Search Results (1,238)

In recent years, artificial intelligence has brought significant changes in architectural practice. The possibilities associated with generating forms on various scales have prompted reflection on the role and contribution of the architect to the design process. An important element of these considerations is the quality of the results provided by algorithm that generate formal and design solutions, in this case apartment plans. This article aims to determine whether artificial intelligence design software, PlanFinder version from February 2026, which is significantly faster and more efficient in delivering finished plans than even the most skilled designers, can achieve a quality comparable to that of professional architects. Based on selected parameters that allow for an objective assessment of apartment plans, a comparative analysis was conducted between the designer’s work and the results of generative algorithm of the mentioned above software. Using case studies of completed residential projects, an assessment was made of whether and to what extent artificial intelligence can provide reliable support in automating the process of creating apartment layouts, whether it can be assigned specific tasks, or a hybrid approach involving post-production and correction of the results is required. The article which is an exploratory evaluation of early-stage PlanFinder outputs shows that, in spite of generating rapidness there are still significant flaws regarding building-code compliance. Full article

Sugarcane harvester performance varies substantially with field geometry, crop, and operator factors, yet separating these sources from telematics data while preserving engineering interpretability remains a methodological gap. This study models field efficiency (Eff) and harvesting capacity (C_a) separately from JDLink telematics, aligning model structure with each target’s response behavior. Operational data covered 105 plots across four seasons (2019/20–2022/23) from three John Deere CH570 chopper harvesters in eastern Thailand. Six engineering-relevant predictors were retained after multicollinearity screening, and linear (MLR), additive nonlinear (GAM), and tree-based models were compared under 5-fold grouped cross-validation by BaseField (87 groups). Eff was assigned to GAM (R²_CV = 0.621 ± 0.114) on the basis of its threshold-like response to turning frequency; C_a was retained for MLR (R²_CV = 0.681 ± 0.121), with GAM essentially tied. Train–validation gaps were substantially smaller for additive models (0.096–0.118) than for tuned tree-based candidates (GBR 0.210–0.302, RF 0.322–0.358). Turning frequency (TF) and perimeter-to-area ratio (PAR) were the strongest predictors, and a constant-turn-time partial-out test indicated that TF’s univariate effect on Eff is largely mediated by the time-budget identity. Tactical interventions (path planning, operator training, machine–field allocation) are immediately feasible, although strategic field-layout change remains constrained by smallholder land tenure. Full article

The digitization of existing building stock often depends on legacy 2D raster floor plans (scanned drawings, PDF exports, or photographs) because structured building information models are frequently unavailable for older properties. Manual measurement and visual inspection of such documents are time consuming and error prone. This paper presents an integrated deep learning pipeline that extracts semantic information from unstructured two-dimensional floor plan images of existing structures and supports preliminary compliance screening via locally deployed large language models. The pipeline employs YOLOv8 for the localization and classification of 18 architectural symbols and furniture items, and a U-Net with a ResNet34 encoder for the semantic segmentation of walls and interior room spaces. To translate pixel-level predictions into physical metrics, we implement an area calculation module based on user-defined reference scale calibration. An LLM evaluation module, deployed locally via Ollama with a retrieval-augmented generation pipeline, interprets extracted room metrics and flags potential non-compliance against referenced residential design guidelines; it is intended for the assessment of existing layouts rather than generative co-design. We expand a core dataset of 101 manually annotated source floor plans to 303 augmented instances using label-aligned geometric transformations, while reporting generalization in terms of the 101 unique source plans. On the held-out validation split (10 source plans), YOLOv8 achieves 92.3% mAP50 versus 87.2% for a Faster R-CNN reference model on the same data split (detection baselines differ in training epochs and pretraining; see Experiments); U-Net achieves 95.71% mIoU, surpassing DeepLabv3+ (93.2%) under matched segmentation training settings. The system is deployed as an interactive web application for legacy building survey and preliminary regulatory review when only two-dimensional documentation is available. Full article

The deployment of offshore wind farms (OWFs) has increased impressively over the last decade. While a group of frontrunner countries has led early deployment, the offshore wind sector is expanding to new regions; the Thracian Sea represents a promising area for OWFs deployment due to its favorable wind and wave climate. The successful implementation of OWFs projects depends on a comprehensive understanding of local environmental conditions, with particular emphasis on complex wind–wave interactions quantification, as well as on robust and representative power performance evaluation. In the present paper, hourly environmental data spanning 29 years (1993–2021), including wind and wave parameters, are utilized to quantify joint probability distributions at selected four locations in the Thracian Sea. Corresponding environmental contours are derived and presented using a probabilistic model for given return period. The joint probability distributions of wind and wave conditions are estimated and the environmental contour surfaces for 50- and 100-year return periods are calculated and presented for generic use. Furthermore, the power production of an OWF comprising nine IEA 15 MW turbine units arranged in an orthogonal grid layout is assessed through a numerical model developed in an open access computational tool. The model accounts for key physical processes influencing OWF capacity performance, including wake interactions, atmospheric conditions, turbine control strategies, and layout effects. The results indicate a substantial value of annual energy production and capacity factor for different zones within Thracian Sea achieving a value of 526 GWh and 44%, respectively. The presented results provide practical guidance for OWFs development in the Thracian Sea and contributes to reducing uncertainty in early-stage project planning and future engineering studies. Full article

Conventional evaluations of indoor environmental quality (IEQ) in office spaces are typically disproportionately influenced by expert experience, often overlooking the cognitive gap between decision makers (experts) and users (employees). To quantify and explain this discrepancy, this study develops a comprehensive evaluation framework including 20 IEQ indicators, grounded in Maslow’s hierarchy of needs. Using the Shenzhen Science Park as a case study, evaluation data were collected from 13 experts and 432 employees. The Analytic Hierarchy Process (AHP) and the Kano model were applied to calculate expert weights and employees’ nonlinear sensitivities, respectively, followed by the construction of an optimization matrix via Importance–Performance Analysis (IPA). The results reveal a notable cognitive gap: experts prioritize foundational physical elements regarding spatial technology, whereas employees place greater emphasis on factors such as privacy protection and flexible layouts. Both groups concur that “noise interference” and “lack of privacy” are the primary shortcomings of open-plan offices. Prospective assessments indicate that embodied AI-enabled robots currently remain in a “early adoption phase,” with employees showing no functional dependency on them. This study confirms that merely improving building physical performance does not proportionally translate to increased employee satisfaction. Spatial optimization should adopt a human-centric approach, emphasizing acoustic control and the reconfiguration of privacy boundaries to enhance the scientific allocation of resources. Full article

Reducing carbon emissions from daily travel has become an important goal of 15-minute living-circle planning, yet it remains unclear which facility configurations are most supportive of green travel. Using 634 living circles and 20 million mobile-phone travel records and point-of-interest (POI) data, this study examines how facility layout within a 15-minute cycling circle influences residents’ walking and cycling travel behavior. Extreme Gradient Boosting (XGBoost) models and Shapley Additive Explanations (SHAP) suggest that low accessibility is generally associated with lower green travel shares, while moderate facility density promotes green travel, yet for some facility types, high density may show diminishing marginal benefits. Vegetable markets and primary schools emerge as key facilities, with education facilities driven mainly by accessibility, entertainment facilities by density, and commercial and healthcare facilities by both. K-means clustering identifies three types of low-green-travel-performing living circles—characterized by low density and poor accessibility—concentrated in peripheral and newly developed areas. The methodology is transferable, and the derived numerical ranges and living-circle typologies offer context-specific implications for Tangshan, and identified differences in facility importance and diminishing marginal benefits enrich 15-minute city theory. Full article

Well-point dewatering can rapidly lower the level of groundwater, making the capillary zone fall below the depth at which the subgrade is frozen. This can have the effect of inhibiting frost heave in the subgrade. This paper draws upon a project focused on treatment of the frozen section of the Shenmu–Shuozhou railway subgrade to present a method for calculating the dynamic groundwater level when pumping water using group wells. A dynamic groundwater seepage model is established, and the influence of the type of pumping wells, their layout, and spacing on variations in the groundwater level and the inhibition of frost heave in the subgrade is examined. This forms the basis of an optimal treatment plan for the frozen section of the Shenmu–Shuozhou railway. Simulation results show that a double row of wells along the route that fully penetrate the phreatic aquifer led to a large drop in the groundwater level, thus significantly inhibiting frost heave. Reducing the spacing of the wells enhances the dewatering effect and frost heave inhibition, but also reduces the strength and stability of the subgrade, so the right balance needs to be struck between the stability requirements and the frost-heave inhibition requirements. This research can serve as a reference for the treatment of frost heave in silty subgrades. Full article

This paper investigates machine learning (ML)-supplemented workflows integrated within a modular parametric modelling framework derived from a typological analysis of stadiums. The objective of the research is to address a gap between numerous isolated computational studies and the realities of early stadium design within the Royal Institute of British Architects (RIBA) Plan of Work (PoW) Stages 0–3. From a practical perspective, the proposed design framework aims to embed supervised learning, semi-supervised learning, and evolutionary optimisation into stadium design development to support site appraisal, brief preparation, concept development, spatial coordination, and stadium bay or stand optimisation based on quantifiable design characteristics. The framework addresses the inefficiencies and limitations of the traditional stadium design process by allowing rapid design space exploration defined by typological drivers, evaluation of a large set of solutions based on performance metrics such as circulation distances, sightline quality, and layout distribution, and the validation of concepts against benchmarks. Within the applicable design pipelines, and where labels are derived from deterministic performance criteria, the supervised approaches achieved prediction accuracies above 85%, while evolutionary optimisation reduced the number of seats with restricted views by approximately 95%. The value of the study is that it demonstrates that the integration of parametric modelling based on shared typological characteristics and the mapping of ML methods to the RIBA PoW has the potential to support stadium design in a novel way. Full article

Public charging infrastructure plays a critical role in supporting the sustainable development of electric vehicles (EVs), yet its effectiveness is often constrained by environmental conditions and spatial mismatches between supply and demand. This study develops a demand-oriented analytical framework to evaluate public charging services and support compensatory layout planning under cold-climate conditions, using Harbin, China, as a case study. The framework integrates demand hotspot identification, climate-adjusted service coverage reconstruction, service mismatch diagnosis, and compensatory layout recommendations. The results show that public charging demand in Harbin exhibits a clear centre-oriented clustering pattern. As cold-climate constraints intensify, the effective service coverage of charging facilities continuously contracts, and service mismatch areas become concentrated in high-demand clusters, forming an overall pattern of prominent central areas and scattered peripheral zones. Under the general winter scenario, a total of 197 service mismatch grids were identified, accounting for 58.98% of all hotspot grids. After the proposed compensatory layout, the number of mismatch grids decreased to 115, representing a reduction of 82 grids or 41.62%. These findings demonstrate that climate-sensitive service evaluation is essential for accurately identifying critical service deficiencies in cold-climate cities. The proposed framework provides a transferable approach for climate-sensitive service evaluation and compensatory layout planning of public charging infrastructure in high-latitude urban areas. Full article

Frequent heavy rainstorm disasters have led to the need for temporary storage of large quantities of heterogeneous disaster-related solid waste within a short period, making temporary storage an important issue in the construction and optimization of the urban comprehensive urban emergency management systems. This study takes the “23·7” catastrophic rainstorm event in Mentougou District, an area prone to rainstorm disasters in Beijing, as a case study and develops an auxiliary decision-making model for site selection that integrates estimates of construction waste and household goods waste, an “initial selection—screening—optimization” suitability evaluation, and the optimization of spatial layout optimization. By combining the spatial analysis method of the Geographic Information System (GIS), an evaluation index system covering natural geography, ecological environment, and socio-economic factors was constructed. An integrated AHP–EWM model was constructed, merging the expert-driven, subjective weighting of the Analytic Hierarchy Process with the objective, data-derived weighting of the Entropy Weight Method to determine indicator weights. The suitability distribution for site selection was studied by combining the multi-factor weighted overlay model, and the area most suitable for construction of Temporary Disaster Waste Storage Sites (TDWSSs), accounting for 4.51% of the total area, was identified. Subsequently, multiple constraints—including ecological protection redlines and minimum area requirements—were superimposed to exclude non-compliant areas. Ultimately, a combined optimization model integrating the minimum facility location model, maximum coverage model, and minimum impedance model was constructed, and the optimal site selection scheme was determined via ArcGIS. The results show that, when seven TDWSSs are considered, the coverage rate of administrative villages within the 20 km transportation service range reaches 97.38%. The results also indicate that, when the number of TDWSSs exceeds eight, the increase in the coverage rate tends to be moderate and the optimization space is limited, indicating that the layout scheme with seven TDWSSs is close to the regional optimal solution. This framework provides crucial guidance for post-rainstorm TDWSS planning and layout optimization. Full article

This study aims to develop a decision-making framework for equalizing urban electric vehicle (EV) charging services, which is applied to improve Wuhan’s charging infrastructure. Using grid units as the basic analytical units, the study constructs measurement models for two scenarios—daily commuting and weekend travel—including a spatial demand index based on classified population distribution prediction, a spatial supply index derived from regional charging station statistics, and a supply–demand balance index. Grading systems are established for each scenario’s demand, layout thresholds, and supply, together with an integrated classification combining both scenarios. According to the suitability of grid units for service improvement, three optimization strategies are proposed: adding charging stations, expanding existing stations, and retrofitting parking lots. Evaluation methods are designed to assess spatial equilibrium pre- and post-optimization for residential quarters and commercial POIs. An empirical case study of Wuhan’s main urban area shows that service satisfaction reaches 88.68% for residential quarters and 75.93% for commercial POIs under the current conditions. The proposed scheme recommends the addition of 6 new stations, expansion of 23 stations, and retrofit of 52 parking lots, increasing satisfaction to 99.16% and 89.66%, respectively. The model provides a feasible technical framework for urban EV charging station planning. Full article

Crack opening and reinforcement stress are two complementary indicators of the service state of reinforced concrete hydraulic structures, yet they are often predicted separately. This study develops a data-driven multi-task temporal fusion framework for joint 48 h ahead prediction of dam crack responses and rebar stress using multi-source monitoring data. The measured data comprise five crack-monitoring series, five rebar stress series, local temperature channels, reservoir water level, antecedent rainfall, and an auxiliary environmental signal over approximately four years. Target responses are aligned only at common measured timestamps; no synthetic target observations are introduced. A simplified engineering layout and plan-based crack–rebar distances are further used to examine whether an explicit spatial prior can strengthen the shared temporal representation without introducing synthetic target values. A residual multi-task temporal fusion network (MTTF-Net) is proposed with a shared Transformer encoder, attention pooling, task-specific decoders, and a response-continuity regularization term. The model is compared with persistence, Ridge regression, random forest, Extra Trees, XGBoost, and GRU baselines under a chronological train/validation/test split. For the independent test period, Ridge regression obtains the lowest overall RMSE (2.2968), whereas MTTF-Net provides the lowest crack RMSE (0.0141), the lowest overall MAE (1.0035), and the second-best overall RMSE (2.3813). Distance-informed ablation, denoted as MTTF-Net-S, remains close to MTTF-Net in macro-averaged $R^2$ but is not superior in the overall test metrics, indicating that the available horizontal distances are valuable engineering metadata but cannot replace richer three-dimensional structural connectivity. These results indicate that the monitoring data contain a strong linear autoregressive component, while multi-task temporal fusion improves nonlinear crack response prediction and remains competitive for stress forecasting. The source code is prepared as a public implementation package, whereas the measured monitoring dataset is subject to data owner restrictions. Full article

Underground gas control is a critical link in coal mine safety production, and drilling robots serve as the core equipment for gas extraction drilling operations. However, the autonomous locomotion technology of coal mine drilling robots has long been constrained by the unstructured underground environment and the limitations of existing navigation schemes, which restrict their intelligent application. To address this bottleneck, this paper conducts systematic research on key autonomous navigation technologies for coal mine drilling robots operating in narrow underground working faces, focusing on their practical operational requirements. First, a hardware scheme complying with coal mine safety standards is selected, the hardware structure and sensor layout are optimized via digital modeling, and the software interface and data interface format of the navigation system are designed. Second, an innovative 3D point cloud-based offline obstacle avoidance algorithm is proposed, which integrates a terrain analysis module, a local path planning method with maximum arrival probability, a Bézier curve-based trajectory library generation strategy, and a trajectory index construction method. Finally, simulation experiments, ground-simulated roadway field tests, and underground coal mine field experiments are performed to validate the proposed system. Experimental results demonstrate that the constructed autonomous navigation system enables smooth and safe autonomous locomotion and fixed-point parking of drilling robots, with an average parking error lower than 0.17 m, and can effectively avoid obstacles in complex environments. This research provides crucial technical support for the intelligent advancement of coal mine drilling robots. Full article

In the context of subtropical cities, the slow-moving environment of HOD (Hospital-Oriented Development) faces the dual challenges of spatial fragmentation and an extreme hot and humid climate, which also restricts the outdoor space’s thermal environment performance. Taking the Macau Light Rapid Transit (LRT) Union Hospital Station as an example, this study constructs a “topology-climate” dual quantitative assessment framework that integrates space syntax and parametric universal thermal climate index (UTCI) simulation. In response to the current problems of mixed pedestrian and vehicular traffic and high-intensity heat radiation, a comprehensive intervention strategy combining three-dimensional stitching and spatial optimization is proposed. The results show that: (1) The implantation of three-dimensional corridors improved the spatial integration of the core area of the site by 67.0%, significantly optimizing network connectivity. (2) During the extreme high-temperature period of daytime (9:00–18:00) in summer and autumn, the intervention strategy precisely opened up a continuous low-heat-stress linear shade zone through the synergistic mechanism of building projection shadows, physical shading of connecting corridors, (landscape shading effect, original evaporation removed). (3) The study confirms that landscape-coupled shading layout is the most effective method, reducing potential pedestrian heat exposure across the entire area, while the three-dimensional connecting corridors precisely control the thermal environment of core walkways. Together, these two elements construct a “topology-climate” optimization framework, achieving a synergistic improvement in spatial accessibility and simulated thermal comfort performance under standard meteorological input and quantitatively verifying the optimization effectiveness of the tiered intervention scheme. This study provides a data-driven decision-making basis for optimizing potential walking thermal conditions for vulnerable groups and reshaping the space’s potential to improve microclimate via shading design of medical hub areas and also provides a scientific paradigm for TOD microclimate planning focused on shading-based thermal environment optimization. Full article

This research proposes a conditional diffusion-based workflow for early-stage floor plan design in university research buildings, addressing complex functional organization, strict boundary constraints, and quantitative area control. The method performs denoising directly in two-dimensional grid space and coordinates building outlines and functional area proportions through dual-condition injection using boundary masks and functional area matrices. A two-stage generation mechanism first constructs horizontal circulation and then generates the complete layout, while a statistic-network-guided explicit constraint improves global area consistency. Based on 600 standard-floor samples and an independent test set of 10 real projects, the method is evaluated through model comparison, ablation, and double-blind experiments. The results show that the proposed model achieves the best overall performance, with an FID of 50.3, a building boundary IoU of 99.9%, and horizontal circulation connectivity of 89.8%. The ablation results confirm that the two-stage mechanism and explicit statistical constraint substantially improve generation success and reduce area error. The expert evaluation indicates that AI-generated floor plans approach real cases in functional spatial form and design inspiration, although spatial organization rationality still requires improvement. The generated layouts can be converted into layered DXF files, supporting subsequent editing and human–AI collaborative design. Full article