Evolution of machine learning in environmental science—A perspective

Hsieh, William W.

doi:10.1017/eds.2022.2

Cited by 16 publications

(10 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means that they can be, on the one hand, more prone to overfitting, but, one the other hand, can also learn more complex, non-linear relationships in the data. Therefore, their use in different scientific disciplines, not least in climate sciences, has been rapidly increasing in recent years [Kashinath et al, 2021, Hsieh, 2022. Due to their complexity many different design choices in the exact layout of the network are possible, here we use an out-of-the-box setup for image classification without hyper-parameter tuning but adjusted to the resolution of the daily temperature maps used in the input layer.…”

mentioning

confidence: 99%

Identifying climate models based on their daily output using machine learning

Brunner¹,

Sippel²

2023

Preprint

View full text Add to dashboard Cite

Climate models are primary tools to investigate processes in the climate system, to project future changes, and to inform decision makers. The latest generation of models provides simulations of unprecedented complexity and resolution, resulting in increasingly realistic representations of the real climate system. At the same time, there is growing awareness that not all models produce equally independent and plausible simulations. Therefore, methods are being developed to evaluate how model dependence affects output similarity and how well models match observed climate. Such methods typically draw on climatological averages over several decades to minimize internal variability. Here we show that models can robustly be identified as different from observations based on temperature output from only a single day using two statistical and machine learning classifiers. The first classifier, a logistic regression, achieves almost perfect accuracy in identifying models never seen in training. An analysis of the derived regression coefficients reveals that this skill is founded in several climatological model biases emerging on daily time-scales already. The second classifier, a convolutional neural network, is even able to correctly identify the majority of 43 different models based on spatial dependencies between daily global weather patterns alone, i.e.,after removing the climatological model biases. Misclassifications appear mostly between models developed at the same institution, indicating that the effects of shared code also emerge already on daily times scales. These results build the basis for further research on the usage of statistical and machine learning for evaluating models without relying on climatological time-scales.

show abstract

mentioning

confidence: 99%

Identifying climate models based on their daily output using machine learning

Brunner¹,

Sippel²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the modern field of generative modeling, GANs and Pix2Pix occupy a special place, solving different but very related problems. GAN, representing a radical shift in the understanding of data generation, uses two networks: a generator [22], [23] and a discriminator [24], [25]. The generator takes a random noise vector as input, after which it creates an image or other type of data, while its main goal is to make sure that the discriminator cannot distinguish the data it generates from the real one.…”

Section: Methodsmentioning

confidence: 99%

Data generation using generative adversarial networks to increase data volume

Aitimova,

Aitimov,

Mukhametzhanova

et al. 2024

IJECE

View full text Add to dashboard Cite

The article is an in-depth analysis of two leading approaches in the field of generative modeling: generative adversarial networks (GANs) and the pixel-to-pixel (Pix2Pix) image translation model. Given the growing interest in automation and improved image processing, the authors focus on the key operating principles of each model, analyzing their unique characteristics and features. The article also explores in detail the various applications of these approaches, highlighting their impact on modern research in computer vision and artificial intelligence. The purpose of the study is to provide readers with a scientific understanding of the effectiveness and potential of each of the models, and to highlight the opportunities and limitations of their application. The authors strive not only to cover the technical aspects of the models, but also to provide a broad overview of their impact on various industries, including medicine, the arts, and solving real-world problems in image processing. In addition, we have identified prospects for the use of these technologies in various fields, such as medicine, design, art, entertainment, and in unmanned aerial vehicle systems. The ability of GANs and Pix2Pix to adapt to a variety of tasks and produce high-quality results opens up broad prospects for industry and research.

show abstract

“…This means that they can be, on the one hand, more prone to overfitting but, one the other hand, can also learn more complex, nonlinear relationships in the data. Therefore, their use in different scientific disciplines, not least in climate sciences, has been rapidly increasing in recent years (Kashinath et al, 2021; Hsieh, 2022). Due to their complexity, many different design choices in the exact layout of the network are possible; here, we use an out-of-the-box setup for image classification without hyperparameter tuning but adjusted to the resolution of the daily temperature maps used in the input layer.…”

Section: Methodsmentioning

confidence: 99%

Identifying climate models based on their daily output using machine learning

Brunner

Sippel

2023

Environ. Data Science

View full text Add to dashboard Cite

Climate models are primary tools for investigating processes in the climate system, projecting future changes, and informing decision makers. The latest generation of models provides increasingly complex and realistic representations of the real climate system, while there is also growing awareness that not all models produce equally plausible or independent simulations. Therefore, many recent studies have investigated how models differ from observed climate and how model dependence affects model output similarity, typically drawing on climatological averages over several decades. Here, we show that temperature maps of individual days drawn from datasets never used in training can be robustly identified as “model” or “observation” using the CMIP6 model archive and four observational products. An important exception is a prototype storm-resolving simulation from ICON-Sapphire which cannot be unambiguously assigned to either category. These results highlight that persistent differences between simulated and observed climate emerge at short timescales already, but very high-resolution modeling efforts may be able to overcome some of these shortcomings. Moreover, temporally out-of-sample test days can be assigned their dataset name with up to 83% accuracy. Misclassifications occur mostly between models developed at the same institution, suggesting that effects of shared code, previously documented only for climatological timescales, already emerge at the level of individual days. Our results thus demonstrate that the use of machine learning classifiers, once trained, can overcome the need for several decades of data to evaluate a given model. This opens up new avenues to test model performance and independence on much shorter timescales.

show abstract

Evolution of machine learning in environmental science—A perspective

Cited by 16 publications

References 61 publications

Identifying climate models based on their daily output using machine learning

Identifying climate models based on their daily output using machine learning

Data generation using generative adversarial networks to increase data volume

Identifying climate models based on their daily output using machine learning

Contact Info

Product

Resources

About