Swarnendu Banerjee

A challenge in epidemic forecasting is that ML models overfit while mechanistic models miss changing transmission conditions. Our new JR Soc Interface paper tests whether physics-informed neural networks—which embed an epidemiological ODE system inside a neural net—can address this.

Overall, we call for a more nuanced investigation of ecosystems and climate systems to better understand and predict potential tipping phenomena, as current tipping theory is based on very simplified assumptions that fail to capture real-world complexity.

Reassessing the alternative ecosystem states proposition in the African savanna‐forest domain Ecologists are being challenged to predict how ecosystems will respond to climate changes. According to the Multi-Colored World (MCW) hypothesis, climate impacts may not manifest because consumers su...

In another related paper, Higgins et al 2024 (nph.onlinelibrary.wiley.com/doi/full/10....), where we argue that although the forest-savanna bistability proposition is theoretically sound, the existing evidence is not yet convincing.

This work takes a step beyond Reitkerk et al 2021(www.science.org/doi/full/10....), where we argue how ecosystems evade tipping through spatial patterns.

Rethinking tipping points in ecosystems YouTube video by Faculty of Geosciences Utrecht University

You can find an animated YouTube video on this research here: www.youtube.com/watch?v=8Jf8....

In this work, we synthesize mechanisms by which spatial processes can alter the theory of tipping. We further propose that the underlying drivers of positive feedback leading to alternative stable states may provide insight into the tipping evasion mechanisms most relevant to a specific ecosystem.

Rethinking tipping points in spatial ecosystems | The American Naturalist: Vol 0, No ja

Our work on rethinking tipping is set to appear in The American Naturalist. Find the accepted version here www.journals.uchicago.edu/doi/10.1086/...