A Deep Learning Approach for Automatic Ionogram Parameters Recognition with Convolutional Neural Networks

The Models, GroundTruth, and 2021P directories contain preserved data to be used for verifying the AI models described in 'A Deep Learning Approach for Automatic Ionogram Parameters Recognition with Convolutional Neural Networks.

Please use the code from GitHub and install all the necessary libraries using the requirements.txt file. The Models, GroundTruth, and 2021P directories need to be extracted and stored in the same directory as the ModelsEvaluation.pyand RunEvaluation.py files. The RunEvaluation.py script consists of two functions: ModelsEvaluation.Evaluate() and ModelsEvaluation.IonogramShow(). The outputs are Evaluation_FOF2.csv, Evaluation_FOF1.csv, etc., which contain GroundTruth, Predictions, Difference, MAE, and RMSE values, along with an ionogram_date.png image that includes the relevant GroundTruth and Prediction parameters.