IoT-Based Smart Coconut Farm Monitoring and Disease Prediction System using CNN

Authors

  • S T PAVITHRA DEVI A.V.V.M Sri Pushpam College (Autonomous), Poondi, (Affiliated to Bharathidasan University, Tiruchirappalli), Thanjavur, TamilNadu, India.
  • DR. V. MANIRAJ A.V.V.M Sri Pushpam College (Autonomous), Poondi, (Affiliated to Bharathidasan University, Tiruchirappalli), Thanjavur, TamilNadu, India.

DOI:

https://doi.org/10.58414/SCIENTIFICTEMPER.2026.17.7.2468

Keywords:

Internet of Things (IoT), Smart Coconut Farm Monitoring, Convolutional Neural Network (CNN), Disease Prediction, Precision Agriculture.

Abstract

Coconut farming is an important crop in the tropics and plays a large role in food production and rural livelihoods in these areas. But the changes in environment, nutrient deficiencies, inadequate irrigation, and disease attacks frequently affect productivity and cause loss of yield and income from the crop. To overcome these issues, a novel system has been proposed which is based on IoT, cloud computing, and CNN for smart monitoring system of coconut plantation for plant disease prediction and precision agriculture. The system involves the use of sensors connected to the Internet of Things (IoT) to track various important parameters in the farm, such as soil moisture, soil temperature, soil humidity, soil pH, nutrient levels (NPK) and rainfall, on a continuous basis. The sensors are then linked to microcontrollers like ESP32 and NodeMCU, allowing for effective data collection and transmission to a cloud-based system where they can be stored, displayed, and analyzed. Besides environmental monitoring, the images of the leaves are taken by the camera module and then analyzed with a CNN-based disease prediction model to know the condition of the plant health. The data set consists of readings from the environmental sensors, old farm records and images of the coconut leaves with three classes: Healthy, Nutrient/Environmental Stress and Diseased. CNN-based discriminative feature extraction and automatic disease classification of leaf images is used to classify the diseases like bud rot, leaf spot, stem bleeding and root wilt. By combining data from IoT devices with deep learning algorithms for image analysis, farmers can detect signs of crop stress and disease early, allowing for prompt action and decision-making. The results of the experiments show that the proposed system is effective in improving the accuracy of disease prediction, optimizes resource utilization, and improves the performance of the entire farm. The developed framework is scalable and cost-effective approach for sustainable coconut farming and smart agricultural management.

Downloads

Download data is not yet available.

Downloads

Published

23-07-2026

Issue

Section

Research article

How to Cite

IoT-Based Smart Coconut Farm Monitoring and Disease Prediction System using CNN. (2026). The Scientific Temper, 17(07), 6486-6498. https://doi.org/10.58414/SCIENTIFICTEMPER.2026.17.7.2468

Similar Articles

91-100 of 433

You may also start an advanced similarity search for this article.