Physics-guided probabilistic modeling of extreme precipitation under climate change

Abstract

Earth System Models (ESMs) are the state of the art for projecting the effects of climate change. However, longstanding uncertainties in their ability to simulate regional and local precipitation extremes and related processes inhibit decision making. Existing state-of-the art approaches for uncertainty quantification use Bayesian methods to weight ESMs based on a balance of historical skills and future consensus. Here we propose an empirical Bayesian model that extends an existing skill and consensus based weighting framework and examine the hypothesis that nontrivial, physicsguided measures of eSM skill can help produce reliable probabilistic characterization of climate extremes. Specifically, the model leverages knowledge of physical relationships between temperature, atmospheric moisture capacity, and extreme precipitation intensity to iteratively weight and combine ESMs and estimate probability distributions of return levels. Out-of-sample validation suggests that the proposed Bayesian method, which incorporates physics-guidance, has the potential to derive reliable precipitation projections, although caveats remain and the gain is not uniform across all cases. Probabilistic projections of precipitation under climate variability and change are necessary to inform water resources planning and management, design and operations of hydraulic infrastructures, and the nexus of water with food and energy 1-3. Uncertainty assessments associated with predictive insights on precipitation extremes are particularly important for flood resilience and risk assessments 4,5. The primary sources of uncertainties in future climate projections at stakeholder-relevant scales include our inability to project greenhouse gas emissions conditioned on social and technological change, gaps in our understanding of climate science as reflected in computer models and their parameters, natural or intrinsic variability of the climate system, and challenges in translating or downscaling larger-scale climate model simulations to the higher resolutions useful for stakeholders 6,7. Emission trajectories are interpreted as what-if decision scenarios and as projections rather than predictions, and ensembles of model runs based on multiple such trajectories attempt to capture the range of variability in this context. While it is difficult to cast this variability in traditional probabilistic settings, prior literature has examined this variability in great detail. Intrinsic or natural climate variability is assumed to be captured through initial condition ensembles (for given model and forcing), and may be best characterized through nonlinear dynamical measures. While a probabilistic description may be possible, uncertainty characterization for systems that are sensitive to initial conditions is an ongoing research area 8. Uncertainties in the downscaling process are challenging to characterize as well. Owing to computational resource requirements, dynamical downscaling approaches typically cannot even consider the range of plausible projections...

Using wild relatives and related species to build climate resilience in Brassica crops

“…Heat stress has negative impacts on plant growth due to its devastating influence on cell membranes and protein stability, and limits plant growth at all developmental stages, but particularly during flowering (Bita and Gerats 2013 ; Bailey-Serres et al 2019 ). On top of direct effects, rising temperature can have two further adverse secondary effects on local climates: at warmer temperatures, the water holding capacity of the air increases about 7% per °C, which can lead to stronger single rain events and increase the likelihood of flooding (Trenberth 2011 ; Kodra et al 2020 ). At the same time, rising transpiration can dry down soils more quickly and increase the likelihood of droughts (Trenberth 2011 ; Lu et al 2019 ).…”

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

“…Although it is a new topic, several recent works employed PGML, underlying its potential. However, most PGML research concentrate in other fields, e.g., fluids dynamics [22,360,414], lake modeling [358,369,370,372,415], climate modelling [416,417] and material science [21,418,419]. The spread of PGML techniques to other domains is a matter of time.…”

Science-integrated Artificial-intelligence for Flooding and precipitation Extremes (SAFE)

“…Our overarching hypothesis is that intelligent blends of AI and physics can improve predictive understanding of crucialyet long-standingchallenges. Our team members are among the pioneers [62][63][64][65][66][67][68][69][70][71][72][73][74][75][76][77][78][79][80] in developing integrated science-AI models for earth systems: we will build upon our foundational work to inform workshops and plans for DOE that will inspire the development of a suite of solutions in physics-guided AI (PGAI), AIenhanced physics (AIEP), including generative models, causal and interpretable AI, as well as uncertainty or risk assessments. Here we define 'physics' broadly to include biogeochemistry and process knowledge.…”