INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Special Issue | Volume XIV, Issue XIII, October 2025
www.ijltemas.in Page 113
Farming the Future: AI and Automation in Environmental
Monitoring
Pooja Dongare1, Nimisha Rai2
1Department of Computer Science, Dr. D. Y. Patil Arts, Commerce and Science College, Pimpri, Pune-18, Maharashtra,
India
2Department of Electronics, Dr. D. Y. Patil Arts, Commerce and Science College, Pimpri, Pune-18, Maharashtra, India
DOI: https://doi.org/10.51583/IJLTEMAS.2025.1413SP025
Received: 26 June 2025; Accepted: 30 June 2025; Published: 24 October 2025
Abstract: The research paper introduces a novel method for monitoring environmental conditions in agricultural environments by
integrating AI technologies with IoT infrastructure. It utilizes data from a variety of sensors including those that measure soil
moisture, gas levels, and other environmental parameters to provide real-time condition tracking. The system uses an Arduino
microcontroller, an ESP module for communication, and the ThingSpeak platform to gather, upload, and manage data from
environmental sensors effectively. One of the system's core functionalities is its weather prediction module, developed in Python
using a Convolutional Neural Network (CNN) to enable AI-driven forecasting. This module delivers valuable weather insights,
supporting informed and proactive farm management. Additionally, the system includes an intuitive web interface that displays
real-time sensor readings and predictive analytics, empowering farmers to optimize resource usage and respond effectively to
environmental changes.
Keywords: Artificial Intelligence (AI), Cloud Service Platforms (Thing Speak), Environmental Sensor, Internet of Things (IoT),
Smart Farming, Predictive analytics
I. Introduction
In recent years, farming has changed a lot because of new technology. Today, farmers use smart methods and machines to grow
crops more efficiently. Despite these advancements, environmental monitoring remains an essential aspect that needs further
innovation to effectively address the challenges posed by climate change, resource conservation, and sustainable farming
practices. Traditional farming methods are increasingly inadequate in the face of escalating extreme weather events, shifting
climate patterns, and the pressing need for efficient water and fertilizer usage. (T. Popović, etal,2017) These factors highlight the
necessity for advanced technologies that can provide real-time monitoring, support data-driven decisions, and offer predictive
analytics to aid in better farm management. This project seeks to close the existing gap by integrating Internet of Things (IoT) and
Artificial Intelligence (AI) technologies to develop an all-encompassing environmental monitoring solution (Singh, P.etal). The
system employs IoT-based sensors to continuously gather real-time data on environmental factors such as soil moisture,
temperature, humidity, air quality, and weather patterns. This information is transmitted to a centralized platform where it
undergoes analysis, enabling farmers to remotely oversee their farm’s environmental conditions and respond promptly when
necessary. The continuous real-time data collection supports better decision-making by delivering valuable insights into the
factors influencing crop health and productivity. This helps farmers use resources better and reduce waste. A standout feature of
this project is the use of AI-driven weather forecasting models. These predictive tools provide farmers with advance notice of
upcoming weather changes, helping them plan and allocate resources more strategically. By anticipating events such as rainfall,
temperature shifts, or frost risks, farmers can implement preventive measures like modifying irrigation schedules or safeguarding
crops against harsh weather. This integration not only improves operational efficiency but also strengthens the adaptability of
agricultural practices to climate fluctuations. This project seeks to address these challenges by integrating Internet of Things (IoT)
and Artificial Intelligence (AI) technologies into a holistic environmental monitoring system. The system collects real-time
environmental data through IoT sensors, measuring key variables such as soil moisture, temperature, humidity, air quality, and
weather conditions. This data is then transmitted to a central platform for in-depth analysis, enabling farmers to monitor the health
and status of their crops remotely. By delivering real-time insights, the system allows farmers to make more informed decisions,
optimizing resource use and minimizing waste. A key innovation in this project is the application of AI, specifically through a
weather prediction model that helps forecast future conditions. This capability empowers farmers to anticipate weather changes
such as rainfall, temperature shifts, or frost risk, allowing them to plan and manage resources more effectively. With predictive
insights, farmers can take preventive actions like adjusting irrigation schedules or protecting crops from adverse weather
conditions, thereby improving the overall efficiency and sustainability of farming operations.
II. Overview
The AI-powered Environmental Monitoring System is a fully integrated solution aimed at advancing farm automation through
modern technology. It combines Arduino for collecting data from sensors, ESP modules for wireless communication, and
ThingSpeak for cloud-based storage and visualization. Sensors connected to the Arduino measure key environmental conditions,
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Special Issue | Volume XIV, Issue XIII, October 2025
www.ijltemas.in Page 114
including soil moisture, temperature, humidity, and air quality. The ESP modules ensure smooth and reliable wireless
transmission of this data to ThingSpeak, where it is safely stored and displayed. ThingSpeak offers a user-friendly web interface
with dynamic graphs and dashboards, giving farmers instant access to real-time information and helping them respond quickly to
changing conditions. A standout feature of the system is its AI-based weather forecasting. These forecasts are available on the
same dashboard, giving farmers a clear picture of current and upcoming conditions. This helps improve planning for irrigation,
crop protection, and deciding the best times for planting and harvesting. Overall, the system bridges traditional farming with
smart technology. By bringing together IoT devices, cloud platforms, and AI, it offers a reliable monitoring solution with built-in
predictive tools. This helps boost efficiency, reduce waste, and protect crops from environmental challenges.
III. Objective
The primary goal of this project is to develop an integrated environmental monitoring and farm automation system using IoT and
AI technologies to improve agricultural productivity and sustainability. The system uses a set of sensors, an Arduino
microcontroller, and an ESP module to collect critical environmental data such as soil moisture, gas levels, and temperature. This
data is transmitted in real time to the ThingSpeak cloud platform, enabling farmers to monitor field conditions remotely. By
automating data collection, the system reduces the need for manual checks, saving time and providing a more efficient way to
manage farms. A key feature of the project is its AI-powered weather forecasting, implemented using a Convolutional Neural
Network (CNN) in Python (LeCun, Y.). This model predicts upcoming weather patterns, allowing farmers to plan irrigation,
fertilization, and crop protection more effectively based on forecasted conditions. The system includes a user-friendly dashboard
that displays real-time environmental data and weather predictions in a clear, visual format, helping farmers make quick,
informed decisions. In summary, this project aims to provide farmers with accurate, actionable insights to support smarter and
more sustainable farming practices.
IV. Methodology
This project adopts a structured approach to developing an AI-powered Environmental Monitoring and Farm Automation System.
It integrates hardware, software, and machine learning to track environmental variables and generate weather forecasts, aiming to
enhance agricultural decision-making. The development process is organized into distinct phases: System Architecture Design,
Sensor-Based Data Acquisition, Data Transmission and Processing, AI Model Implementation, User Interface Development, and
System Evaluation.
System Architecture: The system's architecture illustrates how both hardware and software components are organized and
connected. At the center of the setup is an Arduino microcontroller, which manages input from various environmental sensors,
including those that measure soil moisture, temperature, humidity, and gases like carbon monoxide (CO) and carbon dioxide
(CO₂). Data collected by these sensors is sent wirelessly using the ESP8266 Wi-Fi module to the ThingSpeak cloud, where it is
logged and displayed for real-time monitoring. Designed with a modular structure, each component of the system functions
autonomously yet remains part of an integrated whole. This approach improves adaptability, simplifies system maintenance, and
allows for easy upgrades, such as adding more sensors or expanding functionality without overhauling the entire-setup.
Data Acquisition: Data acquisition forms a crucial part of the system’s functionality. This project uses a range of sensors to
monitor environmental parameters: Soil moisture sensors are used to detect the water content in the soil. Gas sensors measure air
quality by detecting gases such as carbon monoxide (CO) and carbon dioxide (CO₂). Temperature and humidity sensors capture
the surrounding climatic conditions.
These sensors are interfaced with a microcontroller, typically an Arduino, which processes the collected data. The processed
information is then sent via an ESP8266 Wi-Fi module to the ThingSpeak cloud platform, where it is stored and visualized
through dynamic dashboards. This enables real-time tracking of environmental changes and ensures easy accessibility of data for
analysis and decision-making.
Data Processing: Once the sensor data is collected, it undergoes a processing phase to ensure accuracy and consistency. This
involves: Filtering out noise and erroneous readings from the raw data, Normalizing values so that different sensor outputs can be
interpreted on a common scale. These steps prepare the data for further analysis and ensure it is reliable for use in AI-based
forecasting and system-automation.
AI-Based Weather-Forecasting: The system integrates Artificial Intelligence to predict future weather conditions. A
Convolutional Neural Network (CNN) is trained using historical weather data sourced from public databases. The model is
capable of identifying complex patterns within large datasets.
After training, the CNN is embedded into the system and begins using live environmental data to predict upcoming weather
changes—such as expected rainfall or temperature variations. These insights help farmers make proactive and well-informed
decisions based on real-time forecasts.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Special Issue | Volume XIV, Issue XIII, October 2025
www.ijltemas.in Page 115
User Interface Development: A user-friendly web dashboard is developed using Python frameworks such as Flaskor Streamlit.
This interface provides: Live sensor readings, AI-generated weather predictions, Interactive visualizations such as charts, graphs,
and tables. The dashboard allows users to explore historical trends, zoom into specific time intervals, and receive alerts about
unusual or critical environmental events. Designed with ease of use in mind, it offers farmers fast and clear access to vital
information. System Deployment and Live Monitoring. After successful testing, the full system is deployed in an actual farming
environment. All components including the Arduino board, sensors, and the ESP8266 communication module are configured to
enable continuous, real-time monitoring. The system sends live data to ThingSpeak, which logs the readings and refreshes the
predictive dashboards accordingly. Ongoing monitoring ensures that the setup operates correctly. Any issues detected are
addressed promptly. In addition, the system is regularly reviewed for scalability—with the possibility of integrating more sensors
or enhancing the AI model to improve accuracy and performance.
Integration Overview: The ESP8266 module communicates with the Arduino, which is programmed to handle sensor data
acquisition. On the software side, ThingSpeak is used for cloud-based storage and visualization, providing an intuitive and
dynamic interface for environmental monitoring. Simultaneously, a CNN-based weather prediction model built in Python runs
alongside the monitoring system, enabling advanced, data-driven decision-making for agricultural activities.
V. Hardware Implementation
The hardware setup consists of the following components:
Arduino Uno (for data collection from sensors)
Soil Moisture Sensor (for monitoring soil condition
Gas Sensors (for detecting gases like CO2, CO)
DHT11 (for humidity and temperature monitoring)
Soil Moisture Sensor (for monitoring soil conditions)
Gas Sensors (for detecting gases like CO2, CO)
DHT11 (for humidity and temperature monitoring)
ThingSpeak (cloud platform for data storage and visualization).
ESP8266 Wi-Fi module (for internet connectivity)
Wiring Setup –Arduino Uno:
Connect the Soil Moisture Sensor to an analog input pin (A0).
Connect the Gas Sensors (e.g., MQ
Connect the DHT11 to a digital pin.
Connect the ESP8266 Wi-Fi module to the Arduino (TX to RX, RX to TX, VCC to 3.3V, GND to GND)
Connect the Soil Moisture Sensor to an analog input pin (A0). ect the Gas Sensors (e.g., MQ-7 for CO) to analog pins.
Connect the DHT11 to a digital pin. Wi-Fi module to the Arduino (TX to RX, RX to TX, VCC to 3.3V, Gnd to Gnd.
VI. Block Diagram
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Special Issue | Volume XIV, Issue XIII, October 2025
www.ijltemas.in Page 116
Algorithm
1. Begin system operation.
2. Set up and activate all modules, including the Arduino, ESP8266 Wi-Fi module, environmental sensors (soil moisture,
temperature, humidity, gas), and the AI prediction model.
3. Acquire data from the sensors: Measure soil moisture content.
4. Record temperature and humidity values. Detect concentrations of gases such as CO and CO₂.
Use the ESP8266 module to transmit the gathered data from the Arduino to the ThingSpeak cloud platform.
5. Save and display the incoming data on ThingSpeak’s live dashboard for real-time monitoring.
Clean and normalize the collected data to prepare it for analysis.
6. Input the processed data into a trained Convolutional Neural Network (CNN) model for weather prediction.
7. Generate forecast results such as rainfall probability and temperature variations. Show both current environmental data
and AI-generated forecasts through a web dashboard built using Flask or Stream lit. Analyze soil moisture levels and
automatically activate the water pump if irrigation is needed. Continuously repeat the cycle for ongoing data collection,
prediction, and system control.
8. End the system operation when necessary.
Flowchart
VIII. Conclusion
The AI-based Environmental Monitoring and Farm Automation System offers an innovative solution to the evolving needs of
modern agriculture. By merging Internet of Things (IoT) and Artificial Intelligence (AI) technologies, the system provides
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Special Issue | Volume XIV, Issue XIII, October 2025
www.ijltemas.in Page 117
farmers with real-time insights into field conditions through various sensors, including those for soil moisture, temperature,
humidity, and air quality. The integration with ThingSpeak ensures that all environmental data is securely stored and visually
presented on a centralized cloud platform. This makes the system user-friendly and efficient, enabling continuous monitoring and
easy access to critical information. A key feature of this system is its AI-powered weather forecasting, which leverages
Convolutional Neural Networks (CNNs) to analyze environmental trends and predict future conditions. This allows farmers to
make proactive decisions such as scheduling irrigation or taking preventive measures based on reliable forecasts. In conclusion,
this project highlights the potential of combining AI and IoT to develop smart, scalable, and efficient agricultural solutions. It not
only supports better crop management but also contributes to long-term sustainability, productivity, and climate resilience in
farming practices.
IX. Future Scope
The proposed system holds significant potential for future improvements and broader real-world implementation. One promising
direction is the integration of additional sensors—such as pH sensors, light intensity sensors, and crop health monitors. This
would provide a more comprehensive understanding of environmental conditions and soil quality, allowing for more precise
agricultural decision-making. On the AI side, the predictive capabilities can be enhanced by adopting more advanced machine
learning or deep learning models. This upgrade could improve the accuracy of weather forecasting and open up possibilities for
predicting pest outbreaks or crop diseases, enabling farmers to take timely preventive measures. Another major area of growth
lies in scaling the system for large-scale farming operations. By creating a centralized monitoring platform, multiple fields or
farm units could be managed more efficiently. Developing a dedicated mobile application would further enhance usability,
allowing farmers to receive real-time updates, alerts, and recommendations anytime, anywhere. Moreover, incorporating
automated irrigation systems would make the solution more dynamic and efficient. These systems could respond instantly to soil
moisture levels, ensuring optimal water use and reducing resource wastage. In conclusion, the continued evolution of this system
can contribute significantly to the future of agriculture making it smarter, more sustainable, and adaptable to changing conditions.
It offers a clear pathway toward widespread adoption of intelligent farming practices, benefiting both small-scale and commercial
agriculture.
References
1. T. Popović, N. Latinović, A. Pešić, Ž. Zečević, B. Krstajić, S. Djukanović
2. Architecting an IoT-enabled platform for precision agriculture and ecological monitoring: A case study Computers and
Electronics in Agriculture, 140 (2017), pp. 255-265
3. LeCun, Y., & Bengio, Y. Convolutional Neural Networks (CNNs) (1995). Convolutional networks for images, speech, and
time series. Proceedings of the IEEE, 86(9), 2278-2324.
4. AI for Precision Agriculture, Pantazi, X. E., & Atrey, S. (2017). AI applications for precision agriculture: Challenges and
future perspectives. International Journal of Advanced Robotics, 34(4), 1-15. doi:10.1007/s42064-017 0001-4.
5. Singh, P., & Srivastava, P. Smart Agriculture: A Review on IoT Applications, (2019). Smart agriculture using IoT for
sustainable crop production. Journal of Sustainable Agriculture, 41(3), 323-337. doi:10.1007/s10460-019-10042-8.
6. ThingSpeak Documentation, ThingSpeak, Math Works. (n.d.). ThingSpeak API documentation. Retrieved
fromhttps://www.mathworks.com/help/thingspeak/.
7. Arduino Documentation, Arduino, Inc. (n.d.). Arduino official website. Retrieved from https://www.arduino.cc/.