4,409 Hits in 5.7 sec

Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks [article]

Victor Schmidt, Alexandra Luccioni, S. Karthik Mukkavilli, Narmada Balasooriya, Kris Sankaran, Jennifer Chayes, Yoshua Bengio
2019 arXiv   pre-print
We present a project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs).  ...  This visual transformation is paired with climate model predictions to assess likelihood and type of climate-related events in the long term (50 years) in order to bring the future closer in the viewers  ...  The unique aspect of the CycleGAN approach is the cycle consistency loss, which is used along with the traditional adversarial loss to reduce the space of possible domain-todomain mapping functions by  ... 
arXiv:1905.03709v1 fatcat:a7eanimigzahld3bjg234wgyuy

Comparison of Al-Based Approaches for Statistical Downscaling of Surface Wind Fields in the North Atlantic

Vadim Rezvov, Mikhail Krinitskiy, Alexander Gavrikov, Sergey Gulev
2021 Zenodo  
For this, cubic interpolation, various architectures of convolutional networks, and generative adversarial network are applied.  ...  In this paper, we present the novel approach for the downscaling of of near-surface winds in the North Atlantic. Surface wind is one of the most important physical fields in climate research.  ...  The studies were carried out using the resources of the Center for Shared Use of Scientific Equipment "Center for Processing and Storage of Scientific Data of the Far Eastern Branch of the Russian Academy  ... 
doi:10.5281/zenodo.5760066 fatcat:cuvebscgrnbahbijg5vmgu376e

Learning to correct climate projection biases

Baoxiang Pan, Gemma J. Anderson, André Goncalves, Donald D. Lucas, Céline J.W. Bonfils, Jiwoo Lee, Yang Tian, Hsi‐Yen Ma
2021 Journal of Advances in Modeling Earth Systems  
Unfortunately, the fidelity of climate projections is often undermined by GCMs' biases due to their over-simplification, coarse grid cells resolution, or misrepresentation of the climate processes (  ...  Introduction Two Approaches Toward Improving Climate Projection Accuracy Understanding, predicting, and adapting to climate change is a problem of growing urgency.  ...  Acknowledgments This work was performed under the auspices of the U.S.  ... 
doi:10.1029/2021ms002509 fatcat:cwkwskpeqreytlgjvqtxafddxq

Semi-Supervised Super-Resolution [article]

Ankur Singh, Piyush Rai
2022 arXiv   pre-print
We also offer the applicability of our approach in statistical downscaling to obtain high-resolution climate images.  ...  To reduce the cost of generating high-resolution climate information, Super-Resolution algorithms should be able to train with a limited number of low-resolution, high-resolution pairs.  ...  ESRGAN uses an adversarial network architecture for SR.  ... 
arXiv:2204.08192v2 fatcat:tdijhkptgffdxen7fw5oqdd4lm

Adjusting spatial dependence of climate model outputs with cycle-consistent adversarial networks

Bastien François, Soulivanh Thao, Mathieu Vrac
2021 Climate Dynamics  
As proof-of-concept, we propose to adapt a computer vision technique used for Image-to-Image translation tasks (CycleGAN) for the adjustment of spatial dependence structures of climate model projections  ...  The second one assesses the influence of nonstationary properties of climate simulations on the performance of MBC-CycleGAN to adjust spatial dependences.  ...  MV acknowledges support from the CoCliServ project, which is part of ERA4CS, an ERA-NET initiated by JPI Climate and cofunded by the European Union.  ... 
doi:10.1007/s00382-021-05869-8 fatcat:w62fhb2zpzcpnakyqpkztonoba

Using Simulated Data to Generate Images of Climate Change [article]

Gautier Cosne, Adrien Juraver, Mélisande Teng, Victor Schmidt, Vahe Vardanyan, Alexandra Luccioni, Yoshua Bengio
2020 arXiv   pre-print
awareness of the potential future impacts of climate change.  ...  Generative adversarial networks (GANs) used in domain adaptation tasks have the ability to generate images that are both realistic and personalized, transforming an input image while maintaining its identifiable  ...  We thank Léopold Herlaud for his work on lighting and compositing and the creation of shaders for the simulated dataset.  ... 
arXiv:2001.09531v1 fatcat:jowlhjg4yjcttgwbf3flz43qpi

Functionality-Preserving Adversarial Machine Learning for Robust Classification in Cybersecurity and Intrusion Detection Domains: A Survey

Andrew McCarthy, Essam Ghadafi, Panagiotis Andriotis, Phil Legg
2022 Journal of Cybersecurity and Privacy  
In this literature survey, our main objective is to address the domain of adversarial machine learning attacks and examine the robustness of machine learning models in the cybersecurity and intrusion detection  ...  This research was funded by the Partnership PhD scheme at the University of the West of England in collaboration with Techmodal Ltd.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/jcp2010010 fatcat:wh2qqlamovgq7ovqbcdvx4pdnm

Deep neural networks for climate relation extraction

2021 Global NEST Journal  
Then, the parameters of time series consisting of eight variables are encoded by the first hidden-layer in the proposed model.  ...  As an important application, through extracting these co-variation relations, we can further predict the change of climate to provide early warning for natural disasters, e.g., Greenhouse effect.  ...  Figure4displays the trajectory of climate change in an annual cycle, and we visualize the trajectory using 2-dimension.  ... 
doi:10.30955/gnj.003886 fatcat:5gzcv5o2c5fqhfthuasjxc4tsy

NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES)

Amy McGovern, Ann Bostrom, Phillip Davis, Julie L. Demuth, Imme Ebert-Uphof, Ruoying He, Jason Hickey, David John Gagne II, Nathan Snook, Jebb Q. Stewart, Christopher Thorncroft, Philippe Tissot (+1 others)
2022 Bulletin of The American Meteorological Society - (BAMS)  
This AI institute was funded in 2020 as part of a new initiative from the NSF to advance foundational AI research across a wide variety of domains.  ...  We introduce the National Science Foundation (NSF) AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES).  ...  This material is based upon work supported by the National Science Foundation under Grant No. ICER-2019758  ... 
doi:10.1175/bams-d-21-0020.1 fatcat:rxpvlu7k7zazni4dob5qncsvn4

Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [article]

Samar Khanna, Bram Wallace, Kavita Bala, Bharath Hariharan
2022 arXiv   pre-print
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions.  ...  Our method demonstrates improved generalisability from 1) passing geographically correlated climate variables along with the satellite data to a Transformer model and 2) regressing on the model features  ...  A group of methods that offers much promise, however, is that of adversarial adaptation, the primary works being Domain Adversarial Neural Networks and Multi-Domain Adversarial Networks (DANN and MDAN  ... 
arXiv:2204.07030v1 fatcat:kbu5fnyd45gmjnhdux5jl45rp4

Cycle-StarNet: Bridging the gap between theory and data by leveraging large datasets [article]

Teaghan O'Briain, Yuan-Sen Ting, Sébastien Fabbro, Kwang M. Yi, Kim Venn, Spencer Bialek
2020 arXiv   pre-print
The first of which is the calibration of synthetic data to become consistent with observations.  ...  A mock dataset is used to show that absorption lines can be recovered when they are absent in one of the domains.  ...  Acknowledgments TO and SB acknowledge the support provided for a portion of this research by the Natural Sciences and Engineering Research Council of Canada (NSERC) Undergraduate Student Research Awards  ... 
arXiv:2007.03109v3 fatcat:tsjwi5dlcrgj7htkpbifphcczm

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods [article]

Victor Schmidt, Alexandra Sasha Luccioni, Mélisande Teng, Tianyu Zhang, Alexia Reynaud, Sunand Raghupathi, Gautier Cosne, Adrien Juraver, Vahe Vardanyan, Alex Hernandez-Garcia, Yoshua Bengio
2021 arXiv   pre-print
Projecting the potential consequences of extreme climate events such as flooding in familiar places can help make the abstract impacts of climate change more concrete and encourage action.  ...  Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both policy-making and individual behaviour.  ...  Visualizing the consequences of climate change using cycle-consistent adversarial networks. arXiv preprint arXiv:1905.03709, 2019. Schwartz, R., Dodge, J., Smith, N. A., and Etzioni, O.  ... 
arXiv:2110.02871v1 fatcat:rbxdaeimoffcljhtvhg5atxhum

Cycle-Consistency for Robust Visual Question Answering [article]

Meet Shah, Xinlei Chen, Marcus Rohrbach, Devi Parikh
2019 arXiv   pre-print
As a step towards improving robustness of VQA models, we propose a model-agnostic framework that exploits cycle consistency.  ...  Without the use of additional annotations, we show that our approach is significantly more robust to linguistic variations than state-of-the-art VQA models, when evaluated on the VQA-Rephrasings dataset  ...  Since cycle-consistent models have several interconnected sub-networks learning different transformations, it is important to ensure that each of these sub-networks are working in harmony.  ... 
arXiv:1902.05660v1 fatcat:4qkbpcns3bhfzd7xnejby5soba

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Mikael Sabuhi, Ming Zhou, Cor-Paul Bezemer, Petr Musilek
2021 IEEE Access  
Recently, generative adversarial networks (GANs) have attracted much attention in anomaly detection research, due to their unique ability to generate new data.  ...  In summary, GANs are used in anomaly detection to address the problem of insufficient amount of data for the anomalous behaviour, either through data augmentation or representation learning.  ...  A Cycle-GAN uses two different GANs coupled together to perform this transformation. It uses cycle-consistency loss to preserve the original image after a cycle of translation between two domains.  ... 
doi:10.1109/access.2021.3131949 fatcat:wsutmjn6zrhnriofes6unh3ueu

Learning color space adaptation from synthetic to real images of cirrus clouds [article]

Qing Lyu, Minghao Chen, Xiang Chen
2020 arXiv   pre-print
We explore to train segmentation networks with synthetic data due to the natural acquisition of pixel-level labels.  ...  Cloud segmentation plays a crucial role in image analysis for climate modeling. Manually labeling the training data for cloud segmentation is time-consuming and error-prone.  ...  The dataset consists of 284 images from artist A and 425 images from artist B. We use 90% of them for training and 10% for testing. The two sets of data have relatively consistent styles.  ... 
arXiv:1810.10286v2 fatcat:rth7gnnhknea5mlc7stmkzpvga
« Previous Showing results 1 — 15 out of 4,409 results