In the heart of Odisha, India, a groundbreaking study led by P. Ankit Krishna from the School of Engineering and Technology at GIET University is revolutionizing sustainable farm management through the power of machine learning. By integrating crop recommendations with disease identification, this research is poised to transform agricultural practices, offering farmers a robust tool to enhance productivity and mitigate the impact of crop diseases.
The study, published in the journal ‘Engineering Proceedings’ (translated as ‘Engineering Transactions’), leverages advanced machine learning and deep learning algorithms to provide farmers with precise, data-driven insights. “The goal is to empower farmers with accurate recommendations for optimal crop choices and timely detection of plant diseases,” explains Krishna. This integration of technology into agriculture is not just about increasing yields; it’s about creating a more sustainable and resilient food system.
At the core of this innovation is the use of Internet of Things (IoT) sensors, such as NPK and DT11 sensors, which collect crucial data on soil nutrients, temperature, humidity, and other environmental parameters. This real-time data is then processed using state-of-the-art convolutional neural networks (CNNs) like VGG16, ResNet50, and EfficientNetV2. These algorithms analyze high-resolution camera images to identify diseases based on visual cues like leaf color and texture.
The results are impressive. The recommendation system achieved an accuracy rate of 99.98%, while the disease identification system reached 96.06%. “These high accuracy rates are a testament to the potential of machine learning in agriculture,” says Krishna. The models were further implemented on cloud infrastructure, ensuring scalability and availability, which is crucial for widespread adoption.
The commercial impacts of this research are profound. For the energy sector, which is increasingly focused on sustainability, this technology offers a way to optimize agricultural practices, reducing the need for chemical inputs and minimizing environmental impact. “By providing farmers with the tools to make informed decisions, we can create a more efficient and sustainable agricultural system,” Krishna notes.
The study’s findings open up new avenues for future developments in the field. As machine learning and deep learning technologies continue to evolve, their integration into agricultural practices is expected to become more sophisticated. This could lead to even more accurate and timely recommendations, further enhancing productivity and sustainability.
In conclusion, the research led by P. Ankit Krishna represents a significant step forward in the application of machine learning for sustainable farm management. By combining crop recommendations with disease identification, this technology offers a powerful tool for farmers, with far-reaching implications for the energy sector and beyond. As the world grapples with the challenges of climate change and food security, innovations like these are more important than ever.