ESA CCI Research Fellowship: Francisco-Jose Cuesta-Valero

Project: Ground Heat Flux Estimates from Earth Observations and Hybrid Artificial Neural Networks (AI4GHEObs)

Ground Heat Flux Estimates from Earth Observations and Hybrid Artificial Neural Networks (AI4GHEObs)

Fellowship project summary:

Climate change is basically an energy problem: the Earth absorbs more heat than it is radiating back to the Space. This causes a heat storage in the climate system with time, with ~89% of all the heat going to the ocean. In fact the ocean warms due to the influx of heat, altering physical phenomena that are relevant for society and ecosystems. For example, a warmer ocean occupies more volume, thus an increase in heat storage leads to an increase in sea level rise. However, other relevant processes are related to the heat stored in other components, such as the land surface and subsurface, which is the second heat reservoir only after the ocean. Increasing ground heat storage warms the continental subsurface, allowing permafrost thawing and, under certain conditions, contributing to the development of extreme temperature events. Nevertheless, there are no global estimates of ground heat storage after the year 2000 due to a lack of in situ observations.

The AI4GHEObs project aims to provide with global estimates of ground heat flux and ground heat storage using Earth Observation datasets. Previous analytical models based on land surface temperatures and the solution of the one-dimensional heat diffusion equation cannot account for the influence of surface processes, such as vegetation cover, soil moisture and snow cover. Therefore, machine learning models will be used to derive ground heat flux based on satellite remote sensing products of land surface temperature, soil moisture, land cover, leaf area index and snow cover. Machine learning techniques are flexible enough to predict variables taking into account non-linear relationships between target and feature variables, allowing the combination of categorical data (e.g., land cover type) and numerical data (e.g., land surface temperatures). The AI4GHEObs global dataset of ground heat flux will allow us to study the influence of ground heating on other processes, such as soil respiration and extreme temperature events.

Research fellow: Francisco-Jose Cuesta-Valero

Host Institution: Helmholtz Centre for Environmental Research