The North Anatolian Fault Zone is a natural laboratory for this kind of work. It slices across northern Turkey for roughly 1,200 kilometers, accommodating the westward extrusion of the Anatolian plate as it grinds between the Eurasian and African-Arabian plate systems. The fault has a well-documented history of sequential ruptures, with large earthquakes migrating along its length over the past century, including the devastating 1999 Izmit and Duzce events. For the new study, the fault was divided into nine predefined segments, each treated as an analytical unit with its own seismic history and hazard profile. This fault-specific approach departs from broad regional hazard maps, which average risk over large areas and can obscure the concentrated danger posed by a particular locked segment.

At the heart of the framework is a dataset of 539 seismic events drawn from Turkish earthquake catalogs, including records maintained by the Turkish Accelerometric Database and Analysis System operated by AFAD, the country’s disaster and emergency management authority. From this catalog, Ozkan engineered a set of predictive features designed to capture what he describes as short-to-medium-term seismic memory indicators. These are statistical fingerprints of recent earthquake activity on a segment, such as patterns in the timing and magnitude of preceding events, that encode how the fault remembers its own recent behavior. The idea builds on decades of seismological thinking, from the classic Gutenberg-Richter frequency-magnitude relationship to the seismic gap hypothesis of McCann and colleagues in 1979, which holds that segments that have not ruptured recently accumulate the greatest pending hazard.

The machine learning core of the study is the Extreme Gradient Boosting algorithm, widely known as XGBoost. This ensemble technique builds a hierarchy of decision trees in sequence, with each new tree trained to correct the residual errors of its predecessors. Gradient boosting has become a workhorse of tabular data science because it handles heterogeneous features well, resists overfitting through regularization, and often outperforms deep neural networks on structured datasets of modest size. In head-to-head comparison within this study, XGBoost demonstrated superior predictive capability over alternative approaches, ultimately achieving a final test Area Under the Receiver Operating Characteristic Curve score of 0.8930. An AUC of that magnitude indicates that the model ranks a randomly chosen future major earthquake above a randomly chosen quiet period nearly nine times out of ten, a level of discrimination that is considered strong for a problem as notoriously difficult as earthquake forecasting.

Perhaps the most consequential part of the work is not the classifier itself but the calibration layer wrapped around it. Raw machine learning outputs are probabilities in name only; without calibration, a stated 40 percent chance may not correspond to any meaningful real-world frequency. Ozkan performed a high-resolution probability calibration and imposed what he calls a strict Zero Miss operational strategy. The logic is blunt: for disaster management, failing to warn of a major earthquake is far more costly than issuing occasional false alarms. The optimization therefore searched for the decision boundary that would capture every major event in the test set, even at the price of reduced precision. That optimal boundary was formally established at a 35 percent probability threshold.

The results at that threshold are striking. When the calibrated framework was evaluated, it successfully captured 100 percent of the major earthquakes in the test data, meaning no event of magnitude 5.6 or greater slipped through unflagged. At the same time, the model achieved a balanced accuracy of 87.3 percent, a metric that averages the detection rate for hazardous events and the correct rejection rate for quiet periods, thereby preventing a large class of negatives from inflating the score. In practical terms, the framework behaved like a smoke detector tuned to be extremely sensitive: it rarely stays silent when danger is present, while still avoiding the constant crying wolf that would erode institutional trust in any operational warning system.

With the classifier calibrated, the final step was deployment. Ozkan applied the framework to evaluate future hazard probabilities across each of the nine predefined fault segments for their upcoming statistical cycles. The output is a quantitative, segment-by-segment ranking of hazard potential, expressed as probabilities rather than vague qualitative categories. This kind of dynamic, data-driven assessment could give disaster management authorities a defensible basis for deciding where to position search-and-rescue capacity, pre-stage emergency supplies, prioritize retrofitting programs, and focus public preparedness campaigns. Static hazard maps, updated on decadal timescales, cannot offer that level of temporal responsiveness.

The study sits within a rapidly expanding field. Machine learning approaches to seismology have progressed from early artificial neural networks trained on magnitude time series and seismic electric signals, through radon monitoring models, to modern deep learning architectures such as LSTM networks applied to seismicity analysis and satellite data streams. Recent work has extended these methods to ground motion modeling for probabilistic seismic hazard analysis in subduction zones and to real-time prediction of spectral acceleration for earthquake early warning. What distinguishes the new framework is its explicit marriage of classification performance with operational threshold calibration, an element that much of the academic literature leaves as an afterthought but that determines whether a model can actually be used in an emergency management context.

Important caveats remain. The framework was developed and tested on a single fault system, and its 539-event dataset, while substantial for a fault-specific analysis, reflects the catalog completeness and magnitude homogeneity of the Turkish record. Earthquake prediction in the strict sense, meaning the deterministic specification of the time, place, and magnitude of a future event, remains beyond any existing method, and this study does not claim otherwise. What the framework offers is a probabilistic hazard potential, a statement about relative likelihood over statistical cycles, which is a fundamentally more modest and more defensible objective. The author also reports that no external datasets were generated or analyzed beyond the study itself, and the work was conducted without dedicated funding, underscoring the individual, exploratory nature of the research.

Even with those qualifications, the implications are considerable. Turkey’s population is concentrated along corridors that the North Anatolian Fault threads like a fuse, and the Marmara region in particular is regarded by many seismologists as overdue for a major rupture. A tool that can translate decades of cataloged seismicity into calibrated, segment-specific probabilities offers exactly the kind of quantitative guidance that logistical planners need, converting abstract seismological knowledge into actionable resource allocation. If the framework’s performance holds under independent validation and in other tectonic settings, threshold-calibrated machine learning could become a standard component of the seismic risk toolkit, sitting alongside probabilistic seismic hazard analysis and operational forecasting systems rather than replacing them. The study demonstrates that the bottleneck in earthquake forecasting may no longer be the raw predictive power of the algorithms, but the careful, operationally minded engineering that turns a good classifier into a trustworthy decision aid.

Subject of Research: Machine learning-based fault-specific seismic hazard assessment along the North Anatolian Fault Zone

Article Title: A threshold-calibrated machine learning framework for evaluating fault-specific seismic hazard potentials

Article References: Ozkan, E. (2026). A threshold-calibrated machine learning framework for evaluating fault-specific seismic hazard potentials. Earth Science Informatics, 19(11), Article 210. https://doi.org/10.1007/s12145-026-02265-w

Image Credits: AI Generated

DOI: 10.1007/s12145-026-02265-w

Keywords: seismic hazard, machine learning, North Anatolian Fault, XGBoost, earthquake forecasting, threshold calibration, probability calibration, fault segments, Turkey, disaster management, balanced accuracy, seismicity indicators

Researchers led by Sk Tahsin Hossain and Tan Yigitcanlar of Queensland University of Technology, working with colleagues at the Chinese Academy of Sciences and Peking University, have unveiled an Artificial Intelligence of Things, or AIoT, enabled urban platform designed to automate flood detection, exposure assessment and impact mapping. The concept is deceptively simple but technically ambitious: instead of relying on slow, manual overlays of flood maps against property datasets, the platform ingests satellite imagery, runs a pretrained deep learning model to delineate inundation, and then automatically cross-references the resulting flood polygons with authoritative data on suburbs, transport infrastructure, buildings and population. The entire pipeline operates within the Esri ArcGIS ecosystem, delivering results through interactive dashboards that refresh as new imagery is processed.

The stakes are considerable. Between 1990 and 2022, more than 4,700 flood events were documented across 168 countries, affecting over 3.2 billion people, killing 218,353 and causing economic losses exceeding 1.3 trillion US dollars. Floods are Australia’s second-deadliest natural hazard after heatwaves, accounting for roughly 20 percent of all hazard-related deaths since 1900, and Queensland is the nation’s most flood-prone state. A statewide analysis by the Queensland Reconstruction Authority found that 60 percent of local councils face high flood risk, while the Climate Council reports that around 70 percent of Queenslanders have experienced at least one flood in the past five years, the highest exposure rate of any Australian state.

What distinguishes the new platform from existing smart-city systems is its insistence on closing the loop between detection and consequence. The authors note that most current flood platforms focus on delineating flood extent and stop there, leaving the critical question of what and who is affected to laborious human analysis. Their architecture is organised into three interdependent layers typical of AIoT frameworks: a sensing layer that can accommodate satellite remote sensing, IoT water-level and rainfall sensors, drone imagery and weather stations; an edge or fog layer for rapid preprocessing and anomaly detection; and a cloud platform layer where deep learning models perform flood extent extraction and object-level mapping before pushing results to decision-support dashboards. For the demonstration, satellite imagery served as the primary sensing source, but the researchers stress that the downstream components are deliberately agnostic to the sensing modality, allowing real-time IoT sensor streams to be plugged in later without redesigning the workflow.

At the heart of the system sits a remarkable piece of open science: the Prithvi-Flood Segmentation model, co-developed by NASA and IBM and distributed through the ArcGIS Living Atlas. Prithvi is a Vision Transformer trained with a self-supervised masked autoencoder strategy and fine-tuned on the Sen1Floods11 benchmark, a collection of 446 labelled image chips drawn from 14 biomes, 357 ecoregions, six continents and 11 major flood events. The model ingests a six-band composite from Harmonised Sentinel-2 or Landsat imagery, ordered as blue, green, red, narrow near-infrared and two shortwave-infrared bands, and classifies every pixel as no water, flood water, or no data and clouds. Its reported performance is striking: an overall accuracy of 97.25 percent, a mean Intersection-over-Union of 88.68 percent, and a flood-water IoU of 80.46 percent. Crucially, when tested on an unseen flood event in Bolivia, the model retained a mean IoU of 86.7 percent, evidence of genuine generalisation across geographic and hydrological conditions.

To demonstrate the platform, the team turned to the March 2022 floods, selecting 62 suburbs across Logan and the Gold Coast, 34 from Logan and the remainder from the Gold Coast, covering both directly inundated areas and adjacent communities at risk. Suburb boundaries were dissolved into a single administrative polygon that acted as a clipping mask for the satellite imagery. The clipped GeoTIFF was then fed to the Prithvi model through the Classify Pixels Using Deep Learning tool, executed on a GPU with test-time augmentation enabled. The classified raster was reclassified, converted to polygons, enriched with attributes, and published as hosted feature layers in ArcGIS Online. In the demonstration setup, equipped with 64 gigabytes of system memory and an NVIDIA A40 GPU, the segmentation step completed in under ten minutes for the entire area of interest.

The real innovation lies in what happens next. Five analytical modules transform raw flood extent into operational intelligence. Module A intersects flood polygons with suburb boundaries and calculates the geodesic flooded area per suburb. Module B classifies every railway station as Already Affected, At Risk or Not Affected, using a 300-metre buffer around the flood extent as the risk threshold, a distance that can be tuned to local conditions. Module C applies the same logic to building footprints, Module D to road segments, flagging potentially impassable routes to support closure and detour decisions, and Module E overlays population data with flood extents to estimate how many residents are exposed. All outputs flow into a five-page dashboard built in ArcGIS Experience Builder, one page per module, giving planners and emergency responders an interactive, continuously updated picture of the disaster.

The researchers are careful about what their system does and does not claim. The platform performs automated exposure assessment and impact mapping, not damage estimation; calculating physical damage, economic losses or casualties would require flood depth, flow velocity, structural vulnerability and asset values that lie beyond the current scope. Nor did the team conduct an independent quantitative validation of the Prithvi model against Queensland-specific reference flood maps, so the case study should be read as a demonstration of the architecture rather than a formal evaluation of model accuracy under local conditions. Other limitations are candidly acknowledged: cloud-free satellite imagery may not be available in the critical hours after a flood, potentially requiring subscription services such as Planet, ICEYE or Maxar, and the event-driven nature of floods makes automated scheduling tricky. The authors suggest coupling the platform to hydrological and meteorological monitoring so that workflows trigger only when rainfall or water-level thresholds are exceeded.

Even with these caveats, the implications are far-reaching. Because the architecture separates sensing, processing and decision-support into modular, interchangeable components, it can be redeployed in any jurisdiction with suitable imagery, administrative boundaries, building footprints, transport networks and population data. The same pipeline could incorporate road extraction models, infrastructure vulnerability assessment or population displacement modelling, and the authors envision evolution towards digital twins, continuous IoT sensor integration and predictive hydrometeorological forecasting, shifting the system from post-event mapping to proactive early warning. Repeated observations of flood exposure could also help governments identify persistently affected locations, evaluate mitigation measures and prioritise investment in resilient infrastructure and nature-based solutions.

As climate change intensifies extreme rainfall, with CSIRO and Bureau of Meteorology projections indicating that the present one-in-100-year flood threshold for Brisbane could be exceeded far more often by mid-century, and modelling suggesting today’s one-percent annual exceedance level could rise by 1.2 to 2.5 metres by 2050, tools that compress the time between satellite pass and actionable intelligence may become indispensable. The Queensland platform offers a glimpse of what disaster response could look like when cities stop reacting to floods with spreadsheets and start answering, automatically and in near-real time, the question that matters most: who and what is in the water’s way.

Subject of Research: An AIoT-enabled urban platform for automated flood detection, exposure assessment and impact mapping using satellite imagery and deep learning

Article Title: AIoT-enabled urban platform for flood detection and impact mapping: towards near-real-time spatial decision support in disaster management

Article References: Hossain, S. T., Yigitcanlar, T., Lin, Z., & Zhao, P. (2026). AIoT-enabled urban platform for flood detection and impact mapping: towards near-real-time spatial decision support in disaster management. Natural Hazards, 122(18), Article 621. https://doi.org/10.1007/s11069-026-08403-3

Image Credits: AI Generated

DOI: 10.1007/s11069-026-08403-3

Keywords: flood detection, AIoT, deep learning, satellite imagery, disaster management, impact mapping, platform urbanism, smart cities, Queensland floods, Prithvi model, geospatial analytics, decision support

The study, led by George Teo Voicescu of CRIMEDIM, the Center for Research and Training in Disaster Medicine, Humanitarian Aid and Global Health at the Università del Piemonte Orientale in Novara, Italy, together with colleagues including Hamdi Lamine, Luca Ragazzoni and Marta Caviglia, set out to explore current monitoring and evaluation practices among disaster management training organizers. Monitoring and evaluation, often abbreviated as M&E, are two related but distinct activities. Monitoring refers to the ongoing, real-time tracking of a training course while it is running, allowing trainers to adjust content, pacing and methods as problems emerge. Evaluation, by contrast, typically happens after the fact and asks whether the training achieved its intended outcomes. In an ideal world, the two work together in a continuous feedback loop that steadily improves both the course and the competence of its graduates.

To understand how this loop functions in practice, the researchers conducted a prospective qualitative study using semi-structured online interviews. They deliberately sampled training organizers across diverse regions and operational contexts, contacting 53 individuals and ultimately enrolling 15 participants. The interviews were audio recorded, transcribed with pseudonymization, and subjected to thematic analysis, a qualitative method in which researchers systematically code transcripts to identify recurring patterns and themes. The team reported the work in accordance with the Consolidated Criteria for Reporting Qualitative Research, known as COREQ, a checklist designed to improve the transparency and rigor of interview-based studies. Ethical approval was obtained from the ethical review board of the Iuliu Hatieganu University of Medicine and Pharmacy in Cluj-Napoca, Romania, and all participants provided informed consent.

The first striking finding was heterogeneity. The training development process, the formats and the content of disaster management courses varied enormously across the interviewees. Some organizers followed established instructional design frameworks such as ADDIE, which stands for Analysis, Design, Development, Implementation and Evaluation, or evaluation models like CIPP, which examines context, input, process and product. Others relied on ad hoc approaches shaped by institutional habit or funder expectations. Courses ranged from short intensive workshops to extended programs covering topics as varied as major incident medical management, exemplified by frameworks like MIMMS, the Major Incident Medical Management and Support course, and broader disaster planning. This diversity, the authors note, is not inherently a weakness, but it makes standardized assessment extremely difficult, because a measurement tool designed for one type of course may be meaningless for another.

The second major finding concerned the imbalance between monitoring and evaluation. Both activities were valued by the trainers interviewed, but evaluation was frequently prioritized over monitoring. The dominant evaluation method was the pre-post survey, in which trainees rate their knowledge or confidence before and after a course. While such surveys are easy to administer, the study suggests they often capture little more than satisfaction or self-perceived learning, rather than genuine operational readiness. Monitoring, meanwhile, was often informal or absent altogether. The researchers warn that this lack of monitoring might drastically affect short courses in particular, because without real-time feedback trainers have no opportunity to improve the course while it is still ongoing, potentially leaving participants poorly trained by the time the course ends.

Underlying much of this superficiality, the interviewees suggested, was the influence of funders. Evaluation was often guided by funder requirements rather than by a genuine desire to improve training quality. When the primary audience for evaluation data is a donor or an administrative office demanding completion reports, the resulting instruments tend to measure accountability rather than learning. The study also points to a structural problem in the workforce itself: most disaster management trainers are operational professionals, not educational experts. They bring invaluable field experience to the classroom, but they may lack formal training in pedagogy, assessment design or measurement theory. Relying on such trainers to invent their own unstandardized monitoring and evaluation approaches, the authors argue, can be suboptimal, whereas dedicated M&E teams could professionalize the field in the same way that specialized quality assurance functions have improved other high-stakes industries.

The consequences of weak assessment extend beyond the classroom. After action reports from real disasters consistently identify disaster management training as fundamental to effective response, which means that flawed evaluation does not merely produce misleading course certificates; it obscures the true state of operational readiness across the emergency response system. A trainee who completes a course with high satisfaction scores but limited actual capability may be deployed into a crisis believing they are prepared. The study explicitly warns that current practices give limited insight into operational readiness and can create a false sense of preparedness among trainees. In a field where lives depend on performance under extreme pressure, that gap between perceived and actual competence is not a bureaucratic inconvenience but a safety issue.

What do the trainers themselves want? The interviewees recommended a flexible, user-friendly monitoring and evaluation platform dedicated specifically to disaster management, one that would support long-term tracking and follow-up of trainees over time and include networking capabilities connecting trainers, organizers and alumni. Long-term follow-up is particularly important because the true test of disaster training is not performance on a final quiz but the retention and application of skills months or years later, when a disaster actually occurs. A dedicated platform could also help standardize core metrics while remaining adaptable to the heterogeneity of courses, and the authors suggest that mixed methods approaches, combining quantitative indicators such as key performance indicators with qualitative insight into the learning process, could provide a more comprehensive understanding of how disaster responders actually learn.

The researchers are careful to acknowledge the challenges inherent in any such solution. Disaster management courses are short, their topics are diverse, and their training methodologies vary widely, so any monitoring and evaluation system must be adapted to these constraints rather than imported wholesale from other educational domains. There are also risks associated with centralized platforms, including the administrative burden they may impose on trainers and the possibility that standardized metrics could flatten the very diversity that makes disaster training responsive to local contexts. The authors argue that DM-adapted tools could more accurately assess trainees’ readiness to work and that a well-designed platform could fill existing gaps while mitigating the risks associated with it, a balance that will require careful design and consultation with the training community itself.

The study emerges from the International PhD in Global Health, Humanitarian Aid and Disaster Medicine organized by the Università del Piemonte Orientale, and the authors received no external funding for the work, declaring no competing interests. As climate change intensifies hazards and urbanization concentrates populations in vulnerable regions, the demand for disaster management training will only grow, and with it the stakes of getting assessment right. This study does not claim that disaster training is failing; rather, it reveals that the field currently cannot prove it is succeeding. By giving voice to the trainers who deliver these critical courses, the research lays the groundwork for a more professionalized, evidence-based approach to building the competence that disaster response ultimately depends on, one monitored session and one meaningful evaluation at a time.

Subject of Research: Monitoring and evaluation practices in disaster management training

Article Title: Monitoring and evaluating disaster management training: a qualitative study of trainers’ perspectives

Article References: Voicescu, G. T., Lamine, H., Ragazzoni, L., & Caviglia, M. (2026). Monitoring and evaluating disaster management training: a qualitative study of trainers’ perspectives. BMC Medical Education. https://doi.org/10.1186/s12909-026-10465-7

Image Credits: AI Generated

DOI: 10.1186/s12909-026-10465-7

Keywords: disaster management, monitoring and evaluation, medical education, qualitative research, training assessment, emergency preparedness, disaster medicine, pre-post surveys, instructional design, capacity building, thematic analysis, humanitarian aid

The choice of a hexacopter rather than the more common quadcopter is not cosmetic. With six brushless motors driving six propellers in a Hexa-X layout, the aircraft retains controlled flight even if one rotor fails, a margin of safety that matters enormously when the vehicle is dispatched over rubble, smoke or unstable terrain where a crash means losing both the airframe and the mapping data it carries. The redundant rotor configuration also increases total payload capacity, which is what allows the platform to carry multiple sensing systems at once. In disaster scenarios the aircraft can be deployed quickly without runways or significant ground infrastructure, and its maneuverability lets it thread through confined spaces and reach isolated zones that ground vehicles cannot access. The authors also emphasize the operating economics: small multirotors cost a fraction of larger aerial platforms, making repeated reconnaissance sorties financially realistic for agencies that must monitor an affected area many times over.

The thermal imaging payload centers on the FLIR Lepton 3.5, a remarkably small radiometric thermal camera that measures the actual temperature of every pixel rather than merely rendering a heat picture. The sensor is mounted on a tCam-Mini rev4 breakout board built around an ESP32-WROVER microcontroller with an onboard antenna, an open-source hardware and software design that streams the radiometric data over WiFi to a ground computer. Before flight, the camera’s housing is produced by 3D printing, with four STL components and two copies of a vertical holder printed to form an enclosure that shields the delicate sensor from vibration and mechanical stress during operation. Firmware is flashed to the ESP32 board using Espressif’s serial download tool, loading a bootloader, a partition table and the main tCam firmware in sequence; a dual-color LED confirms a successful boot by briefly turning red and then blinking yellow as the camera begins advertising its own WiFi access point. The companion desktop application then connects to the camera’s default address and displays the live thermal feed, allowing operators to detect human body heat and other thermal anomalies in real time even through smoke, darkness or visual clutter that would defeat an ordinary camera.

The mapping side of the system uses the Garmin LiDAR-Lite V3, a compact and lightweight laser rangefinder chosen for its accurate distance measurements and wide field of view. Because a single fixed sensor sees only one direction at a time, the team mounted it on a pan-and-tilt assembly built from two HS-422 servo motors and an aluminium bracket kit, letting the laser sweep across the terrain below. An Arduino Uno orchestrates the scanning: it toggles the sensor’s enable pin, manages the I2C clock and data lines used for communication, and arbitrates the mode-control pin through parallel resistors to prevent bus contention, all while driving the two servos through PWM signals. As the sensor sweeps, distance readings are transmitted over serial to a ground station, where an open-source interface written in C++ with the OpenGL graphics library converts each measurement into Cartesian coordinates and renders it as a cube whose color encodes angle and distance. The operator can fly through the emerging 3D point cloud while scanning is still in progress, and completed scans can be saved to file and reloaded for later analysis, producing the kind of terrain model that helps responders understand where paths, debris fields and structures lie.

The airframe itself follows a build path that any reasonably well-equipped workshop could follow. Six A2212 brushless motors rated at 1000 KV are bolted to the arms of an F550 hexacopter frame, with their bullet connectors routed through the arms before the electronic speed controllers are positioned. A power distribution board mounted on the lower frame plate feeds all six speed controllers, and every solder joint is tinned with flux to prevent the cold joints that can fail mid-flight. The top plate then encloses the electronics, with the battery carefully balanced along the centerline. An APM 2.8 flight controller with a built-in compass coordinates the six rotors, receiving commands from a Flysky FS-i6X 2.4 GHz transmitter and its ten-channel receiver. The team configured and calibrated the entire flight system using Mission Planner, an open-source ground-control application: firmware for the Hexa X frame is installed over a serial connection, the accelerometer and compass are calibrated by rotating the vehicle until calibration markers clear, the radio sticks are swept to their extremes to record their ranges, and the electronic speed controllers are programmed through a sequence of throttle-position beeps. Anti-vibration dampers sit between the frame and the controller to keep sensor readings clean.

Field validation put the whole assembly through its paces. The team performed pilot testing and initial flight calibrations before moving to full flight and field testing of the integrated platform, confirming aerial monitoring, environmental sensing and real-time wireless transmission of the thermal feed. Wireless transmission tests measured system performance characteristics such as the maximum achievable frame rate for the life-form detection stream, data that defines how quickly an operator on the ground can see a heat signature appear. The platform’s architecture also leaves room for growth: the authors note that the airframe can support a gripper mechanism for object retrieval, temperature and humidity sensors for environmental monitoring, and integration with Geographic Information System databases to sharpen situational awareness during response operations. Multi-sensor fusion of the LiDAR, thermal and environmental streams is presented as the path toward a comprehensive picture of a disaster zone, and the communication module could in principle relay temporary network connectivity into areas where infrastructure has been knocked out.

The build is also refreshingly honest about its limits, several of which will be familiar to anyone who has tried to put serious sensors on a small drone. The single biggest disappointment came during flight testing of the LiDAR: the team was unable to operate the scanner airborne because of the platform’s significant payload capacity and power limitations, a constraint the authors note is common to compact UAV-based LiDAR systems. Continuous LiDAR operation demands sustained laser emission and real-time computation, while the thermal camera needs uninterrupted power for image acquisition, so balancing sensor operation against flight stability and mission duration remains a central engineering challenge. The Garmin sensor itself is also slow: a complete scan yields roughly 92,000 data points, a process that can stretch over several hours when performed thoroughly. On the ground, that is acceptable; in the air, it would be impractical without a faster scanning approach or a lighter, more efficient sensor.

Other constraints are more exotic but no less instructive. The LiDAR’s laser ranging degrades on highly reflective surfaces and transparent materials such as glass, which scatter or pass through the beam rather than returning a clean reflection. Reliable serial communication required fixed-length data strings, so the software pads angular measurements and sensor values with leading zeros, an unglamorous detail that nonetheless determines whether the ground station parses the stream correctly. Perhaps most surprisingly for a civilian disaster tool, the FLIR Lepton 3.5 and certain LiDAR technologies fall under the International Traffic in Arms Regulations, the United States export-control regime for sensitive technologies. Complying with ITAR imposed administrative burdens that affected the project’s timelines, supplier selection and collaboration opportunities, and even sharing LiDAR-derived data with foreign entities required careful legal review. For a low-budget undergraduate project, these regulatory hurdles were as real an obstacle as any engineering problem.

What makes the publication notable is less any single component than the demonstrated end-to-end feasibility of the whole stack. A six-rotor aircraft with rotor-failure redundancy, a radiometric thermal camera that can spot living organisms through conditions that blind optical cameras, a LiDAR system that builds navigable 3D terrain models, and wireless streaming of the thermal data to an operator on the ground were all assembled for a total bill of materials of Rs. 73,689.35, with the single most expensive item, the LiDAR-Lite V3 at Rs. 23,215, costing less than many commercial camera drones on its own. All design files, from the LiDAR schematic and Arduino code to the STL enclosure prints and the tCam-Mini firmware, are archived in Zenodo repositories under Creative Commons and GNU General Public licenses. The authors frame the modular platform as a foundation for continued research in drone-assisted disaster management, with future work pointing toward machine-learning techniques for autonomous navigation that would reduce response times and keep human rescuers out of hazardous zones. For research groups and volunteer response teams in resource-constrained settings, it is a blueprint that turns a disaster-response capability once reserved for well-funded agencies into something a small team can build, fly and improve.

Subject of Research: Low-cost hexacopter platform integrating thermal imaging and LiDAR mapping for disaster management

Article Title: Thermal imaging and LiDAR mapping for disaster management with hexacopter

Article References: Vuucha, H., Jomon, J., Somasundaram, D., & M., M. S. (2026). Thermal imaging and LiDAR mapping for disaster management with hexacopter. HardwareX, Article e00841. https://doi.org/10.1016/j.ohx.2026.e00841

Image Credits: AI Generated

DOI: 10.1016/j.ohx.2026.e00841

Keywords: hexacopter, thermal imaging, LiDAR, disaster management, FLIR Lepton 3.5, Garmin LiDAR-Lite V3, open-source hardware, UAV, search and rescue, ESP32, 3D point cloud, Mission Planner

The study’s starting point is a theoretical one. Disaster and emergency management, the authors contend, behaves as a complex adaptive system: a network of interdependent actors—central and local government agencies, emergency services, Indigenous partners, civil society organizations, and private sector entities—whose roles and relationships shift as hazard conditions evolve. Three properties of such systems matter most for DEM. Self-organization allows actors to reconfigure coordination autonomously, as observed during the 2011 Tōhoku disaster in Japan, where local actors improvised networks after formal command structures collapsed. Nonlinearity means disruptions can propagate in ways that produce consequences disproportionate to their initial cause, a dynamic famously analyzed by Charles Perrow in his work on normal accidents. Emergent behavior, meanwhile, means system performance arises from interactions among actors rather than from prescribed plans, and therefore cannot be fully anticipated or controlled in advance.

These characteristics expose a structural mismatch. Leadership scholarship has evolved from trait-based theories toward relational, situational, and transformational models, yet it has remained anchored within the organizational unit rather than the interorganizational system. Even systems-oriented approaches such as meta-leadership and complexity leadership theory retain a largely leader-centric orientation, privileging the individual actor as the primary locus of control. The limitations of that orientation are visible in disaster history: post-event analyses of Hurricane Katrina identified failures of individual leadership alongside structural fragmentation, unclear cross-agency mandates, and inadequate mechanisms for aligning distributed actors toward shared objectives. The 2010 Haiti earthquake similarly showed how leadership capacity interacted with pre-existing institutional weakness and fragmented international coordination.

To fill this gap, the researchers turned to stewardship theory, which emerged as a counterpoint to agency theory’s assumption that actors are self-interested and require monitoring and incentives to perform. Stewardship instead conceptualizes actors as fundamentally motivated to pursue collective goals when organizational identification and value alignment are strong. Extended to the system level, stewardship becomes a form of meta-governance—concerned with shaping a system’s goals, rules, feedback, and response—rather than with directing operational activity. The concept has been applied in natural resource governance, public health system management, and complexity-informed public policy, but had not been systematically examined within DEM, despite the field’s combination of distributed authority, multi-agency interdependence, and nonlinear hazard environments.

The empirical work employed constructivist networked grounded theory, a methodology combining Charmaz’s constructivist grounded theory with social network analysis to examine both the relational structure of the DEM system and practitioners’ experiences within it. Data were collected between August 2024 and June 2025 from participants recruited across national forums, professional networks, emergency services, territorial authorities, civil society organizations, and private sector actors. Interviews ranged from 43 to 96 minutes, with a mean of approximately 60 minutes, and analysis proceeded through iterative coding, constant comparison, and progressive category refinement until theoretical saturation was reached. Notably, stewardship was not a predetermined analytical construct; it emerged inductively as the integrative category explaining how participants understood coherence, legitimacy, learning, and adaptive coordination to be sustained across organizational boundaries.

Four interdependent themes emerged from the analysis. The first concerned governing a distributed system. Participants described uncertainty about who holds overarching responsibility for the system as a whole, with national oversight perceived as bounded to particular hazards rather than extending across the full breadth of interagency coordination. Recurrent misalignment between nationally designed arrangements and local operational realities was a persistent friction, sharpened by the fact that national guidance, absent legislative force, cannot be required to be followed. Participants also described ambiguity about which actors were recognized as legitimate contributors to the system, with the operational network extending well beyond formally prescribed structures.

The second theme centered on trust and inclusive participation as the relational infrastructure of coordination. Participants emphasized that the quality of pre-existing relationships was a more reliable predictor of coordination effectiveness than formal arrangements or statutory roles—one practitioner quipped that you need to build a relationship over eight cups of coffee before you can start asking for something. Civil society organizations were described as providing relational networks and community intelligence that are substantial but underrecognized within formal system definitions. Indigenous partnership emerged as a distinct dimension: under Te Tiriti o Waitangi, signed in 1840, Māori hold an enduring basis for partnership in governance, and participants described how the quality of that engagement directly shaped both the legitimacy and operational reach of the system, though Treaty-based partnership quality varied significantly across regions.

The third theme addressed information sharing and learning. The aspiration of a common operating picture was widely referenced but characterized as aspirational rather than operational—one participant observed that the only common thing about it is the word common. Incompatible information systems, platform fragmentation, and institutional protectiveness over data combined to produce what the authors call a feedback deficit: a system theoretically capable of shared sensemaking but operationally fragmented along institutional boundaries. Compounding this, insights gained through events and exercises were described as fading as urgency declined and personnel changed, leaving institutional memory residing in individuals rather than organizational systems and rendering learning sporadic rather than cumulative.

The fourth theme concerned sustaining capability and legitimacy over the long term. Resourcing was described as unevenly distributed, with reliance on locally generated ratepayer revenue producing what participants called a postcode lottery of capability, where organizational capacity reflects local financial circumstances rather than hazard exposure or statutory obligation. Workforce sustainability emerged as a significant concern, with 31 of 40 participants describing burnout, illness, recruitment delays, inconsistent professional standards, and the absence of any centralized repository for qualifications or competency requirements. Accountability, meanwhile, was described as diffuse, operating primarily through post-event inquiry rather than ongoing assurance of preparedness and coordination quality.

From these findings, the authors distill a three-pillar framework of system stewardship. Relational stewardship encompasses the trust, boundary-spanning networks, and inclusive participation through which coordination becomes possible, including sustained investment in Treaty-based partnerships with iwi and the formalization of relationships into organizational arrangements rather than individual positions. Informational stewardship covers shared situational awareness, data transparency, and feedback-informed learning, requiring both technical investment in compatible information management and cultural change that treats learning as a shared system function. Institutional stewardship concerns equitable resourcing, workforce capability, and accountability mechanisms that sustain capability and legitimacy over time. Crucially, the three pillars are interdependent: weakness in one degrades the others, while alignment across all three creates the conditions for sustained adaptive performance. Trust facilitates information sharing; shared understanding strengthens institutional confidence; equitable resourcing enables the sustained engagement through which relationships are built.

The practical implications are considerable. For national agencies, stewardship implies a reorientation of the governance function—from setting requirements to cultivating conditions, from assuring compliance to strengthening capability. For policymakers, the framework makes visible the structural interdependencies between funding, professional standards, and accountability mechanisms, demonstrating that reforms to any single dimension in isolation are unlikely to produce durable improvement. The authors caution that the conditions underpinning system stewardship should not be assumed to persist indefinitely; trust, shared learning, institutional legitimacy, and collaborative relationships require continual investment and renewal, and may be eroded by organizational change, resource constraints, and competing priorities. The study’s limitations are acknowledged: findings derive from a single national context, reflect participant interpretations rather than direct observation, and capture a single point in time, though the framework forms part of a cumulative research program. Ultimately, the study argues that strengthening disaster and emergency management requires moving beyond episodic leadership during events toward the deliberate, continuous stewardship of the relational, informational, and institutional conditions through which adaptive coordination, collective learning, and long-term system coherence are cultivated and sustained.

Subject of Research: System stewardship as a complex adaptive system governance framework for disaster and emergency management in Aotearoa New Zealand

Article Title: Stewardship for Disaster and Emergency Management: A Complex Adaptative System Governance Framework

Article References: Miller, T., Le De, L., & Hore, K. (2026). Stewardship for Disaster and Emergency Management: A Complex Adaptative System Governance Framework. International Journal of Disaster Risk Science, 17(4), 725-738. https://doi.org/10.1007/s13753-026-00762-6

Image Credits: AI Generated

DOI: 10.1007/s13753-026-00762-6

Keywords: disaster and emergency management, system stewardship, complex adaptive systems, meta-governance, governance framework, adaptive coordination, Aotearoa New Zealand, trust and collaboration, institutional memory, emergency management workforce, Māori partnership, disaster risk science

The review, authored by Neha Sen, Swarup Chattopadhyay, and Rudra Mohan Tripathy of XIM University in Bhubaneswar, India, together with Dilip K. Prasad and Arif Ahmed Sekh of UiT The Arctic University of Norway in Tromsø, offers an unusually broad synthesis of how deep learning models have been applied to disaster data analysis across both domains. Rather than cataloging techniques in isolation, the authors trace the evolution of research trends, compare the architectures that have dominated different phases of the field, and assemble a rich archive of existing disaster datasets that researchers can draw upon for future work. The result is both a status report and a diagnosis of why so much promising laboratory work has failed to reach the field.

Technically, the field’s trajectory mirrors the broader history of computer vision. Early disaster-focused studies leaned heavily on convolutional neural networks for image classification, sorting satellite scenes into categories such as flooded or intact, damaged or undamaged. As datasets grew and architectures matured, attention shifted toward semantic segmentation, in which models label every pixel of an image, producing detailed damage maps that can guide aerial assessment. More recently, the authors observe a pronounced pivot toward object detection and real-time human monitoring, tasks that produce directly actionable outputs: the coordinates of stranded people, the footprint of a collapsed structure, the extent of an oil spill or wildfire front. This shift reflects a hard-earned lesson about deployment, because a classifier that reports aggregate statistics is far less useful to a rescue coordinator than a detector that points to individuals in need.

On the social media side, deep learning has transformed what is possible with text, images, and video posted by people in the middle of a disaster. Natural language processing models can triage millions of tweets and posts in minutes, extracting requests for help, identifying locations mentioned in messages, and filtering out the misinformation that predictably floods platforms during emergencies. Multimodal models that jointly process the text and attached images of a post can distinguish, for example, a genuine photograph of a flooded street from a recycled image circulating with false context. These streams provide something satellites cannot: the ground-level perspective of the people actually experiencing the event, often within seconds of impact.

Geospatial data offers the complementary virtue of synoptic coverage and physical precision. Satellite platforms deliver wide-area views that reveal the overall extent of flooding, fire, or structural destruction, while unoccupied aerial vehicles can be dispatched quickly to capture high-resolution imagery of specific sites. Deep learning pipelines built on this imagery support damage assessment, road network analysis for routing relief convoys, and change detection that compares pre- and post-disaster scenes to isolate what has been altered. Techniques such as deep fusion, in which information from multiple sensors or multiple moments in time is combined within a single learned representation, have become central to squeezing maximum value from these heterogeneous sources.

The core argument of the review is that these two domains, social media and geospatial sensing, have largely been studied by separate research communities with separate datasets, benchmarks, and processing pipelines. Yet during an actual disaster, responders must reason about both simultaneously. A flooded highway visible in satellite imagery gains operational meaning when combined with social media reports of vehicles trapped along it; a cluster of distress messages becomes verifiable when cross-checked against aerial imagery of the location. The authors propose a conceptual framework that consolidates the processing pipelines of both domains into a single, cohesive generative ecosystem, one in which inter-domain disaster data is used concurrently so that AI systems can develop a more comprehensive, human-like understanding of evolving disaster scenarios.

That ambition runs into sobering practical constraints, which the review catalogs candidly. Most existing implementations, despite substantial methodological advances, remain difficult to deploy in real-world disaster response settings. Timeliness is a recurring problem: models trained offline on curated datasets can be slow to adapt to an unfolding event whose imagery, vocabulary, and visual conditions differ from anything in their training data. Scalability is another, because processing the full firehose of crisis-related data at national scale demands infrastructure that many response agencies lack. Operational integration may be the deepest challenge of all, since research prototypes rarely connect to the software systems, workflows, and communication protocols that emergency managers actually use under pressure. The review identifies four categories of limitations spanning both domains, and its dataset archive is intended in part to help researchers benchmark against deployment-relevant conditions rather than convenient laboratory ones.

The implications for the disaster management community are considerable. As climate change intensifies floods, wildfires, and storms, and as urbanization concentrates populations in hazard-prone regions, the volume of both crisis data and crisis demand is rising together. A unified AI-driven pipeline that fuses citizen-generated signals with remote sensing could shorten the gap between an event’s onset and a coordinated response from days to hours or minutes. The authors’ emphasis on generative, ecosystem-level integration also points toward systems that do not merely classify incoming data but actively synthesize a coherent operational picture, prioritizing the locations, populations, and infrastructure most at risk and adapting as new information arrives from every source.

Published as open access with funding provided by UiT The Arctic University of Norway, the review is positioned as a resource for the entire field rather than a narrow technical contribution. By consolidating datasets, comparing model families, and mapping the research frontier from image classification toward real-time detection and human monitoring, it gives both newcomers and specialists a common map of where disaster informatics stands. The authors’ unifying vision is straightforward in principle: AI systems that see disasters the way skilled human responders do, from above and from the ground at once. Closing the gap between that vision and deployable practice, the review makes clear, is now the defining challenge for artificial intelligence in disaster management.

Subject of Research: Deep learning integration of social media and geospatial data for AI-driven disaster management

Article Title: Ai-driven disaster management: a comprehensive review of deep learning for social media and geospatial data integration

Article References: Sen, N., Chattopadhyay, S., Tripathy, R. M., Prasad, D. K., & Sekh, A. A. (2026). Ai-driven disaster management: a comprehensive review of deep learning for social media and geospatial data integration. Artificial Intelligence Review. https://doi.org/10.1007/s10462-026-11696-2

Image Credits: AI Generated

DOI: 10.1007/s10462-026-11696-2

Keywords: deep learning, disaster management, social media, satellite imagery, UAV, computer vision, remote sensing, damage assessment, object detection, real-time monitoring, data fusion, artificial intelligence

The study, published in the Journal of Emergency and Disaster Medicine, was conducted by Shannon Sherk of the University of Victoria and set out to answer two questions: what ground-level knowledge paramedics and emergency health services employees in British Columbia hold about climate hazards, and what interventions should be proposed to help pre-hospital systems adapt. The research fills a conspicuous gap. While the impacts of climate change on hospital-based clinical care have been documented extensively, the pre-hospital environment, where paramedics work in homes, on streets and along flooded highways, has been almost entirely overlooked. A recent scoping review cited in the paper concluded that no comprehensive study of strategies and solutions for pre-hospital emergency systems against climate change had yet been completed.

To gather evidence, Sherk used a mixed-methods design combining a 16-question survey with in-depth, semi-structured interviews. The survey, distributed through a British Columbia Emergency Health Service-specific Facebook group and word-of-mouth snowball sampling, ran from February 27 to March 9, 2025, and drew 109 respondents. Participants spanned all five of the province’s health regions, with Vancouver Island the most represented at 30 percent. Women comprised 54 percent of the sample, the average length of service with the ambulance service was 8.94 years, and respondents ranged from newly oriented staff to veterans with more than two decades on the road. Three interviews complemented the survey, drawing on a member of management, a union representative and a health and safety representative, all experienced paramedics.

The findings reveal a workforce that is both concerned and largely unsupported. Three-quarters of respondents believed climate change is anthropogenic, a higher proportion than the Canadian population at large, where around a third rejected human causation in 2018. More than three-quarters reported seeing a rise in climate-related hazards during their time with the service. Yet only about one in five had ever attended a climate event, workshop, protest or lecture, a disconnect the author describes as a gap between concern and educational engagement. Perceived impacts on the respondents’ own jobs scored slightly lower than perceived impacts on public health, but both were expected to worsen in the future.

Across every health region, the hazards judged most damaging to public health were the same: wildfires, in both their flames and their smoke, extreme heat, and flooding. Notably, perception did not always track mortality statistics. In 2021, fire-related deaths in the province numbered 59, while the single week of the heat dome killed more than 600. The author suggests this mismatch may indicate that slower, less quantifiable health harms, such as respiratory disease driven by smoke exposure or infectious disease linked to flooding, are being missed when systems respond only to body counts.

The interviews added texture to these numbers. All three interviewees identified hot and cold emergencies as the highest-acuity hazards. Heat deaths during the dome occurred almost exclusively indoors, while cold deaths fell primarily on people living outdoors, particularly homeless individuals whose deaths are often attributed to comorbidities such as overdose rather than exposure. Wildfire smoke emerged as a chronic threat that rarely triggers a 911 call on its own but saturates emergency departments with patients in respiratory distress, degrading capacity for the entire system. Flooding and relentless rain were linked to hypothermia and skin breakdown resembling trench foot, conditions one interviewee summarized by observing that things have gotten soggier in the last five or six years.

Paramedics themselves are far from immune. One described working the heat dome by taping bags of hospital ice to their neck and head between calls. Uniform and personal protective equipment requirements make heat harder to escape than cold, and wildfire smoke degrades respirator filters faster, raising costs and exposure. Responders described colleagues rushing from one cardiac arrest to the next during the dome, and the physical demands of the job continue regardless of air quality warnings, because, as the study puts it, no one chooses where their patient arrests. Extreme weather also severs the logistics of response: flooded roads, fallen trees and closed highways delay ambulances, strand commuting paramedics and force patients who cannot self-transport to depend entirely on ambulance service.

Perhaps the most striking statistical finding concerns politics. Consistent with earlier research, self-reported political orientation correlated with climate views in the survey. But when multiple linear regression was applied, perceived impacts on the respondents’ own jobs emerged as by far the strongest predictor of support for involving health care professionals in climate policy, with a standardized coefficient of 0.492, exceeding the next strongest variable by a margin of 0.3 and remaining significant at p less than 0.01. In other words, paramedics across the political spectrum translated lived experience of climate impacts at work into a desire for institutional action. Only five of 109 respondents rejected climate action outright.

The qualitative data exposed a workforce starved of planning. One 20-year paramedic, writing after three minor earthquakes struck in March 2025, described having no idea what the plan is for a catastrophic disaster, asking what is expected of staff on or off shift, how crews would be relieved, fed or deployed, and pleading for classroom-led rather than online training. Interviewees described management as reactionary rather than proactive, and noted that existing mental health supports rely on self-referral, leaving chronic, cumulative stress from repeated environmental emergencies unaddressed at a time when the service is already grappling with a documented mental health crisis. Interviewees also described how the decline of primary care has pushed sicker patients toward 911, compounding the load.

From these findings, the study distills a disaster-risk framework, hazard multiplied by vulnerability and exposure, divided by capacity, and derives four recommendations: commit to an organizational culture of proactivity that treats disasters as a matter of when, not if; develop region-specific hazard education and planning; integrate weather modelling and forecasting into operational management with early warnings pushed to frontline staff; and build recovery programs designed for multi-incident and chronic stress rather than single traumatic events. The author acknowledges limitations, including the self-selecting sample, the absence of a pilot phase and a scope that excluded climate mitigation topics such as electrifying the ambulance fleet. But the conclusion is pointed: for most paramedics surveyed, climate change is already harming the public, and the emergency health system absorbs that harm. Having triaged the problem, the paper suggests, the pre-hospital system can now move to treatment.

Subject of Research: British Columbia paramedics' perspectives on climate change impacts and adaptation measures for pre-hospital emergency care

Article Title: Triaging the climate crisis: An investigation into British Columbia paramedics’ perspectives on climate change impacts and evidence-based adaptation measures

Article References: Sherk, S. (2026). Triaging the climate crisis: An investigation into British Columbia paramedics’ perspectives on climate change impacts and evidence-based adaptation measures. Journal of Emergency and Disaster Medicine, 2(1), Article 12. https://doi.org/10.1007/s44467-026-00015-y

Image Credits: AI Generated

DOI: 10.1007/s44467-026-00015-y

Keywords: climate change, paramedics, emergency medical services, British Columbia, extreme heat, wildfire smoke, flooding, disaster management, pre-hospital care, climate adaptation, public health, occupational stress