Abstract

This paper proposes a comprehensive approach for data-driven participatory community monitoring based on “Citizen Science” (CS), ISO 37120, and artificial intelligence (AI). The design integrates AI with the CS six-stage life cycle and citizen data governance principles through an AI-CS framework, aligning with the Copenhagen Social Summit. The framework was developed for local governments in Ecuador, a country where territorial planning lacks citizen data disaggregated by territorial, sociodemographic, and contextual variables. This fact limits the capacity of local governments to make evidence-based decisions. Between October 2025 and February 2026, data from 30,253 events were collected in 22 provinces and 93 cantons of the country. The data were analyzed by means of ordinal logistic regression to identify predictors of perceived severity and by means of DBSCAN, an unsupervised machine learning clustering algorithm, to characterize territorial patterns. The results suggest that citizen perception is organized into systemic and predictable patterns when structured using ISO 37120 categories. The spatial analysis reveals heterogeneous territorial patterns with levels of urgency that differ depending on the canton and the urban–rural context. The proposed approach allows local governments to obtain disaggregated territorial data for participatory planning. Its design may be transferable to other Global South contexts facing similar data gaps and is aligned with SDGs 9, 11, 16, and 17.

IPC Classification

Keywords