IoT-based monitoring and intelligent control for microgreens in vertical farming systems

2025

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.1016/j.procs.2025.10.254
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This paper describes an IoT-powered smart vertical farming system that helps microgreens grow better. The solution includes environmental sensors for light, temperature, humidity, pH, and electrical conductivity (EC). These sensors are all connected through an ESP8266 microcontroller. Azure IoT Hub receives the data, which is then processed by cloud services. A dashboard shows the results in real time. The architecture makes it possible for automated decision-making to manage the cycles of nutrients and irrigation. Experimental results show that crop yields and resource use are better. The system shows how new IoT technologies can make urban farming more sustainable and accurate. Vertical farming system combines inexpensive sensors and an Azure-based streaming pipeline for intelligent control and real-time monitoring. The methodology consists of a four-week controlled A/B experiment (IoT vs. manual), cloud ETL for analytics, and a Random Forest model for classifying environmental states. At 92% classification accuracy, the system reduced water use by 30% (0.9 L/day vs. 1.3 L/day) and increased biomass by 20% (124 g vs. 103 g per tray at day 10). Sensor accuracy was ±0.1 pH and ±1.2 °C (temperature); each box had about 20,000 readings with a loss of less than 2%. Among the contributions are: (i) a scalable, end-to-end IoT and ML architecture; (ii) verified improvements in resource efficiency; and (iii) an open, cloud-based pipeline that is prepared for urban implementations. These findings show a feasible route to large-scale precision microgreen production.