New hybrid machine learning forecasts lake ecosystem responses to climate change
Through the middle of the 20th century, phosphorus inputs from detergents and fertilizers degraded the water quality of Switzerland's Lake Geneva, spurring officials to take action in the 1970s to remediate the pollution.
"The obvious remedy was to reverse the phosphorus loading, and this simple idea helped enormously, but it didn't return the lake to its former state, and that's the problem," said George Sugihara, a biological oceanographer at University of California San Diego's Scripps Institution of Oceanography.
Sugihara, Boston University's Ethan Deyle, and their colleagues spent five years searching for a better way to forecast and manage Lake Geneva's ecological response to the threat of phosphorus pollution, to which the effects of climate change must now be added.
The U.S. National Science Foundation-funded team published its new hybrid empirical dynamic modeling, or EDM, approach in the journal Proceedings of the National Academy of Sciences.
"Nature is much more interconnected and interdependent than scientists would often like to think," said Sugihara. EDM can help in this context, Sugihara believes, as a form of supervised machine learning, a way for computers to learn patterns and teach researchers about the mechanisms behind the data.
"You pull one lever and everything else changes, whack-a-mole style," Sugihara said. "Single-factor experiments, the hallmark of 20th century science where everything is held constant, can teach you a lot in principle, but that is not how the world works."
Sugihara calls EDM "math without equations." But EDM is not a "black box" method, said Deyle, "rather, it uses the data to tell you in the most direct way, with minimal assumptions, what is going on. What are the important variables? How do the relationships change through time? It has a mechanism and transparency that comes directly from the data."
What Sugihara's team has attempted departs from traditional modeling methods used in recent decades. As Deyle said, parts of the well-established models are represented by constants.
"Take the fixed and constant force of gravity, or the shape and depth of a lake, for example," he said. "Physical processes in the lake can be very well modeled with simple equations." Not so for the lake's changing ecology and biochemistry.
The organisms driving change in an ecosystem like Lake Geneva's have changed over the last two decades, and the food web is constantly changing, along with the lake biochemistry, the scientists said.
Lake Geneva is one of the most well-studied systems in the world. "It's not a coincidence that it was an opportunity to push the envelope with a machine-learning approach to ecological forecasting," Deyle said.
The authors demonstrate that their hybrid approach leads to substantially better prediction and description of the processes, such as the biogeochemical and ecological, that drive the lake's water quality.
"By advancing ecological modeling capabilities, this team is helping us better understand the natural world, which is challenging, especially under changing environmental conditions," said Betsy Von Holle, a program director in NSF's Division of Environmental Biology.