The problem the researchers set out to quantify is not the typhoon itself but the chain reaction it unleashes. A landfalling storm typically arrives as a compound package of strong winds, torrential rainfall, and storm surge, which then cascades into secondary hazards—riverine flooding, urban waterlogging, and infrastructure failure—that propagate across scales and amplify losses. Climate projections indicate that although future typhoon frequency remains uncertain, maximum wind speeds and rainfall intensity are expected to increase, raising the likelihood that extreme rain and surge will strike concurrently. Fujian offers a stark test case. Its 3,324-kilometer coastline sits squarely in the East Asian monsoon belt, and between 2000 and 2020 typhoons caused an average of 12.74 billion yuan in direct economic losses annually—58.3 percent of the province’s total natural-hazard losses. More than 76 percent of those typhoon-related losses stemmed from compound disaster chains rather than any single hazard, precisely the conditions under which conventional single-hazard risk assessments break down.

To measure resilience against such cascades, the team defined typhoon disaster chain urban resilience, or TDCUR, organized into three capacities: absorption, the ability to withstand the initial shock; coping, the ability to manage impacts as they unfold; and recovery and adaptation, the ability to bounce back and adjust over time. These capacities were operationalized through 21 indicators spanning terrain, vegetation, impervious surface coverage, drainage and flood-control infrastructure, economic conditions, and population—among them three chain-specific sensitivity indices for typhoon–rainstorm–waterlogging, typhoon–rainstorm–flooding, and typhoon–strong wind–storm surge sequences. All indicators were computed on 30-arc-second grids of roughly one kilometer, restricted to a fixed urban mask covering areas with at least 600 residents per square kilometer and totaling about 9,680.6 square kilometers, so every year was compared across identical territory. Indicator weights were specified in advance using an objective procedure combining GeoDetector-based spatial stratified heterogeneity statistics with recursive entropy weighting, and Monte Carlo perturbation of those weights quantified the uncertainty surrounding each score.

The framework then tackles a problem that plagues most resilience studies: the mismatch between fine-grained data and the administrative units where decisions are made. Grid-level scores were aggregated to counties, cities, and eight major river-basin units using a population-aware scheme. Each cell’s exposed population—area multiplied by population density—was converted into an effective exposure weight through an exponential penalty, with a coefficient of 0.7, that systematically down-weights cells whose baseline resilience is already high. Unit-level resilience is the exposure-weighted mean of its cells, scaled by the share of the unit’s census population living in exposed cells. The result is an index reflecting not just where resilience is weak but where weakness and human exposure overlap, giving provincial, municipal, and county authorities a common metric for cross-level planning.

The headline numbers show real but uneven progress. The provincial mean TDCUR rose from 0.4275 in 2010 to 0.4571 in 2020, a 6.9 percent gain, and areas classified as very high resilience expanded by 1,638.6 square kilometers. Kernel density estimation showed the distribution’s peak shifting from 0.47 to 0.51 before settling at 0.50, while its width narrowed by about 22 percent—evidence that regional disparities converged even as averages improved. Yet the spatial pattern is a tale of two provinces. Western inland cities, with lower urbanization intensity, richer vegetation cover, and more dispersed populations and assets, consistently posted higher absorption and coping scores. In the eastern coastal belt the picture inverted: the lowest values appeared not in poor or peripheral areas but in the dense urban cores of Fuzhou, Quanzhou, and Xiamen, where impervious surfaces cover more than 85 percent of the land and drainage systems were built to outdated standards. Core districts including Gulou and Taijiang in Fuzhou and Siming and Huli in Xiamen actually lost resilience over the decade.

The multi-scale aggregation sharpens the contrast. The five weakest counties in 2020 all lay in the east, averaging just 57.8 percent of the resilience of the strongest western counties such as Yongding District, which scored 0.5016. Among cities, Xiamen ranked last at 0.3252, while Putian posted the fastest improvement at +0.0166. On the watershed scale, the coastal directly discharging composite basin scored lowest at 0.3710, whereas the Jinjiang Basin gained +0.0269—roughly 1.6 times the provincial mean increase—hinting at the payoff of integrated river-basin management. Component analysis explains the mechanism: Jinjiang’s median absorption capacity of 0.103 sits 58 percent below the provincial maximum of 0.245, and coping capacity in Siming, Huli, and Jinjiang ran 40 to 50 percent below comparable inland areas by 2020. Recovery capacity remained highest along the coast, but most of its decade’s gains accrued inland—a diffusion of improvement that stopped short of the urban cores that need it most.

Hotspot analysis converted those gradients into statistically rigorous geography. Getis-Ord Gi* statistics revealed a landscape of clustered low resilience and dispersed high resilience: significant cold spots covered 447 square kilometers, or 4.6 percent of the urban domain, with more than 80 percent concentrated in the Xiamen–Quanzhou core, while hot spots shrank to a mere 18 square kilometers scattered across inland cities. Between 2010 and 2020, cold-spot area expanded by 48 percent as hot-spot area contracted by 51 percent—a deepening spatial polarization. Local Moran’s I analysis confirmed a persistent low–low clustering belt along the coast, though it weakened by 243.7 square kilometers over the decade. Spatiotemporal classification sorted the cold spots into three trajectories: persistent cold spots occupying 43.8 percent of classified area along the Xiamen–Zhangzhou–Quanzhou coastline, diminishing cold spots at 4.0 percent in recovering inland counties, and emerging cold spots at 2.4 percent on urban fringes—early warning zones where vulnerability is only beginning to condense.

The study’s methodological punchline is its use of explainable machine learning as a diagnostic layer. The team trained an XGBoost regression model—gradient-boosted decision trees with a maximum depth of 6, 600 estimators, a learning rate of 0.05, and L1 and L2 regularization of 0.5 and 1.0—on grid-level observations pooled from all three years, with the 21 indicators as features and Monte Carlo-averaged TDCUR as the response. Tuned by grid search with five-fold cross-validation, the model achieved a coefficient of determination of 0.9932 and a root mean squared error of 0.0062 on held-out data. The authors then applied SHapley Additive exPlanations, using the TreeSHAP algorithm to decompose every prediction into additive contributions from individual indicators. Three variables dominated: typhoon–strong wind–storm surge sensitivity, contributing 23.52 percent of mean absolute SHAP values; typhoon–rainstorm–flooding sensitivity at 15.72 percent; and impervious surface proportion at 10.06 percent. Segmented regression identified sharp slope changes—empirical turning points—at normalized values of −0.60 for surge sensitivity, −0.66 for flood sensitivity, and −0.79 for impervious surface, the last corresponding to roughly 85 percent imperviousness, beyond which resilience losses accelerate. The researchers stress these are features of the fitted response surface, not physical or regulatory thresholds, and the machine learning was strictly post hoc: it explains the index without redefining it.

Interaction analysis revealed that the top drivers do not act independently. Across all 231 indicator pairs, the strongest joint association belonged to the flood-sensitivity and surge-sensitivity pairing, with a mean absolute SHAP interaction of 1.88 × 10⁻³, accounting for 22 percent of the total among the top ten pairs; impervious surface interacting with flood sensitivity contributed another 13.8 percent, and with surge sensitivity 12.0 percent. Most interaction values were negative, meaning that where high sensitivities and high imperviousness coincide, predicted resilience drops further than either factor alone would suggest. Mapping summed absolute SHAP values per grid cell and aggregating them across scales produced an unambiguous target list: Huli, Taijiang, and Gulou districts all exceeded 0.18 at the county level; Xiamen, Quanzhou, and Fuzhou topped the city rankings; and the Jinjiang, Minjiang, coastal directly discharging, and Jiulongjiang basins averaged about 0.145. A robustness check using only five core indicators shifted the results by just 3 to 5 percent and preserved the spatial rankings almost perfectly, with a Spearman correlation of roughly 0.96.

For planners, the framework converts diagnosis into a spatial work list. In the coastal cores, where imperviousness exceeds 85 percent, the authors point to nature-based measures such as rain gardens and permeable pavements, combined with drainage-system upgrading, storm-surge defense enhancement, and impervious-surface management—precisely because the machine learning shows those pressures interacting. Inland, the priority is the opposite: protecting the ecological buffers and vegetation cover that underpin high absorption capacity, and siting regional emergency supply hubs, such as in Yongding District, where geography favors support for coastal disaster response. A dynamic monitoring system tracking persistent, emerging, and diminishing cold spots, with periodic SHAP reanalysis after major interventions, would let strategies be iterated over time—an approach tied to the UN’s Sustainable Development Goal 11 for resilient cities. The framework has limitations the authors acknowledge: proxy indicators cannot deliver engineering-grade precision, landslide cascades are not yet included, and spatial autocorrelation in the training data may inflate the model’s apparent fit, motivating spatial cross-validation in future work. But the method is transferable to any typhoon-exposed coastline, and its central message resonates far beyond Fujian: a decade of double-digit economic growth did not automatically buy safety, and in the very districts where coastal wealth concentrates, the machinery of resilience—drainage, buffers, and surge defenses—has quietly fallen behind the rising risks.

The researchers initiated their investigation by addressing the growing need for reliable evaluation methods that consider the variability of seismic forces over time. Traditional seismic analyses often rely on stationary ground motion models that fail to account for the real-world complexities encountered during significant earthquakes. Recognizing this limitation, the authors employed a comprehensive probabilistic framework to assess the performance of a prototype single-pylon suspension bridge, which serves as a crucial component of urban infrastructure in many cities globally.

This innovative study utilizes advanced computational techniques and simulations to model nonstationary ground motions, reflecting the unpredictable nature of seismic events. By integrating real seismic data from past earthquakes, the researchers have developed a more accurate representation of the forces that these long-span bridges may endure. This methodology not only enhances the precision of the assessment but also contributes valuable insights into the dynamic behavior of suspension bridges during seismic activity.

A key aspect of this research is its probabilistic approach, which considers a range of uncertainty factors. The team conducted a thorough analysis of various potential seismic scenarios, examining how these factors influence the bridge’s response under different conditions. This thorough evaluation allows engineers to quantify risk levels and make informed decisions when designing bridges that must withstand the forces generated by earthquakes.

Moreover, Zhang and colleagues emphasized the importance of understanding the impact of structural design choices on seismic performance. By altering parameters such as the bridge’s material properties and geometric characteristics, they could observe how these changes affected overall resilience. Their findings reveal critical insights into the trade-offs that designers must consider to achieve the desired balance between performance and cost-effectiveness in the construction of long-span bridges.

In their results, the researchers identified specific design improvements that could enhance the seismic resilience of single-pylon suspension bridges. They revealed that implementing certain engineering practices could mitigate potential damage during seismic events, thereby ensuring greater safety for users and reducing economic losses associated with bridge failures. This aspect of the study is particularly appealing to both civil engineers and policymakers, as it offers actionable recommendations for future infrastructure projects.

The implications of this research extend beyond academic interest; they hold significant relevance for real-world applications. With urban populations increasing and infrastructure aging, the demand for safe, reliable bridges is more pressing than ever. By providing a robust assessment framework, this study aims to bridge the gap between theory and practice, enabling engineers to design structures that can withstand the rigors of seismic activity while also meeting the demands of modern transportation systems.

Another noteworthy contribution of this research is its potential to influence building codes and regulations. The findings on the probabilistic performance assessment of bridges could lead to revised standards that incorporate dynamic analyses for seismic design. Such updates would ensure that infrastructure development is aligned with cutting-edge research, ultimately fostering safer environments and minimizing risks associated with natural disasters.

Furthermore, Zhang et al.’s work aligns with ongoing global efforts to enhance urban resilience against natural disasters. As cities across the world face escalating risks from earthquakes, adopting advanced design methodologies informed by contemporary research will be crucial. This study serves as a testament to the evolving landscape of structural engineering, where innovation and rigorous analysis coalesce to address complex challenges effectively.

The research has already sparked interest among professionals in the field, with many advocating for its wider application in bridge design and evaluation. Conferences and seminars focused on civil engineering are expected to highlight these findings, ensuring that engineers are equipped with the knowledge needed to implement improved safety measures in bridge construction.

In conclusion, the work of Zhang, Mo, and Yang represents a significant advance in understanding the seismic performance of long-span single-pylon suspension bridges. By addressing the limitations of traditional evaluation methods and introducing a probabilistic framework that incorporates nonstationary ground motions, their research stands to make a profound impact on the engineering community. As the field moves forward, studies such as this one will be instrumental in paving the way for future innovations in infrastructure resilience.

In a world where earthquakes pose a significant threat to infrastructure and human life, the importance of such research cannot be overstated. The proactive measures recommended by these researchers will undoubtedly contribute to safer bridges and, by extension, safer cities, fostering a sense of security for communities worldwide.

Subject of Research: Seismic performance probabilistic assessment of long-span single-pylon suspension bridges

Article Title: Seismic performance probabilistic assessment of long-span single-pylon suspension bridge subject to nonstationary ground motions

Article References:

Zhang, J., Mo, Y., Yang, Z. et al. Seismic performance probabilistic assessment of long-span single-pylon suspension bridge subject to nonstationary ground motions.
Earthq. Eng. Eng. Vib. 24, 843–859 (2025). https://doi.org/10.1007/s11803-025-2340-6

Image Credits: AI Generated

DOI: July 2025

Keywords: Seismic performance, probabilistic assessment, long-span bridges, single-pylon suspension bridges, nonstationary ground motions.

Earthquakes remain a dynamic threat to structures worldwide, causing catastrophic destruction and loss of life. As urban areas expand and the demand for resilient infrastructures grows, the integration of comprehensive engineering solutions becomes paramount. This research notably focuses on the interaction between RC buildings and vertical cuts—an often overlooked aspect in conventional seismic designs.

A remarkable feature of this study is the numerical simulation model constructed to replicate real-world conditions. The researchers utilized advanced computational techniques to analyze the seismic response of buildings situated nearby reinforced vertical cuts. By employing methodologies that mirror various seismic events, the authors are capable of presenting detailed insights into how ground motion affects these structures, particularly in urban environments.

The study begins by providing a contextual foundation on ground motion characteristics and their influence on engineering designs for RC buildings. Ground motion during an earthquake can induce lateral forces that challenge structural integrity. This dynamic forces building codes to evolve continually, necessitating research that unveils hidden vulnerabilities—such as those posed by adjacent vertical cuts that may not have been previously considered.

Incorporating a range of variables, the study evaluates different configurations of vertical cuts adjacent to RC buildings. These configurations include variations in depth and the angle of the cut. This fundamental analysis aids engineers in better predicting how unique site conditions impact overall seismic performance. For engineers, understanding such variables can lead to designing safer and more resilient urban environments.

Furthermore, the authors detail their numerical methodologies, offering an in-depth look into the finite element models employed for simulations. The precision in modeling ground motion is emphasized, as different earthquake magnitudes and frequencies have unique impacts on structural performance. This level of detail ensures applicability across various seismic regimes, catering to regions with differing levels of earthquake hazards.

Crucially, this research explores the behavioral response of RC materials when subject to the vibrations generated by seismic activities. The reinforced concrete members of a building, designed to withstand certain limits, may experience unforeseen stresses due to adjacent vertical cuts. The interaction effects, compounded by the dynamics of ground motions, highlight vulnerabilities that engineers must account for in seismic design.

One of the pivotal findings of this research indicates that traditional design strategies may fall short in accurately predicting the performance of structures subjected to combined horizontal and vertical stressors induced by seismic activities. This realization underscores the need for adaptive engineering approaches that integrate new findings into updated building codes and practices.

Real-world implications of this study should not be underestimated as they extend well beyond academia. As urban populations increase, the likelihood of constructing buildings near vertical cuts rises. Furthermore, regions historically affected by earthquakes, such as those along tectonic plate boundaries, must recognize the importance of this research as they seek to implement effective building practices.

The authors call attention to the pressing need for updated design standards that incorporate these innovative research findings. Engineers and policymakers must collaborate to ensure that contemporary practices reflect learned experiences from advanced studies such as this one. By fostering a culture of continuous improvement based on empirical data, communities can enhance their resilience to seismic events.

As discussions continue surrounding climate change and its effects, the importance of this research becomes underscored by considerations of extreme weather events and geological shifts that could exacerbate earthquake risks. Therefore, it is imperative to understand the integrative nature of environmental factors impacting urban infrastructures and their surrounding landscapes.

The future of earthquake engineering is undeniably intertwined with the findings presented in this study. As the field advances, embracing numerical studies that challenge traditional methodologies will foster innovations to safeguard lives and properties. The role of empirical research is crucial in transitioning from conventional designs to adaptive strategies that meet the demands of modern engineering challenges.

Overall, it is evident that the comprehensive methodologies and analyses conducted by Amrita, Jayalekshmi, B.R. and Shivashankar, R. present unique insights that could drive reforms in the field of earthquake engineering. This study encourages continued exploration and responsiveness to the evolving challenges of seismic resilience. The countdown to October 2025, when the complete findings will be publicly available, has begun, and anticipation is growing within both the scientific and engineering communities.

Through a multidisciplinary approach that merges engineering principles with computational analysis, this research represents a significant advancement in the understanding of reinforced vertical cuts in earthquake-prone areas. By reshaping perspectives on seismic risk, it ultimately positions engineers to design buildings that can withstand the forces of nature more effectively, thereby enhancing safety and stability in our urban landscapes.

Subject of Research: Effects of ground motion on reinforced vertical cuts integrated with RC buildings

Article Title: Numerical study on reinforced vertical cuts integrated with RC buildings under the effects of ground motion.

Article References:

Amrita, Jayalekshmi, B.R. & Shivashankar, R. Numerical study on reinforced vertical cuts integrated with RC buildings under the effects of ground motion.
Earthq. Eng. Eng. Vib. 24, 959–976 (2025). https://doi.org/10.1007/s11803-025-2354-0

Image Credits: AI Generated

DOI: October 2025

Keywords: Earthquake Engineering, Ground Motion, Reinforced Concrete, Numerical Modeling, Seismic Analysis, Structural Integrity, Urban Resilience.

Flooding in urban areas is a multivariate problem characterized by nonlinear interactions between precipitation, terrain, drainage systems, and urban infrastructure. Conventional predictive methodologies, while effective in some respects, frequently falter when attempting to extrapolate beyond trained datasets or accommodate the rapidly shifting nature of rainfall distribution and intensity. To overcome these limitations, the research team employed a convolutional long short-term memory (ConvLSTM) neural network architecture, capable of capturing spatiotemporal dependencies intrinsic to flood phenomena.

ConvLSTM networks extend traditional LSTM capabilities by incorporating convolutional operations within the state transitions, allowing the model not only to process sequential temporal information but also to extract spatial features from input data like rainfall intensity grids. This architecture aligns perfectly with the requirements for urban flood prediction, where both time-dependent weather changes and the spatial heterogeneity of urban landscapes significantly dictate flood dynamics.

One of the most striking aspects of the study is its focus on dynamic rainfall patterns, recognizing that not all precipitation events impact urban flooding equally. Flash floods, sustained rainfalls, and intermittent showers present distinct challenges to predictive models, demanding a system adaptive enough to discern subtle variations in rainfall characteristics and their subsequent hydrological effects. The ConvLSTM model achieves this by integrating temporally sequenced rainfall data with spatially resolved urban morphology, generating nuanced flood risk forecasts.

The research methodology entailed training the ConvLSTM model on extensive datasets comprising rainfall measurements, urban topographic maps, drainage network schematics, and historical flood incidences. By coupling these diverse datasets, the model learned to associate specific rainfall sequences and spatial contexts with flooding outcomes. Importantly, the training included scenarios exhibiting variable rainfall intensities and distributions to enhance the model’s robustness against real-world unpredictability.

To verify the efficacy of their model, the researchers conducted exhaustive validation exercises, employing unseen rainfall events to assess the model’s predictive accuracy and generalizability. Results demonstrated that the ConvLSTM outperformed traditional machine learning approaches and physics-based hydrological models, especially in scenarios involving abrupt changes in rainfall patterns. This superiority underscores the potential of deep learning architectures to revolutionize urban flood forecasting.

A particularly innovative dimension of the study is the examination of the model’s extrapolation capability. Extrapolation—the model’s ability to accurately predict outcomes beyond the range of its training data—is notoriously challenging in environmental systems due to their complexity and nonlinearity. Through rigorous testing, the ConvLSTM showed promising extrapolation performance, suggesting it can provide reliable flood predictions during unprecedented or extreme rainfall events, which are becoming more frequent due to climate change.

Beyond the technical prowess, the implications of this research are profound for urban planners, emergency responders, and policymakers. Real-time flood prediction powered by such advanced models enables proactive resource allocation, early warning systems, and adaptive urban design strategies that collectively reduce flood damages and save lives. Furthermore, the model’s adaptability suggests scalability to diverse urban contexts globally, accounting for region-specific climatic and infrastructural nuances.

The fusion of spatial and temporal data within a deep learning framework represents a significant leap toward smarter, data-driven disaster risk management. By capturing the intricate interplay between rainfall dynamics and urban infrastructure, the ConvLSTM model provides a holistic view necessary for understanding and responding to flood hazards. This integrated approach surpasses prior models that often treated spatial and temporal factors independently, thereby limiting predictive accuracy.

Moreover, this research aligns with the broader trend of harnessing artificial intelligence to tackle complex environmental problems. The success of ConvLSTM in urban flood forecasting may inspire similar applications across other disaster domains, such as landslides, wildfires, and extreme heat events, where spatiotemporal modeling is essential. The uptake of such AI-driven solutions marks a transformative moment in disaster risk science and urban resilience frameworks.

While the study showcases impressive advancements, it also highlights ongoing challenges. For instance, data quality and availability remain pivotal for model performance; urban areas with sparse sensor networks or incomplete records may face difficulties in achieving comparable prediction accuracy. Addressing these data gaps through enhanced sensing technologies and open data initiatives will be critical for broad deployment.

Furthermore, explaining and interpreting deep learning models like ConvLSTM pose obstacles in gaining stakeholder trust and facilitating decision-making. Future work could incorporate explainability techniques to demystify model outputs, enabling clearer communication of flood risks and actionable insights to non-expert audiences ranging from municipal authorities to local communities.

The research also opens avenues for integrating real-time data streams, such as radar rainfall measurements and IoT sensor networks, into adaptive flood prediction systems. Dynamic updating of the ConvLSTM model in operando could elevate responsiveness during active flood events, potentially enabling minute-scale predictions that inform emergency operations with unprecedented precision and lead time.

In addition to immediate flood risk management, the model’s findings bear relevance for long-term urban sustainability and climate adaptation. As rainfall regimes evolve under global warming scenarios, continuous refinement of predictive models will be necessary to anticipate shifting flood patterns and inform resilient infrastructure investments. The ConvLSTM framework offers a flexible foundation to incorporate future climatological projections and urban growth trajectories.

Collaboration across disciplines—combining hydrology, urban planning, computer science, and social sciences—will be vital to fully leverage this modeling approach. Such interdisciplinary efforts ensure that technical innovations translate into tangible societal benefits, fostering communities that are more prepared, adaptive, and equitable in facing flood hazards.

Ultimately, this ConvLSTM-based urban flood prediction study exemplifies how state-of-the-art machine learning can address pressing environmental challenges with real-world impact. Its success reinforces the growing importance of artificial intelligence in sustainable development and disaster risk reduction, charting a promising course for safer, smarter cities amid uncertain climatic futures.

In the face of escalating urban flood risks, innovative technologies such as the ConvLSTM model provide vital tools for resilience. By delivering more accurate, dynamic, and extrapolative predictions, such approaches empower societies to anticipate and mitigate flood disasters effectively. The intersection of AI and urban hydrology heralds a new era in disaster preparedness—one anchored in data, science, and proactive intervention.

As cities worldwide strive towards sustainability under mounting environmental pressures, embracing advanced predictive analytics like the ConvLSTM model will be indispensable. This research marks a critical step forward, not only advancing scientific understanding but also equipping decision-makers with actionable foresight. In doing so, it contributes meaningfully to building flood-resilient urban futures that safeguard lives, livelihoods, and ecosystems.

Subject of Research: Urban flood prediction using deep learning models under dynamic rainfall patterns

Article Title: A ConvLSTM-Based Model for Urban Flood Prediction Under Dynamic Rainfall Patterns and Exploration on Its Extrapolation Capability

Article References:
Xiao, J., Wang, Z., Liao, Y. et al. A ConvLSTM-Based Model for Urban Flood Prediction Under Dynamic Rainfall Patterns and Exploration on Its Extrapolation Capability. Int J Disaster Risk Sci (2025). https://doi.org/10.1007/s13753-025-00685-8

Image Credits: AI Generated

The UNU-INWEH research team employed cutting-edge synthetic aperture radar (SAR) data acquired from the Sentinel-1 satellite to conduct a meticulous assessment of the damage across the hardest-hit urban centers, including Mandalay, Pyin Oo Lwin, Madaya, Kyaukse, Sagaing, Shwebo, and Woundwin. This remote sensing technique allowed for rapid, high-resolution mapping of building damage over vast areas, providing unprecedented detail about the spatial extent and severity of destruction caused by seismic shaking.

Analysis revealed an alarming figure exceeding 157,000 buildings categorized as likely damaged. The scale of the devastation deeply affected entire communities, with estimates indicating between 3,600 and 5,350 fatalities and approximately 200,000 individuals displaced from their homes. The city of Woundwin emerged as the epicenter of urban destruction, where 73% of buildings suffered damage, while in Mandalay, a major metropolitan hub, 36% of structures were compromised. This uneven distribution highlights complex factors including building stock, construction quality, and local geology that influenced damage patterns.

Critical infrastructure was not spared: at least three hospitals were completely destroyed, with 22 others suffering partial damage, severely limiting emergency medical response capabilities in the quake’s aftermath. Additionally, the earthquake triggered significant disruptions in vital water supply and energy distribution networks, compounding the humanitarian crisis. This breakdown in essential services emphasized the interdependence of resilient infrastructure systems for disaster risk reduction and community survival.

Cultural heritage sites also bore the brunt of the earthquake’s wrath. Thousands of historical pagodas and ancient monasteries, representing generations of Myanmar’s rich history and religious identity, sustained varying levels of damage. The loss of these structures signifies not only physical destruction but also a profound cultural and psychological impact on local populations whose identities are intertwined with these landmarks.

Dr. Manoochehr Shirzaei, Chief Scientist at UNU-INWEH’s Global Environmental Intelligence Lab and lead author of the report, emphasized that the tragedy, while immense, was not unforeseen. He highlighted that the primary cause of the high mortality and damage rates was the widespread prevalence of non-engineered buildings, specifically unreinforced masonry structures. Such buildings are inherently prone to collapse during seismic events due to their inability to withstand lateral forces generated by ground shaking.

The report detailed how technical deficiencies were compounded by systemic governance challenges. Despite the existence of the Myanmar National Building Code, established in 2016 to improve seismic resilience, enforcement has been inconsistent and inadequate. Political and security complexities within Myanmar further hinder efforts to implement effective building regulations and disaster preparedness strategies, leaving vulnerable populations at continued risk.

This event is illustrative of the multifaceted nature of seismic vulnerability, where technical inadequacies intersect with socio-political realities. The report underscores how seismic risk cannot be fully managed through engineering solutions alone but requires integrated approaches that encompass institutional capacity building, public education, and community engagement. Such multidimensional strategies are essential for breaking the cycle of recurring disaster losses.

Professor Kaveh Madani, Director of UNU-INWEH, stressed that the devastating impacts of earthquakes are largely preventable. He argued for a transformative shift toward embracing building codes, land-use planning, and public safety measures as critical pillars of public health policy. This includes fostering a culture of safety that prioritizes resilience as a foundational element of societal well-being, especially in seismically active regions such as Myanmar.

The report put forth a series of actionable recommendations aimed at enhancing future resilience. Central among these is the urgent need to adopt and rigorously enforce modern seismic building codes, recognizing their cost-effectiveness and lifesaving potential. This demand extends beyond new construction to include retrofitting existing vulnerable buildings, a crucial step for safeguarding critical facilities such as hospitals and schools.

Moreover, the research highlighted the importance of preserving cultural heritage through specialized retrofitting techniques designed to protect irreplaceable historical sites without compromising their integrity. Complementary to structural measures, sound land-use planning is advocated to limit developments in zones with elevated seismic hazards, thereby minimizing future exposure.

Education and capacity building form another cornerstone of the proposed strategy. The report identifies a pressing necessity for investment in public awareness programs, disaster education initiatives, and comprehensive training for engineers and builders. Such efforts ensure that earthquake mitigation measures are not only designed properly but also understood, accepted, and effectively implemented on the ground.

This pioneering rapid damage assessment employing remote sensing and artificial intelligence exemplifies how modern technology can revolutionize disaster response. By providing real-time insights into the scale and geography of destruction, these tools enable more efficient prioritization of emergency aid and reconstruction efforts, ultimately saving lives and optimizing resource allocation during critical periods.

As Myanmar grapples with the aftermath of this seismic catastrophe, the lessons learned resonate globally, particularly for other vulnerable regions where urban growth, governance challenges, and seismic risk converge. A paradigm shift toward resilience, driven by science, policy reform, and community participation, is indispensable to mitigating the devastating consequences of future earthquakes.

In sum, the March 2025 Myanmar earthquake serves as a stark reminder of the high human and socioeconomic costs linked to neglecting structural safety and institutional preparedness. Harnessing technological advancements alongside holistic governance reforms offers a pathway toward sustainable disaster risk reduction, turning tragedies into opportunities for lasting societal transformation.

Subject of Research: Building damage assessment and seismic vulnerability in Myanmar following the March 2025 earthquake.

Article Title: Building Damage Assessment of the March 2025 Myanmar Earthquake

News Publication Date: 2025

Web References:
https://unu.edu/inweh/collection/building-damage-assessment-march-2025-myanmar-earthquake
https://doi.org/10.53328/INR24MSIR002

References:
Shirzaei, M., Awasthi, S., Oyedele, E. O., Khorrami, M, Kamaraj, N., Werth, S., Matin, M., Madani, K. (2025). Building Damage Assessment of the March 2025 Myanmar Earthquake, United Nations University Institute for Water, Environment and Health (UNU-INWEH), Richmond Hill, Ontario, Canada.

Keywords:
Myanmar earthquake 2025, seismic vulnerability, building damage, unreinforced masonry, earthquake resilience, Sentinel-1 SAR, disaster risk reduction, seismic building codes, retrofitting, infrastructure damage, cultural heritage loss, remote sensing in disaster response

Utilizing state-of-the-art satellite radar interferometry, the research team constructed detailed, high-resolution maps capturing the subtle yet consequential subsidence patterns beneath densely populated metropolitan areas. These cities together house approximately 34 million residents—roughly 12% of the entire U.S. population—highlighting the extensive societal reach of this geophysical process. Satellite-based monitoring offers unprecedented precision, measuring tiny ground motions that, over time, can compromise foundational stability in complex urban environments.

The study’s results are unequivocal: every city examined exhibits significant land sinking, with at least 20% of urban areas subsiding. Even more alarming, 25 out of the 28 cities studied display subsidence in over 65% of their urban footprint. This widespread phenomenon accentuates a creeping threat that has received too little attention amid other urban challenges like traffic congestion or air pollution but poses a silent and persistent risk to critical infrastructure assets.

Subsidence, the gradual downward settling or sudden sinking of the ground surface, can severely degrade the structural integrity of buildings, transportation networks, bridges, and dams. Leonard Ohenhen, a former Virginia Tech graduate student and lead author of the study, emphasizes that even seemingly minor vertical shifts accumulate over time. These incremental movements may initially go unnoticed but progressively magnify vulnerabilities within urban systems, exacerbating weak points and significantly elevating flood risks in low-lying and coastal areas.

In terms of magnitude, cities including New York, Chicago, Seattle, and Denver sank at rates near 2 millimeters per year. Texas cities, however, present a starkly different and more troubling picture. Multiple Texan urban centers registered elevated subsidence rates — 5 millimeters annually on average — with localized pockets in Houston experiencing accelerations up to 10 millimeters per year. This demonstrates dramatic heterogeneity in subsidence velocity, highlighting the importance of localized monitoring and targeted intervention measures.

Houston’s experience elucidates one of subsidence’s most insidious aspects: spatial variability. Within metropolitan regions, specific zones may sink markedly faster than adjacent neighborhoods, inducing uneven ground deformation. Unlike flooding, which typically poses a risk when water levels breach certain heights, differential land motion incrementally imposes mechanical stresses on infrastructures. Uneven sinking can induce cracking, tilting, and foundational destabilization, often long before damage becomes perceptible, undermining safety in a stealthy and persistent manner.

Manoochehr Shirzaei, Associate Professor at Virginia Tech and co-investigator on the project, explains that rising variability in subsidence rates significantly amplifies infrastructure risk. Cities like New York, Las Vegas, and Washington, D.C., display such differential sinking patterns, raising red flags for urban planners and engineers tasked with maintaining resilient frameworks in dynamic environments. The latent nature of these risks means that irreversible damage may manifest suddenly and catastrophically after years of undetected degradation.

The root cause of this alarming subsidence is primarily anthropogenic: groundwater extraction. As urban populations burgeon and the demand for potable freshwater soars, cities increasingly tap into underground aquifers to meet their needs. When water is withdrawn from these subterranean reservoirs faster than natural replenishment occurs, the aquifer materials compact, causing the overlying land surface to subside. This geotechnical process involves soil consolidation and loss of pore water pressure, physically compressing sediment layers and shrinking the volume of the subsurface matrix.

Compounding this issue is climate variability and shifting precipitation patterns, which interact with socio-economic growth to accelerate subsidence trends. Fluctuations in seasonal rainfall and prolonged drought conditions reduce recharge rates of aquifers, intensifying depletion linked to human extraction. As previously stable urban areas begin to subside, they become increasingly vulnerable to flooding, infrastructure failure, and progressive land degradation, further complicating urban sustainability and disaster risk management efforts.

Given the widespread risks highlighted in the study, integrating continuous land subsidence monitoring into urban planning frameworks is imperative. This involves establishing systematic, long-term geodetic observation networks capable of detecting minute land surface movements in real time, enabling early warning and preemptive response. Moreover, detailed mapping of differential subsidence can inform engineering design adjustments and prioritize areas for infrastructure reinforcement to ensure resilience against uneven ground movement.

Mitigation strategies proposed by the research emphasize sustainable groundwater management practices aimed at reducing excessive withdrawals. Efforts may include promoting alternative water sources, enhancing aquifer recharge programs, and implementing regulatory frameworks that control usage rates. Equally critical is enhancing infrastructure resilience through adaptive planning that accommodates localized subsidence variability, ensuring that transport corridors, utilities, and critical facilities retain operational integrity despite ground movement.

This latest research builds on Virginia Tech’s comprehensive efforts to understand urban flood and sinking risks across U.S. coastal cities. In a related study, the research team mapped flood vulnerabilities for 32 cities on the Atlantic, Pacific, and Gulf coasts, projecting conditions out to 2050. Additionally, they identified regions of the Atlantic coast sinking as much as 5 millimeters per year, emphasizing that subsidence compounds the effects of sea-level rise, necessitating integrated and proactive regional management practices.

Together, this body of research underscores subsidence as an urgent, if often overlooked, urban challenge with far-reaching consequences. By illuminating the invisible yet pervasive sinking beneath America’s cities, the Virginia Tech team calls for heightened awareness, innovative policy integration, and interdisciplinary collaboration among geophysicists, urban planners, engineers, and policymakers to safeguard the future of urban landscapes in a changing environment.

Subject of Research: Urban land subsidence driven by groundwater extraction across major U.S. cities and its impact on infrastructure and flood vulnerability.

Article Title: [Not Provided]

News Publication Date: 8-May-2025

Web References:

• https://www.nature.com/articles/s44284-025-00240-y
• https://news.vt.edu/articles/2024/01/research-sinkingcoasts.html
• https://news.vt.edu/articles/2024/01/COS-PNAS-subsidence.html

Keywords: Subsidence, Geophysics, Earth sciences, Climatology, Climate change, Climate data, Climate variability, Groundwater

Urban pluvial flooding occurs when intense rainfall overwhelms drainage systems, causing surface water accumulation that can disrupt city infrastructure and endanger millions. Traditional hydrodynamic models, though accurate, often require intensive computational resources and time, limiting their utility for real-time disaster response. To overcome these limitations, the team devised a hybrid modeling framework that synergizes convolutional neural networks (CNNs)—a class of deep learning algorithms known for extracting spatial features from complex data—and cellular automata (CA), which simulate the spatially distributed evolution of flood dynamics over discrete time steps.

The heart of this innovation lies in coupling the data-driven capacities of CNNs with the spatially explicit and rule-based characteristics of cellular automata. Unlike conventional models that rely purely on physical parameters and extensive simulations, this approach applies CNNs to dynamically weight the transition rules governing the CA, effectively learning and adapting to the nuanced patterns of water flow in urban settings. This dynamic weighting enables the CA to model the flooding process more realistically and accurately, accounting for the heterogeneous nature of urban terrain, drainage networks, and rainfall distribution.

Importantly, the model was trained and validated using high-resolution datasets obtained from a metropolitan area prone to pluvial flooding events. This dataset included digital elevation models, land use maps, rainfall time series, and historical flood records. By integrating these heterogeneous data sources, the CNN component could discern key hydrological features that govern flood propagation while the CA component efficiently simulated the temporal evolution of the floodwaters across the urban terrain. This hybridization results in a robust predictive tool capable of considerably reducing computational costs compared to traditional numerical simulations.

The researchers highlight that the CNN-weighted CA model exhibits remarkable speed, achieving real-time or near-real-time forecasting capabilities, a feature critical for emergency management and urban planning agencies. Such rapid predictions allow for timely warnings and the implementation of flood mitigation strategies such as dynamic traffic rerouting, emergency evacuations, and water diversion measures. The scalability of the model also means it can be adapted to cities worldwide, provided that sufficient local data is available for training.

Another core advancement offered by this research is the model’s resilience to data gaps and uncertainties often encountered in urban hydrological data collection. Traditional hydraulic models typically require continuous, high-quality input data, but the neural network training phase endows the system with the ability to generalize from incomplete or noisy data, maintaining reliable prediction performance. This adaptability is a game-changer in disaster-prone urban environments where sensor failures, communication breakdowns, or unexpected meteorological events may hamper data availability.

Moreover, the model’s modular design enables seamless integration with other urban management platforms. By serving as the forecasting engine, the CNN-weighted CA model can feed predictions into geographic information systems (GIS), smart city dashboards, and decision support tools, empowering stakeholders with actionable, spatially explicit flood risk assessments. This integrated approach paves the way for more responsive, data-driven urban resilience frameworks that leverage both cutting-edge artificial intelligence and established hydrological modeling methods.

The study’s extensive validation experiments demonstrated that predictions generated by the CNN-weighted CA model align closely with observed flooding extent and depth metrics from past flood events. The model outperformed conventional hydrodynamic solvers in both computational efficiency and predictive accuracy, particularly in complex urban microtopographies where traditional methods struggle. Its ability to represent localized pooling effects, flow paths through urban canyons, and rapid shifts in flood extents under varying rainfall intensities marks a significant advance in urban flood science.

Beyond emergency forecasting, such a model provides urban planners and engineers with a powerful tool to evaluate the impacts of land use changes, drainage system upgrades, and climate adaptation measures. By simulating different scenarios, the CNN-weighted CA system can inform infrastructure investments and regulatory policies aimed at reducing flood vulnerability and enhancing the sustainability of urban environments. This capability represents a crucial intersection between scientific innovation and practical urban governance.

This pioneering research also opens new avenues for interdisciplinary collaboration, merging expertise from hydrology, computer science, urban studies, and environmental engineering. The successful development and deployment of such a hybrid model demonstrate the transformative potential of artificial intelligence techniques when creatively applied to long-standing environmental challenges. As urban centers continue to grapple with the consequences of extreme weather, models like this one will be indispensable in shaping resilient and adaptive cities.

Looking ahead, the research team suggests several directions for future work, including extending the modeling framework to incorporate subsurface water flow, sediment transport, and pollutant dispersion during flood events. They also aim to improve the model’s interpretability, providing end-users with clearer insights into how specific urban features and rainfall inputs influence flood outcomes. Such transparency is essential for fostering trust and facilitating the adoption of AI-driven models within policy and operational contexts.

The algorithm’s design also lends itself to continuous updating as new data becomes available, making it suitable for learning and evolving in response to changing urban environments and climatic conditions. This dynamic learning aspect promises a long-term, sustainable approach to urban flood risk management, where predictive models improve incrementally based on real-world feedback and monitoring data streams.

In essence, the CNN-weighted cellular automaton model represents a paradigm shift in urban flood forecasting, demonstrating how artificial intelligence can revolutionize environmental hazard prediction. Its blend of speed, accuracy, and adaptability equips cities with vital knowledge to safeguard lives, property, and economic vitality against the mounting threat of pluvial floods. By blending physics-based modeling traditions with machine learning advances, Yang, Liu, Wang, and their colleagues offer a promising blueprint for the urban resilience challenges of the future.

As cities worldwide confront escalating flood risks due to climate change-induced shifts in precipitation patterns and urban expansion, tools like this new model will become ever more critical. The research not only advances scientific understanding but also sets a foundation for more informed urban planning and disaster preparedness. By facilitating rapid, actionable predictions, the CNN-weighted CA approach could save lives, reduce economic losses, and enable smarter urban development in the decades to come.

Ultimately, this study embodies the convergence of technology and society, illustrating how innovative computational approaches can transform how communities anticipate and respond to natural disasters. The model underscores the importance of interdisciplinary research and offers a powerful example of AI-driven science serving the public good. As cities grow and climate hazards intensify, such advanced forecasting tools may become the bedrock of 21st-century urban resilience strategies.

Subject of Research: Urban pluvial flooding prediction using hybrid AI and cellular automaton modeling.

Article Title: A Convolutional Neural Network-Weighted Cellular Automaton Model for the Fast Prediction of Urban Pluvial Flooding Processes.

Article References: Yang, J., Liu, K., Wang, M. et al. A Convolutional Neural Network-Weighted Cellular Automaton Model for the Fast Prediction of Urban Pluvial Flooding Processes. Int J Disaster Risk Sci 15, 754–768 (2024). https://doi.org/10.1007/s13753-024-00592-4

Image Credits: AI Generated