ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Schmidt, Víctor; Luccioni, Alexandra; Teng, Mélisande; Zhang, Tianyu; Reynaud, A.; Raghupathi, Sunand; Cosne, Gautier; Juraver, Adrien; Vardanyan, V. R.; Hernández-García, Álex; Bengio, Yoshua

doi:10.48550/arxiv.2110.02871

Cited by 3 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DA has been used in a wide variety of applications in computer vision. Examples include adapting a model trained on synthetic images to real images (Peng et al 2017), simple to complex images (Tzeng et al 2017), and virtual worlds with controlled data to the real world (Schmidt et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptation for Simulation-based Dark Matter Searches with Strong Gravitational Lensing

Alexander,

Gleyzer,

Parul

et al. 2023

ApJ

View full text Add to dashboard Cite

The identity of dark matter has remained surprisingly elusive. While terrestrial experiments may be able to nail down a model, an alternative method is to identify dark matter based on astrophysical or cosmological signatures. A particularly sensitive approach is based on the unique signature of dark matter substructure in galaxy–galaxy strong lensing images. Machine-learning applications have been explored for extracting this signal. Because of the limited availability of high-quality strong lensing images, these approaches have exclusively relied on simulations. Due to the differences with the real instrumental data, machine-learning models trained on simulations are expected to lose accuracy when applied to real data. Here domain adaptation can serve as a crucial bridge between simulations and real data applications. In this work, we demonstrate the power of domain adaptation techniques applied to strong gravitational lensing data with dark matter substructure. We show with simulated data sets representative of Euclid and Hubble Space Telescope observations that domain adaptation can significantly mitigate the losses in the model performance when applied to new domains. Lastly, we find similar results utilizing domain adaptation for the problem of lens finding by adapting models trained on a simulated data set to one composed of real lensed and unlensed galaxies from the Hyper Suprime-Cam. This technique can help domain experts build and apply better machine-learning models for extracting useful information from the strong gravitational lensing data expected from the upcoming surveys.

show abstract

Section: Introductionmentioning

confidence: 99%

Domain Adaptation for Simulation-based Dark Matter Searches with Strong Gravitational Lensing

Alexander,

Gleyzer,

Parul

et al. 2023

ApJ

View full text Add to dashboard Cite

show abstract

“…Domain adaptation techniques have been used in a wide variety of applications related to computer vision, such as adapting a model trained on synthetic images to real images [64], simple to complex images [65] and virtual worlds with controlled data to the real world [66].…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptation for Simulation-Based Dark Matter Searches Using Strong Gravitational Lensing

Alexander¹,

Gleyzer²,

Reddy³

et al. 2021

Preprint

View full text Add to dashboard Cite

Clues to the identity of dark matter have remained surprisingly elusive, given the scope of experimental programs aimed at its identification. While terrestrial experiments may be able to nail down a model, an alternative, and equally promising, method is to identify dark matter based on astrophysical or cosmological signatures. A particularly sensitive approach is based on the unique signature of dark matter substructure on galaxy-galaxy strong lensing images. Machine learning applications have been explored in detail for extracting just this signal. With limited availability of high quality strong lensing data, these approaches have exclusively relied on simulations. Naturally, due to the differences with the real instrumental data, machine learning models trained on simulations are expected to lose accuracy when applied to real data. This is where domain adaptation can serve as a crucial bridge between simulations and real data applications. In this work, we demonstrate the power of domain adaptation techniques applied to strong gravitational lensing data with dark matter substructure. We show with simulated data sets of varying complexity, that domain adaptation can significantly mitigate the losses in the model performance. This technique can help domain experts build and apply better machine learning models for extracting useful information from strong gravitational lensing data expected from the upcoming surveys.

show abstract

Idea paper: How are ecosystem services related to biodiversity and ecological integrity in each site under climate change?

Ohsawa

2022

Ecological Research

View full text Add to dashboard Cite

Conventional nature conservation has attempted to protect biodiversity, ecological integrity (i.e., composition and biomass/abundance of native species), and ecosystem services in parallel, assuming generally positive relationships among them. However, many native species are potentially weakened by and maladapted to a new, warmer climate. Such native species may not be able to offer ecosystem services at previous levels. If the relationship between ecosystem services and native species is no longer positive due to climate change, pursuing ecological integrity could be ineffective for maximizing ecosystem services. Hence, there is room to investigate future relationships among biodiversity, ecological integrity, and ecosystem services. This investigation can be done by describing the changes in ecosystem services as a function of biodiversity and ecological integrity. Herein, biodiversity and ecological integrity can be expressed by phylogenetic diversity and species intactness indices based on abundance, respectively. According to my hypothetical figure, the metrics of biodiversity and ecological integrity are potentially not positively but rather negatively related to ecosystem services. The hypothetical figure can be examined and improved using three different approaches: computer simulations (e.g., the LANDIS-II forest simulation model), collection of actual data (e.g., measuring ecosystem services of some sites with psychrophilic and thermophilic species), and questionnaire surveys about cultural services (e.g., using digitally manipulated photographs and generative adversarial networks). Thus, we can successfully enable practitioners to understand new relationships, which will be relevant to ecosystem management under changing climates.

show abstract

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Cited by 3 publications

References 47 publications

Domain Adaptation for Simulation-based Dark Matter Searches with Strong Gravitational Lensing

Domain Adaptation for Simulation-based Dark Matter Searches with Strong Gravitational Lensing

Domain Adaptation for Simulation-Based Dark Matter Searches Using Strong Gravitational Lensing

Idea paper: How are ecosystem services related to biodiversity and ecological integrity in each site under climate change?

Contact Info

Product

Resources

About