ADCP-Based Proxy Sediment Transport Monitoring – Data and Code Archive

Overview This release provides a citable, reproducible snapshot of the revised workflow used for ADCP-based preprocessing and ML/DL experiments to predict the corrected bottom-track velocity proxy (BT_Vel) from ADCP-derived hydraulic, acoustic, and measurement-geometry features. Contents Data/ Processed_LAB_Data_with_BS.xlsx Processed_Field_Data_with_BS.xlsx Raw Data/Lab_raw/ — 15 flow rate .mat files Raw Data/Lab_raw/rsqmb/ — lab RS5 binary files for BS_rel extraction Raw Data/Field_raw/ — 7 campaign transect .mat files Raw Data/Field_raw/rsqmb/ — field RS5 binary files for BS_rel extraction Notebooks/ LAB_Preprocessing_v2.ipynb FIELD_Preprocessing_v2.ipynb LAB_ML_v2.ipynb FIELD_ML_v2.ipynb LAB_DL_v2.ipynb FIELD_DL_v2.ipynb Model analysis_revised.ipynb Reproducibility Recommended environment: Python 3.x, Jupyter/Colab Run order: Preprocessing → ML→ DL→ Model analysis All paths are relative (../Data/) GitHub: https://github.com/thtuhin488/ADCP_BT_Vel_ML_DL