Nature Climate Change · 2022 · 49 citations · 62 references
Life SciencesMarine BiologyMarine SciencesMarine EcologyPhycologyPlankton EcologyEnvironmental StressHarmful Algal BloomsMarine AlgaeMarine Ecosystem FunctionPhytoplankton EcologyPlankton Life CyclesPhytoplankton AdaptationPhytoplankton Community DynamicsPhytoplankton Defense MechanismsPhytoplankton DynamicsPhytoplankton Stress Physiology
Globally, anthropogenic climate change is threatening marine species. However, whether and how global marine phytoplankton, which represent the base of marine food webs, will exceed their tipping points under multiple climate factors remain unclear. Here, by establishing machine learning models, we identified the tipping points of global marine phytoplankton production and resistance under eight environmental stressors. Phytoplankton production and resistance are affected by multiple factors and the temperature and partial pressure of carbon dioxide dominate the risks for reaching their tipping points. If the current emission scenario continues, 50% (40–61% at 90% confidence) and 41% (2–80% at 90% confidence) of tropical areas would reach the tipping points of ongoing phytoplankton production and resistance decline, respectively, in 2100. Compared with single- or few-factor studies, machine learning (for example, ensemble machine learning) provides a powerful and realistic solution for policy-makers facing large-scale ecological responses to global climate changes under multiple environmental stressors. The authors establish machine learning models to identify multifactor tipping points of global marine phytoplankton. They show that temperature and carbon dioxide dominate risks, and project crossing tipping points in tropical area production (50%) and resistance (41%) by 2100 under high emissions.
62
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
Recent advances in convolutional neural networks
Jiuxiang Gu, Zhenhua Wang, Jason Kuen et al. · Pattern Recognition · 2017 · 6.3K citations