Farm Aadhar: An Intelligent Integrated System for Precision Agriculture Management

Abstract

Farm Aadhar is an intelligent precision-agriculture man-agement system designed to improve monitoring and decision sup-port in controlled-environment farming, especially polyhouse culti-vation. The system integrates low-cost ESP32-based sensing nodes, environmental sensors, a Supabase cloud backend, and an interactive web dashboard to support continuous observation of temperature, hu-midity, air quality, and gas concentration. Unlike manual inspection practices that depend heavily on periodic human observation, Farm Aadhar provides real-time data synchronization, configurable crop-specific thresholds, alert generation, and automation support for de-vices such as exhaust fans, humidifiers, and cooling units. The proto-type was tested at Weikfood Foods Pvt. Ltd., Bakori, Maharashtra, to evaluate its practical suitability in a commercial farming environment. The proposed system demonstrates how IoT and AI-enabled analytics can make polyhouse management more responsive, resource-efficient, and scalable for farmers.

Introduction

The paper presents Farm Aadhar, an integrated Internet of Things (IoT)-based precision agriculture management system designed to improve monitoring and automation in polyhouse farming. Traditional farming practices rely heavily on manual observation and delayed decision-making, making it difficult to maintain optimal environmental conditions. In controlled environments such as polyhouses, even slight variations in temperature, humidity, air quality, and harmful gas concentration can negatively affect crop health, productivity, and resource efficiency.

The system leverages recent advancements in IoT, cloud computing, and artificial intelligence to enable real-time, data-driven farm management. It integrates ESP32 microcontrollers, DHT22, MQ-135, and MQ-2 sensors with a Supabase cloud backend and a React/Node.js web dashboard in a three-tier architecture consisting of hardware, cloud, and application layers. This architecture supports continuous environmental monitoring, crop-specific threshold settings, historical data analysis, remote access, and automated climate control. The prototype was successfully tested in a real polyhouse environment at Weikfood Foods Pvt. Ltd., Bakori, Maharashtra, demonstrating its practical applicability beyond laboratory conditions.

The literature review highlights that precision agriculture combines sensing, communication, analytics, and automation to improve site-specific farming decisions. Although previous smart farming systems have implemented environmental monitoring and irrigation automation, many are limited to basic data visualization or single-parameter control. Farm Aadhar addresses these limitations by providing an integrated workflow that includes real-time monitoring, customizable thresholds, cloud synchronization, remote management, alerts, and historical analytics through an easy-to-use interface.

The primary objectives of the project were to develop a real-time monitoring system for environmental parameters, establish a low-latency communication pipeline between field hardware and cloud services, enable threshold-based automation for climate control devices such as exhaust fans, humidifiers, and air conditioners, provide an interactive dashboard for monitoring and analysis, and validate the system under real farming conditions.

The proposed system is divided into three functional modules. The hardware sensing module employs an ESP32 microcontroller with built-in Wi-Fi to collect data from DHT22, MQ-135, and MQ-2 sensors measuring temperature, humidity, air quality, and gas concentration. The cloud synchronization module uses Supabase to securely store sensor readings and provide near real-time updates to users through WebSocket-based communication. The application module consists of a React/Node.js web dashboard that displays live sensor readings, environmental status, alerts, historical trends, and device control options while allowing users to configure crop-specific environmental thresholds.

During implementation, the ESP32 periodically collected validated sensor data and transmitted it to the cloud. The dashboard displayed information using charts, status indicators, and reports, making environmental monitoring simple and intuitive for farm operators. The threshold configuration feature enabled farmers to define different environmental limits for different crops, making the system more flexible than fixed-threshold solutions. The automation module continuously compared sensor readings with configured thresholds and automatically triggered corrective actions, such as activating cooling units, exhaust fans, humidifiers, or ventilation systems whenever environmental conditions moved outside the desired range. This rule-based automation also provides a foundation for future AI-driven decision support.

Field testing at Weikfood Foods Pvt. Ltd. demonstrated that the system successfully collected and synchronized environmental data with low latency, enabling real-time monitoring and timely climate control decisions. The dashboard reduced the need for frequent manual inspections while allowing operators to monitor conditions remotely. Crop-specific threshold settings proved valuable for managing different crops under varying environmental requirements. However, the study identified several limitations, including the need for improved sensor calibration, enhanced protection of hardware for long-term outdoor deployment, and validation across multiple crop types and growing seasons.

Conclusion

Farm Aadhar presents an intelligent integrated system for pre-cision agriculture management in polyhouse farming. By com-bining ESP32-based sensing, Supabase cloud synchronization, and a real-time dashboard, the system provides continuous monitoring, configurable thresholds, alerts, and automation support. Field testing at Weikfood Foods Pvt. Ltd., Bakori, Maharashtra, showed that the system is practical for real farm-ing conditions and can help reduce manual effort while improv-ing microclimate awareness. With further calibration, extended trials, and AI-based recommendation features, Farm Aadhar can become a scalable decision-support platform for sustain-able smart farming.

References

[1] K. A. Patil and N. R. Kale, “A model for smart agriculture using IoT,” in Proc. International Conference on Global Trends in Signal Processing, Information Computing and Communication, Jalgaon, India, 2016, pp. 543–545. [2] M. Ayaz, M. Ammad-Uddin, Z. Sharif, A. Mansour, and E. H. M. Ag-goune, “Internet-of-Things (IoT)-based smart agriculture: Toward mak-ing the fields talk,” IEEE Access, vol. 7, pp. 129551–129583, 2019. [3] M. S. Farooq, S. Riaz, A. Abid, K. Abid, and M. A. Naeem, “A survey on the role of IoT in agriculture for the implementation of smart farming,” IEEE Access, vol. 7, pp. 156237–156271, 2019. [4] S. Wolfert, L. Ge, C. Verdouw, and M.-J. Bogaardt, “Big data in smart farming–a review,” Agricultural Systems, vol. 153, pp. 69–80, 2017. [5] Supabase, “Supabase Realtime documentation,” 2026. [Online]. Avail-able: https://supabase.com/docs/guides/realtime [6] Espressif Systems, “ESP32 series datasheet,” 2024. [Online]. Avail-able: https://www.espressif.com/sites/default/files/documentation/ esp32 datasheet en.pdf [7] Aosong Electronics, “DHT22 digital-output relative humidity and tem-perature sensor module datasheet,” 2022.

Copyright

Copyright © 2026 Anushka Patil, Aniket Sadakale, Kavita Dige. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.