Design and Evaluation of an AI-Enabled Cloud-Edge Architecture for Connected Precision Agriculture Farms

Deckshitha Angadi; Koteshwar Goud Surga; Nagaraju Lakkaraju; Naveena Budda; Vikas Agarwal; Giridhara Venkata Ram Raj Mulasa; Ravi Killamsetty; Chandrasekhara Sarma Mallubhotla

cs.ROAug 4, 2026

Design and Evaluation of an AI-Enabled Cloud-Edge Architecture for Connected Precision Agriculture Farms

Authors: Deckshitha Angadi, Koteshwar Goud Surga, Nagaraju Lakkaraju, Naveena Budda, Vikas Agarwal, Giridhara Venkata Ram Raj Mulasa, Ravi Killamsetty, Chandrasekhara Sarma Mallubhotla, +1 more

Organizations: AI, IoT and Robotics Lab (AIR Lab), UAVs Group, Autonomous Robotics Systems Limited, Hyderabad, India · Department of Microelectronics and VLSI Design, University of Hyderabad, Hyderabad, India · Department of Artificial Intelligence, ThoughtGreen Technologies Private Limited, Hyderabad, India · Department of Internet of Things, Ideabytes Software India Private Limited, Hyderabad, India · School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA · Enterprise Solutions Unit, Tata Consultancy Services, Atlanta, GA, USA · Business Analysis Product Division Management, EPAM India, Hyderabad, India · Department of Genetics and Plant Breeding, Kaveri University, Gowraram, India · Department of Artificial Intelligence, University of Malaya, Kuala Lumpur, Malaysia

Abstract

Plant diseases cause significant yield losses worldwide, with tomato crops particularly susceptible to early blight, late blight, and leaf mold. Manual monitoring is practical only for small-scale farms and becomes unmanageable at larger scales. To tackle this limitation, an artificial intelligence (AI) enabled cloud-edge architecture is proposed for autonomous crop monitoring. This proposed architecture integrates Internet of Things (IoT) sensors, unmanned aerial vehicles (UAVs), deep learning, Azure IoT Hub-based cloud analytics, and multi-platform (mobile app, web app, and embedded edge device platform) interfaces to enable real-time detection of tomato diseases. For training and validation, we used publicly available datasets, such as PlantVillage and Kaggle. A TensorFlow model trained on a collected dataset is deployed across mobile, web, and edge-device platforms. Experimental results show detection effectiveness around 92-95%, with consistent performance over diverse environments and device platforms. The proposed system improves disease detection effectiveness, lowers dependence on manual inspection, and enables prompt interventions, thereby supporting sustainable, connected precision agriculture farms.

Explore similar work

AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification
May 2, 2026Minh-Dung Le, Minh-Duc Hoang, Hoang-Vu Truong +1Tomato Diseases Apple Tree Leaf Disease Segmentation Dataset
Enhancing Precision Agriculture with a Hybrid Deep Learning Framework for Multi-Class Plant Disease Classification and Interpretability
Jun 13, 2026Hasibul Islam Sufi, Ridam Roy, Shayla Alam Setu +1Tomato Diseases Deep Learning Framework
AgriMind: An Ensemble Deep Learning Framework for Multi-Class Plant Disease Classification
May 15, 2026Salma Hoque Talukdar Koli, Fahima Haque Talukder JelyTomato Diseases Deep Learning Framework

May 2, 2026 · cs.CVJ/K move · Enter open · S save

AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification

Minh-Dung Le, Minh-Duc Hoang, Hoang-Vu Truong, Thi-Thu-Hong Phan

AIT laboratory, Faculty of Artificial Intelligence, FPT University, Da Nang, 550000, Viet Nam

Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) provide strong representation capability by modeling long-range dependencies and inter-class relationships; however, their high computational cost makes them impractical for deployment on edge devices. As a result, existing approaches struggle to effectively transfer these rich representations to lightweight models. This paper introduces AgriKD, a cross-architecture knowledge distillation framework for efficient edge deployment, which transfers knowledge from a Vision Transformer (ViT) teacher to a compact convolutional student model. To bridge the representational gap between Transformer and CNN architectures, the proposed approach integrates multiple distillation objectives at the output, feature, and relational levels, where each objective captures a different aspect of the teacher knowledge. This enables the student model to better preserve and utilize transformer-derived global representations. Experiments on multiple leaf disease datasets show that the distilled student achieves performance comparable to the teacher while significantly improving efficiency, reducing model parameters by approximately 172 times, computational cost by 47.57 times, and inference latency by 18-22 times. Furthermore, the optimized model is deployed across multiple runtime formats, including ONNX, TFLite Float16, and TensorRT FP16, achieving consistent predictive performance with negligible accuracy degradation. Real-world deployment on NVIDIA Jetson edge devices and a mobile application demonstrates reliable real-time inference, highlighting the practicality of AgriKD for AI-powered agricultural applications in resource-constrained environments.

Tomato Diseases Apple Tree Leaf Disease Segmentation Dataset Mobilenetv2 Self-Supervised Vision Transformers Heterogeneous Edge Devices Vision Transformer

Open paper Ask about it PDF

Abstract

Explore similar work

AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification

Enhancing Precision Agriculture with a Hybrid Deep Learning Framework for Multi-Class Plant Disease Classification and Interpretability

AgriMind: An Ensemble Deep Learning Framework for Multi-Class Plant Disease Classification