2026 CSDMS meeting-033
From CSDMS
(if you haven't already)
Log in (or create account for non-CSDMS members)
Forgot username? Search or email:CSDMSweb@colorado.edu
Browse abstracts
Integrated Data Analytics and Machine Learning for Scalable Environmental Data Analysis
Senait Gebriye,
Florida Gulf Coast University Fort Myers Florida, United States. sagebriye3718@eagle.fgcu.edu
Jonathan Gebriye, Florida Atlantic University Boca Raton Florida, United States. jgebriye2024@fau.edu
Environmental systems generate large, heterogeneous datasets from sensors, remote sensing, field observations, and model outputs, creating a need for integrated analytical workflows that improve interpretation and prediction. This presentation introduces a framework for environmental data analysis that combines data preprocessing, geospatial analysis, statistical modeling, machine learning, visualization, and process-based simulation within a unified workflow. The approach supports the detection of spatial and temporal patterns, the identification of anomalies, the forecasting of system behavior, and the improved understanding of complex watershed and landscape dynamics.
Machine learning methods can complement conventional environmental modeling by extracting nonlinear relationships from large datasets, while statistical and visualization tools strengthen the interpretability and communication of results. When integrated with simulation models, these tools support more robust calibration, validation, uncertainty assessment, and scenario evaluation. The framework is designed to enhance reproducibility, efficiency, and decision support in applications such as hydrologic analysis, land surface assessment, and environmental change detection.
By linking multiple analytical tools into a coherent workflow, this approach advances environmental data science from isolated analysis toward scalable, transparent, and actionable modeling systems for research and management.
