The July 2022 European heat wave turned into a UK national emergency, yet climate models still cannot reliably predict the "feels-like" temperatures that actually cause heat stroke and death. Current atmospheric models rely on physical equations for large-scale weather but use crude approximations—called parameterizations—for smaller processes like radiation and surface moisture. These approximations introduce errors that accumulate over decades of simulation. A researcher at the University of Reading plans to fix this by embedding machine learning directly inside a physics-based climate model, using decades of global observations to automatically correct those approximations as the model runs. This "online learning" approach ensures physical consistency: if the model learns that rain falls more over mountains, soil moisture and humidity adjust accordingly—something offline methods cannot do. If successful, the project will produce a global catalogue of feels-like temperature probabilities for the 2050s, broken down by season and time of day. Policymakers and the public could use it like a long-range weather forecast to assess heat-stress risk for any location, enabling targeted adaptation—rescheduling outdoor events, designing cooling infrastructure, or issuing early warnings. The broader scientific advance is a prototype hybrid climate model that reveals missing physics in current simulations, potentially improving predictions of droughts, floods, and other hazards beyond heat alone.
View original technical description
Climate models provide crucial information for climate change mitigation and adaptation, but their predictions also lack necessary accuracy with respect to many atmospheric variables. Correctly predicting the probability of heat waves and especially the risk of associated heat illnesses, including heat strokes, has a great importance for society. The July 2022 European heat wave caused a UK national emergency with further socio-economic impacts due to the following drought. However preparation is possible as, for example, major outdoor sport events have adapted schedules to reduce the risk of heat illnesses. Conventional atmospheric models predicting heat waves are built on physical laws for resolved dynamics but include so-called parameterizations of processes that are not explicitly resolvable, such as radiation, precipitation and surface fluxes. Decades of global observational data are available which machine learning can learn from and, if embedded inside an atmospheric model, could automatically correct the simulated climate. With this NERC Independent Research Fellowship, I want to build a hybrid physics and data-driven atmospheric model that learns automatically from global data of feels-like temperatures to quantify the heat stress on the human body. I will develop so-called online learning for data-driven parameterizations in the atmospheric general circulation model SpeedyWeather.jl that I wrote over the last year. If the simulated precipitation learned to rain more over mountains, then the current offline learning methods would not increase soil moisture, nor impacting surface humidity and temperature. The proposed online learning however will provide physical consistency with machine learning in a climate model. The main objective is to create a global dataset of feels-like temperature probabilities for the 2050s. The public and policymakers will have access to a catalogue quantifying the risk of critical heat exposure in their global location. This catalogue is like a weather forecast but for climate, for every season and time of day, providing vital information to mitigate and adapt to the expected human heat stress. With project partners in the UK and Germany, I will build on top of previous work on heat forecasts for the Tokyo 2020 Olympics. The major scientific advance is the use of explainable machine learning inside a physics-based atmospheric model. With project partners in the USA, I will develop a hybrid climate model that can reveal missing physics in current modelling efforts by learning corrections to existing parameterizations. Only this combination of a model obeying physical laws with online learning for unresolved processes will allow climate simulations to be consistently enhanced with machine learning. This methodology will generally allow climate science to better understand the missing physics in current climate models. The proposed hybrid climate models which include machine-learned physics does not exist yet, but this project will develop a prototype. Only with online learning can we combine physics knowledge and observations towards a new generation of reliable climate predictions. For individuals and policymakers, it is necessary to translate such predictions into crucial information. To better prepare against future heat waves, we have to predict and communicate effectively the feels-like temperatures and associated risks of heat illnesses.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know