Architectures & Methodologies
Selected deep learning frameworks, neural architectures, and scientific modeling pipelines published in international peer-reviewed journals.
Research Models
Click any model diagram to view high-resolution architecture details.
Hybrid deep learning framework for precipitation forecasting integrating large-scale climate drivers with dilated causal convolutions.
Machine learning workflow for statistical calibration, bias-correction, and spatial downscaling using CMIP6 global climate model data.
Graph-based climate-crop modeling framework for analyzing climate variability and extreme weather impacts on rainfed agricultural yields.
Direct and indirect potential evapotranspiration prediction combining automated meteorological data systems with deep neural networks.
Comparative machine learning and deep learning benchmark families for rainfall-runoff, streamflow, and basin-scale environmental hydrology.
Hybrid deep learning and non-parametric time-series trend analysis for detecting climate-change signals in multi-decadal meteorological records.
