Innovative Approaches to Surveying and Monitoring Potentially Invasive Alien Plants in Agro-Ecosystems-Review

Abstract

Invasive Alien Plants (IAPs) pose significant threats to biodiversity, crop productivity, and ecosystem services within agroecosystems. Effective surveillance and monitoring are critical for early detection and rapid management. This review synthesizes recent advances and interdisciplinary innovations in IAP monitoring, with a focus on their application in agricultural landscapes. Traditional methods, including field surveys, herbarium records, and farmer reports, provide foundational data but suffer from limitations such as spatial bias, high labor costs, and limited scalability. In response, emerging technologies such as remote sensing, Machine Learning (ML), Deep Learning (DL), citizen science platforms, and smart-chip IoT systems are being integrated into modern monitoring frameworks. Remote sensing coupled with ML enables automated detection across large areas, while citizen science applications expand spatial coverage and public engagement. Smart sensors and AI-driven analytics offer continuous, real-time monitoring and risk assessment. Integrated systems, such as Early Detection and Rapid Response (EDRR) platforms, increasingly combine these tools to support informed decision-making. Despite these advances, challenges remain, including data quality issues, model generalizability, interoperability across platforms, and socio-political barriers. This review highlights key research gaps, including the need for standardized data protocols, federated learning, and ethical frameworks for data use. It concludes with strategic recommendations for future development: fostering interdisciplinary collaboration, advancing scalable technologies, and aligning monitoring systems with governance frameworks. Collectively, these efforts offer a pathway toward more resilient, adaptive, and data-driven approaches to managing IAPs in agroecosystems.