<p>Multi-source geomagnetic interferences have detrimental impacts on the magnetic field of geomagnetic observatories, resulting in reduced data availability and reliability. The detection and identification of potential magnetic disturbances with clear or unknown causes contributes to enhancing the anti-interference capability of international geomagnetic networks. In this study, we presented an integrated framework for detecting and identifying some typical magnetic interferences, which includes signal characteristic discrimination, detection algorithm design, correlation verification, and performance evaluation. Two INTERMAGNET stations in Japan and one geomagnetic observatory in China are used in this study. We analyzed the characteristics of magnetic disturbances caused by solar activity, climate activity, and human activities on ground observations referring to mechanisms. Considering three basic characteristics (amplitude, frequency, and morphology), various algorithms for interferences are developed for detecting geomagnetic anomalies. The detected anomalies are further identified using the verification of spatiotemporal correlation between the anomalies and interferences. The performance of the presented algorithms was evaluated using recall rate, precision, and accuracy, demonstrating their accuracy and effectiveness. Accordingly, the two-step method, sliding window method, time–frequency analysis method, and one-dimensional convolutional neural network model (1D CNN) are considered the optimal algorithms for identifying the anomalies caused by geomagnetic storms, thunderstorms, subway operations, and high-voltage direct current transmission (HVDC), respectively. This study provides a reference paradigm for addressing diversified interferences, facilitating the screening of weak magnetic disturbances generated by unknown factors such as geophysical activities, and providing a potential solution for pioneering applications.</p>