About
I build artificial intelligence and physics-based methods that make water and hazard predictions more accurate, better quantified, and easier to trust. Floods, droughts, and landslides hit hardest where forecasting and risk mapping are weakest, so I focus on methods that work with limited data and explain their own reasoning. My work runs in three threads: mountain and arid hydrology, hazards and infrastructure risk, and sustainable development. Below is a short tour of each, with selected publications and a way to get in touch.
1. Mountain and arid hydrology
Reliable water prediction underpins both supply and safety. I develop machine learning and physics-based methods that improve the accuracy of streamflow forecasts and quantify their uncertainty, and I use explainable AI to make sense of groundwater and hydrologic processes where data are scarce. Much of the streamflow work targets the arid basins of the US Southwest. Selected work: explainable AI for groundwater potential in data-scarce regions (Dahal et al., 2023); ensemble streamflow forecasting with diverse loss functions (Dahal et al., 2026).
2. Hazards and infrastructure risk
Water-driven hazards cascade: rainfall triggers landslides that block rivers that flood the towns and infrastructure downstream. I map and forecast these cascading hazards and the exposure of critical infrastructure, so communities can see the risk before it arrives. Selected work: cascading-hazard characterization on mountain terrain (Talchabhadel et al., 2023); rainfall-triggered landslide zonation for critical infrastructure (Gnyawali et al., 2023); flood-exposure assessment for schools (Bishui et al., 2026).
3. Sustainable development
Beyond mitigation, the pressing question is development: clean water, food, infrastructure, and livelihoods. I use earth observation and machine learning to inform that agenda with evidence. Selected work: carbon and biodiversity stakes of climate-driven wildfires (Dahal et al., 2025); urban agriculture as a sustainability lever (Pradhan et al., 2024); IPCC science applied to the SDG agenda (Pradhan et al., 2025).
Currently
At the University of Kansas (May 2026 – present), I conduct AI, satellite earth observation, and geospatial research on water resources and water-distribution infrastructure under natural hazards, on an NSF-funded project. Recent fellowship: AGU Thriving Earth Exchange Community Science Fellow on the Lumberton, NC flood project (2024 – 2026).
Open to collaborations on:
- mountain and arid hydrology, and AI streamflow forecasting.
- multi-hazard and infrastructure-risk mapping.
- earth observation for water, food, and infrastructure resilience.
News
- May 12, 2026: Started as a Postdoctoral Researcher at the University of Kansas.
- April 10, 2026: Defended my PhD at Arizona State University.
- February 22, 2026: Coverage in The Times of India on school flood-exposure research (article).
- January 24, 2026: Lumberton Flood Dashboard launched (dashboard).
Find your way
- Publications: full list with links and citations.
- CV: appointments, awards, and talks.
- Resources: open course materials and code (Stats, py4all, azwaters).
- News: updates and selected media coverage.
Reach me at geokshitij [at] gmail [dot] com or via Google Scholar.