University of Kurdistan, Iran.
Dr. Ataollah Shirzadi is an Assistant Professor at the University of Kurdistan, Iran, specializing in Watershed Management Engineering. With over 90 peer-reviewed publications, he has become an internationally recognized figure in the field of natural hazard modeling. His expertise spans flash flood forecasting, shallow landslide prediction, soil erosion modeling, and geospatial risk assessment, all enhanced through artificial intelligence techniques. Notably, he was listed among the top 2% and 1% of global scientists in 2022 and 2023 by Stanford University and ISC. Dr. Shirzadi has contributed to several high-impact collaborative projects, including an international Iran-China initiative on flood susceptibility. He serves as a reviewer and editorial member for multiple international journals and actively mentors graduate researchers. His research bridges theoretical modeling and real-world disaster management, making significant strides in environmental resilience.
🔎Author Profile
🏅Awards and Honors
-
Ranked among the Top 2% Scientists in the World
-
Ranked among the Top 1% Scientists in the Islamic World
-
Elite and Talent Recognition Awards
-
National University Admission Ranks
-
Excellence Awards
🏆Strengths for the Award
-
High-Impact Research Contributions
Dr. Shirzadi has co-authored over 90 international publications, with many articles appearing in top-tier journals such as Science of The Total Environment, Journal of Hydrology, Environmental Modelling & Software, Geomatics, Natural Hazards and Risk, and Remote Sensing. His research has garnered significant citations (e.g., 756 citations for a 2018 paper and 699 for a 2019 paper), reflecting the impact and relevance of his work in the scientific community.
-
Pioneering Work in Natural Hazard Modeling
His expertise lies in landslide, flash flood, and flood susceptibility modeling, with a strong emphasis on machine learning, deep learning, and hybrid AI techniques. Notably, he has developed several novel hybrid intelligence models integrating techniques like ANFIS, Genetic Algorithms, SVMs, Decision Trees, and ensemble approaches, widely cited and validated across diverse geographies.
-
Recognition & Global Ranking
He has been recognized among the top 2% and 1% of scientists globally by Stanford University and the Islamic World Science Citation Center (ISC) in 2022 and 2023 — a rare distinction that underlines his international academic standing.
-
Editorial and Reviewer Excellence
He holds editorial roles in journals such as Frontiers in Earth Science and has reviewed for more than 30 ISI-indexed journals, including Scientific Reports, Journal of Hydrology, CATENA, and Environmental Earth Sciences. This affirms his reputation as a trusted evaluator of cutting-edge scientific work.
-
Academic Mentorship and Leadership
Dr. Shirzadi has supervised over 17 M.Sc. and Ph.D. students, contributing actively to capacity building in environmental modeling and risk assessment. He has also been involved in international collaborations, including a recent Iran-China flood monitoring project, reflecting both leadership and global outreach.
🎓 Education
Dr. Shirzadi earned his Ph.D. in Watershed Management Engineering (2014–2017) from Sari Agricultural Sciences and Natural Resources University, where his thesis focused on spatial prediction of shallow landslides using advanced data mining algorithms. He previously obtained an M.Sc. in Mass Movements (2007–2009) with a GPA of 19/20, also from Sari University, where he developed regional models for rockfall hazard mapping. His B.Sc. in Hydrology and Climatology (2003–2007) was awarded by the University of Agricultural Science and Natural Resources of Gorgan . Over the years, Dr. Shirzadi has cultivated robust expertise in geospatial modeling, sediment transport, and flood risk analysis. He also holds certifications in GIS, SPSS, AutoCAD, and multiple machine learning platforms, demonstrating both strong academic credentials and technical fluency.
🔬 Research Focus on Natural Hazards
Dr. Shirzadi’s research centers on the integration of AI, machine learning, and geospatial analysis to assess and mitigate natural hazards. His core focus includes:
-
Flood Susceptibility Mapping using hybrid machine learning models (e.g., ANFIS, rotation forests).
-
Shallow Landslide Prediction with ensemble algorithms combining decision trees, support vector machines, and neural networks.
-
Risk Zonation for erosion and sediment transport based on satellite data and multi-criteria analysis.
-
Uncertainty Quantification in hazard models to improve resilience strategies.
-
Remote Sensing Applications using Sentinel-1/2 and Landsat data for urban and rural hazard detection.
His goal is to create smart, scalable, and interpretable models that guide land use planning, policy-making, and emergency preparedness in climate-sensitive regions.
📘 Publication Top Notes
-
A Comparative Assessment of Decision Trees Algorithms for Flash Flood Susceptibility Modeling
Authors: Khosravi K., Pham B.T., Chapi K., Shirzadi A., et al.
Journal: Science of The Total Environment (2018)
Summary: Compared multiple decision tree algorithms to model flash flood susceptibility in Iran’s Haraz watershed, showing ensemble methods outperformed traditional single classifiers.
-
Flood Susceptibility Modeling Using MCDM and Machine Learning
Authors: Khosravi K., Shahabi H., Adamowski J., Shirzadi A., et al.
Journal: Journal of Hydrology (2019)
Summary: Evaluated and contrasted MCDM techniques and AI models; hybrid ML models proved superior in spatial flood risk analysis.
-
A Novel Hybrid AI Approach for Flood Susceptibility
Authors: Chapi K., Singh V.P., Shirzadi A., et al.
Journal: Environmental Modelling & Software (2017)
Summary: Developed a hybrid model combining several AI algorithms to predict flood risk, improving classification accuracy in complex terrains.
-
Flood Susceptibility Using ANFIS-GA-DE Hybrid
Authors: Hong H., Panahi M., Shirzadi A., et al.
Journal: Science of the Total Environment (2018)
Summary: Applied ANFIS enhanced with genetic and differential evolution algorithms for flood prediction in China’s Hengfeng area.
-
Forecasting Floods Using ML & Statistical Models
Authors: Shafizadeh-Moghadam H., Shahabi H., Shirzadi A., et al.
Journal: Journal of Environmental Management (2018)
Summary: Combined ML and traditional statistical techniques to forecast flood-prone zones, optimizing accuracy and runtime efficiency.
🚀Conclusion
Dr. Ataollah Shirzadi stands out as an exceptionally qualified candidate for the Best Researcher Award, with an impressive combination of scholarly output, innovative AI-based methodologies, global recognition, and academic service. His work not only advances theoretical models but also addresses urgent environmental and societal challenges. With continued growth in communication and cross-disciplinary application, he is poised to make even greater contributions to science and practice.
