<![CDATA[Land surface temperature (LST) is an important indicator of climate change because increasing surface temperatures can trigger environmental degradation, drought, and extreme weather events. In Indonesia, long-term monitoring of extreme temperature anomalies remains limited, as most studies rely on conventional statistical methods that are less effective in detecting complex and non-linear anomaly patterns. Therefore, this study analyzes the spatio-temporal dynamics of LST and identifies extreme temperature anomalies across Indonesia during 1940–2024 using a machine learning approach. Monthly LST data were examined through exploratory data analysis (EDA), including temporal trend analysis and 10-year moving averages, to characterize long-term temperature variability, while the Isolation Forest algorithm was implemented as an unsupervised anomaly detection method using n_estimators = 100 and contamination = 0.05. The results identified 51 temperature anomalies, representing approximately 5% of the 1,020 monthly observations analyzed. Most anomalies occurred during periods associated with major climate disturbances and corresponded closely with documented El Niño events, particularly in 1997–1998 and 2015. Trend analysis revealed a persistent increase in Indonesia’s surface temperature, indicating an ongoing warming pattern consistent with climate change, while anomaly score distributions showed a clear separation between normal and extreme observations, confirming the effectiveness of the Isolation Forest algorithm. These findings demonstrate that integrating spatio-temporal analysis with machine learning provides a robust framework for detecting extreme temperature events and monitoring climate variability, thereby supporting climate risk assessment and strengthening BMKG’s early warning systems for climate change adaptation and mitigation.]]>
