Among the highest distinctions are four new AMS Honorary Members: atmospheric scientist Inez Fung, former AMS executive director Keith Seitter, climate and atmospheric scientist J. Marshall Shepherd, and longtime NOAA leader Louis W. Uccellini. Honorary Membership is reserved for individuals whose scientific achievements, applications, leadership, or service have had an exceptional influence on the atmospheric, oceanic, or hydrologic sciences. Their selection reflects the increasingly interdisciplinary nature of modern Earth-system science, in which climate, weather, society, and policy are tightly connected.

The Carl-Gustaf Rossby Research Medal will go to Rong Fu for pioneering observations of the atmospheric water cycle and land-atmosphere coupling. These processes describe how moisture moves between soil, vegetation, and the atmosphere, influencing rainfall, drought, and fire weather. Paola Cessi will receive the Henry Stommel Research Medal for advancing understanding of the ocean’s large-scale meridional overturning circulation, a system that transports heat, carbon, and nutrients around the planet. Sharon Nicholson, honored with the Hydrologic Sciences Medal, is recognized for foundational work on dryland hydroclimatology, particularly across Africa, where rainfall variability directly affects food and water security.

Other major science medals highlight the global machinery driving weather and climate. Renhe Zhang will receive the Sverdrup Gold Medal for clarifying Asian monsoon variability and its relationship with Northwest Pacific ocean-atmosphere interactions and El Niño–Southern Oscillation. Christian Kummerow will be awarded the Verner E. Suomi Technology Medal for transforming precipitation measurement through satellite microwave remote sensing. By detecting how raindrops, ice particles, and cloud structures interact with microwave radiation, such systems provide critical observations over oceans and remote regions where ground-based instruments are scarce.

David Thompson will receive the Jule G. Charney Medal for research into climate variability, stratospheric influences on global change, and the reliability of observed temperature records. Venkatachalam Ramaswamy will receive the Warren Washington Research and Leadership Medal for influential research on radiation-climate interactions and his leadership of NOAA’s Geophysical Fluid Dynamics Laboratory. The Jagadish Shukla Earth System Predictability Prize will recognize Xin-Zhong Liang, whose regional Earth-system models integrate atmospheric, hydrologic, ecological, and human influences to improve decision support for climate-sensitive communities.

The awards also emphasize the infrastructure and public institutions that make scientific progress possible. Eric DeWeaver is being honored for two decades of leadership in the National Science Foundation’s Climate and Large-Scale Dynamics Program, while Jim Mather is recognized for strengthening the scientific reach and accessibility of a major atmospheric observing facility. The National Weather Service AI Language Translation Program Team will receive the Francis W. Reichelderfer Award for developing the agency’s first artificial-intelligence-powered multilingual weather translation system. The technology is designed to make urgent forecasts and warnings accessible to people who may not receive life-saving information in English.

Several awards focus on mentorship, inclusion, and the human side of science. Jennifer D. Small Griswold will receive the Edward N. Lorenz Teaching Excellence Award for connecting atmospheric science with culture, place, and community while supporting students from diverse backgrounds. Isha Renta López will receive the Robert H. and Joanne Simpson Mentorship Award for expanding STEM access among Hispanic and Latin communities through science communication and engagement. Mona Behl will receive the Charles E. Anderson Award for advancing diversity and equity through organizational change, advocacy, and sustained mentorship in the geosciences.

Research addressing immediate societal challenges is also prominent. David Nolan will receive the Joanne Simpson Tropical Meteorology Research Award for work combining theory, field measurements, and numerical modeling to improve understanding of hurricane dynamics and forecasting. John Mitchell will receive the Syukuro Manabe Climate Research Award for developing and applying climate models that revealed how greenhouse gases and aerosols influence human-caused climate change. Sara Pryor is recognized for advancing renewable-energy research through actionable science, international collaboration, and mentorship, while Claudia Wagner-Riddle is honored for explaining the processes controlling greenhouse-gas emissions from agricultural ecosystems.

The 2027 recipients further include scientists working on urban meteorology, boundary-layer turbulence, ocean dynamics, and climate extremes. Shiguang Miao is being honored for research that improves urban forecasting, disaster-risk reduction, and resilience. John Albertson will receive an award for connecting turbulence physics with environmental challenges through simulations and field experiments. Early-career honors go to Ángel Adames Corraliza for moisture-mode theory in tropical dynamics, Aaron Piña for bridging science, policy, and community service, Zhiwei Zhang for research on submesoscale ocean dynamics, and Karen McKinnon for studying how internal variability and land-atmosphere feedbacks shape extreme temperatures and precipitation.

Forecasting and communication awards underscore the direct connection between atmospheric science and public safety. The National Weather Service office in Paducah, Kentucky, will receive the Award for an Exceptional Specific Prediction for life-saving forecasts during historic high-impact weather events in spring 2025. Jason Sippel will receive the Charles L. Mitchell Award for improving hurricane prediction through the operational use of reconnaissance observations. Broadcast meteorologists Jay Trobec and Drew Anderson are recognized for global leadership and for making topics ranging from earthquakes to auroras understandable through engaging scientific storytelling.

The AMS will also honor the Farthest North Chapter as its Local Chapter of the Year and the CU Boulder American Meteorological Society Chapter as its Local Student Chapter of the Year. Lectureships will recognize Jeffrey Pierce for research linking atmospheric particles with air quality, climate, and human health; Ashok Mishra for work on drought propagation and water security; and Daniela Domeisen for research into stratosphere-troposphere coupling and subseasonal prediction. The National Lightning Safety Council will receive a Special Award for 25 years of public education and advocacy, while 28 scientists will become AMS Fellows. Together, the selections illustrate a field moving rapidly from observation and theory toward prediction systems, inclusive communication, and practical tools for a safer world.

Subject of Research: Weather, water, climate science, atmospheric and oceanic research, forecasting, Earth-system modeling, scientific communication, and public safety.

Article Title: AMS Announces 2027 Honors Recognizing Breakthroughs in Climate Science, Forecasting, and Public Safety

Web References: https://www.ametsoc.org/ams/about-ams/ams-awards-honors/2027-award-and-honors-recipients; https://annual.ametsoc.org/2027/

Keywords: American Meteorological Society, AMS Awards 2027, climate science, meteorology, atmospheric science, hydrology, oceanography, hurricanes, drought, Earth-system modeling, artificial intelligence, weather forecasting, renewable energy, lightning safety, science communication

The WMO, a specialized United Nations agency headquartered in Geneva, orchestrates global initiatives aimed at enhancing meteorological forecasts and early warning systems that critically safeguard populations from natural hazards. Recognizing the transformative potential of AI, the WMO established JAG-AI as an exclusive consortium of global experts. This group undertakes the ambitious task of integrating AI methodologies into meteorological and hydrological data systems worldwide. By doing so, JAG-AI seeks to refine forecasting accuracy and augment predictive capabilities, particularly when addressing complex extreme weather patterns and climate risks that pose increasing threats to societies worldwide.

Assistant Professor Mengaldo’s expertise uniquely positions him at the nexus of AI, numerical weather modeling, and extreme event prediction. His research leverages advanced AI algorithms alongside high-performance computing frameworks to tackle intrinsic challenges in weather and climate simulations. These challenges often arise from the chaotic nature of atmospheric processes, which demand exceptional computational efficiency and innovative data assimilation techniques to capture fine-scale dynamics. By integrating AI, such as deep learning and neural network architectures, Mengaldo’s work enhances the interpretability and precision of models forecasting phenomena ranging from tropical cyclones to flash floods.

The application of AI in climatology extends beyond mere pattern recognition. It encompasses the enhancement of physical models through hybrid approaches where physics-based simulations are augmented by data-driven insights. This symbiosis enables the extraction of latent features and non-linear dynamics inaccessible to traditional algorithms. Mengaldo’s contributions include designing computational schemes that optimize this integration, thus producing statistically robust ensemble predictions that better quantify uncertainty and risk. The implication of these advances is profound, offering new pathways toward resilient climate adaptation strategies globally.

The WMO’s JAG-AI advisory group not only focuses on scientific innovation but also stresses the ethical deployment of AI technologies within meteorology. Ensuring transparency, replicability, and accountability in AI models is paramount, particularly given these systems’ societal ramifications. Assistant Professor Mengaldo, through his role on this panel, advocates for rigorous standards that uphold scientific integrity while broadening AI’s applicability to regional forecasting frameworks. His participation reinforces Singapore’s voice in shaping international policy and technical guidelines overseeing AI’s role in climate science.

As climate systems grow more erratic in the context of anthropogenic change, the need for real-time, reliable meteorological predictions becomes increasingly urgent. AI’s capacity to process vast datasets—from satellite imagery to sensor networks—facilitates near-instantaneous model updates and scenario analyses previously unattainable. Mengaldo’s research taps into this capability, harnessing scalable computation to deliver timely warnings that can mitigate disaster impacts. These advancements exemplify the crucial intersection where theoretical AI research meets practical climate resilience and disaster risk management.

In parallel, the group’s work addresses longstanding challenges in hydrology, particularly in flood forecasting and water resource management. The incorporation of AI tools aids the synthesis of diverse data types—such as river discharge measurements, precipitation models, and topographic information—to predict hydrological extremes with greater nuance. Mengaldo’s contribution underscores the essential role of interdisciplinary methods, combining civil engineering principles with computational intelligence to safeguard vulnerable communities.

The appointment of Assistant Professor Mengaldo signals a broader trend where AI expertise is becoming indispensable in earth sciences. His role symbolizes a shift towards multidisciplinary research that leverages machine learning not only to model current climatic phenomena but also to anticipate future changes under varying emission scenarios. This forward-looking perspective is critical as governments and organizations worldwide shape adaptive policies in response to emerging risks related to climate change.

Mengaldo’s involvement with JAG-AI is also a testament to Singapore’s growing prominence in the global AI and climate science arena. By fostering collaborations across academia, industry, and international institutions, Singapore aims to catalyze innovations that transcend geographical boundaries. Assistant Professor Mengaldo’s leadership thus contributes to a global knowledge exchange, inspiring cross-pollination of ideas that can enhance predictive meteorology universally.

This endeavor also emphasizes the importance of high-performance computing infrastructures, which empower the computational intensity required for AI-augmented climate modeling. Mengaldo’s work integrates these technological advancements, utilizing supercomputers to execute complex simulations that consider myriad variables influencing weather systems. Such computational power is indispensable for resolving spatial and temporal scales that influence extreme climate events, a critical factor in risk assessment and mitigation.

Collectively, the efforts spearheaded by Assistant Professor Mengaldo through his role in the WMO JAG-AI highlight the transformative potential of blending AI with earth system sciences. As the climate crisis accelerates, leveraging AI-driven techniques offers a beacon of hope for enhancing our understanding of atmospheric phenomena and developing effective response mechanisms. This appointment not only advances scientific frontiers but also embodies a strategic vision where technology and environmental stewardship converge to address the planet’s most pressing challenges.

In summary, Assistant Professor Gianmarco Mengaldo’s recognition by the WMO aligns with a global imperative to harness artificial intelligence in service of climate resilience and disaster preparedness. His work exemplifies the innovative spirit required to navigate the complexities of natural systems in the era of rapid technological growth. Through meticulous research and international collaboration, Mengaldo is poised to influence how societies worldwide harness AI for a safer, more predictable future in the face of evolving climate risks.

Subject of Research: Artificial Intelligence Integration in Weather and Climate Forecasting

Article Title: Pioneering AI’s Role in Transforming Weather and Climate Science: The Appointment of Assistant Professor Gianmarco Mengaldo to the WMO Joint Advisory Group on Artificial Intelligence

Web References:

• Assistant Professor Gianmarco Mengaldo, NUS Mechanical Engineering
• WMO Joint Advisory Group on Artificial Intelligence (JAG-AI)
• World Meteorological Organization (WMO)

Image Credits: College of Design and Engineering at NUS

Keywords: Artificial intelligence, climate science, weather forecasting, high-performance computing, extreme events prediction, WMO, meteorology, hydrology, numerical modeling, climate change adaptation, machine learning, disaster risk management

The phenomenon of hailstorms—characterized by sudden, violent hail precipitation—has long posed threats to agriculture, infrastructure, and human safety. Yet, understanding their long-term trends has remained elusive due to sparse and fragmentary records. This pivotal investigation fills critical knowledge gaps by meticulously analyzing a vast array of historical documents and recorded weather station data spanning over two millennia. By integrating these extensive datasets, the team elucidated that, prior to approximately 1850, hailstorm frequency in China remained relatively stable, reflecting underlying natural climate variability.

Post-1850, however, a stark divergence emerges: the number of hailstorm days increased markedly, mirroring global temperature trends which shifted from minor fluctuations to a steady rise, approximately 0.8 degrees Celsius between 1850 and 1948. To quantify this relationship, the researchers employed advanced decomposition methodologies that parse out climatic signals from noise, thereby isolating human-induced warming as a predominant driver behind the intensifying frequency of hailstorms. This approach highlights the subtle yet powerful imprint of industrialization on regional and global atmospheric dynamics.

Significantly, the research also uncovers the synergistic role of natural climate oscillations, particularly the Pacific Decadal Oscillation (PDO), in modulating hailstorm patterns. The PDO, a long-term ocean-atmosphere phenomenon characterized by decadal shifts in Pacific Ocean temperatures and wind patterns, has been observed to amplify or dampen hailstorm activity when interacting with the baseline warming imposed by human activity. This nuanced interaction suggests that future hailstorm frequency will be influenced not only by continued anthropogenic warming but also by the phase and intensity of intrinsic oceanic cycles, complicating long-term projection efforts.

In an innovative leap, the team developed a convolutional neural network (CNN) model, trained on the comprehensive historical hail data, to forecast hailstorm trends throughout the twenty-first century. The model’s predictions reveal a continuing upward trajectory in hailstorm days, with a pronounced peak anticipated around the 2070s. This projection underscores the urgency of integrating AI-driven climate models into policy and adaptation strategies, providing more refined temporal insights into extreme weather phenomena exacerbated by climate change.

The implications of these findings extend beyond meteorological curiosity—hailstorms impose tangible economic and societal costs, from massive crop losses to structural damages and heightened risk to human health and safety. Understanding their future trajectory is thus vital for developing effective risk assessments and resilience frameworks. Policymakers and urban planners can leverage the study’s insights to anticipate and mitigate hailstorm impacts, balancing infrastructural investments with adaptive agricultural practices.

Moreover, the temporal depth of this analysis offers a rare millennia-scale perspective on the acceleration of extreme weather events. Unlike transient observational records, this extended timeline vividly illustrates how the industrial era has not merely shifted baseline climate parameters but has also amplified the frequency and intensity of severe phenomena like hailstorms. Such long-term datasets are invaluable for distinguishing anthropogenic signals from natural variability, refining climate models, and anchoring global climate discourse in empirical reality.

The study’s multidisciplinary approach, combining climatology, historical analysis, oceanography, and machine learning, serves as a model for future climate research endeavors. It demonstrates how harnessing diverse data sources and innovative analytical frameworks can unravel complex atmospheric processes. This integration is essential as the scientific community grapples with the multifaceted challenges posed by climate change and seeks to predict and counter its cascading effects with greater precision.

Furthermore, the research reaffirms the critical role that localized climate studies play in the global context. While hailstorms in China are the focal point, the global spike in hail occurrences observed in 2025 after record-breaking heatwaves in 2024 suggests parallel patterns worldwide. Such regional investigations can inform a holistic understanding of extreme weather evolution, bridging surface-level phenomena with broader planetary climate dynamics.

In conclusion, the contribution of this study extends beyond academic discourse, providing actionable knowledge for climate adaptation strategies in an era marked by rapid environmental transformation. Its findings emphasize that the progression of anthropogenic climate warming fundamentally reshapes the Earth’s atmospheric volatility, heralding a future where hailstorms—and likely other extreme weather events—become more frequent and severe. Addressing these challenges necessitates urgent, coordinated scientific, governmental, and societal efforts aiming to mitigate emissions and enhance resilience to unavoidable climatic changes.

Subject of Research: Long-term trends in hailstorm frequency and their relation to anthropogenic climate change in China.

Article Title: Not explicitly provided in the source.

News Publication Date: November 4, 2025.

Web References: https://news.pku.edu.cn/jxky/70c4a91b63444ab1880ee6fe9977c003.htm

References: Nature Communications, September 2025 publication by Zhang Qinghong and Li Rumeng et al.

Image Credits: Not mentioned.

Keywords: Climate change, Anthropogenic warming, Hailstorms, Extreme weather, Pacific Decadal Oscillation, Convolutional neural networks, Climate variability, Historical climatology, Climate adaptation

Solar wind, the continuous flow of charged particles emitted by the Sun, has far-reaching effects on the Earth’s environment. These particles are not merely harmless; under specific conditions, they can trigger significant disturbances in the Earth’s magnetosphere. Such disruptions can lead to a phenomenon popularly known as “space weather,” which can, in turn, affect navigation systems, electric grids, and the operation of satellites orbiting the planet. In 2022, for instance, a powerful solar wind event resulted in the loss of 40 Starlink satellites belonging to SpaceX, underlining the pressing need for enhanced predictive capabilities in this area.

The research team, led by Postdoctoral Associate Dattaraj Dhuri and Co-Principal Investigator Shravan Hanasoge, embarked on a quest to improve the accuracy of solar wind speed forecasts. Traditionally, meteorological models rely on text and numerical data to analyze past events and generate predictions. In a significant departure from this norm, Dhuri and his team trained their AI model utilizing high-resolution ultraviolet (UV) imagery obtained from NASA’s Solar Dynamics Observatory. By focusing on images rather than textual data, the AI system analyzes distinct patterns present in the solar images that correlate with shifts in solar wind behavior.

The implications of this methodological shift are profound. The NYUAD team’s innovative AI model has demonstrated a remarkable 45 percent enhancement in forecasting accuracy when compared to existing operational models. Furthermore, it showcases a 20 percent improvement over previous AI-based approaches, marking a significant milestone not only for the research team but for the broader scientific community focused on solar and space science.

Such advancements in forecasting are critical for mitigating the potential risks posed by space weather events. According to Dhuri, who is the primary author of the study published in The Astrophysical Journal Supplement Series, this AI-driven approach is a “major step forward” in safeguarding the satellites, navigation systems, and power infrastructure that underpin modern life. The capacity to predict solar wind conditions in advance allows scientists and engineers to preemptively bolster our defenses against disruptive solar events, enhancing our resilience to technological challenges.

As global reliance on satellite communication, GPS navigation, and power systems increases, the need for reliable space weather forecasts becomes ever more urgent. The research conducted at NYU Abu Dhabi not only highlights the versatility and potential of AI applications in scientific research but also exemplifies how interdisciplinary collaboration can lead to significant breakthroughs in understanding complex natural phenomena.

This AI model presents a paradigm shift in the art of prediction. By combining the vast observational datasets from NASA with advanced machine learning techniques, the researchers have opened the door to possibilities previously thought to be distant dreams. The model not only forecasts solar wind speeds but potentially offers insights into other sun-related phenomena, leading to a deeper understanding of solar dynamics.

As this research unfolds, the NYUAD team underscores the importance of continuous monitoring and refinement of their model. They aim to integrate more diverse datasets, allowing for an even more nuanced comprehension of solar conditions. The implications for future research are enormous, with possibilities for applying similar AI techniques to study other celestial bodies and their interactions within our solar system.

In our ever technologically dependent society, the ramifications of improved solar wind forecasting capabilities could extend well beyond the immediate environment. As power grids and communication systems become more intertwined with solar activities, preemptive measures based on accurate predictions could save millions in potential damages caused by unforeseen solar events.

The aspects of space weather and solar wind dynamics represent delicate and complex systems that are yet to be fully understood. However, this innovative research effort serves as a beacon of hope for scientists grappling with these challenges. More reliable forecasting models are not just about protecting our infrastructure; they also signify progress toward a more comprehensive understanding of the Sun and its myriad effects on planetary systems.

In conclusion, as scientists endeavor to decode the mysteries of the cosmos, the intersection of artificial intelligence and traditional astrophysics lays the groundwork for magnificent discoveries. The NYUAD team’s pioneering work exemplifies the potential of harnessing advanced technology to address some of space science’s toughest challenges, fostering a future where we can better predict and understand the solar phenomena that directly affect life on Earth.

Subject of Research: Not applicable
Article Title: A Multimodal Encoder–Decoder Neural Network for Forecasting Solar Wind Speed at L1
News Publication Date: 8-Sep-2025
Web References: https://iopscience.iop.org/article/10.3847/1538-4365/adf436
References: 10.3847/1538-4365/adf436
Image Credits: Courtesy of NASA/SDO and the AIA, EVE, and HMI science teams

Keywords

Artificial Intelligence, Solar Wind, Space Weather, NYU Abu Dhabi, NASA, Predictive Modeling, Machine Learning, Solar Dynamics Observatory, Charged Particles, Cosmic Phenomena, Astrophysics, Navigation Systems.

Traditional weather models and GNSS tomography techniques often produce smoothed and blurred representations of atmospheric moisture fields. The intrinsic limitation stems from the coarse resolution of raw GNSS derived data, which averages the integrated humidity content along satellite-to-receiver signals without capturing fine-scale structures. While downscaling techniques exist to enhance the resolution of these low-fidelity maps, their effectiveness is severely hampered by noisy and under-constrained humidity inputs, leading to unreliable interpretations that can misguide forecast models. Addressing this bottleneck requires a methodological innovation that not only sharpens the tomographic images but also preserves or improves their physical fidelity. The new research achieves this by harnessing a Super-Resolution Generative Adversarial Network (SRGAN) trained on state-of-the-art weather model outputs, effectively bridging the gap between low-resolution GNSS observations and high-resolution humidity fields.

The research team, led by scientists at the Wrocław University of Environmental and Life Sciences with international collaborators, presents a completely novel framework published in Satellite Navigation in August 2025. Their methodology creatively fuses the strengths of the Weather Research and Forecasting (WRF) system and GNSS tomography through a deep learning intermediary. The SRGAN operates as a sophisticated translator, converting blurry, spatially coarse atmospheric reconstructions into finely detailed three-dimensional humidity maps. By training this neural network on thousands of simulated atmospheric scenarios from the WRF model, the system learns to infer high-resolution structures—such as sharp moisture gradients and small-scale convective cells—from ambiguous low-resolution data. This marks the first instance where deep learning has been successfully employed to produce super-resolved GNSS tropospheric tomography, overcoming inherent limitations of traditional interpolation methods.

Testing the approach on real-world geographies with diverse meteorological characteristics provided compelling evidence of its transformative potential. Experiments conducted over Poland and California demonstrated substantial error reductions, with improvements up to 62% and 52% respectively when compared to baseline interpolation schemes. Notably, these tests included challenging rainy conditions, which notoriously complicate humidity retrievals due to rapid spatial and temporal moisture variability. The SRGAN-enhanced tomography preserved the fidelity of sharp humidity fronts and storm-sensitive regions, outperforming popular schemes such as Lanczos3 interpolation in unveiling meaningful atmospheric details. These results directly translate into improved input data quality for downstream weather prediction models, which depend heavily on accurate representations of moisture distributions to capture convective development and precipitation initiation.

A particularly groundbreaking aspect of this work lies in its use of explainable artificial intelligence (XAI) tools — namely Grad-CAM and SHAP — to illuminate the decision-making processes within the deep learning model. Unlike many black-box AI applications, this system provides transparent insights into which spatial regions and atmospheric features most influence its predictions. Visualization of the neural network’s “attention” revealed a pronounced focus on meteorologically sensitive areas, such as Poland’s western weather fronts and California’s coastal mountain ranges. This transparency is not merely academic; it facilitates validation by meteorologists and fosters trust in AI-generated maps for operational forecasting. The ability to explain why certain atmospheric features weigh more heavily in the model’s reconstruction is a milestone toward integrating AI safely and confidently within meteorological workflows.

This fusion of satellite navigation technology, advanced atmospheric modeling, and deep learning opens a new dimension in weather science. Previously, the indirect and sparse nature of GNSS tomography limited its operational utility, but now the refinement process elevates it into a powerful observational asset. The study demonstrates how assimilating higher-resolution humidity maps into existing weather models can drastically enhance our ability to predict small-scale, rapidly evolving weather phenomena. Precision in humidity fields enables better representation of cloud microphysics, convection triggering, and storm dynamics—elements essential for reliable forecasts of flash floods, severe thunderstorms, and other extreme weather events that critically impact societies worldwide.

Dr. Saeid Haji-Aghajany, the study’s lead author, emphasizes the practical significance of their innovation: “High-resolution atmospheric data is the missing link in forecasting the kind of weather that disrupts lives. Our approach doesn’t just sharpen GNSS tomography—it also shows us how the model makes its decisions. That transparency is critical for building trust as AI enters weather forecasting.” His words capture the dual importance of accuracy and interpretability in future meteorological tools, highlighting how the approach transcends mere data enhancement to offer a paradigm shift in forecast confidence and communication.

As climate change accelerates, intensifying the frequency and severity of extreme weather, the demand for sophisticated predictive capabilities grows urgent. This research contributes a vital piece to that puzzle by enabling meteorologists to observe and model atmospheric moisture with unprecedented clarity. By integrating this deep learning-based GNSS tomography into operational forecasting systems, early warning times for extreme events can be extended and false alarm rates potentially curtailed. Communities vulnerable to rapid-onset hazards like flash floods and tropical storms stand to benefit from improved situational awareness, enabling swifter, more informed responses.

Moreover, the framework’s compatibility with explainable AI principles aligns with evolving standards for responsible technology integration. The demonstrated ability to interrogate and understand AI model behavior will be critical in the coming era, where automated systems increasingly inform public safety decisions. This ensures that forecasts not only gain precision but also maintain accountability, transparency, and scientific rigor.

Looking forward, researchers envision incorporating this high-resolution, AI-enhanced GNSS tomography into global observation networks, bolstering international efforts to create comprehensive, high-fidelity weather monitoring systems. By complementing conventional remote sensing and ground-based observations with refined tropospheric humidity data, a new synthesis of meteorological inputs can emerge, enhancing model initialization and data assimilation pipelines. This would ultimately fortify resilience against climate-driven hazards worldwide, contributing to safer, more adaptive societies.

The breakthrough also stimulates exciting avenues for further research, such as extending the approach to different atmospheric constituents, enhancing algorithmic efficiency, and exploring real-time implementations. Given the modular nature of deep learning models, future iterations may integrate multi-source data streams, including radar and lidar, to achieve even more holistic environmental awareness. Such cross-disciplinary innovations are emblematic of the evolving landscape of Earth sciences, where artificial intelligence functions as both a magnifier and elucidator of natural phenomena.

In conclusion, the inaugural application of a Super-Resolution Generative Adversarial Network to GNSS troposphere tomography represents a milestone in atmospheric science and weather prediction. By marrying satellite navigation data with sophisticated AI and explainable techniques, the research opens new frontiers for visualizing atmospheric moisture at scales once thought unreachable. This advancement transforms blurred, ambiguous snapshots into vivid, actionable maps that capture the small-scale structures underpinning extreme weather events. As this technology matures and expands, it promises to elevate forecasting precision and trustworthiness, ultimately forging a stronger defense against the capricious forces of weather.

Subject of Research: Not applicable

Article Title: High-resolution GNSS troposphere tomography through explainable deep learning-based downscaling framework

News Publication Date: 14-Aug-2025

Web References:

• https://satellite-navigation.springeropen.com/articles/10.1186/s43020-025-00177-6
• https://satellite-navigation.springeropen.com/

References:
DOI: 10.1186/s43020-025-00177-6

Keywords: Troposphere, GNSS tomography, Super-Resolution Generative Adversarial Network (SRGAN), Weather Research and Forecasting model, Explainable AI, Grad-CAM, SHAP, Weather forecasting, Atmospheric humidity, Deep learning, Downscaling, Extreme weather prediction

Tropical easterly waves have long been recognized as precursors to many Atlantic hurricanes; however, their accurate detection has posed persistent challenges for meteorologists. These waves are clusters of convective clouds and associated wind patterns that propagate westward across the tropics. The complexity arises because TEWs often appear similar in satellite and observational data to other expansive tropical circulations like the ITCZ and MT, which do not necessarily develop into cyclones. Traditional observational methods and computational models struggled to distinctly classify these meteorological entities, particularly in complex regions such as the Caribbean basin, where atmospheric dynamics are convoluted.

Addressing this longstanding obstacle, Will Downs, a doctoral candidate in the Department of Atmospheric Sciences at the Rosenstiel School of Marine, Atmospheric, and Earth Science, spearheaded the creation of a convolutional neural network (CNN)-based AI tool. Leveraging four decades of historical weather data spanning from 1981 to 2023, this system was meticulously trained to parse enormous volumes of meteorological datasets comprising satellite observations, reanalysis products, and data from the NHC’s Tropical Analysis and Forecast Branch. The sophisticated CNN architecture enables the AI to learn the subtle spatial and temporal signatures unique to TEWs, ITCZ, and MT, effectively learning to distinguish them with exceptional accuracy.

The deep learning model’s robustness stems from its training on diverse climatic scenarios, including El Niño events that profoundly influence the West Atlantic and Pacific storm tracks. Notably, the AI identified a discernible westward expansion of the monsoon trough in recent Atlantic seasonal cycles and documented shifts in tropical wave behavior during strong El Niño phases in the Pacific. These findings not only improve forecast accuracy but also contribute valuable climatological insight into evolving tropical dynamics under changing global conditions.

Forecasters at the National Hurricane Center now utilize this AI-powered wave tracker in real-time, enhancing their situational awareness and predictive capability. Sharan Majumdar, a leading atmospheric scientist and advisor to Downs, highlights the transformational nature of this technology, emphasizing the system’s ability to provide comprehensive datasets tracking the lifecycle and trajectories of tropical waves. This advance enables meteorologists to monitor the evolution from diffuse cloud clusters into organized cyclonic structures with greater lead time, which is critical for issuing timely warnings and mitigating disaster impacts.

The AI’s capacity to detect weak yet significant tropical waves within the Caribbean Sea, traditionally a challenging area for wave tracking, marks a remarkable achievement. Prior methods often glossed over or misclassified these signals due to their subtlety and interference from surrounding meteorological phenomena. By isolating these signals, the AI offers novel avenues for research into localized storm genesis and aids in the refinement of regional weather models.

The project’s development involved rigorous collaboration between atmospheric scientists analyzing the intricate dynamics of tropical waves. Ph.D. student Aidan Mahoney, an intern at the NHC and co-researcher, contributed essential domain expertise to fine-tune the training data. Their combined efforts ensured the CNN was not a ‘black box’ but an interpretable and scientifically grounded tool, capable of unearthing fundamental meteorological insights while maintaining high predictive fidelity.

Downs’ personal journey into tropical meteorology is deeply intertwined with lived experience. Growing up in New Orleans amid Hurricane Katrina’s devastation and subsequently tracking tropical storms in the wake of Hurricane Isaac, his early engagement with storm dynamics fueled his academic pursuit of cyclogenesis—the process by which tropical cyclones form and intensify. His doctoral research extends beyond algorithm development, aiming to unravel the nuanced physical processes underlying wave formation and their variability in a changing climate.

Published in the prestigious Monthly Weather Review, the study titled “Using Deep Learning to Identify Tropical Easterly Waves, the Intertropical Convergence Zone, and the Monsoon Trough” represents a fusion of atmospheric science and cutting-edge AI methodologies. The research was generously supported by multiple grants from the National Science Foundation and fellowships from the University of Miami, underscoring the interdisciplinary nature of this work and its potential societal impact.

Technically, the CNN leverages convolutional layers adept at recognizing spatial patterns within the multidimensional meteorological inputs, enabling effective classification among complex weather systems. By integrating reanalysis datasets with near real-time operational inputs, the system translates historical knowledge into actionable intelligence, bridging research and operational meteorology. This computational innovation aligns with broader trends of employing AI to augment weather prediction, enhancing both accuracy and interpretability.

Beyond its immediate application to hurricane forecasting, this AI tool contributes to the broader atmospheric sciences community by providing a reproducible, scalable framework for pattern recognition within dynamic Earth systems. The wave tracker facilitates extensive climatological studies and could be adapted to other tropical basins worldwide, where wave dynamics similarly influence weather and climate.

As extreme weather events become more frequent and impactful, advancements such as this AI wave tracker are vital for bolstering resilience. By delivering early and reliable identification of hurricane precursors, this technology enables emergency managers, policymakers, and the public to prepare more effectively, potentially saving lives and reducing economic losses. The University of Miami’s Rosenstiel School continues to be at the forefront of marine and atmospheric research, embodying a commitment to leveraging science and technology for societal benefit.

Subject of Research: Not applicable

Article Title: Using Deep Learning to Identify Tropical Easterly Waves, the Intertropical Convergence Zone, and the Monsoon Trough

News Publication Date: 1-Aug-2025

References: Using Deep Learning to Identify Tropical Easterly Waves, the Intertropical Convergence Zone, and the Monsoon Trough, Monthly Weather Review, DOI: 10.1175/MWR-D-24-0195.1

Image Credits: NOAA

Keywords: Atmospheric science, Cyclones, Extreme weather events, Hurricanes, Weather forecasting, Weather simulations

Traditional forecasting methods primarily rely on numerical weather prediction models and various statistical approaches. While these methodologies contribute to our understanding of cyclone behavior, they often fall short in effectively capturing the complex interplay of environmental conditions and structural parameters that influence RI. The inherent complexity of these systems, characterized by numerous influencing factors—from sea surface temperatures to atmospheric dynamics—poses a significant barrier to accurate prediction.

In recent years, the integration of artificial intelligence (AI) into meteorological forecasting has emerged as a potential solution to enhancing prediction accuracy. However, numerous AI techniques have reported challenges, particularly high rates of false alarms and inconsistent reliability. This inconsistency underscores the ongoing need for innovative methodologies capable of addressing the unique forecasting challenges posed by RI events.

Research conducted by scientists at the Institute of Oceanology of the Chinese Academy of Sciences (IOCAS) has yielded a groundbreaking model aimed at forecasting tropical cyclone rapid intensification through the lens of "contrastive learning." Published in the esteemed Proceedings of the National Academy of Sciences (PNAS), the study represents a substantial leap forward in predictive technology, leveraging modern computational techniques to glean insights from historical cyclone data.

The new forecasting model employs a dual-input system, comprising an Input A that includes known RI TC samples and an Input B representing an unknown sample that requires forecasting. The model functions by extracting features from both inputs and calculating their proximity within a high-dimensional feature space. A minimal distance between the two inputs suggests a likelihood that Input B is also an RI TC, whereas a larger distance indicates a lower probability.

This innovative approach involves a comparison process where each unknown sample is juxtaposed with a set of 10 known RI TC samples. If more than five of these comparisons classify the unknown sample as an RI TC, it receives the same designation. This methodology is instrumental in improving the accuracy and reliability of RA predictions, as it allows the model to draw upon a breadth of comparative data.

The researchers employed satellite imagery along with pertinent atmospheric and oceanic data to maintain a balanced dataset, ensuring that both RI and non-RI TC data were equally represented. By refining this data balance, the model effectively learns the defining features of RI versus non-RI TCs, markedly enhancing its predictive capability during the training phase. The application of diverse data types enriches the model’s understanding, thus directly contributing to the improvement of overall forecasting accuracy.

In rigorous testing, the contrastive learning model demonstrated impressive performance metrics, achieving an accuracy rate of 92.3% when applied to data from the Northwest Pacific region between 2020 and 2021. Furthermore, it managed to reduce the false alarm rate to a remarkable 8.9%, significantly outperforming existing forecasting methods. Notably, this improvement translates to a 12% increase in accuracy and a reduction in false alarms by a factor of three, underscoring the model’s transformative potential in the realm of cyclone prediction.

Initially, the contrastive learning model was trained using reanalysis data; however, the researchers methodically transitioned to an operational forecasting environment by substituting the reanalysis data with numerical model forecast data from the ECMWF-IFS (European Centre for Medium-Range Weather Forecasts – Integrated Forecasting System) for the same time frame. This strategic pivot yielded comparable forecasting accuracy, reinforcing the model’s real-world applicability. Validation of the model’s performance within operational scenarios signifies an important development, paving the way for more reliable real-time meteorological prediction.

The implications of this advanced forecasting model are profound, particularly in terms of enhancing early warning systems. Given the potential for improved predictive accuracy, this advancement could significantly bolster disaster preparedness measures globally. Improved early warnings empower communities to make informed decisions, ultimately saving lives and minimizing property damage during intense weather events.

Prof. LI Xiaofeng, the corresponding author of the study, emphasized the model’s significance, stating, "This study addresses the challenges of low accuracy and high false alarm rates in RI TC forecasting. Our method enhances understanding of these extreme events and supports better defenses against their devastating impacts." Prof. Li’s remarks point to the broader implications of the research, highlighting its role in augmenting our understanding of tropical cyclone dynamics and equipping communities with tools for proactive risk reduction.

In conclusion, the emergence of the contrastive learning model represents a pivotal advancement in the scientific community’s approach to forecasting tropical cyclone rapid intensification. By effectively leveraging contemporary data analysis techniques within an innovative framework, researchers at IOCAS have paved the way for a more accurate and reliable forecasting paradigm. As climate change continues to alter storm patterns and intensities, honing our predictive capabilities will become increasingly critical.

Efforts to refine forecasting systems for tropical cyclones through innovative techniques such as AI and contrastive learning not only exemplify the marriage of traditional meteorological sciences and modern computational methodologies but also underscore the urgency of enhancing global resilience against extreme weather phenomena. This research stands as a testament to the relentless pursuit of scientific advancement in the face of the ever-evolving challenges posed by a changing climate.

As ongoing research continues to explore the depths of machine learning applications within meteorological sciences, the findings from this study serve as an inspiring benchmark. Advancements such as these delineate a future where forecasting tropical cyclone behavior is not only a formidable scientific challenge but a consummate reality through the integration of cutting-edge technology.

Subject of Research: Forecasting capabilities of tropical cyclone rapid intensification using contrastive learning
Article Title: Advancing forecasting capabilities: A contrastive learning model for forecasting tropical cyclone rapid intensification
News Publication Date: 21-Jan-2025
Web References: 10.1073/pnas.2415501122
References: Proceedings of the National Academy of Sciences
Image Credits: Not Provided

Keywords

Weather forecasting, Artificial intelligence, Meteorology, Tropical cyclones, Rapid Intensification.