Advancing the Understanding of Risk, Extreme Weather Impacts, and Disasters with Interactive and Emerging Technologies

Meeting the moment: decision support amidst great environmental change and uncertainty

Decision making is inherently a complex social and cultural process that is shaped by myriad influential factors both internal and external to the environments, people, and institutions affected. Natural resource management is no exception in this regard. As the Earth’s climate rapidly changes, disturbances increasingly threaten forests across the globe, while the demand for resilient conditions and ecosystem services increases. As risks and threats to forests are building, so are assumptions, uncertainties, and stakes associated with management and mitigation outcomes. Decision support tools (DSTs) serve many functions in landscape and forest management, most centrally in helping decision makers and interest holders cope with complexity and uncertainty. Similarly, increasingly complex data, statistics, ecosystem dynamics, uncertainty, and technological advances have driven the evolution and integration of DSTs into forest and landscape management decision processes. We explore five factors driving DST development and integration into forest ecosystem management: environmental change, risk management, call for transparency, implicit and explicit social contracts, and technological advancement. We identify the challenges that DST growth and expanding deployment have addressed, as well as the emerging dilemmas that their current and future uses are likely to create. As environmental risks mount with changing climate, and computing capabilities continue to advance (e.g., statistical models, artificial intelligence), social norms and priorities are also changing. DSTs are expected to become central to forest and landscape management to help adjudicate the complexities of managed and unmanaged systems, the consequences of management actions and inaction, and their impact on environmental quality and forest resilience.

Flood damages in India – causes, data analysis, and way forward

ABSTRACT Floods are a recurring and highly damaging disaster in India. This paper begins with a brief review on meteorological and hydrological processes relevant from a flooding perspective in India. Subsequently, flood damage data pertaining to area and population impacted and damage to crops, houses, humans, and public utilities for the past about 70 years published by the Government of India have been analyzed to determine the overall and recent trends. In recent times, the area and population impacted by floods are showing a declining trend, but damage values for houses, public utilities, and total damages are seen to be mounting. Also, small cities are new areas of flood vulnerability. Among other steps, flood management efforts should focus on further curtailing human deaths by reducing exposure, early warnings/forecasts and timely evacuation to safer areas. For exposure reduction, experience of other countries can be gainfully employed, e.g. the ‘Room for the River’ approach implemented in the Netherlands. It would also be helpful to develop a disaster database comprising time series and spatial data of relevant variables by collating efforts of related organizations. Considering the current water development scenarios and future projections of causative variables, it would be necessary to follow climate‑resilient development (CRD) pathways.

A Comprehensive Disaster Risk Analysis Model With GeoAI

Abstract. Natural and technological disasters continue to threaten communities, infrastructure, and the environment, and the cascading nature of contemporary risks complicates their assessment. This study presents a disaster risk analysis model coupling Geographic Information Systems (GIS), ensemble machine learning, and AI-driven interpretation tools, collectively termed GeoAI, to support multi-hazard risk assessment, resilience planning, and citizen-oriented risk communication. Rather than building isolated models per hazard, the framework applies a single, modular pipeline consistently across flood, wildfire, earthquake, landslide, drought, and urban heat island hazards. Hazard, vulnerability, and exposure layers are derived from open geospatial datasets and processed in QGIS, after which Random Forest and XGBoost classifiers generate hazard and vulnerability maps validated using AUC-ROC, F1-score, and Cohen's Kappa. A distinctive component is an AI agent built on Large Language Models (LLMs) and the Model Context Protocol (MCP), which queries structured risk databases and produces region-specific narrative risk reports in natural language. Outputs are delivered through a web-based platform with an MCP-connected chatbot, lowering the barrier to understanding complex risk information for experts and the public. The model was tested in Türkiye's Marmara Region, which is important due to its dense population, heavy industry, and earthquake risk along the North Anatolian Fault. The pilot showed good results: XGBoost performed better than the baseline models, and the LLM-based interpretation layer gave clear, well-grounded outputs. The framework offers a scalable, open, interoperable approach linking spatial analytics, machine learning, and generative AI for evidence-based disaster risk reduction.

Sand and dust storm disaster risk reduction framework for Kuwait

Hydrologic Science Opportunities to Better Understand Floods: A Community Perspective

We synthesize community priorities for advancing flood science and flood decision support over the next decade. We argue that useful information for flood monitoring and forecasting require integrated observations and models that quantify where water is, how much is stored, how fast it moves, how watershed conditions prime flood response, and how river, floodplain, and coastal geometry control inundation. We identify four priority science gaps: topo-bathymetry, surface water dynamics, antecedent land-surface conditions, and high-resolution precipitation forcing for flash floods. Progress will require sustaining trusted baseline observations while investing in targeted innovation, model-observation fusion, and decision-ready products developed with operational partners. Together, these advances will improve early warning, emergency response, infrastructure planning, recovery, insurance, zoning, and long-term flood-risk reduction. This white paper is an outcome of a community-led, community-engaged effort to elevate hydrologic science opportunities which would have significant benefit to support decision-making for drought, floods, water quality, water supply and water demand.

Climate adaptation and design: from science to action through advanced research and widely shared skills

The climate crisis is a growing risk for cities, infrastructure, and landscapes. The rise in global mean temperature (approximately more than ~1.3°C compared with the pre‑industrial period), and the higher frequency and intensity of extreme weather and climate events are already affecting key sectors such as health, the economy, and safety. Alongside ambitious mitigation policies, making adaptation strategies workable is now a concrete need for design practice, as well as for land and asset management. In this chain of processes, climate science does not only “provide scenarios”. It also builds information that can be used in the built environment, such as choosing the most suitable datasets, checking consistency between models and observations from the past, and helping decision‑makers read uncertainties in a way that fits technical choices. Experience from applied research and from collaborations with actors working on planning, infrastructure, and service management shows that the added value is given by the ability to turn high quality and innovative data into requirements and thresholds that designers and administrations can understand, and into monitoring systems that allow adaptation choices to be improved over time. Generally speaking, the entire process “from data to actions” requires a multidisciplinary chain that leads: (i) from data availability to interpretation through clear indicators; (ii) to risk assessments that include hazard, exposure, vulnerability, and adaptive capacity; (iii) to prioritising and implementing measures; and (iv) to continuous monitoring of effectiveness over time. One of the most delicate steps is co‑design with administrations, professionals, and citizens. To work well, it needs a shared language, ongoing dialogue, and innovative skills from the scientific community to both maximise environmental and social co‑benefits, and reduce inequalities that climate change tends to worsen.