Search

To help reduce anthropogenic climate change impacts, various forms of solar radiation modification have been proposed to reduce the rate of warming. One method to intentionally reflect sunlight into space is through the introduction of reflective particles into the stratosphere, known as stratospheric aerosol injection (SAI). Previous research has shown that SAI implementation could lead to future climate impacts beyond surface temperature, including changes in El Niño Southern Oscillation (ENSO) variability. This response has the potential to modulate midlatitude variability and predictability through atmospheric teleconnections. Here, we explore possible differences in seasonal surface temperature predictability under a future with and without SAI implementation, using neural networks and the ARISE-SAI-1.5 simulations. We find significant future predictability changes in both boreal summer and winter under SSP2-4.5 with and without SAI. However, during boreal winter when SAI is implemented, seasonal predictability is more similar to the base climate than when SAI is not implemented, particularly in regions impacted by ENSO teleconnections.

The importance of climate change for driving adverse climate impacts has motivated substantial effort to understand the rate and magnitude of regional climate change in different parts of the world. However, despite decades of research, there is substantial uncertainty in the time remaining until specific regional temperature thresholds are reached, with climate models often disagreeing both on the warming that has occurred to-date, as well as the warming that might be experienced in the next few decades. Here, we adapt a recent machine learning approach to train a convolutional neural network to predict the time (and its uncertainty) until different regional warming thresholds are reached based on the current state of the climate system. In addition to predicting regional rather than global warming thresholds, we include a transfer learning step in which the climate-model-trained network is fine-tuned with limited observations, which further improves predictions of the real world. Using observed 2023 temperature anomalies to define the current climate state, our method yields a central estimate of 2040 or earlier for reaching the 1.5 °C threshold for all regions where transfer learning is possible, and a central estimate of 2040 or earlier for reaching the 2.0 °C threshold for 31 out of 34 regions. For 3.0 °C, 26 °C out of 34 regions are predicted to reach the threshold by 2060. Our results highlight the power of transfer learning as a tool to combine a suite of climate model projections with observations to produce constrained predictions of future temperatures based on the current climate.

Identifying predictable states of the climate system allows for enhanced prediction skill on the generally low-skill subseasonal timescale via forecasts with higher confidence and accuracy, known as forecasts of opportunity. This study takes a neural network approach to explore decadal variability of subseasonal predictability, particularly during forecasts of opportunity. Specifically, this work quantifies subseasonal prediction skill provided by the tropics within the Community Earth System Model Version 2 (CESM2) Large Ensemble and assesses how this skill evolves on decadal timescales. Utilizing the networks’ confidence and explainable artificial intelligence, physically meaningful sources of predictability associated with periods of enhanced skill are identified. Using these networks, we find that tropically-driven subseasonal predictability varies on decadal timescales during forecasts of opportunity. Further, we investigate the drivers of the low frequency modulation of the tropical-extratropical teleconnection and discuss the implications. Analysis is extended to ECMWF Reanalysis v5 data, revealing that the relationships learned within the CESM2-Large Ensemble holds in modern reanalysis data. These results indicate that the neural networks are capable of identifying predictable decadal states of the climate system within CESM2 that are useful for making confident, accurate subseasonal precipitation predictions in the real world.

The human footprint index (HFI) is an extensively used tool for interpreting the accelerating pressure of humanity on Earth. Up to now, the process of creating the HFI has required significant data and modeling, and updated versions of the index often lag the present day by many years. Here we introduce a near-present, global-scale machine learning-based HFI (ml-HFI) which is capable of routine update using satellite imagery alone. We present the most up-to-date map of the HFI, and document changes in human pressure during the past 20 years (2000–2019). Moreover, we demonstrate its utility as a monitoring tool for the United Nations Sustainable Development Goal 15 (SDG15), ‘Life on Land’, which aims to foster sustainable development while conserving biodiversity. We identify 43 countries that are making progress toward SDG15 while also experiencing increases in their ml-HFI. We examine a subset of these in the context of conservation policies that may or may not enable continued progress toward SDG15. This has immediate policy relevance, since the majority of countries globally are not on track to achieve Goal 15 by the declared deadline of 2030. Moving forward, the ml-HFI may be used for ongoing monitoring and evaluation support toward the twin goals of fostering a thriving society and global Earth system.