Fuzzy K-nearest neighbor for fine particles focusing on big data challenges and Introducing the GreenDeen concept towards pollution mitigation

Abstract

Abstract Rapid urban expansion and economic activity in densely populated cities have significantly contributed to worsening air quality. Jakarta, Indonesia’s capital, frequently experiences PM 2.5 concentrations that exceed "unhealthy" levels, posing serious public health risks. While various studies have explored air pollution modeling, there remains a gap in integrating localized educational and ethical frameworks into predictive approaches. This study applies the Fuzzy k-Nearest Neighbor (FKNN) algorithm to classify PM 2.5 concentration levels in Jakarta using meteorological variables as predictive inputs. With a data split of 80% for training and 20% for testing, the model achieved its best performance using parameters k = 21 and m = 3, yielding an accuracy of 52.75%, a weighted F1-score of 51%, and a Matthews Correlation Coefficient (MCC) of 0.29. The training and prediction times were 30.48 and 28.20 s, respectively. Although the classification performance is moderate, this study highlights the feasibility of FKNN as a lightweight method for environmental monitoring when source-specific emission data is limited. Additionally, this research introduces the GreenDeen concept—a faith-based environmental ethics framework—as a complementary narrative to promote pollution awareness and behavioral change among urban communities in Indonesia.By combining predictive modeling with ethical environmental discourse, this study offers a contextually relevant contribution to the broader discussion on sustainable urban air quality management.