Hydrological controls of slope response to precipitation - Code and Data

This repository contains the dataset and codes used in the study of sloping soil response to precipitation through machine learning analysis. The dataset includes synthetic data of precipitation, soil moisture, and groundwater level mimicking field observations conducted in a experimental field. The codes include scripts for data preprocessing, analysis, and visualization. Here you will find: The dataset used to build a random forest (RF) model (01_RF_dataset.csv), the script for building the model (01_RF_model.py) using the sciki-learn library in Python (https://scikit-learn.org/stable/index.html), the dataset for the cluster analysis (SyntheticData.mat) and the script for the analysis using the k-means clustering technique implemented in Matlab (https://it.mathworks.com/help/stats/kmeans.html). The data and the codes in the present repository are part of the research entitled "Understanding hydrologic controls of sloping soil response to precipitation through machine learning analysis applied to synthetic data", published in Hydrology and Earth System Sciences - HESS journal. More details can be found for now in the paper preprint: Roman Quintero DC, Marino P, Santonastaso GF, Greco R (2023). Understanding hydrologic controls of sloping soil response to precipitation through machine learning analysis applied to synthetic data. EGUsphere: 1-41. DOI: 10.5194/EGUSPHERE-2022-1078