An important aspect of environmental monitoring is anomaly detection, which allows for identifying unusual patterns that may indicate an environmental change or sensor malfunction. K-Nearest Neighbors (KNN) and Isolation Forests (IF) are used in this study to identify anomalies using hybrid algorithms. The model was applied to data obtained from Lake Macquarie City Council using environmental monitoring system (EMS) sensors developed by ARCS Group in partnership with the University of Technology, Sydney, as part of the TULIP Project, which were used by the Lake Macquarie City Council. Through the use of the Council’s Community IoT LoRaWAN Network—The Things Network, the Council was able to collect data from these sensors. Based on 56,996 data points, the hybrid model effectively identified 2872 anomalous patterns from 52,978 data points, with a detection accuracy of approximately 5.44%. Combining KNN and IF augments the detection accuracy and robustness of the hybrid model, providing valuable insight into the nature and distribution of anomalous patterns. This approach redresses limitations that may be encountered in environmental monitoring, such as computational complexity and heuristic threshold setting, and offers a reliable method of detecting anomalies that significantly contributes to the improvement of environmental data analysis and monitoring while addressing limitations.