient resource utilization. However, multilayer cultivation creates spatial, vertical, and temporal variations in temperature, humidity, CO₂, airflow, and lighting, complicating the maintenance of uniform growing conditions. This review analyzed 70 recent studies on remote monitoring and control in smart vertical farms, focusing on environmental variability, sensing infrastructure, sensor-node placement, communication architectures, actuator operation, and control strategies. Studies were classified into five thematic areas: sensing and monitoring, automation and control, environmental and climate control, IoT and wireless communication, and CFD-based analysis. Recent research advances include the development of spatially distributed sensing networks for monitoring and the adoption of adaptive, data-driven, model-based, and hierarchical methods for control. Nevertheless, significant research gaps persist, such as the lack of standardized sensor-placement strategies, limited integration of actuator-level operational data, insufficient long-term commercial-scale validation, and limited transferability of monitoring and control frameworks across facility configurations. Many methods remain adapted from greenhouse systems rather than specifically designed for vertical farms. Addressing these gaps is essential for improving the reliability, energy efficiency, and scalability of smart vertical farm systems.

Reliable assessment of crop water stress is essential for improving irrigation efficiency for upland crop and orchard fruit production. Thermal sensing combined with the crop water stress index (CWSI) provides a non-destructive approach for characterizing plant water status; however, its performance depends strongly on baseline determination, sensing platform, canopy architecture, environmental conditions, image-processing procedures, and validation strategy. This paper aimed to review thermal imaging and point-based infrared thermometry (IRT) approaches for CWSI measurement and mapping, with particular emphasis on sensing requirements of upland field crops and orchard fruit tree canopies. A PRISMA-aligned literature search was conducted using major scientific databases and complementary citation tracking, resulting in 68 primary studies included in the structured thematic synthesis. Empirical, theoretical, and artificial-reference CWSI formulations were compared together with handheld, ground-based, unmanned aerial vehicle (UAV)-mounted, fixed camera, and point-based IRT sensing configurations. Radiometric calibration, canopy segmentation, temperature extraction, spatial interpolation, and physiological validation methods were critically evaluated. The reviewed evidence indicates that image-based approaches provide valuable spatial information but remain sensitive to radiometric drift, mixed canopy–background pixels, shadowing, and baseline uncertainty, whereas point-based IRT offers high temporal resolution but depends strongly on representative sensor placement and field-of-view geometry. These limitations differed according to canopy architecture, with soil–background contamination being particularly important in incomplete field canopies and radiation-driven within-canopy heterogeneity being more important in orchards. Combining periodic spatial thermal mapping with continuous point-based monitoring provided a promising framework for precision irrigation. Future research should prioritize transferable baseline parameterization, standardized uncertainty reporting, multi-season commercial validation, benchmark datasets, and crop-specific irrigation thresholds.

Accurate plant counting supports stand assessment and crop management, but canopy overlap, camera motion, and temporary occlusion complicate video-based monitoring. This study developed an RGB image- and video-based framework for detecting, tracking, and counting cabbage seedlings and grown plants under greenhouse and open-field conditions. The framework integrated YOLOv8n with convolutional block attention modules (CBAM) and an improved BoT-SORT procedure incorporating trajectory persistence, short-gap relinking, class-consistent identity management, and counting-event filtering. Detector performance was evaluated across five independent training runs, counting performance across nine held-out videos, and tracking performance on four manually annotated videos. YOLOv8n-CBAM achieved mean precision, recall, mAP@0.50, and mAP@0.50:0.95 values of 0.880 ± 0.007, 0.920 ± 0.007, 0.960 ± 0.006, and 0.600 ± 0.008, respectively (mean ± sample standard deviation). The complete framework achieved 99.27% mean counting accuracy, a mean absolute error of 0.56 plants, a root mean square error of 0.88 plants, and an R² of 0.997. On the annotated subset, Improved BoT-SORT increased mean IDF1 from 79.6% to 82.3% and mean HOTA from 74.3% to 83.2%, while reducing total identity switches from 23 to 12. Complete-pipeline throughput was 23.38 frames per second on an RTX 3090 workstation. These findings support cabbage population monitoring under the evaluated conditions; independent-site validation, tracking-component ablation, and deployment-device testing remain necessary to establish broader applicability.

Reliable environmental sensing is essential for stable monitoring and control in vertical farms; however, high data-acquisition completeness does not ensure that measurements are valid, temporally consistent, or operationally meaningful. This study proposed an interpretable two-layer framework that distinguished direct signal-quality errors from in-range temporal and operating-context abnormalities in a Wi-Fi-based small-scale vertical farm. Nine sensor nodes were installed across nine cultivation beds under empty-bed and continuous LED-on conditions. Air temperature, relative humidity, CO₂ concentration, and light intensity were measured at 30 s intervals for 10 days and transmitted through MQTT, Node-RED, and InfluxDB on a Raspberry Pi local server. Layer 1 screened timestamp discontinuities, invalid or null packets, and physically invalid measurements. Layer 2 evaluated only valid records using moving-window variability, rate of change, peer-node residuals, and LED-on context consistency, and a study-specific F-code taxonomy converted detected abnormalities into interpretable operating-status labels. Detection thresholds were determined from a separate two-day period immediately preceding the 10-day evaluation and were not adjusted using the evaluation records. Of 259,200 expected records, 258,910 were received (99.888% completeness). Layer 1 identified 290 missing timestamp positions, 25 invalid packets, and 40 out-of-range records. The framework achieved 99.68% accuracy, 98.49% precision, 98.89% recall, 98.69% binary F1 score, and 84.69% macro-averaged F-code F1 score. Combining signal validation with temporal and context analysis detected abnormalities that static range validation could not identify.

Reliable actuator operation is essential for maintaining stable environmental and production conditions in smart vertical farms. The objective of this study was to characterize power consumption data from five actuator types, including a brushless direct-current (BLDC) fan, a dehumidifier, a light-emitting diode (LED) lighting system, a pump, and a solenoid valve, under normal and abnormal operating conditions using a common experimental approach. The combined evaluation of these five actuator types provided a unified basis for comparing power-consumption characteristics across actuators with different operating mechanisms. The experiments were conducted under controlled laboratory-scale conditions, and each operating condition was evaluated in three experimental repetitions. Power consumption data were measured using Hall-effect current sensors at a sampling frequency of 1 kHz. Time-domain characteristics, including power magnitude, variability, power range, coefficient of variation (CV), transient behavior, and temporal variability, were evaluated together with standardized feature heatmaps and relative-frequency distributions. The results indicated that power responses varied according to actuator type and abnormal condition. Blockage or restricted operation increased power demand and variability in the BLDC fan, pump, and solenoid valve, whereas pump dry-run operation produced a lower operating demand. Dehumidifier short cycling resulted in repeated activation and interruption and produced pronounced signal variability, with a CV of 31.3% and a power range of 598.2 W. Unstable LED flicker altered both power level and temporal behavior, while intermittent connections produced repeated power reductions in the pump and solenoid valve. No-response conditions remained near actuator-specific baseline levels, with mean power ranging from approximately 0.5 to 6.0 W. These results confirmed that actuator operational status could be represented by combinations of power magnitude, variability, transient response, and temporal behavior. The proposed power-consumption characterization provides a basis for actuator-status monitoring and future fault-detection applications in smart vertical farms.