An official website of the United States government
Revolutionary advances in artificial intelligence (AI) in the past decade have brought transformative innovation across science and engineering disciplines. In the field of Arctic science, we have witnessed an increasing trend in the adoption of AI, especially deep learning, to support the analysis of Arctic big data and facilitate new discoveries. In this paper, we provide a comprehensive review of the applications of deep learning in sea ice remote sensing domains, focusing on problems such as sea ice lead detection, thickness estimation, sea ice concentration and extent forecasting, motion detection, and sea ice type classification. In addition to discussing these applications, we also summarize technological advances that provide customized deep learning solutions, including new loss functions and learning strategies to better understand sea ice dynamics. To promote the growth of this exciting interdisciplinary field, we further explore several research areas where the Arctic sea ice community can benefit from cutting-edge AI technology. These areas include improving multimodal deep learning capabilities, enhancing model accuracy in measuring prediction uncertainty, better leveraging AI foundation models, and deepening integration with physics-based models. We hope that this paper can serve as a cornerstone in the progress of Arctic sea ice research using AI and inspire further advances in this field.
more »
« less
Benchmarking Probabilistic Machine Learning Models For Arctic Sea Ice Forecasting
The Arctic is a region with unique climate features, motivating new AI methodologies to study it. Unfortunately, Arc- tic sea ice has seen a continuous decline since 1979. This not only poses a significant threat to Arctic wildlife and surrounding coastal communities but is also adversely affecting the global climate patterns. To study the potential of AI in tackling climate change, we analyze the performance of four probabilistic machine learning methods in forecasting sea-ice extent for lead times of up to 6 months, further comparing them with traditional machine learning methods. Our comparative analysis shows that Gaussian Process Regression is a good fit to predict sea-ice extent for longer lead times with lowest RMSE score.
more »
« less
- PAR ID:
- 10340885
- Date Published:
- Journal Name:
- The International Geoscience and Remote Sensing Symposium (IGARSS 2022)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Although standard statistical methods and climate models can simulate and predict sea-ice changes well, it is still very hard to distinguish some direct and robust factors associated with sea-ice changes from its internal variability and other noises. Here, with long-term observations (38 years from 1980 to 2017), we apply the causal effect networks algorithm to explore the direct precursors of September Arctic sea-ice extent by adjusting the maximal lead time from one to eight months. For lead time of more than three months, June downward longwave radiation flux in the Canadian Arctic Archipelago is the only one precursor. However, for lead time of 1–3 months, August sea-ice concentration in Western Arctic represents the strongest positive correlation with September sea-ice extent, while August sea-ice concentration factors in other regions have weaker influences on the marginal seas. Other precursors include August wind anomalies in the lower latitudes accompanied with an Arctic high pressure anomaly, which induces the sea-ice loss along the Eurasian coast. These robust precursors can be used to improve the seasonal predictions of Arctic sea ice and evaluate the climate models.more » « less
-
Abstract Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.more » « less
-
Abstract Recent advances in explainable artificial intelligence (XAI) methods show promise for understanding predictions made by machine learning (ML) models. XAI explains how the input features are relevant or important for the model predictions. We train linear regression (LR) and convolutional neural network (CNN) models to make 1-day predictions of sea ice velocity in the Arctic from inputs of present-day wind velocity and previous-day ice velocity and concentration. We apply XAI methods to the CNN and compare explanations to variance explained by LR. We confirm the feasibility of using a novel XAI method [i.e., global layerwise relevance propagation (LRP)] to understand ML model predictions of sea ice motion by comparing it to established techniques. We investigate a suite of linear, perturbation-based, and propagation-based XAI methods in both local and global forms. Outputs from different explainability methods are generally consistent in showing that wind speed is the input feature with the highest contribution to ML predictions of ice motion, and we discuss inconsistencies in the spatial variability of the explanations. Additionally, we show that the CNN relies on both linear and nonlinear relationships between the inputs and uses nonlocal information to make predictions. LRP shows that wind speed over land is highly relevant for predicting ice motion offshore. This provides a framework to show how knowledge of environmental variables (i.e., wind) on land could be useful for predicting other properties (i.e., sea ice velocity) elsewhere. Significance StatementExplainable artificial intelligence (XAI) is useful for understanding predictions made by machine learning models. Our research establishes trustability in a novel implementation of an explainable AI method known as layerwise relevance propagation for Earth science applications. To do this, we provide a comparative evaluation of a suite of explainable AI methods applied to machine learning models that make 1-day predictions of Arctic sea ice velocity. We use explainable AI outputs to understand how the input features are used by the machine learning to predict ice motion. Additionally, we show that a convolutional neural network uses nonlinear and nonlocal information in making its predictions. We take advantage of the nonlocality to investigate the extent to which knowledge of wind on land is useful for predicting sea ice velocity elsewhere.more » « less
-
Abstract Summer Arctic sea ice is declining rapidly but with superimposed variability on multiple time scales that introduces large uncertainties in projections of future sea ice loss. To better understand what drives at least part of this variability, we show how a simple linear model can link dominant modes of climate variability to low-frequency regional Arctic sea ice concentration (SIC) anomalies. Focusing on September, we find skillful projections from global climate models (GCMs) from phase 6 of the Coupled Model Intercomparison Project (CMIP6) at lead times of 4–20 years, with up to 60% of observed low-frequency variability explained at a 5-yr lead time. The dominant driver of low-frequency SIC variability is the interdecadal Pacific oscillation (IPO) which is positively correlated with SIC anomalies in all regions up to a lead time of 15 years but with large uncertainty between GCMs and internal variability realization. The Niño-3.4 index and Atlantic multidecadal oscillation have better agreement between GCMs of being positively and negatively related, respectively, with low-frequency SIC anomalies for at least 10-yr lead times. The large variations between GCMs and between members within large ensembles indicate the diverse simulation of teleconnections between the tropics and Arctic sea ice and the dependence on the initial climate state. Further, the influence of the Niño-3.4 index was found to be sensitive to the background climate. Our results suggest that, based on the 2022 phases of dominant climate variability modes, enhanced loss of sea ice area across the Arctic is likely during the next decade. Significance StatementThe purpose of this study is to better understand the drivers of low-frequency variability of Arctic sea ice. Teasing out the complicated relationships within the climate system takes a large number of examples. Here, we use 42 of the latest generation of global climate models to construct a simple linear model based on dominant named climate features to predict regional low-frequency sea ice anomalies at a lead time of 2–20 years. In 2022, these modes of variability happen to be in the phases most conducive to low Arctic sea ice concentration anomalies. Given the context of the longer-term trend of sea ice loss due to global warming, our results suggest accelerated Arctic sea ice loss in the next decade.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
