info@marketresearchfuture.com   📞 +1 (855) 661-4441(US)   📞 +44 1720 412 167(UK)   📞 +91 2269738890(APAC)

Deep Learning Estimates Watershed Subsurface Permeability using Stream Discharge

By Aarti Dhapte , 21 November, 2022

Scientists from Pacific Northwest National Laboratory, Oak Ridge National Laboratory, and Los Alamos National Laboratory trained deep neural networks (DNNs) to estimate subsurface permeability from stream discharge hydrographs in a study published in Frontiers in Earth Science.

In watershed models, subsurface permeability is a critical parameter that determines the contribution of subsurface flow to stream flows. It is difficult and expensive to directly measure permeability at the spatial extent and resolution required by the watershed models. Researchers often use inverse modeling to evaluate permeability. Compared to groundwater monitoring data, the wide availability of stream surface flow data provides a novel data source for integrated surface and subsurface hydrologic models to infer soil and geologic features.

First, they trained the DNNs to map the correlations between soil and geologic layer permeabilities and simulated stream discharge from the examined watershed's integrated surface-subsurface hydrologic model. The DNNs outperformed the classic inverse modeling method in terms of permeability estimates. Using observed stream discharge from the research site, the DNNs assessed the permeability of a natural watershed (Rock Creek Catchment in the headwaters of the Colorado River). The watershed model accurately predicted the stream flows, with permeability calculated by DNNs. This study highlights the importance of upcoming deep learning methods for assisting with integrated watershed modeling by enhancing parameter estimation, which will eventually reduce uncertainty in predictive watershed models.

The permeability of subsurface rocks and soils measures how well liquids flow through them. It is essential in determining subsurface flow and transport mechanisms in watersheds. However, measuring permeability directly at the size and precision required by watershed models is challenging and expensive. Stream flow monitoring data, on the other hand, is publicly available. The connections between permeability and stream flow open a new avenue for evaluating subsurface permeability. Deep learning, a sort of artificial intelligence, was used in this study. Deep understanding assesses a watershed's subsurface permeability from stream discharge data more precisely than standard methods. This enhancement will aid in calibrating watershed models and minimize the uncertainty in stream discharge prediction.

The deep learning algorithm produced realistic estimates of a genuine watershed system's permeability. The projected and observed stream discharges were more closely matched in the results. This study demonstrates how deep learning may be a valuable technique for estimating watershed parameters from indirect but meaningful information like stream flow. This study opens new avenues for enhancing the subsurface characterization of vast watersheds by successfully employing deep learning to map the link between permeability and stream discharge. It opens the door for more generalized ways to calibrate watershed models with numerous parameters and data formats in the future.
 

Traditional Machine Learning and Deep Learning Performance Comparison

Learning.jpg

Latest News

2050.png
Big Tech Backs Nuclear Expansion: Pledges to Triple Global Capacity by 2050

Leading technology giants Amazon, Google, and Meta have teamed up with other big energy users in a historic action at the CERAWeek 2025 energy conference in Houston to promote an ambitious initiative: doubling world nuclear power capacity by 2025…

Read More

Shifts.png
China’s Refining Industry Sees 2.1% Growth in Early 2025 Amid Rising Fuel Demand and Geopolitical Shifts

China's refining sector showed resilience and adaptability in the first months of 2025, raising crude oil throughput by 2.1 percent over the year before. According to the National Bureau of Statistics, this increase resulted in a processing volume of…

Read More

2025.png
Elsevier Unveils ScienceDirect AI in 2025 to Revolutionize Research Efficiency

In March 2025, Elsevier launched ScienceDirect AI, a world-renowned leader in science and health information science. This state-of-the-art generative AI tool can potentially transform the industry with its revolutionary advances in research. This…

Read More

Drop.png
EV Revolution: Battery Prices Drop Below USD 100/kWh Amid China's Dominance of the Market in 2025

The global electric vehicle (EV) industry has reached a pivotal milestone. The average price of lithium-ion battery packs has dropped below the USD 100 per kilowatt-hour (kWh) threshold, a benchmark long considered critical for achieving price parity…

Read More

2025.png
China Accelerates Push for Domestic EV Chips Amid Global Trade Tensions in 2025

In 2025, China will focus on self-sufficiency in high-tech industries by further integrating domestically produced semiconductor chips into the country\'s electric vehicle (EV) industry. By doing so, China aims to reduce reliance on foreign…

Read More

Author Pic
Aarti Dhapte

Team Lead - Research