Multi-Source Error Compensation for Weighing Rain Gauge Based on Adaptive GOOSE-BP Network

Purpose: To address the measurement inaccuracies of weighing-type rain gauges caused by environmental disturbances such as vibration, temperature drift, and creep, this study aims to develop a robust error modeling and compensation framework adaptable to complex conditions. Method: A nonlinear error model was constructed by analyzing multi-source disturbance factors and incorporating both linear and nonlinear temperature terms. A BP neural network was employed to compensate for complex error patterns, and several intelligent optimization algorithms (a genetic Algorithm (GA), a particle swarm algorithm (PSO), and a GOOSE algorithm (GOOSE)) were used to enhance training performance. An improved adaptive GOOSE algorithm (ADGOOSE) was further proposed to optimize the BP network by integrating dynamic control coefficients and perturbation-based restart strategies. Results: Experiments under various rainfall intensities and temperatures demonstrated that the ADGOOSE-BP model outperformed traditional filtering and other optimization methods, achieving the lowest RMSE of 0.0494 and the highest R2 of 0.9835. Conclusion: The proposed method effectively models and compensates for environmentally induced errors in weighing rain gauges, demonstrating strong potential as a high-precision, adaptive compensation framework that provides a solid foundation for future field-deployable hydrological monitoring systems.