An upper bound for the background rate of human extinction

Abstract

We evaluate the total probability of human extinction from naturally occurring processes. Such processes include risks that are well characterized such as asteroid impacts and supervolcanic eruptions, as well as risks that remain unknown. Using only the information that Homo sapiens has existed at least 200,000 years, we conclude that the probability that humanity goes extinct from natural causes in any given year is almost guaranteed to be less than one in 14,000, and likely to be less than one in 87,000. Using the longer track record of survival for our entire genus Homo produces even tighter bounds, with an annual probability of natural extinction likely below one in 870,000. These bounds are unlikely to be affected by possible survivorship bias in the data, and are consistent with mammalian extinction rates, typical hominin species lifespans, the frequency of well-characterized risks, and the frequency of mass extinctions. No similar guarantee can be made for risks that our ancestors did not face, such as anthropogenic climate change or nuclear/biological warfare.

Figure 1

Likelihood of extinction rates given our track record of survival so far, with estimated ranges of Hominin extinction rates, mammalian extinction rates, and mass extinction frequency included for reference. Blue horizontal lines indicate likelihood of 10% and 1%. Rates exceeding 6.9 × 10⁻⁵ are ruled out even with the most conservative data. Extending humanity’s track record of survival to match older fossils, the divergence with Homo neanderthalensis, or the origin of Homo creates even stricter bounds.

Figure 2

Models of observer selection bias. Surface plots show likelihood for combinations of μ and θ (where k = 3 for Models 2 and 3) or τ in Model 4. Upper righthand plots show how likelihood shifts when θ → 0 in Model 1, and for a variety of k values in Models 2 and 3. For the first three models, the unbiased model is recovered for large θ, and results start to become biased as the expected observerhood time approaches humanity’s track record of survival. However, even as θ → 0, the bias is limited, and the likelihood of rates exceeding 10⁻⁴ remains at zero. This is only violated in the final fixed time model, or in models 2 and 3 when k is sufficiently large.