Our baseline runs followed the ClimateSet single emulator specifications (Kaltenborn et al., 2023): Training Process: Each emulator is trained on data from a single climate model, predicting outputs for an entire sequence of monthly data for each year. Pre-Processing: The data has been pre-processed by ClimateSet to have a spatial resolution of approximately 250 km (144 x 96 longitude-latitude cells) and a temporal resolution of monthly data. The time series is divided into 1-year chunks, resulting in data with a shape of scenarios, years * months, variables, longitude, latitude . Input and Output Shapes: The input data has the shape batch, sequence length, num vars, lon, lat, where the sequence length is 12 (monthly data). The output has the shape batch, sequence length, 2, lon, lat, where the '2' corresponds to temperature (T AS) and precipitation (PR). Training Parameters: The models are trained for 50 epochs with an initial learning rate of 2e-4, using an exponential decay scheduler. For the non-frozen ClimaX models, training begins with a 5-epoch warm-up phase at 1e-8, followed by training at 5e-4. Loss: The latitude-longitude weighted mean squared error (LLMSE) as implemented in (Nguyen et al., 2023) is used.

The development of science has been transforming man's view towards nature for centuries. Observing structures and patterns in an effective approach to discover regularities from data is a key step toward theory-building. With increasingly complex data being obtained, revealing regularities systematically has become a challenge. Correlation is a most commonly-used and effective approach to describe regularities in data, yet for complex patterns, spatial inhomogeneity and complexity can often undermine the correlations. We present an algorithm to derive maps representing the type and degree of correlations, by taking the two-fold symmetry of the correlation vector into full account using the Stokes parameter. The method allows for a spatially resolved view of the nature and strength of correlations between physical quantities. In the correlation view, a region can often be separated into different subregions with different types of correlations. Subregions correspond to physical regimes for physical systems, or climate zones for climate maps. The simplicity of the method makes it widely applicable to a variety of data, where the correlation-based approach makes the map particularly useful in revealing regularities in physical systems and alike. As a new and efficient approach to represent data, the method should facilitate the development of new computational approaches to regularity discovery.

The objective of the paper is to price weather derivative contracts based on temperature and precipitation as underlying climate variables.

Earth System Models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low-cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low-cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio-temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity.

Earth system models (ESMs) are the principal tools used in climate science to generate future climate projections under various atmospheric emissions scenarios on a global or regional scale. Generative deep learning approaches are suitable for emulating these tools due to their computational efficiency and ability, once trained, to generate realizations in a fraction of the time required by ESMs. We extend previous work that used a generative probabilistic diffusion model to emulate ESMs by targeting the joint emulation of multiple variables, temperature and precipitation, by a single diffusion model. Joint generation of multiple variables is critical to generate realistic samples of phenomena resulting from the interplay of multiple variables. The diffusion model emulator takes in the monthly mean-maps of temperature and precipitation and produces the daily values of each of these variables that exhibit statistical properties similar to those generated by ESMs. Our results show the outputs from our extended model closely resemble those from ESMs on various climate metrics including dry spells and hot streaks, and that the joint distribution of temperature and precipitation in our sample closely matches those of ESMs.

Climate models often require post-processing in order to make accurate estimates of local climate risk. The most common post-processing applied is bias-correction and spatial resolution enhancement. However, the statistical methods typically used for this not only are incapable of capturing multivariate spatial correlation information but are also reliant on rich observational data often not available outside of developed countries, limiting their potential. Here we propose an alternative approach to this challenge based on a combination of image super resolution (SR) and contrastive learning generative adversarial networks (GANs). We benchmark performance against NASA's flagship post-processed CMIP6 climate model product, NEX-GDDP. We find that our model successfully reaches a spatial resolution double that of NASA's product while also achieving comparable or improved levels of bias correction in both daily precipitation and temperature. The resulting higher fidelity simulations of present and forward-looking climate can enable more local, accurate models of hazards like flooding, drought, and heatwaves.

Artificial intelligence has made a disheartening discovery – 85 percent of the world's population has already been affected by human-induced climate change. The findings were made by German scientists, led by Max Callaghan from the Mercator Research Institute on Global Commons and Climate Change, who, according to the study, trained the system to'identify, evaluate and summarize scientific publications on climate change and its consequences.' Researchers used machine learning to sift through data published from 1951 through 2018 and found more than 100,000 studies with evidence that shows 80 percent of Earth's inhabited land has been impacted by climate change. The results also uncovered an'attribution gap' around the globe, where evidence is is distributed unequally across countries - 'evidence for potentially attributable impacts are twice as prevalent in high-income than in low-income countries,' according to the study. Artificial intelligence has made a disheartening discovery – 85 percent of the world's population has already been affected by human-induced climate change.

Downscaling is a landmark task in climate science and meteorology in which the goal is to use coarse scale, spatio-temporal data to infer values at finer scales. Statistical downscaling aims to approximate this task using statistical patterns gleaned from an existing dataset of downscaled values, often obtained from observations or physical models. In this work, we investigate the application of deep latent variable learning to the task of statistical downscaling. We present ClimAlign, a novel method for unsupervised, generative downscaling using adaptations of recent work in normalizing flows for variational inference. We evaluate the viability of our method using several different metrics on two datasets consisting of daily temperature and precipitation values gridded at low (1 degree latitude/longitude) and high (1/4 and 1/8 degree) resolutions. We show that our method achieves comparable predictive performance to existing supervised statistical downscaling methods while simultaneously allowing for both conditional and unconditional sampling from the joint distribution over high and low resolution spatial fields. We provide publicly accessible implementations of our method, as well as the baselines used for comparison, on GitHub.