Search for: All records

Abstract Artificial intelligence (AI) can be used to improve performance across a wide range of Earth system prediction tasks. As with any application of AI, it is important for AI to be developed in an ethical and responsible manner to minimize bias and other effects. In this work, we extend our previous work demonstrating how AI can go wrong with weather and climate applications by presenting a categorization of bias for AI in the Earth sciences. This categorization can assist AI developers to identify potential biases that can affect their model throughout the AI development life cycle. We highlight examples from a variety of Earth system prediction tasks of each category of bias. 

Abstract Many of our generation’s most pressing environmental science problems are wicked problems, which means they cannot be cleanly isolated and solved with a single ‘correct’ answer (e.g., Rittel 1973; Wirz 2021). The NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES) seeks to address such problems by developing synergistic approaches with a team of scientists from three disciplines: environmental science (including atmospheric, ocean, and other physical sciences), AI, and social science including risk communication. As part of our work, we developed a novel approach to summer school, held from June 27-30, 2022. The goal of this summer school was to teach a new generation of environmental scientists how to cross disciplines and develop approaches that integrate all three disciplinary perspectives and approaches in order to solve environmental science problems. In addition to a lecture series that focused on the synthesis of AI, environmental science, and risk communication, this year’s summer school included a unique Trust-a-thon component where participants gained hands-on experience applying both risk communication and explainable AI techniques to pre-trained ML models. We had 677 participants from 63 countries register and attend online. Lecture topics included trust and trustworthiness (Day 1), explainability and interpretability (Day 2), data and workflows (Day 3), and uncertainty quantification (Day 4). For the Trust-a-thon we developed challenge problems for three different application domains: (1) severe storms, (2) tropical cyclones, and (3) space weather. Each domain had associated user persona to guide user-centered development. 

Abstract The predictability of sea ice during extreme sea ice loss events on subseasonal (daily to weekly) time scales is explored in dynamical forecast models. These extreme sea ice loss events (defined as the 5th percentile of the 5-day change in sea ice extent) exhibit substantial regional and seasonal variability; in the central Arctic Ocean basin, most subseasonal rapid ice loss occurs in the summer, but in the marginal seas rapid sea ice loss occurs year-round. Dynamical forecast models are largely able to capture the seasonality of these extreme sea ice loss events. In most regions in the summertime, sea ice forecast skill is lower on extreme sea ice loss days than on nonextreme days, despite evidence that links these extreme events to large-scale atmospheric patterns; in the wintertime, the difference between extreme and nonextreme days is less pronounced. In a damped anomaly forecast benchmark estimate, the forecast error remains high following extreme sea ice loss events and does not return to typical error levels for many weeks; this signal is less robust in the dynamical forecast models but still present. Overall, these results suggest that sea ice forecast skill is generally lower during and after extreme sea ice loss events and also that, while dynamical forecast models are capable of simulating extreme sea ice loss events with similar characteristics to what we observe, forecast skill from dynamical models is limited by biases in mean state and variability and errors in the initialization. Significance Statement We studied weather model forecasts of changes in Arctic sea ice extent on day-to-day time scales in different regions and seasons. We were especially interested in extreme sea ice loss days, or days in which sea ice melts very quickly or is reduced due to diverging forces such as winds, ocean currents, and waves. We find that forecast models generally capture the observed timing of extreme sea ice loss days. We also find that forecasts of sea ice extent are worse on extreme sea ice loss days compared to typical days, and that forecast errors remain elevated following extreme sea ice loss events. 

Abstract The latitudinal location of the east Pacific Ocean intertropical convergence zone (ITCZ) changes on time scales of days to weeks during boreal spring. This study focuses on tropical near-surface dynamics in the days leading up to the two most frequent types of ITCZ events, nITCZ (Northern Hemisphere) and dITCZ (double). There is a rapid daily evolution of dynamical features on top of a slower, weekly evolution that occurs leading up to and after nITCZ and dITCZ events. Zonally elongated bands of anomalous cross-equatorial flow and off-equatorial convergence rapidly intensify and peak 1 day before or the day of these ITCZ events, followed 1 or 2 days later by a peak in near-equatorial zonal wind anomalies. In addition, there is a wide region north of the southeast Pacific subtropical high where anomalous northwesterlies strengthen prior to nITCZ events and southeasterlies strengthen before dITCZ events. Anomalous zonal and meridional near-surface momentum budgets reveal that the terms associated with Ekman balance are of first-order importance preceding nITCZ events, but that the meridional momentum advective terms are just as important before dITCZ events. Variations in cross-equatorial flow are promoted by the meridional pressure gradient force (PGF) prior to nITCZ events and the meridional advection of meridional momentum in addition to the meridional PGF before dITCZ events. Meanwhile, variations in near-equatorial easterlies are driven by the zonal PGF and the Coriolis force preceding nITCZ events and the zonal PGF, the Coriolis force, and the meridional advection of zonal momentum before dITCZ events. 

Abstract Neural networks (NN) have become an important tool for prediction tasks—both regression and classification—in environmental science. Since many environmental-science problems involve life-or-death decisions and policy making, it is crucial to provide not only predictions but also an estimate of the uncertainty in the predictions. Until recently, very few tools were available to provide uncertainty quantification (UQ) for NN predictions. However, in recent years the computer-science field has developed numerous UQ approaches, and several research groups are exploring how to apply these approaches in environmental science. We provide an accessible introduction to six of these UQ approaches, then focus on tools for the next step, namely, to answer the question:Once we obtain an uncertainty estimate (using any approach), how do we know whether it is good or bad?To answer this question, we highlight four evaluation graphics and eight evaluation scores that are well suited for evaluating and comparing uncertainty estimates (NN based or otherwise) for environmental-science applications. We demonstrate the UQ approaches and UQ-evaluation methods for two real-world problems: 1) estimating vertical profiles of atmospheric dewpoint (a regression task) and 2) predicting convection over Taiwan based onHimawari-8satellite imagery (a classification task). We also provide Jupyter notebooks with Python code for implementing the UQ approaches and UQ-evaluation methods discussed herein. This article provides the environmental-science community with the knowledge and tools to start incorporating the large number of emerging UQ methods into their research. Significance StatementNeural networks are used for many environmental-science applications, some involving life-or-death decision-making. In recent years new methods have been developed to provide much-needed uncertainty estimates for NN predictions. We seek to accelerate the adoption of these methods in the environmental-science community with an accessible introduction to 1) methods for computing uncertainty estimates in NN predictions and 2) methods for evaluating such estimates. 

ABSTRACT Arctic–midlatitude teleconnections are complex and multifaceted. By design, targeted modeling studies typically focus only on one direction of influence—usually, the midlatitude atmospheric response to a changing Arctic. The two-way, coupled feedbacks between the Arctic and the midlatitude circulation on submonthly time scales are explored using a regularized regression model formulated around Granger causality. The regularized regression model indicates that there are regions in which Arctic temperature drives a midlatitude circulation response, and regions in which the midlatitude circulation drives a response in the Arctic; however, these regions rarely overlap. In many regions, on submonthly time scales, the midlatitude circulation drives Arctic temperature variability, highlighting the important role the midlatitude circulation can play in impacting the Arctic. In particular, the regularized regression model results support recent work that indicates that the observed high pressure anomalies over Eurasia drive a significant response in the Arctic on submonthly time scales, rather than being driven by the Arctic.