A bit off topic maybe because 'pure' research, but interesting nonetheless in that it shows how AI / ML is becoming increasingly adopted in climate science

From the abstract:

Many problems in climate science require the identification of signals amidst a sea of climate “noise” and across a variety of models which can disagree with one another. Here, we demonstrate that machine learning techniques, specifically artificial neural networks, can help identify forced patterns of temperature and precipitation within climate model simulations as well as the observations. In fact, the neural network is able to identify patterns of forced change of surface temperature as early as the 1960’s in climate model simulations. The results shown here are strongly suggestive of the potential power of machine learning for climate research.

link

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2019GL084944

Hello everyone

Just wanted to say that I am currently leading a research project aimed at trying to develop better (more accurate) and more locally relevant (‘downscaled’) seasonal climate forecasts using ML. In a nutshell the project is / will explore the potential of several ML approaches (including Deep Learning) to derive more local seasonal climate forecast products. We are using large scale fields from several GCMs (e.g. ECMWF, UKMO, Meteo-France, NCEP-CFSv2, etc …) as inputs (with some experimentations with different feature engineering methods) and ‘local’, observed, seasonally aggregated climate variables as target variables. The geographical focus of this project is New Zealand, where I live and work, but the approaches are generalizable.

Even though this project is not strictly speaking aimed at the climate change problem, I think better climate services, including better forecasts at different time-scales, have an important role to play in adaptation strategies.

Happy to hear if other people have similar projects or are interested in discussing more

Also wanted to say thanks to everyone involved in building this forum …

Nico

@Eric-Vanular the main motivation for this project is that the current generation of General Circulation Models (GCMs) used to generate seasonal climate forecasts are still limited by a relatively coarse spatial resolution (typically 2.5 degrees, at most 1 degree in latitude / longitude), this means GCMs are missing important orographic and land-atmosphere interactions, which are highly relevant to New Zealand (or any 'small' country with complex topography ...). They are therefore not well-adapted for the provision of local-scale climate forecasts. The idea is that we use the information contained in the well-validated, large-scale fields from the GCMs (SSTs, geopotential, ...) to train ML models along with observed, seasonally integrated climate variables as target variables, therefore providing potentially more accurate, and also more locally relevant seasonal climate forecast products.

@Rob-Bennett yes ! they actually set up the task as a prediction / classification task in this study, where the target / label to predict is the year where the patterns are coming from, very clever way to look at the issue of separating the climate change signal from the background, climate variability 'noise' ...

@Sam-Hughes Hi Sam, the thinking in a nutshell is that if people can anticipate climate extremes (e.g. droughts, floods, warm seasons) they can take actions to mitigate their impacts, more accurate and locally relevant seasonal climate forecasts would help with this ...

@Eric-Vanular Hi Eric, the district level is our first target (see https://en.wikipedia.org/wiki/Districts_of_New_Zealand) and we have also some application cases with similar spatial scales but across districts (e.g. fruit producing regions).

@Pascal-Ramsey Hi Pascal ... so far the challenges have been related to the 'harmonisation' of the different GCMs hindcasts use to train the models: they come in various formats (grib, netcdf) with various conventions, variable and dimension names etc., and sometimes the documentation available on how the data is organized in these datasets is a bit sparse :-). Also thinking hard about how to structure the various tasks involved in the project, from pre-processing to processing, to feature extraction, model building, evaluation, testing etc ... there are lots of moving parts, and we want to release the code on github, but need to ensure it will be structured in a way that other people could take it and adapt it to their needs.

@Rob-Bennett yes ! they actually set up the task as a prediction / classification task in this study, where the target / label to predict is the year where the patterns are coming from, very clever way to look at the issue of separating the climate change signal from the background, climate variability 'noise' ...

@Eric-Vanular the main motivation for this project is that the current generation of General Circulation Models (GCMs) used to generate seasonal climate forecasts are still limited by a relatively coarse spatial resolution (typically 2.5 degrees, at most 1 degree in latitude / longitude), this means GCMs are missing important orographic and land-atmosphere interactions, which are highly relevant to New Zealand (or any 'small' country with complex topography ...). They are therefore not well-adapted for the provision of local-scale climate forecasts. The idea is that we use the information contained in the well-validated, large-scale fields from the GCMs (SSTs, geopotential, ...) to train ML models along with observed, seasonally integrated climate variables as target variables, therefore providing potentially more accurate, and also more locally relevant seasonal climate forecast products.

A bit off topic maybe because 'pure' research, but interesting nonetheless in that it shows how AI / ML is becoming increasingly adopted in climate science

From the abstract:

Many problems in climate science require the identification of signals amidst a sea of climate “noise” and across a variety of models which can disagree with one another. Here, we demonstrate that machine learning techniques, specifically artificial neural networks, can help identify forced patterns of temperature and precipitation within climate model simulations as well as the observations. In fact, the neural network is able to identify patterns of forced change of surface temperature as early as the 1960’s in climate model simulations. The results shown here are strongly suggestive of the potential power of machine learning for climate research.

link

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2019GL084944

Hello everyone

Just wanted to say that I am currently leading a research project aimed at trying to develop better (more accurate) and more locally relevant (‘downscaled’) seasonal climate forecasts using ML. In a nutshell the project is / will explore the potential of several ML approaches (including Deep Learning) to derive more local seasonal climate forecast products. We are using large scale fields from several GCMs (e.g. ECMWF, UKMO, Meteo-France, NCEP-CFSv2, etc …) as inputs (with some experimentations with different feature engineering methods) and ‘local’, observed, seasonally aggregated climate variables as target variables. The geographical focus of this project is New Zealand, where I live and work, but the approaches are generalizable.

Even though this project is not strictly speaking aimed at the climate change problem, I think better climate services, including better forecasts at different time-scales, have an important role to play in adaptation strategies.

Happy to hear if other people have similar projects or are interested in discussing more

Also wanted to say thanks to everyone involved in building this forum …

Nico