Evaluating Feature Impact on Ocean Wind Speed Predictions: An Application of Explainable AI to GNSS Reflectometry Data

Artificial intelligence (AI) models developed for the Global Navigation Satellite System Reflectometry (GNSS-R) observations are capable of estimating geophysical parameters, especially ocean surface wind speeds. Understanding the decision-making process of deep learning models can be as significant as improving output accuracy in practical applications. This study explores the exploitation of Explainable Artificial Intelligence (XAI) for interpreting complex deep learning models. With the assistance of SHAP (SHapley Additive exPlanations) Gradient Explainer, this study evaluates the impact of both Delay-Doppler Map (DDM) pixels and ancillary parameters on model predictions, which can further help in understanding the role of specific input parameters. Additionally, this study investigates the potential of applying XAI to enhance the accuracy of deep learning models, which can be extended for climate-related applications.