Historically, coastal areas experienced what were classified as “one-in-a-hundred-year” water level extremes—events with a mere 1% chance of occurring in any given year. However, the study highlights that due to significant global sea-level rise, these events now occur with twelve times greater frequency on average. This means extreme flooding that used to be expected once per century is today likely to happen approximately once every eight years, with some regions experiencing such catastrophes annually. The implications of this finding extend far beyond mere statistical record-keeping—it demands a reassessment of how societies prepare for and adapt to flooding risks.

The research, co-authored by Associate Professor Thomas Wahl from the University of Central Florida’s College of Engineering and Computer Science, dives deep into the causal factors behind this alarming trend. Wahl emphasizes a metaphorical illustration: traditionally, residents within flood zones faced a 100-sided die where one out of 100 rolls (representing years) would result in a flood event. As sea levels rise, this die metaphorically loses sides, significantly increasing the odds of flooding each year. Eventually, the odds may become so high that many might consider these areas uninhabitable or too risky for long-term investment.

The catalyst for the increased frequency of extreme coastal water levels is unequivocally tied to human-induced sea-level rise, which has measured a nearly eight-inch global increase over the past 126 years. Wahl’s team utilized a multidisciplinary approach, combining observational data—such as tide gauges and satellite measurements—with sophisticated computer model simulations. This integration of data sources allowed the researchers to differentiate between naturally occurring fluctuations and those driven by anthropogenic influences, such as greenhouse gas emissions and climate change.

Natural variability has long influenced sea levels, with tidal cycles, storm surges, and climatic phenomena like El Niño contributing to the fluctuations. However, Wahl and his colleagues demonstrate that anthropogenic forcing has overtaken natural variability as the dominant driver behind the heightened likelihood of coastal extremes. Their analysis reveals that human impacts alone have increased the odds of experiencing a one-in-100-year event by a factor of four. This anthropogenic influence, when combined with ongoing natural variability, drastically amplifies risk.

Beyond statistical modeling, recent advancements in understanding subsidence and geological changes to coastal landscapes have shed further light on how these factors exacerbate flooding. Wahl’s recent contribution to a Nature Geosciences study reveals that sinking grounds—subsidence—combined with rising sea levels accelerate flooding risks more rapidly than previously appreciated. This dual effect intensifies water level extremes, making areas more vulnerable, especially in regions where land subsidence is significant due to groundwater extraction or sediment compaction.

This mounting evidence underscores the urgency of reassessing and redesigning coastal infrastructure to withstand these new realities. Traditional flood frequency estimates and design standards, based on historical data, often fail to account for the rapidly changing environmental conditions driven by both sea-level rise and subsidence. As Wahl warns, coastal communities and policymakers must pivot toward adaptive strategies that incorporate the increasing risks posed by these amplified extremes.

Collaborating with esteemed institutions such as Tulane University and Harvard University, along with research centers in Germany and the Netherlands, this study represents a global scientific effort to clarify the evolving threats posed by climate change to coastal regions. Wahl’s own research trajectory—from his fellowships in Europe to his postdoctoral work in Florida—reflects a dedicated pursuit of solutions to the multifaceted challenges of sea-level rise, storm surge, and coastal flooding.

The study’s findings emphasize the need for comprehensive data integration—including satellite oceanography, tidal monitoring networks, and advanced climate models—to forecast future risks accurately and inform robust coastal management practices. This integrative approach not only enhances prediction skill but also aids in tailoring infrastructure investments that can mitigate loss of life and property.

Emerging coastal flood risk assessment frameworks must therefore embrace dynamic, forward-looking data rather than relying solely on historical recurrence intervals. Such paradigms should account for projected anthropogenic climate impacts and localized factors like land subsidence, ensuring communities are better equipped to face an era of unprecedented sea-level extremes.

This research signals a clarion call for immediate policy action and public awareness. As the frequency of what were once rare, extreme flooding events inches closer to becoming annual hazards for many coastal zones, there is no longer room for complacency. Engineering solutions must evolve, zoning regulations must be revisited, and emergency preparedness plans must be recalibrated to confront a harsher hydrological reality.

In conclusion, the study by Thomas Wahl and his international team fundamentally challenges our understanding of coastal flood risks in the Anthropocene. Human-induced sea-level rise has not only raised ocean heights but has also dramatically shifted the statistical landscape of extreme water events. This shift mandates a transformative approach to how societies perceive, prepare for, and adapt to the growing risks—ensuring resilience in the face of a changing sea.

Subject of Research: Not applicable

Article Title: Human-driven sea-level rise has quadrupled the frequency of coastal sea-level extremes since 1900

News Publication Date: 10-Jun-2026

Web References: https://doi.org/10.1038/s41558-026-02659-0

Image Credits: UCF College of Engineering and Computer Science

Keywords

Environmental management, Civil engineering, Environmental sciences, Environmental engineering

Sea level anomaly (SLA) emerges as a pivotal metric in this realm, representing deviations in sea surface height relative to a long-term average. SLA embodies the fluctuations of geostrophic ocean currents, denoting discrepancies between present ocean surface states and their climatological baseline. This measure, rendered accessible through satellite altimetry, offers a global vantage point of sea surface dynamics, capturing subtle but consequential changes that precede coastal impacts. However, translating these data into accurate forecasts remains a formidable task.

Numerical models have traditionally driven short-term SLA prediction efforts. By integrating satellite altimetry data and physical oceanographic principles, these models simulate ocean circulation and sea level dynamics to forecast SLA trends. Yet, numerical approaches often grapple with persistent biases, limited resolution, and high computational demands that restrict their applicability—and accuracy—particularly in regional or near-coast contexts where high precision is paramount. The quest for improvement has catalyzed a shift toward data-driven methodologies.

Artificial intelligence (AI) has revolutionized many scientific domains by leveraging vast datasets to unveil complex, nonlinear patterns—capabilities that classical numerical models occasionally struggle to capture. In marine sciences, AI-driven ocean forecasting systems have begun to surpass traditional approaches in skill, especially across 10-day prediction horizons. These large-scale Global Ocean Forecast Systems (GOFSs), while effective, are tailored for global operations and require substantial computational resources, impeding their deployment for localized, resource-limited applications.

Recognizing these constraints, a cross-institutional team of researchers from Sun Yat-Sen University, Zhejiang Institute of Marine Planning and Design, and Pusan National University pursued an alternative route. Their aim was to enhance regional sea level prediction capacity in the North Pacific by refining AI training protocols without escalating the complexity of model architectures. This strategic pivot underscores a paradigm shift from model intricacy to model training efficacy.

The researchers’ work was recently published in Ocean-Land-Atmosphere Research, framing a novel approach centered on optimizing the training methodologies of AI models for SLA forecasting. Rather than constructing more intricate neural networks, they revisited the assumptions underlying prediction targets and temporal training frameworks to diminish errors that typically accumulate over extended forecasting intervals. The emphasis on improved training decoration rather than architectural modification holds promise for broad applicability.

One breakthrough involved redefining the forecasting focus from absolute SLA values toward the temporal tendency of SLA—that is, the day-to-day change in sea level anomalies. This subtle reframing captures slower-evolving dynamics more effectively, aligning prediction goals with the physical behavior of ocean currents and mitigating noise introduced by rapid, smaller-scale fluctuations. Another innovation dealt with the critical challenge of the “training-forecast gap.”

The “training-forecast gap” refers to the mismatch arising when models are trained on short-term forecast horizons yet deployed for longer-range predictions, leading to error propagation and reduced reliability over time. The team addressed this by employing a multi-step training paradigm and rolling forecast technique. This strategy entailed training the model primarily for daily SLA tendencies but enabling it to generate reliable forecasts over broader horizons through sequential, stepwise updates—akin to effectively chaining short-term predictions into robust medium-range outlooks.

At the heart of the AI architecture lies Earthformer, a cutting-edge deep learning model designed to process spatiotemporal data in parallel rather than sequentially. This parallelism enables efficient handling of complex oceanographic datasets while capturing crucial temporal correlations. Tailoring Earthformer to the extrinsic characteristics of the North Pacific’s altimetry data and imbuing it with optimized training schemata, the researchers crafted the Multistep-Earthformer forecasting system.

Comparative evaluations underscored the superiority of this approach. The Multistep-Earthformer significantly outperformed conventional approaches, including persistence forecasts—which naively assume future states will mirror the present—and even benchmarked numerical models such as GLO12v4. These improvements did not necessitate complicated model modifications but rather stemmed from intelligent training adjustments, suggesting a scalable pathway for other geophysical forecasting challenges.

Beyond sea level prediction, the conceptual advancements introduced—the focus on temporal tendencies and training regimen refinement—may invigorate broader applications in geosciences. AI modelers working on atmospheric, terrestrial, or coupled Earth system predictions could potentially adapt these strategies to mitigate forecast drift and error accumulation, thereby elevating forecast reliability across domains.

With the promising results in the North Pacific region as a foundation, the research collective now envisages scaling their approach globally. This expansion will demand careful tailoring of training strategies to accommodate regional oceanographic peculiarities and data availability. Their ultimate vision is the realization of an AI-driven, globally comprehensive sea level forecasting platform capable of supporting diverse stakeholders, from environmental managers to maritime industries.

This breakthrough emerges in the context of a rapidly evolving scientific landscape where interdisciplinary collaboration—spanning oceanography, AI, and computational modeling—fuels progress. The study received support from the Guangdong Basic and Applied Basic Research Foundation and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), exemplifying the vital role of sustained funding and institutional synergy in addressing pressing environmental challenges.

Co-authors include Yong Liu of the Zhejiang Institute of Hydraulics & Estuary, Guangyu Yang of Sun Yat-Sen University, Young-Heon Jo of Pusan National University, and Zhigang Lai of Sun Yat-Sen University, reflecting a collaborative network bridging China and South Korea in marine sciences innovation.

As coastal regions worldwide confront intensifying climate-related hazards, tools that enable anticipatory action through advanced sea level forecasting will be indispensable. The Multistep-Earthformer model and its training-focused innovations provide a beacon of progress, illustrating how methodical refinement rather than mere complexity can unlock new horizons in ocean state prediction. This blend of sophisticated AI design and pragmatic training strategy exemplifies the next wave of environmental modeling poised to better safeguard coastal futures.

Subject of Research: Not applicable

Article Title: Optimized Training Strategies for AI-Based Sea Level Anomaly Forecasting in the North Pacific Ocean

News Publication Date: 23-Jan-2026

Web References: 10.34133/olar.0128

Image Credits: Jiangnan He et al. / Ocean-Land-Atmosphere Research

Keywords: Ocean circulation, Ocean physics, Oceanography, Air-sea interactions