The study introduces δHBV-Pot, a physics-informed deep learning hydrologic model that integrates the HBV conceptual model with probabilistic pothole fill–spill–connection processes to better simulate hydrology in Prairie Pothole Region catchments. Tested across 98 catchments, it outperforms traditional and purely data-driven models and can regionalize high-flow behavior and pothole water storage dynamics even in ungauged basins without detailed pothole inventories.
Link to the paper: doi.org/10.1029/2025WR040280@a_ameli2
Key points:
1. The Prairie Pothole Region may be the toughest hydrological puzzle on the planet. Millions of wetlands fill, spill, and merge unpredictably — the same rain can produce wildly different streamflow depending on how full the potholes are.
2. Standard models fail here. Pure deep learning struggles too — it can't learn the complex storage dynamics from weather data alone.
3. Our new model embeds fill-spill physics directly into a neural network. It predicts both streamflow and pothole storage dynamics in ungauged catchments — no detailed wetland inventory required.
#Hydrology#DeepLearning#PhysicsInformedML#HydrologicModeling#PrairiePotholeRegion#UngaugedCatchments#WaterResources#EnvironmentalModeling#HBVModel#HydrologicalProcesses
📢[Research Article] Modeling deforestation drivers in the Brazilian Amazon: a comparison of quantitative approaches by Alisson Castro Barreto, Tailon Martins & Adriano Mendonça Souza
👉Article link: doi.org/10.1080/20964471.202…
💌#Deforestation in the Brazilian #Amazon, with approximately 17% of the #biome lost, remains a critical global issue. This study finds that while traditional models like #OLS and #ARIMA offer useful insights, the #BVAR model more effectively captures the complex temporal dynamics of #deforestation by modeling lagged effects and feedback loops. Granger causality tests, impulse response analysis, and variance decomposition collectively reveal that cattle ranching is the dominant short-term driver, while timber extraction emerges as the primary long-term influence on deforestation.
#environmentalmodeling#bigearthdata#digitalearth#geoscience#GIS#remotesensing#Brazil#statisticalmethod
🌟Editorial Board Member of the Water Emerging Contaminants & Nanoplastics: Prof. Dr. Julian Aherne
🏫School of the Environment, Trent University, Peterborough, Canada.
🌈Research Interests
#Pollutants, #EnvironmentalModeling,#Microplastics
📢 Interested in integrated socio-environmental models?
Explore our latest paper introducing a novel approach for auto-calibration and validation of integrated models, focusing on coupled socioeconomic and environmental systems🌍📊#EnvironmentalModelingdoi.org/10.1016/j.jenvman.20…
Happening now- Diving deep into Environmental Modeling and Decision Making with Dr. Caterina Valeo at #PEOPLE2023inMTL online session! Her expertise is shedding light on crucial insights for a sustainable future. This is an enlightening presentation! #EnvironmentalModeling
Picked out these environmental concepts, waiting for my mentor to approve one and flush out 🧱🏗🧪
Which concept you like the most?
***All environmental concepts aren’t designed by me***
#EnvironmentalModeling