Coastal areas face intensifying threats from rising sea levels, erosion, and extreme storms, making real-time shoreline monitoring critical. This systematic review aims to evaluate how integrating Earth Observation (EO) technologies, citizen science, low-cost sensors, and Machine learning (ML) can improve real-time coastal dynamics monitoring. Following PRISMA guidelines, we identified 60 relevant studies and synthesised their monitoring methodologies, including spatial and temporal resolution thresholds and comparative performance metrics. We also systematically identified key methodological and geographic gaps in the literature. The review demonstrates that combining satellite EO, drone-based surveys, community-sourced observations (e.g. smartphone beach photographs), and ML techniques provides more comprehensive and timely insights into coastal changes than traditional methods alone. ML models can accurately predict shoreline changes, while citizen-contributed observations offer reliable, low-cost measurements that complement conventional monitoring. However, significant gaps remain in many coastal regions that are under-studied, and few fully operational real-time systems exist. To advance the field, we recommend practical steps such as improved data-sharing, better coordination among stakeholders, and integration of multi-source monitoring into early warning systems. Overall, this review highlights the innovative potential of integrating EO, citizen science, low-cost sensors and ML, and provides a roadmap for strengthening coastal monitoring practices and resilience in the face of climate change.
Riaz et al. (Sun,) studied this question.