Dataset on irrigation for Tomato

This dataset is collected through real-time sensors to develop an automated underground drip irrigation system based on the Edge Internet of Things (IoT). Sensors used for collecting data include the BME280 temperature, humidity, and pressure sensors. Soil moisture value is measured through the capacitive SEN0193 soil moisture sensor. A 5-volt RS485 NPK sensor measures the N, P, and K values in mg/kg. A real-time API measures wind speed and solar radiation value based on the longitude and latitude of the farming field. Real-time data is collected in JavaScript Object Notation (JSON) and converted to CSV. Research in this study uses real-time data to test and analyze the automation of drip underground irrigation for tomato crops. The CSV format data are preprocessed and normalized to train the data for scheduling drip underground irrigation and predicting soil health status through an artificial intelligence approach. Several smart precision farming analysis methods for tomato crops can be applied using this data. For example, estimating total water demand and predicting soil and NPK fertilizer. Real time sensor data captured during testing of the automated irrigation scheduling system in JSON format.本数据集通过实时传感器采集而来，用于研发基于边缘物联网（Edge Internet of Things）的自动化地下滴灌系统。用于数据采集的传感器包括BME280温湿度气压传感器。土壤湿度值通过电容式SEN0193土壤湿度传感器测得。一款5伏RS485型NPK传感器可测量以mg/kg为单位的氮、磷、钾含量。一款实时API可基于农田的经纬度获取风速与太阳辐射数值。实时数据以JavaScript对象标记（JavaScript Object Notation）格式采集，并转换为CSV格式。本研究利用该实时数据，对番茄作物的地下滴灌自动化系统开展测试与分析。研究人员会对CSV格式的数据进行预处理与归一化，以通过人工智能方法训练模型，用于规划地下滴灌调度方案并预测土壤健康状态。本数据集可支撑多种面向番茄作物的智能精准农业分析方法，例如估算总需水量、预测土壤状况与NPK肥料需求。 本自动化灌溉调度系统测试过程中采集的实时传感器数据，以JSON格式存储。