Fatigue has become a major consideration factor in modern offshore wind farms as optimized design codes and a lack of lifetime reserve have made continuous fatigue life monitoring become an operational concern. In this contribution we discuss a data-driven methodology for farm-wide tower-transition piece fatigue load estimation. We specifically tackle the employment of this methodology in a real-world farm-wide setting and the implications of continuous monitoring. With reliable nacelle-installed accelerometer data at all locations, along with the customary ten-minute SCADA statistics and three strain gauge-instrumented ’fleet-leaders’ we discuss the value of two distinct approaches: use of fleet-leader or population-based data for training a physics-guided neural network model with a built-in conservative bias, with the latter taking precedence. In the context of continuous monitoring, we touch on the importance of data imputation, working under the assumption that if data is missing, then its fatigue loads should be modelled as under idling. With this knowledge at hand, we analyzed the errors of the trained model over a period of nine months, with monthly accumulated errors always kept below ±5% . A particular focus was given to performance under high loads, where higher errors were found. The cause for this error was identified as being inherent to the use of ten-minute statistics, but mitigation strategies have been identified. Finally, the farm-wide results are presented on fatigue load estimation, which allowed to identify outliers, whose behaviour we correlated with the operational conditions. Finally, the continuous data-driven, population-based approach here presented can serve as a springboard for further lifetime-based decision-making.