Artificial intelligence learns continental hydrology

August 27, 2020

Changes to water masses which are stored on the continents can be detected with the help of satellites. The data sets on the Earth's gravitational field which are required for this, stem from the GRACE and GRACE-FO satellite missions. As these data sets only include the typical large-scale mass anomalies, no conclusions about small scale structures, such as the actual distribution of water masses in rivers and river branches, are possible. Using the South American continent as an example, the Earth system modellers at the German Research Centre for Geosciences GFZ, have developed a new Deep-Learning-Method, which quantifies small as well as large-scale changes to the water storage with the help of satellite data. This new method cleverly combines Deep-Learning, hydrological models and Earth observations from gravimetry and altimetry.

So far it is not precisely known, how much water a continent really stores. The continental water masses are also constantly changing, thus affecting the Earth's rotation and acting as a link in the water cycle between atmosphere and ocean. Amazon tributaries in Peru, for example, carry huge amounts of water in some years, but only a fraction of it in others. In addition to the water masses of rivers and other bodies of fresh water, considerable amounts of water are also found in soil, snow and underground reservoirs, which are difficult to quantify directly.

Now the research team around primary author Christopher Irrgang developed a new method in order to draw conclusions on the stored water quantities of the South American continent from the coarsely-resolved satellite data. "For the so called down-scaling, we are using a convolutional neural network, in short CNN, in connection with a newly developed training method", Irrgang says. "CNNs are particularly well suited for processing spatial Earth observations, because they can reliably extract recurrent patterns such as lines, edges or more complex shapes and characteristics."

In order to learn the connection between continental water storage and the respective satellite observations, the CNN was trained with simulation data of a numerical hydrological model over the period from 2003 until 2018. Additionally, data from the satellite altimetry in the Amazon region was used for validation. What is extraordinary, is that this CNN continuously self-corrects and self-validates in order to make the most accurate statements possible about the distribution of the water storage. "This CNN therefore combines the advantages of numerical modelling with high-precision Earth observation" according to Irrgang.

The researchers' study shows that the new Deep-Learning-Method is particularly reliable for the tropical regions north of the -20° latitude on the South American continent, where rain forests, vast surface waters and also large groundwater basins are located. Same as for the groundwater-rich, western part of South America's southern tip. The down-scaling works less well in dry and desert regions. This can be explained by the comparably low variability of the already low water storage there, which therefore only have a marginal effect on the training of the neural network. However, for the Amazon region, the researchers were able to show that the forecast of the validated CNN was more accurate than the numerical model used.

In future, large-scale as well as regional analysis and forecasts of the global continental water storage will be urgently needed. Further development of numerical models and the combination with innovative Deep-Learning-Methods will take up a more important role in this, in order to gain comprehensive insight into continental hydrology. Aside from purely geophysical investigations, there are many other possible applications, such as studying the impact of climate change on continental hydrology, the identification of stress factors for ecosystems such as droughts or floods, and the development of water management strategies for agricultural and urban regions.

This study was funded by the Helmholtz-Association as well as The Initiative and Networking Fund of the Helmholtz-Association through the Advanced Earth Modelling Capacity project (ESM).

Original study:

Irrgang, C., Saynisch-Wagner, J., Dill, R., Boergens, E., & Thomas, M. (2020). Self-validating deep learning for recovering terrestrial water storage from gravity and altimetry measurements. Geophysical Research Letters, 47, e2020GL089258.

Scientific contact:

Dr. Christopher Irrgang
Scientist in GFZ-section Earth System Modelling
Helmholtz Centre Potsdam
GFZ German Research Centre for Geosciences
Telegrafenberg, 14473 Potsdam
Phone: +49-331-288-2847

Media contact:

Josef Zens
Head of Public and Media Relations
Helmholtz Centre Potsdam
GFZ German Research Centre for Geosciences
14473 Potsdam
Phone: +49 331 288-1040

GFZ GeoForschungsZentrum Potsdam, Helmholtz Centre

Related Water Articles from Brightsurf:

Transport of water to mars' upper atmosphere dominates planet's water loss to space
Instead of its scarce atmospheric water being confined in Mars' lower atmosphere, a new study finds evidence that water on Mars is directly transported to the upper atmosphere, where it is converted to atomic hydrogen that escapes to space.

Water striders learn from experience how to jump up safely from water surface
Water striders jump upwards from the water surface without breaking it.

'Pregnancy test for water' delivers fast, easy results on water quality
A new platform technology can assess water safety and quality with just a single drop and a few minutes.

Something in the water
Between 2015 and 2016, Brazil suffered from an epidemic outbreak of the Zika virus, whose infections occurred throughout the country states.

Researchers create new tools to monitor water quality, measure water insecurity
A wife-husband team will present both high-tech and low-tech solutions for improving water security at this year's American Association for the Advancement of Science (AAAS) annual meeting in Seattle on Sunday, Feb.

The shape of water: What water molecules look like on the surface of materials
Water is a familiar substance that is present virtually everywhere.

Water, water everywhere -- and it's weirder than you think
Researchers at The University of Tokyo show that liquid water has 2 distinct molecular arrangements: tetrahedral and non-tetrahedral.

What's in your water?
Mixing drinking water with chlorine, the United States' most common method of disinfecting drinking water, creates previously unidentified toxic byproducts, says Carsten Prasse from Johns Hopkins University and his collaborators from the University of California, Berkeley and Switzerland.

How we transport water in our bodies inspires new water filtration method
A multidisciplinary group of engineers and scientists has discovered a new method for water filtration that could have implications for a variety of technologies, such as desalination plants, breathable and protective fabrics, and carbon capture in gas separations.

Source water key to bacterial water safety in remote Northern Australia
In the wet-dry topics of Australia, drinking water in remote communities is often sourced from groundwater bores.

Read More: Water News and Water Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to