Poly House Monitoring and Controlling System with the Detection of Micro Plastics in Soil

Abstract

The burgeoning demand for food production has catapulted playhouse[1] farming to the forefront of modern agriculture, enabling year-round crop production irrespective of environmental conditions. However, this method also poses significant ecological concerns, including micro plastic contamination, which can have far-reaching and devastating consequences on ecosystems and human health. Furthermore, culminating in substantial economic losses for farmers. To address these pressing challenges, this study presents a ground-breaking IoT-based polyhouse monitoring and controlling system designed to detect micro plastics and diagnose crop diseases. The system integrates a plethora of sensors for temperature, humidity, soil moisture, and gas detection, along with an LCD screen display and Bluetooth connectivity for real-time data transmission to farmers\' mobile devices. A dedicated app enables farmers to report crop issues and receive expert advice, while a Python-based software module detects micro plastics and identifies crop diseases, providing treatment recommendations. The proposed system offers a novel solution for sustainable polyhouse farming practices, empowering farmers to take prompt action against micro plastic contamination and crop diseases, thereby reducing environmental pollution and improving crop yields. The \"Poly house Monitoring and Controlling System with the detection of Micro plastics in soil \" is advanced solution in agriculture mimicking real-time detection of various physical and weather conditions at any location desired. The ESP8266 and Arduino as the microcontroller, the Blynk IoT platform, and the weather forecast API are integrated within the system, which regulates primary various environmental parameters such as the: temperature, humidity, gas level and light intensity within a closed acrylic chamber. Key hardware components include a microcontroller, LDR sensor, humidity level sensor, DHT11 sensor, fan, and grow lights that provide simulations for different climatic conditions. The system is designed to assist in agricultural research, environmental studies, and even materials testing with a cost-effective, compact, and reliable solution. The project also incorporates real-time data analytics, decision-support mechanisms, detection of micro plastics in soil as organic soil is used in polyhouse but using of different mulching techniques some amount of micro plastic is present in soil, cloud-based databases in polyhouse management, improving productivity through mobiles.

Introduction

Overview
The integration of Internet of Things (IoT), mobile apps, and cloud platforms (e.g., Blynk) is transforming agriculture by enabling real-time monitoring, remote control, and automated decision-making. These technologies are especially effective in controlled environments like polyhouses, optimizing crop growth conditions and minimizing resource waste.

2. Key Technologies and Functions

• Sensors monitor temperature, humidity, soil moisture, gas levels, and light intensity.

• Data is processed via Arduino and NodeMCU ESP8266 and displayed on LCDs or apps.

• Blynk enables cloud storage, data visualization, and remote access.

• A Python-based AI module detects microplastics in soil and helps diagnose crop diseases.

• An automated irrigation system activates pumps when moisture levels fall below a set threshold.

• Additional features include weather simulations, crop recommendations, and real-time alerts.

3. Proposed System Methodology

• Combines hardware sensors (DHT11, LDR, Gas Sensor, Soil Moisture Sensor, LM35) with microcontrollers (Arduino, NodeMCU).

• All collected data is analyzed and used to control conditions in the polyhouse (ventilation, lighting, irrigation).

• An AI-based microplastic detection tool, developed in Python, assists in maintaining soil health.

4. System Components

• NodeMCU ESP8266: Enables Wi-Fi connectivity for IoT control.

• Sensors: DHT11 (temperature/humidity), LDR (light), gas sensor (CO?), soil moisture, LM35 (temperature).

• Actuators: Relay module, DC pump, DC motor, and motor driver (L293D) for controlling irrigation and ventilation.

• Microplastic Detector App: A user-friendly mobile app for farmers to monitor parameters and share crop images via platforms like WhatsApp.

5. Microplastic Detection & Disease Diagnosis

• A Python-based software leverages machine learning to identify soil contamination by microplastics and detect early signs of crop diseases, enhancing proactive farm management.

Conclusion

This automated system increases farm efficiency by producing customized growth conditions. With real-time climate control, it maximizes crop yield and quality and minimizes human labour. Automated watering ensures optimal water management, eliminating over- and under-watering. Farmers receive immediate alerts for system operations, including pump operations, to inform timely decision-making. Field trials show that IoT-based polyhouse management drastically reduces labour cost while maximizing agricultural output. Besides, data-driven insights help farmers implement precision farming techniques for better resource utilization. The \"Smart Polyhouse Automation System Using Arduino Uno and IoT\" is highly scalable, technology-driven, as well as cheaper in terms of cost. On the other side, the same system integrates with Blynk. IoT by processing real time data, such that continuous adaptation of control variables is ensured continuously. The employment of wireless sensor networks and irrigation al mechanisms renders farming more productive and resource-based. Future refinements may provide additional functionalities or features such as solar power harnessing, efficient pest detection algorithms, and possibly AI-based predictability.

References

[1] https://www.researchgate.net/publication/“On Field Monitoring and Control of Polyhouse”. [2] Jhttps://ijsrset.com/paper/12058.pdf-“ IOT Based Polyhouse Farming with Controlled Environment and Monitoring”. [3] https://journalofbigdata.springeropen.com/articles/10.1186/s40537-023-00863-9#ref-CR1-“Plant disease detection and classification techniques: a comparative study of the performances” [4] https://www.ijraset.com/research-paper/real-time-emblica-fruit-disease-monitoring-system-“Real Time Emblica Fruit Disease Monitoring System” [5] https://ieeexplore.ieee.org/document/9395847-“A Polyhouse: Plant Monitoring and Diseases Detection using CNN”

Copyright

Copyright © 2025 Ritika Srivastava, Dhriti ., Vartika ., Ritu Vats, Jiya , Geeta Dahiya, Indu Arora. 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.