Monitoring crops’ biotic and abiotic responses through sensors is crucial for conserving resources and maintaining crop production. Existing sensors often have technical limitations, measuring only specific parameters with limited reliability and spatial or temporal resolution. Wearable sensing systems are emerging as viable alternatives for plant health monitoring. These systems employ flexible materials attached to the plant body to detect nonchemical (mechanical and optical) and chemical parameters, including transpiration, plant growth, and volatile organic compounds, alongside microclimate factors like surface temperature and humidity. In smart farming, data from real‐time monitoring using these sensors, integrated with Internet of Things technologies, can enhance crop production efficiency by supporting growth environment optimization and pest and disease management. This study examines the core components of wearable standalone systems, such as sensors, circuits, and power sources, and reviews their specific sensing targets and operational principles. It further discusses wearable sensors for plant physiology and metabolite monitoring, affordability, and machine learning techniques for analyzing multimodal sensor data. By summarizing these aspects, this study aims to advance the understanding and development of wearable sensing systems for sustainable agriculture.

Crop fresh weight and leaf area are considered non-destructive growth factors due to their direct relation to vegetative growth and carbon assimilation. Several methods to measure these parameters have been introduced; however, measuring these parameters using the existing methods can be difficult. Therefore, a non-destructive measurement method with high versatility is essential. The objective of this study was to establish a non-destructive monitoring system for estimating the fresh weight and leaf area of trellised crops. The data were collected from a greenhouse with sweet peppers (Capsicum annuum var. annuum); the target growth factors were the crop fresh weight and leaf area. The crop fresh weight was estimated based on the total system weight and volumetric water content using a simple formula. The leaf area was estimated using top-view images of the crops and a convolutional neural network (ConvNet). The estimated crop fresh weight and leaf area exhibited average R² values of 0.70 and 0.95, respectively. The simple calculation was able to avoid overfitting with fewer limitations compared with the previous study. ConvNet was able to analyze raw images and evaluate the leaf area without additional sensors and features. As the simple calculation and ConvNet could adequately estimate the target growth factors, the monitoring system can be used for data collection in practice owing to its versatility. Therefore, the proposed monitoring system can be widely applied for diverse data analyses.

The importance of implementing recirculating drainage for greenhouse strawberries is often overlooked because of the low electrical conductivity (EC) of drainage and transpiration despite the large area of cultivation in Korea. In this study, we analyzed the growth of strawberry crops and their water and individual nutrient use efficiency when using closed-loop hydroponics in greenhouses. The study consisted of two parts: Experiment (Exp) 1 and Exp 2, each of which employed a different closed-loop hydroponic control method. In Exp 1, the system was controlled solely based on the EC of the drainage mixed with raw water. In Exp 2, the nutrient solution (NS) was corrected according to the ion concentrations in the drainage, with correction intervals of 2 weeks, 4 weeks, and no correction, while the control treatment was open-loop. In Exp 1, a prolonged increase in drainage EC resulted in an imbalance in NS ion composition and reduced fruit yield. In Exp 2, the NS composition was stabilized through periodic nutrient correction, and the fruit yield of the closed-loop treatments did not differ from the open-loop treatment. However, the closed-loop with 2- and 4-week correction in Exp 2 showed 94% and 88% higher nutrient use efficiency (NUE), respectively, than an open-loop system. Among the closed-loop treatments, the 2- and 4-week correction intervals had 36% and 32% higher NUE than the no-correction treatment. Furthermore, the 2-week correction interval showed a 3% improvement in NUE compared to the 4-week interval. These findings highlight the importance of considering a shorter ion correction interval for optimal NUE and normal plant growth in recirculating hydroponic systems of strawberry cultivation.

Since transpiration plays a key role in optimal irrigation management, knowledge of the irrigation demand of crops like tomatoes, which are highly susceptible to water stress, is necessary. One way to determine irrigation demand is to measure transpiration, which is affected by environmental factor or growth stage. This study aimed to estimate the transpiration amount of tomatoes and find a suitable model using mathematical and deep learning models using minute-by-minute data. Pearson correlation revealed that observed environmental variables significantly correlate with crop transpiration. Inside air temperature and outside radiation positively correlated with transpiration, while humidity showed a negative correlation. Multiple Linear Regression (MLR), Polynomial Regression model, Artificial Neural Network (ANN), Long short-term Memory (LSTM), and Gated Recurrent Unit (GRU) models were built and compared their accuracies. All models showed potential in estimating transpiration with R 2 values ranging from 0.770 to 0.948 and RMSE of 0.495 mm/min to 1.038 mm/min in the test dataset. Deep learning models outperformed the mathematical models; the GRU demonstrated the best performance in the test data with 0.948 R 2 and 0.495 mm/min RMSE. The LSTM and ANN closely followed with R 2 values of 0.946 and 0.944, respectively, and RMSE of 0.504 m/min and 0.511, respectively. The GRU model exhibited superior performance in short-term forecasts while LSTM for long-term but requires verification using a large dataset. Compared to the FAO56 Penman-Monteith (PM) equation, PM has a lower RMSE of 0.598 mm/min than MLR and Polynomial models degrees 2 and 3 but performed least among all models in capturing variability in transpiration. Therefore, this study recommended GRU and LSTM models for short-term estimation of tomato transpiration in greenhouses.

Closed hydroponics (recirculating) is increasingly recognized as a sustainable approach for conserving water and fertilizer resources. However, concerns remain among growers regarding ionic imbalances and yield instability during nutrient–solution recirculation. This study aimed to clarify these issues through continuous ionic monitoring of drainage water and optimization of nutrient compensation intervals in commercial tomato (Solanum lycopersicum L.) cultivation. Two greenhouse systems, an open (non-recirculating) and a closed (recirculating) system, were compared. Electrical conductivity (EC), pH, and major ions (NO₃⁻, K⁺, Ca²⁺, Mg²⁺, SO₄²⁻, PO₄³⁻, and Na⁺) were analyzed using ion chromatography. Based on ionic fluctuation trends, compensation intervals of 0, 2, and 4 weeks were evaluated in the closed system. Contrary to expectations of growers, open hydroponics exhibited greater ionic imbalance due to uncontrolled leaching. Periodic compensation (every 4 weeks) stabilized ionic ratios, reduced fertilizer input by 67–69%, and decreased water use by 33–36% compared with the open system. These findings demonstrate that drainage-based ionic monitoring and interval-based compensation can improve the environmental and economic performance of closed hydroponics.