Researchers from Loughborough University, the University of Sheffield, Newcastle University and Beijing University of Technology have built a deterministic workflow that reads an Industry Foundation Classes, or IFC, file directly and turns it into a complete material decision engine. IFC is the vendor-neutral exchange format maintained by buildingSMART, designed so that a model created in one authoring platform can be understood by another. Instead of treating that file as a mere snapshot for drawings and schedules, the prototype extracts component quantities and material assignments, runs automated data-quality checks, maps the results to a prototype material database, and then evaluates entire wall-floor-roof combinations for both embodied carbon and circularity. Because every step follows fixed rules, the same input file always produces the same output, a property the authors regard as essential for traceable design support.

The test bed was a buildingSMART reference IFC model, a deliberately ordinary assembly of walls, slabs and roofs. The extraction stage targeted eight elements. Seven of them carried enough material and quantity information to proceed into the calculation; one incomplete roof aggregate was excluded, and, crucially, the reason for that exclusion was recorded rather than silently dropped. The retained set comprised four walls, one floor slab and two roof slabs, a small but complete envelope that allowed the researchers to keep the entire decision space within reach of exact evaluation.

That decision space was constructed from six wall materials, five floor materials and five roof materials, producing 150 whole-building configurations. Each configuration was scored on two axes: cradle-to-gate embodied carbon, measured in kilograms of carbon dioxide equivalent, and a prototype Building Circularity Score that reflects how readily materials can be recovered and reused. All 150 combinations were then compared pairwise to identify Pareto-optimal solutions, the mathematical term for configurations in which neither objective can be improved without degrading the other. This is where multi-objective optimisation earns its keep, because it replaces a single ranked list with a map of genuine trade-offs.

The result was strikingly structured. Twelve of the 150 configurations proved non-dominated, and they split cleanly into two camps. Six low-carbon-oriented candidates were dominated by timber-roof systems, while the six circularity-oriented candidates all used aluminium roofs. Not a single configuration met the study’s balanced classification thresholds, meaning no option satisfied both objectives simultaneously at the levels the researchers defined. The contrast illustrates a practical feature of material choice that designers rarely see laid bare: the design space may contain distinct clusters rather than one obvious best answer, and choosing between clusters is a values question, not a calculation.

The roof emerged as the decisive lever in this reference case, and the numbers explain why. The two roof slabs alone accounted for 53.5 percent of the extracted material volume, so whatever sat above the walls shaped the whole-building result. In one paired comparison, swapping a timber roof for an aluminium roof raised embodied carbon from 591.8 to 21,706.5 kilograms of carbon dioxide equivalent, a more than thirtyfold increase, while lifting the circularity score from 0.712 to 0.865. The authors are careful to frame this as a case-specific observation rather than a general rule for buildings, but it demonstrates the kind of quantified, element-level insight the workflow is designed to surface before specifications harden.

On top of the calculation engine sits a controlled semantic query layer with twelve predefined query types. These can retrieve low-carbon or high-circularity options, identify which components drive a building’s material profile, compare Pareto candidates side by side, or explain why a particular option earned its score. Because the queries operate through fixed rules rather than free-form interpretation, reproducibility is guaranteed: the same data and the same query yield the same answer every time. The system can also package its results into structured prompt text suitable for downstream interpretation, though the study explicitly did not call or evaluate a large language model, keeping the pipeline fully deterministic end to end.

Sensitivity testing forms a substantial part of the paper’s argument that the reference-case findings are robust rather than artefacts of arbitrary modelling choices. The same twelve candidate scenarios survived five different weighting schemes applied to the circularity score. The classification of zero balanced, six low-carbon-oriented and six circularity-oriented candidates held across nine different threshold settings. Under uncertainty assumptions tested with 1,000 scenario-based Monte Carlo runs, every baseline candidate remained non-dominated in at least 83.2 percent of the runs. For a field where early-stage carbon estimates often wobble with every assumption, that level of stability is a meaningful claim.

Performance numbers come with an honest caveat. The full 150-configuration case completed in about 0.79 seconds, including roughly 0.023 seconds for the pairwise Pareto filtering, fast enough for interactive design sessions. However, runtime tests with larger synthetic sets showed that exhaustive pairwise comparison does not scale indefinitely; as the number of configurations grows combinatorially, the filtering step becomes a bottleneck. The authors note that much larger design spaces would require more efficient Pareto-search strategies, a recognised challenge in multi-objective optimisation that algorithms such as sorting-based filters have begun to address elsewhere.

The team is candid that the work is a proof of concept built on one reference IFC model and a prototype material database. It does not yet account for structural performance, fire resistance, moisture behaviour, cost, procurement realities, regulation, operational energy, or product-specific verified Environmental Product Declarations, all of which shape real material decisions. Testing across multiple authoring platforms and live projects will be needed before field deployment can be judged. Even so, the study makes a persuasive case that open BIM data can serve as far more than a visual or documentation layer. By keeping quantities, materials, carbon calculations, circularity scores and candidate explanations connected in one deterministic process, the workflow offers a traceable foundation for exploring early-stage trade-offs, exactly the phase of a project where decisions are cheapest to change and most consequential for the built environment’s carbon and material future.

Subject of Research: An open IFC-based BIM workflow for whole-building embodied carbon and circularity assessment

Article Title: Open BIM workflow links whole-building carbon and circularity decisions

Article References: Open BIM workflow links whole-building carbon and circularity decisions. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: BIM, IFC, embodied carbon, circularity, multi-objective optimisation, Pareto optimality, building materials, life cycle assessment, smart construction, decision support, buildingSMART, Monte Carlo analysis

The method, called Alignment-Based Deformation Modeling, or ABDM, was developed and validated by Thanh Bao Nhut Trinh and Tsung-Chin Hou, who subjected three full-scale reinforced concrete beams, each four meters long, to three-point bending tests in the laboratory. Instead of relying on point-wise contact instruments such as linear variable differential transformers, the team scanned each beam with a terrestrial laser scanner at every loading stage, from the unloaded reference state through to failure. The scanner, a Leica ScanStation C10, captured dense three-dimensional point clouds of the entire beam surface, providing the full-field geometric data that conventional sensors cannot offer.

The technical core of the approach lies in how it processes those clouds. Rather than comparing raw point sets directly—a strategy the authors argue is fragile under large deformation, cracking, or partial data loss—the framework first reconstructs a structured parametric geometric model of the unloaded beam. Using the efficient RANSAC algorithm, it segments the point cloud into the planar faces of the prismatic beam. Because laser scans inevitably suffer from occlusion, particularly on rear faces hidden from the scanner, the workflow then infers the missing surfaces: it classifies the connections between adjacent planes as convex or concave based on their surface normals and centroids, and generates the absent faces by translating detected surfaces along their outward normals by the beam width. The result is a closed geometric envelope representing the complete as-built beam.

From that envelope, the pipeline extracts boundary points using Delaunay triangulation combined with statistical neighborhood filtering, then slices the edge data into segments along the beam axis. Within each slice, the DBSCAN clustering algorithm groups boundary points into the corners of the beam cross-section, and each cluster is turned into a rectangular prism whose dimensions come directly from the measured geometry. Merging these volumetric slices yields a parametric model of the undeformed beam—a reference against which every subsequent loading stage can be judged. The authors are careful to note that the term 3D model here means a structured parametric geometric representation carrying only geometric attributes, not a semantically enriched building information model with materials or scheduling data.

Modeling the loaded beam is where the alignment strategy earns its name. Loaded scans are registered to the unloaded reference rather than to isolated undeformed features, because under three-point bending the beam’s surface features themselves deform, crack, and rotate as the test progresses. The workflow slices both datasets around the expected cracking zone, rotates the loaded segments to align with the global axis, and applies Iterative Closest Point registration to each pair. When large cracks or local rotations cause a single rigid registration to become unstable, the algorithm splits the loaded data along failure zones and re-runs the registration independently on each sub-segment, iterating until the root mean square error falls below a threshold of 0.01. The recovered transformation matrices are then applied to the corresponding parametric segments of the reference model, mapping them into the deformed configuration and producing a complete as-loaded geometric model.

The framework also detects surface spalling—material loss on the beam face—by identifying holes and abrupt discontinuities in the extracted front surface of the loaded scan. Spalling area is computed as the difference between the reconstructed full front surface area and the area of the extracted damaged region, using an alpha-shape method that handles irregular boundaries. In the experiments, Beam A, cast from conventional 280 kgf/cm² reinforced concrete, developed a spalling zone of roughly 0.028 square meters near midspan at the final loading stage. Beam B, which incorporated steel fibers in its midspan region, showed only about 0.00184 square meters—a reduction of approximately 90 percent—because the fibers bridge cracks and resist tensile failure. Beam C, reinforced with polyvinyl-alcohol fibers, exhibited no detectable spalling at all, consistent with the tight crack-width control that polymeric fibers provide.

Validation against independent reference measurements demonstrated millimeter-level accuracy. Linear variable differential transformers installed at midspan and the quarter points recorded vertical displacements throughout each test, and the automated model-based deflections tracked them closely. Mean deflection errors of the ABDM method relative to the LVDTs stayed within about ±1 millimeter, or roughly ±2 percent, with relative errors never exceeding 3.60 percent. Bland–Altman analysis showed mean biases below 1 millimeter for all three beams—0.72 millimeters for Beam A, −0.19 for Beam B, and 0.03 for Beam C—with more than 95 percent of differences falling within narrow limits of agreement. A comparison against a least-squares curve-fitting approach showed the new method to be more stable, particularly for Beam A, where wide, localized cracking and lateral torsional movement made polynomial fitting err by nearly 4 millimeters, about 10 percent, at midspan.

Speed is the framework’s headline claim. Once the algorithm parameters—RANSAC thresholds, DBSCAN clustering radius, and ICP convergence tolerance—were fixed for the point cloud density, the entire workflow ran without manual intervention from raw scan to deformation analysis. On an ordinary desktop computer with an Intel Core i7-8700 processor and 16 gigabytes of RAM running MATLAB, generating the 3D models and computing deformations took between 40 and 48 seconds per beam, with the final deformation calculation itself requiring only about 2 seconds. The authors position the method as a rapid automated post-processing tool rather than a strict real-time monitoring system, but the contrast with conventional Scan-to-BIM workflows, which typically demand semi-automatic region selection and interactive alignment, is stark.

The study is candid about its limits. The geometric inference assumes prismatic beams with planar, roughly orthogonal faces, so non-prismatic members, diagonal elements, and complex joints would require relaxed constraints and additional segmentation. The alignment relies exclusively on surface-based registration without external control targets, and the spalling quantification was compared against manual delineation of the same point clouds rather than an independent ground truth, yielding relative errors below 6.5 percent and Intersection over Union values up to 0.88. All three specimens were laboratory beams tested under controlled conditions, and the authors acknowledge that real-world structures with complex geometries, environmental variability, and practical scanning constraints remain untested territory.

Even so, the implications reach well beyond the laboratory. Because the method needs no training data, it sidesteps the large annotated datasets and computational demands that constrain deep-learning approaches to damage detection, while offering interpretability that black-box models lack. It also complements techniques such as three-dimensional digital image correlation, which achieves sub-millimeter precision but requires controlled lighting, textured surfaces, and a limited field of view. The authors point toward seismic performance evaluation and routine monitoring of reinforced concrete components as near-term applications, with future work targeting the computational efficiency needed for large datasets from bridges and high-rise buildings. If automated pipelines like this one mature, the era of inferring a structure’s health from a few glued-on gauges may give way to full-field, model-based assessment delivered in under a minute.

Subject of Research: Automated point cloud-to-BIM conversion for deformation and spalling monitoring of reinforced concrete beams

Article Title: Automated point cloud-to-BIM conversion for fast deformation monitoring of structural elements

Article References: Trinh, T. B. N., & Hou, T.-C. (2026). Automated point cloud-to-BIM conversion for fast deformation monitoring of structural elements. Results in Engineering, 32, Article 113270. https://doi.org/10.1016/j.rineng.2026.113270

Image Credits: AI Generated

DOI: 10.1016/j.rineng.2026.113270

Keywords: terrestrial laser scanning, point cloud, BIM, structural health monitoring, deformation monitoring, reinforced concrete, three-point bending, spalling detection, ICP registration, RANSAC, DBSCAN, deflection measurement

The research, led by Ming Hao and Longping Liu under the corresponding authorship of Jianbin Wang, focuses on granulosa cells, the somatic cells that surround the oocyte and sustain its growth. Granulosa cell apoptosis, the team notes, initiates a considerable portion of follicular atresia, making these cells the natural place to look for the molecular switches of follicle death. The investigators’ earlier work had already identified the hypoxia-inducible factor 1 pathway, activated by follicle-stimulating hormone, as a protective factor that guards follicles against atresia. What remained unclear was precisely how that protection works, and how it interacts with the known pro-apoptotic forces inside the ovary.

To answer that question, the team adopted a methodological approach that sets the study apart from much of the existing literature. Rather than pooling many follicles together and averaging their molecular profiles, they employed a single-follicle, multi-dimensional profiling strategy based on serial sectioning. This allowed them to dissect the signaling logic underlying physiological follicle fate decisions follicle by follicle, preserving the spatial and individual variation that bulk analyses tend to erase. The technical toolkit behind the study included immunofluorescence, laser capture microdissection, and TUNEL labeling to detect apoptotic cells, alongside markers of oxidative stress such as 4-hydroxynonenal, 8-hydroxyguanosine, and 3-nitrotyrosine, which report lipid peroxidation, DNA oxidation, and protein nitration respectively.

The central finding is a striking complementarity. In the granulosa cells of healthy, growing mouse follicles, the HIF1 pathway is active, while in atretic follicles, those destined for destruction, it is the forkhead box protein O1 pathway that dominates. FOXO1 is a well-known transcription factor in the apoptosis field, capable of driving expression of pro-death genes including Bim, a member of the BH3-only family that pushes cells toward self-destruction. The observation that HIF1 and FOXO1 activation patterns are mutually exclusive across healthy and dying follicles suggests that the two pathways do not merely coexist in granulosa cells but actively compete to set the cell’s course.

Perhaps the most provocative element of the study concerns reactive oxygen species. ROS are often cast as villains in biology, the corrosive byproducts of metabolism that damage DNA, proteins, and membranes. Yet the researchers found that in growing mouse follicles, HIF1 pathway activity is associated with increased ROS-related signals, likely a consequence of enhanced granulosa-cell metabolic activity. Far from being a harbinger of doom, these ROS signals appear under physiological conditions to help maintain HIF1 pathway activity in granulosa cells during follicle growth. Crucially, the team reports that ROS-related signals are not by themselves associated with follicle atresia, a finding that complicates the simple oxidative-stress narrative and instead frames moderate ROS production as part of the metabolic engine that keeps a follicle alive and growing.

How, then, does HIF1 translate its activity into survival? The study’s answer lies in Bcl-XL, short for B-cell lymphoma-extra large, a canonical anti-apoptotic protein that works at the mitochondrial level to prevent the cascade of events leading to programmed cell death. The researchers present evidence that the HIF1 pathway appears to promote Bcl-XL expression in granulosa cells. This pro-survival output, they propose, may counterbalance the FOXO1-associated atretic pressure, the constant push toward apoptosis that FOXO1 and its downstream target Bim exert on the follicle. In other words, the follicle’s fate may hinge on which arm of this transcriptional contest wins control of the cell’s mitochondrial life-or-death machinery.

The authors synthesize these observations into a model of follicular fate as a dynamic balance between two axes: the pro-survival HIF1/Bcl-XL axis and the pro-apoptotic FOXO1/Bim axis. When HIF1 activity is sustained, supported in part by the ROS generated through active granulosa-cell metabolism, Bcl-XL expression holds the apoptotic machinery in check and the follicle continues to grow. When HIF1 activity wanes and FOXO1 takes over, Bim rises, Bcl-XL’s protective grip loosens, and the follicle slides into atresia. This framing transforms atresia from a passive failure into an active tug-of-war, one that can in principle be tipped in either direction by changes in hormonal signaling, metabolic state, or oxygen availability.

The experimental design reinforces the credibility of this model. The team used pregnant mare serum gonadotropin to stimulate follicle growth in mice and echinomycin, a pharmacological inhibitor of HIF1, to perturb the pathway experimentally, alongside N-acetyl-L-cysteine to modulate ROS levels. The use of Foxl2-CreER mice, obtained as a kind gift from Kui Liu’s laboratory at the University of Hong Kong Shenzhen Hospital, allowed granulosa-cell-specific manipulation. All animal experiments were approved by the Institutional Animal Care and Use Committee of Tsinghua University. The work was supported by the National Natural Science Foundation of China, and the authors declare no competing interests.

It is worth emphasizing what the study does and does not claim. The language of the paper is deliberately measured: HIF1 pathway activity is associated with Bcl-XL expression, and the balance model is presented as an association-based framework rather than a fully resolved causal chain. The findings are rooted in mouse ovaries, and while the conservation of HIF1, FOXO1, Bcl-XL, and Bim across mammals suggests the logic may generalize, direct evidence in human ovaries remains to be established. The authors themselves frame their conclusion as a description of what follicular fate appears to be associated with, a caution appropriate for a system as complex as the ovarian follicle, where endocrine, paracrine, and metabolic signals all converge.

Even with those caveats, the implications are considerable. Follicular atresia sits at the heart of some of the most consequential questions in reproductive biology: how the ovarian reserve is spent over a lifetime, why some follicles are selected while others are discarded, and how conditions such as polycystic ovary syndrome, a subject the journal explicitly links to this work, disrupt follicle selection. A clearer mechanistic understanding of the HIF1/Bcl-XL and FOXO1/Bim axes provides researchers with a defined set of molecular levers to investigate in these contexts. If the balance identified in mouse ovaries proves relevant to human follicle dynamics, it could eventually inform strategies aimed at preserving ovarian function, improving assisted reproduction outcomes, or extending fertility. For now, the study stands as a vivid demonstration that a follicle’s survival is not a matter of chance but of a measurable, contestable molecular equilibrium, one that science is only beginning to read in full.

Subject of Research: The molecular regulation of ovarian follicle atresia by the opposing HIF1/Bcl-XL survival and FOXO1/Bim apoptotic signaling axes in mouse granulosa cells

Article Title: HIF1 counteracts FOXO1/Bim-associated follicle atresia in mouse ovaries by promoting Bcl-XL expression

Article References: Hao, M., Liu, L., & Wang, J. (2026). HIF1 counteracts FOXO1/Bim-associated follicle atresia in mouse ovaries by promoting Bcl-XL expression. Journal of Ovarian Research. https://doi.org/10.1186/s13048-026-02284-7

Image Credits: AI Generated

DOI: 10.1186/s13048-026-02284-7

Keywords: follicle atresia, granulosa cells, HIF1 pathway, FOXO1, Bcl-XL, Bim, apoptosis, reactive oxygen species, ovarian follicles, fertility, follicle selection, Journal of Ovarian Research

The core idea borrows directly from nature. Real ants deposit pheromones along the trails they walk, and subsequent ants prefer paths carrying stronger chemical signals, a positive feedback loop that gradually steers the colony toward the shortest route to food. The ant colony optimization algorithm encodes this behavior in software: a population of virtual ants moves across a grid map, probabilistically choosing the next node based on pheromone concentration and a distance-based heuristic, then reinforcing the routes it traverses in proportion to their length. Over many iterations, the swarm converges on short paths. The method is prized for its robustness, distributed computing character, and adaptability, and it has already found use in robot navigation, transportation networks, and urban fire rescue.

But the standard algorithm has a blind spot when applied to burning villages. Its original heuristic measures nothing but geometric distance, which means it can happily route evacuees through an alley filled with lethal smoke simply because that alley happens to be short. Qiu and colleagues redesigned the heuristic to weigh three additional factors alongside raw distance: a human activity index that combines air temperature, toxic gas concentration, and crowd density through piecewise penalty functions; a passage difficulty coefficient that penalizes alleys narrower than three meters and effectively blocks those narrower than 1.5 meters with a penalty factor of 1000; and the remaining distance to the destination. The resulting equivalent evacuation length converts each grid cell into a risk-adjusted cost, so virtual ants automatically detour around high-temperature zones, CO-heavy corridors, and congested passages without any manual route instruction.

The fire physics feeding this risk map came from Pyrosim, a computational fluid dynamics tool. The team first built a three-dimensional model of Ma’an Village in Revit, capturing more than 30 ancient buildings, the road network, vegetation, and firefighting facilities in detail. They then imported that model into Pyrosim and simulated a five-megawatt fire ignited outside the village’s central drum tower over a 240 by 200 meter domain at half-meter resolution, some 6.1 million grid cells in total. Sensors placed at two meters in height at each exit recorded temperature, visibility, and smoke concentration. The simulation showed the fire source reaching 130 degrees Celsius within 50 seconds; by 500 seconds, the blaze had spread to nearby buildings, visibility had dropped below 13 meters across a hazardous core near the fire, and smoke concentration had climbed to 4.5 times 10 to the negative fifth mol per mol, well beyond the safety threshold.

The researchers extracted temperature, gas concentration, and crowd density data at two static snapshots, 200 and 500 seconds, and mapped them onto a 30 by 30 evacuation grid of 1.5 by 1.5 meter cells. Cell size matters here: the authors emphasize that grid cells represent the longitudinal step of a passage, not its transverse width, so genuinely impassable alleys are excluded by the passage difficulty coefficient rather than by grid resolution. This BIM-to-Pyrosim-to-MATLAB pipeline creates a closed data loop in which architectural geometry, fire field data, and route optimization flow automatically from one platform to the next, without repeated manual conversion, and the framework is explicitly designed as a generalized method for any historic dense settlement with similar characteristics, not just one village.

Three further upgrades sharpened the algorithm itself. An adaptive pheromone concentration steps down through the run, from 100 early on to 75 and then 50, boosting exploration at the start and refining convergence later. An adaptive evaporation coefficient gradually declines until it hits a floor tied to the fire’s impact level, with higher severity driving higher minimum evaporation to keep the swarm from fixating on stale routes. And a backtracking strategy rescues any ant that wanders into a dead end: the blocked node joins a taboo list and the ant retreats until it finds a passable cell, preventing infinite loops in the maze-like village geometry. After systematic single-factor tuning of the pheromone and heuristic weights, the optimal configuration settled at alpha equal to 2, beta equal to 9, evaporation factor 0.4, 70 ants, and 100 maximum iterations.

The performance gains were substantial and statistically solid. Running each parameter combination across 25 independent random seeds to eliminate stochastic noise, the team found that the improved algorithm shortened the shortest physical escape path from S1 to exit E4 from 17.75 meters under the standard algorithm to 15.11 meters under the improved version, a 14.9 percent reduction, the largest decrease among all seven tested exit paths. Every planned route came out shorter with the improved method, and paired-sample t-tests confirmed the differences were significant at p less than 0.05. Convergence improved even more dramatically: the upgraded algorithm locked onto optimal routes within an average of 3 to 10 iterations, while the standard version needed about 18, a gap significant at p less than 0.01, and its late-stage curve fluctuations indicated a stronger ability to avoid premature convergence on local optima.

When the simulated fire reached its spread phase, with 19 fire grids covering 42.75 square meters and four of seven exits blocked, the framework adapted cleanly, rerouting evacuees to the three remaining passable exits and still identifying exit E4 as the shortest at 15.11 meters. Computationally, the method is light: a single route calculation for the entire village takes roughly 28 seconds on an ordinary 16-gigabyte desktop with about 4.2 gigabytes of memory, and enlarged grids slow convergence slightly without stalling, suggesting the approach scales to larger heritage sites. The authors stress that all geometric parameters came from field measurements of the real village, grounding the virtual experiment in authentic conditions.

The team is candid about the work’s limits. The simulation covers only carbon monoxide as a toxic gas, excludes CO2, hypoxia, hydrogen cyanide, structural collapse, and wind effects, and relies on two static fire snapshots rather than continuous dynamic re-planning as occupants move. Validation so far rests on a single village and BIM-based co-simulation, with no field evacuation drills or historical fire records to calibrate the model, and the full route optimization currently targets physical distance alone without quantifying route safety. The authors also note that a complete, standardized fire risk ontology remains future work. Still, the framework offers heritage managers and emergency planners an immediate practical tool: an offline way to draft evacuation plans for the world’s many vulnerable historic settlements, with real-time sensor integration and dynamic occupant modeling as the clear next step toward protecting both lives and irreplaceable cultural heritage.

Subject of Research: Optimization of fire evacuation routes in historic dense settlements using BIM and an improved ant colony algorithm

Article Title: Generalized optimization method for fire evacuation routes in historic dense settlements based on improved ant colony algorithm and BIM

Article References: Qiu, J., Qin, J., Hu, Y., Liu, Y., & Qin, J. (2026). Generalized optimization method for fire evacuation routes in historic dense settlements based on improved ant colony algorithm and BIM. Discover Artificial Intelligence, 6(1), Article 1214. https://doi.org/10.1007/s44163-026-02256-2

Image Credits: AI Generated

DOI: 10.1007/s44163-026-02256-2

Keywords: fire evacuation, historic dense settlements, ant colony optimization, BIM, path planning, Pyrosim, Revit, Ma'an Village, heuristic function, adaptive pheromone, emergency planning, cultural heritage