Safdar, Zanab, Rehman, Ikram ORCID: https://orcid.org/0000-0003-0115-9024, Saeed, Nagham ORCID: https://orcid.org/0000-0002-5124-7973, Khan, Abdul Manan and Nasralla, Moustafa M. (2025) I-TREES: A Context-Aware Framework for Energy-Efficient Tree Health Monitoring in Forest Internet of Trees (IoTr) Networks. In: 2025 Association for the Advancement of Artificial Intelligence Summer Symposium Series, 20–22 May 2025, Dubai, UAE..

Full text not available from this repository.

Abstract

Internet of Trees (IoTr) technology enables a novel approach to real-time remote monitoring, particularly of trees and forest ecosystems. However, existing literature focuses on soil moisture monitoring of trees and lacks the contextual intelligence and adaptive sensing capabilities necessary for smart tree monitoring. This paper proposes a novel layered architecture for IoTr and the I-TREES (IoTr-based Tree Routing for Energy-Efficient Systems) framework for smart sensing and context-driven monitoring. I-TREES integrates embedded IoTr environmental sensors, LPWAN communication, edge processing, and cloud-based reasoning to monitor physiological and ecological stress parameters in vulnerable tree species. The proposed architecture enables selective sensing, where sensors adapt their behaviour based on real time environmental conditions to reduce energy consumption and avoid redundant transmissions. We evaluate I-TREES using Network Simulator 3 (NS-3) simulations across 700 node deployments under forest-like conditions and compare them with benchmark routing protocols. Results show that I-TREES achieves a superior packet delivery ratio approximately 97%, reduced latency, and lower energy consumption than existing schemes. I-TREES offers a robust solution for sustainable forest ecosystem monitoring and early disease detection by combining scalable sensing with intelligent context awareness.

Item Type:	Conference or Workshop Item (Paper)
ISSN:	2994-4317
ISBN:	10 1-57735-899-6
Page Range:	pp. 127-136
Identifier:	10.1609/aaaiss.v6i1.36043
Subjects:	Construction and engineering > Digital signal processing
Date Deposited:	01 Oct 2026
Dates:	Date Publication status 1 August 2025 Published
School, department or research centre:	School of Computing and Engineering
URI:	https://repository.uwl.ac.uk/id/eprint/15485

Actions (admin access)