Experimental Comparative Study on Self-Imputation Methods and Their Quality Assessment for Monthly River Flow Data with Gaps: Case Study to Mures River
2025
Zsolt Magyari-Sáska | Ionel Haidu | Attila Magyari-Sáska
Incomplete environmental datasets pose significant challenges in developing accurate predictive models, particularly in hydrological research. This study addresses data missingness by investigating gap imputation methodologies for datasets with 5–20% data absence, focusing on the Mureș River in Romania. Utilizing a novel approach, we applied various imputation techniques, including the ratio method, Kalman filtering, and machine learning algorithms (XGBoost, Gradient Boosting, Random Forest and CatBoost), while developing an innovative self-assessment metric for evaluating imputation performance without relying on external reference data. Through systematic analysis of hydrological station data from four monitoring points, we artificially introduced data gaps to rigorously test method applicability. The research demonstrates the feasibility of constructing a robust self-evaluation framework for selecting optimal imputation techniques, potentially enhancing data reliability and analytical precision in environmental and geospatial research. Our findings contribute a structured methodology for addressing data incompleteness, offering researchers a quantitative approach to improving dataset integrity and predictive modeling in complex environmental systems.
Afficher plus [+] Moins [-]Informations bibliographiques
Cette notice bibliographique a été fournie par Directory of Open Access Journals
Découvrez la collection de ce fournisseur de données dans AGRIS
