Non-Noble Metal and Heteroatom Co-Doped Biochar for Cr(VI) Removal
Processes
Publications
Research outputs in AI climate modeling, hydrology, and sustainable agriculture.
Browse first-page paper previews, open full papers, and download publication files from the archive.
Selected Publications
Recent research highlights
Physics-informed neural networks and variants in weather and hydrological modeling: a systematic review
Natural Hazards Research
Machine Learning and Deep Learning in River-Basin Modeling: A Comprehensive Review
Applied Soft Computing
Deep learning-based potential evapotranspiration prediction in the Nakdong River basin
Ecohydrology & Hydrobiology
Geospatial graph neural network framework for climate variability impacts on crop yields
Theoretical and Applied Climatology
Artificial intelligence-driven precipitation downscaling and projections over Thailand
Big Earth Data
Seasonal WaveNet-LSTM for precipitation forecasting with climate drivers
Water
Research Themes
Publication archive organized by topic, not just by year.
River-basin modeling, runoff estimation, groundwater trends, streamflow variability, evapotranspiration, water-quality monitoring, and basin-scale decision support.
Crop-yield risk, greenhouse water systems, smart irrigation, potential evapotranspiration, crop water requirements, and climate-smart agriculture analytics.
Numerical Weather Prediction (NWP), CMIP6 projections, precipitation downscaling, drought forecasting, ENSO effects, climate signal detection, and agrometeorology.
QGIS workflows, land-use and land-cover change, remote sensing data, geospatial graph neural networks, spatial feature engineering, and regional risk mapping.
Top Paper Summaries
Why the research matters beyond the journal page.
Physics-informed neural networks for weather and hydrological modeling
This review connects physics-guided learning with weather and water-system prediction, showing how PINNs and related variants can combine governing knowledge with data-driven modeling for more interpretable environmental AI.
Machine learning and deep learning in river-basin modeling
This review helps water managers and researchers understand which AI methods fit runoff, streamflow, and basin-scale prediction problems. It turns a complex model landscape into practical guidance for choosing defensible hydrology workflows.
AI-driven precipitation downscaling and projections
Regional planners often need rainfall information at a finer scale than global climate models provide. This work shows how AI can translate broad climate projections into more usable precipitation intelligence for flood, drought, and agricultural planning.
Geospatial graph neural network for crop-yield impacts
Crop risk is spatial: nearby regions, climate drivers, and landscape patterns influence each other. This research uses graph-based AI to represent those relationships and support smarter food-security and climate-adaptation decisions.
Download Library
Publication files with first-page previews
Filter by year, preview the first page, open each paper in a new tab, and download the full file.
Search supports expanded citation keywords, abbreviations, and related research terms.