Climate Forecasting AI
Machine learning and deep learning workflows for precipitation forecasting, drought projection, CMIP6 downscaling, and ENSO teleconnections.
🏆
World's Top 2% Scientist (Stanford/Elsevier 2026) • Sub-Field Rank #950
👑
Top1000 Scholar • World Rank #109 (AI Hydrology)
Senior Researcher @ Gyeongsang National University • Environmental AI & Hydrology
AI Climate Intelligence • Hydrology • Agriculture
Dr. Muhammad Waqas
Environmental AI researcher advancing predictive modeling across climate risk, groundwater dynamics, river-basin hydrology, and smart agricultural systems.
Global Scholarly Honors & Verified Recognitions
Internationally certified scientific excellence and impact rankings
Verified recognition across premier global scientific indexes: Stanford University & Elsevier World's Top 2% Scientists and Scholarly Index World Top1000.
🏆
World's Top 2% Scientist • Stanford University & Elsevier
Edition: 2026 • Single-Year Impact
Verified: TOPSCINET
Global Sub-Field Rank #950 • Top 2% Worldwide
Main Field: Engineering • Sub-Field: Environmental Engineering
Affiliation: Gyeongsang National University • Republic of Korea
Verified and sourced from Elsevier and Stanford University's Top 2% Scientists database (TOPSCINET). Dr. Muhammad Waqas is officially recognized among the top 2% of scientists globally across all fields, securing an elite World Rank of #950 in Environmental Engineering (Global Discipline Rank: 157,452 across all sciences worldwide).
Sub-Field Rank
#950
Environmental Engineering
Global Percentile
Top 2%
Stanford / Elsevier List
Global Rank
157,452
All Scientific Disciplines
Discipline
Engineering
Primary Domain
H-Index
10
Research Impact
Hm-Index
4
Co-authorship Adjusted
Database Source:
Elsevier & Stanford University
•
Verification: TOPSCINET Verified (2026)
•
Listed: Single Year Data
Official Stanford & Elsevier Verified Card • 2026 Edition
👑
Top1000 Scholar • Verified Ranking Certificate
Edition: 2026 • Scholarly Index
World Rank #109 • Thailand Rank #2
Topic: Hydrological Forecasting Using AI
Based on 2021–2025 Impact Window (2025 Data) • Thailand Affiliation
Ranked within the global Top1000 and certified under Dr. Waqas's Thailand Affiliation (Doctoral and AI Climate modeling research at King Mongkut's University of Technology Thonburi — KMUTT), honoring high-impact breakthroughs across AI rainfall forecasting, climate downscaling, and river-basin hydrology.
World Rank
#109
Global Top 1000
Thailand Rank
#2
TH Rank in Category
Statistical Percentile
Top 2.1%
Worldwide Scholars
Impact Score
95.39
Verified Impact
Category D-Index
9
Discipline Metric
H-Index
14
Citation Benchmark
Certificate ID:
SI-6E73-0D58-A036
•
Scholar Hash: SI-c2dfa1b8a95776beedc9fb08f483a29b
Official Verified Ranking Certificate • Scholarly Index 2026 Edition
★ Latest 2026 Breakthrough Publication
Weekly Cyanobacterial Bloom-Risk Early Warning Using Deep LSTM and Hybrid CNN-LSTM Models in Jinyang Lake, South Korea
A multi-week probabilistic cyanobacterial bloom-risk early-warning framework (1–4 week lead time for >1000 cells/mL) integrating basin-scale spatial PCA gradients, ExtraTrees screening, Deep LSTM, and Hybrid CNN-LSTM classifiers with Platt scaling calibration across Jinyang Lake and the Namgang Dam watershed.
★ Featured 2026 Breakthrough Publication
CMIP6-Driven Groundwater-Level Projections and Climate Risk Mapping for South Korea Using a Hybrid Deep Learning Framework
An attention-based hybrid CNN-BiLSTM (HACL) framework integrating 199 telemetric groundwater monitoring stations with multi-GCM CMIP6 climate scenarios and the Climate Groundwater Risk Index (CGRI) across South Korea.
AI Climate Intelligence
From satellite, sensor, weather, and field data to decisions that can be trusted.
I combine environmental domain knowledge with reproducible modeling to connect complex climate, water, and agricultural datasets with clear scientific outputs and real-world policy insights.
Research Focus
Core pillars of my scientific research
Multi-disciplinary innovation connecting artificial intelligence with physical Earth systems.
Hydrology & Water Systems
River-basin modeling, groundwater head prediction, CGRI risk mapping, streamflow forecasting, and automated evapotranspiration estimation.
Advanced Deep Learning
Hybrid architectures including WaveNet-LSTM, Geospatial Graph Neural Networks (GNN), Attention mechanisms, and Physics-Informed Neural Networks (PINNs).
Smart Agriculture & Remediation
Crop water demand modeling, smart greenhouse circulation, circular biorefinery, biochar soil amendment, and heavy metal environmental remediation.