nimanpra/Systematic-Feature-Engineering---Multi-source-Sat: v1.0.0 — Initial Release

Read full text Summarise with VIRAT
Authors: nimanpra
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Includes the five-stage feature engineering pipeline (70 → 36 features via iterative VIF selection), LR / SVR / Random Forest / XGBoost precipitation prediction models (best: XGBoost R² = 0.628), VIF multicollinearity analysis, ablation study, and the integrated 358-record multi-satellite dataset for Ratnapura District, Sri Lanka (2015–2019).

Fields of Study & Subjects

Hydrological Forecasting Using AI Precipitation Measurement and Analysis Hydrology and Drought Analysis

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN