Heetae Kim

Information and communication technology (ICT) components, especially actuators in automated irrigation systems, are essential for managing precise irrigation and optimal soil moisture, enhancing orchard growth and yield. However, actuator malfunctions can lead to inefficient irrigation, resulting in water imbalances that impact crop health and reduce productivity. The objective of this study was to develop a signal processing technique to detect potential malfunctions based on the power consumption level and operating status of actuators for an automated orchard irrigation system. A demonstration orchard with four apple trees was set up in a 3 m × 3 m soil test bench inside a greenhouse, divided into two sections to enable independent irrigation schedules and management. The irrigation system consisted of a single pump and two solenoid valves controlled by a Python-programmed microcontroller. The microcontroller managed the pump cycling ‘On’ and ‘Off’ states every 60 s and solenoid valves while storing and transmitting sensor data to a smartphone application for remote monitoring. Commercial current sensors measured actuator power consumption, enabling the identification of normal and abnormal operations by applying threshold values to distinguish activation and deactivation states. Analysis of power consumption, control commands, and operating states effectively detected actuator operations, confirming reliability in identifying pump and solenoid valve failures. For the second solenoid valve in channel 2, with 333 actual instances of normal operation and 60 actual instances of abnormal operation, the model accurately detected 316 normal and 58 abnormal instances. The proposed method achieved a mean average precision of 99.9% for detecting abnormal control operation of the pump and solenoid valve of channel 1 and a precision of 99.7% for the solenoid valve of channel 2. The proposed approach effectively detects actuator malfunctions, demonstrating the potential to enhance irrigation management and crop productivity. Future research will integrate advanced machine learning with signal processing to improve fault detection accuracy and evaluate the scalability and adaptability of the system for larger orchards and diverse agricultural applications.

LoRa-based sensor nodes may provide a reliable solution for wireless communication in orchard cultivation and smart farming, facilitating real-time environmental monitoring. However, the signal strength and data integrity can be affected by several factors, such as trees, terrain, weather, and nearby electrical devices. The objective of this study is to evaluate the impact of orchard trees on the performance of a LoRa sensor node under orchard conditions. A sensor node, built with a commercial LoRa transceiver and microcontroller unit (MCU), was paired with a single-channel gateway linked to an orchard irrigation system. Performance metrics such as the packet delivery ratio (PDR), received signal strength indicator (RSSI), and signal-to-noise ratio (SNR) were measured over a range of 20 to 120 m under open field conditions and in an orchard with trees averaging 3.12 and 4.36 m in height. Data were sent every 20 s using three spreading factors (SF8, SF10, and SF12) and stored as a CSV file in the MCU via a Python program. The results showed that the PDR remained consistently high (100%) under non-vegetative (open field) conditions. In the orchard under vegetative conditions, the PDR dropped significantly, with SF12 maintaining 100% only up to 120 m. For SF10, the packet delivery rates dropped to 45% at 80 m, while SF8 achieved 100% at 20 m but decreased to 52% at 40 m. SNR values also declined with an increase in distance, becoming largely undetectable beyond 40 m for SF8. These findings indicate that vegetation greatly impacts LoRa sensor node performance, reducing packet delivery and signal quality in orchards.

When utilizing the Crop Water Stress Index (CWSI), the most critical factor is accurately measuring canopy temperature, which is typically done using infrared sensors and imaging cameras. In this study, however, we aimed to develop a machine learning model capable of predicting leaf temperature based on environmental data, without relying on sensors, for calculating CWSI. The data underwent preprocessing to remove outliers and missing values. The number of training data points for each factor was 307,924. After data preprocessing, a Pearson correlation analysis (bivariate correlation coefficient) was conducted to select the training data for model operation. The relationship between leaf temperature and air temperature showed a strong positive correlation of 0.928 (p < 0.01). Solar radiation and relative humidity were also found to have high correlations. However, wind speed and soil moisture tension showed very low correlations with leaf temperature and were excluded from the model operation. The Decision Tree, Random Forest, and Gradient Boosting models were selected, and each model was evaluated using RMSE (Root Mean Squared Error), MAE (Mean Absolute Error), MSE (Mean Squared Error), and R² (coefficient of determination). The evaluation results showed that the Gradient Boosting model had a high R² (0.97) and low RMSE (0.88) and MAE (0.54), making it the most suitable model for predicting leaf temperature. Through the leaf temperature prediction model developed in this study, labor and costs associated with sensors can be reduced, and by applying it to real agricultural settings, it can improve crop quality and enhance the sustainability of agriculture.

The demand for efficient water use and automatic systems has been increasing due to the frequent drought damage to crops as a result of climate change, the shortage of water resources in rural areas, and the aging of farmers. The existing automatic irrigation systems reduce the amount of labor required for irrigation and maintain soil moisture. However, the irrigation threshold criteria are user-determined as opposed to being automated according to input objectives such as improving crop productivity and saving water. In this study, an algorithm that could automatically determine suitable soil moisture according to a database and an automatic irrigation system with intermittent irrigation for efficient water use were developed. An experiment was then conducted on the productivity of crops for protected cultivation according to the application of the system. As the frequency domain reflectometry (FDR) sensor used in this system measured the volumetric water content of the soil, the soil moisture tension corresponding with the set value was converted into the volumetric water content using a regression equation. The process of intermittent irrigation was defined by using the moisture movement modeling of Hydrus 2D to reduce water loss on the soil surface and allow moisture to penetrate the soil unobstructed. An experimental field of a tomato farm was divided into empirical manual and controlled automatic irrigation plots. A total of 97.3% of the soil moisture values in the −33 kPa-controlled automatic irrigation plot and 96.6% of the soil moisture values in the −25 kPa-controlled automatic irrigation plot were within each set range during the first cropping season. During the second cropping season, a total of 94.8% of the soil moisture values in the −33 kPa-controlled automatic irrigation plot was within the set range. Compared with the empirical manual irrigation plot, the water productivity in the first cropping season was 113.9% in the −33 kPa-controlled automatic irrigation plot and 106.3% in the −25 kPa-controlled automatic irrigation plot. In the second cropping season, the water productivity was 117.3% in the −33 kPa-controlled automatic irrigation plot. Therefore, an automatic irrigation system applied with intermittent irrigation could be critical to increasing agricultural production and improving water-use efficiency.