Urban morphology as a proxy for housing and infrastructure inequality: A machine learning approach using open building footprint data

Pedestrian-level wind plays a critical role in shaping the urban microclimate and is significantly influenced by urban form and geometry. The most common method for determining spatial wind speed patterns in cities relies on numerical computational fluid dynamics (CFD) simulations, which resolve Navier–Stokes equations around buildings. While effective, these simulations are computationally intensive and require specialised expertise, limiting their broader applicability. To address these limitations, this study proposes a more cost-effective alternative while achieving 90 % performance in capturing the mean and maintaining spatial wind patterns captured by CFD. We developed a machine learning (ML) approach with U-net architecture to predict time mean wind speed patterns from prevailing wind directions and three-dimensional urban morphology, which are increasingly available for global cities. The model is trained and tested using a comprehensive dataset of 512 numerical simulations of urban neighbourhoods, representing diverse morphological configurations in cities worldwide. We find that the ML algorithm accurately predicts complex wind patterns, achieving a normalised mean absolute error of less than 10 % , which is comparable to wind anemometer measurement in a low wind speed environment. In predicting wind statistics, the ML model also surpasses that of regression models based solely on statistical representations of urban morphology. The R 2 values measuring grid-level agreement between ML and CFD range from 0.94–0.99 and 0.65–0.95 for the idealised and whole datasets, respectively. However, we find that grid-based R 2 is not an effective metric for evaluating the 2D model performance due to localised biases arising from faster wind speed grid regions, which is revealed by the wind probability density function. These findings demonstrate that complex pedestrian wind patterns can be effectively predicted using an image-based ML approach, offering the potential to emulate physics-based large-eddy simulation models, which are computationally expensive, thereby significantly reducing computing costs.

Pedestrian-level wind plays a critical role in shaping the urban microclimate and issignificantly influenced by urban form and geometry. The most common method fordetermining spatial wind speed patterns in cities relies on numerical computationalfluid dynamics (CFD) simulations, which resolve Navier-Stokes equations aroundbuildings. While effective, these simulations are computationally intensive and requirespecialised expertise, limiting their broader applicability. To address these limitations,this study proposes a more cost-effective alternative while achieving 90% performancein capturing the mean and maintaining spatial wind patterns captured by CFD. Wedeveloped a machine learning (ML) approach with U-net architecture to predict timemean wind speed patterns from prevailing wind directions and three-dimensionalurban morphology, which are increasingly available for global cities. The modelis trained and tested using a comprehensive dataset of 512 numerical simulationsof urban neighbourhoods, representing diverse morphological configurations in citiesworldwide. We find that the ML algorithm accurately predicts complex wind patterns,achieving a normalised mean absolute error of less than 10%, which is comparableto wind anemometer measurement in a low wind speed environment. In predictingwind statistics, the ML model also surpasses that of regression models based solelyon statistical representations of urban morphology. The R2 values measuring grid-level agreement between ML and CFD range from 0.94-0.99 and 0.65-0.95 for theidealised and whole datasets, respectively. However, we find that grid-based R2 is notan effective metric for evaluating the 2D model performance due to localised biasesarising from faster wind speed grid regions, which is revealed by the wind probabilitydensity function. These findings demonstrate that complex pedestrian wind patternscan be effectively predicted using an image-based ML approach, offering the potentialto emulate physics-based LES models, which are computationally expensive, therebysignificantly reducing computing costs.

An improved machine learning approach for predicting granular flows

Developing a rapid method for 3-dimensional urban morphology extraction using open-source data

Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

<p>The advancement of big data and increased computational power have contributed to an increased use of Machine Learning (ML) approaches in hydrological modelling. These approaches are powerful tools for modeling non-linear systems. However, the applicability of ML in non-stationary conditions needs to be studied further. As climate change will change hydrological patterns, testing ML approaches for non-stationary conditions is essential. Here, we used the Differential Split-Sample Test (DSST) to test the climate transposability of ML approaches (e.g., calibrating in a wet period and validating in a dry one, and vice-versa).  We applied five ML approaches using daily precipitation and temperature as input for the prediction of the daily discharge in six snow-dominated Swiss catchments. Lower and upper benchmarks were used to evaluate performances through a relative performance measure. The lower benchmark is the average of the bucket-type HBV model runs from 1000 random parameter sets. The upper benchmark is the automatically calibrated HBV model. In comparison with the stationary condition, the models performed slightly poorer in the non-stationary condition. The performance of simple ML approaches was poor for non-stationary conditions with an underestimation of peak flows, as well as a poor representation of the snow-melting period. On the other hand, a more complex ML approach (deep learning), the Long Short -Term Memory (LSTM), showed a good performance when compared with the lower and upper benchmarks. This might be explained by the fact that the so-called memory cell allowed to simulate the storage effects. </p>

Background: This paper attempts to identify suitable Machine Learning (ML) approach for image denoising of radiology based medical application. The Identification of ML approach is based on (i) Review of ML approach for denoising (ii) Review of suitable Medical Denoising approach.Discussion: The review focuses on six application of radiology: Medical Ultrasound (US) for fetus development, US Computer Aided Diagnosis (CAD) and detection for breast, skin lesions, brain tumor MRI diagnosis, X-Ray for chest analysis, Breast cancer using MRI imaging. This survey identifies the ML approach with better accuracy for medical diagnosis by radiologists. The image denoising approaches further includes basic filtering techniques, wavelet medical denoising, curvelet and optimization techniques. In most of the applications, the machine learning performance is better than the conventional image denoising techniques. For fast and computational results the radiologists are using the machine learning methods on MRI, US, X-Ray and Skin lesion images. The characteristics and contributions of different ML approaches are considered in this paper.Conclusion: The problem faced by the researchers during image denoising techniques and machine learning applications for clinical settings have also been discussed.

Recently, global climate change discussions have become more prominent, and forests are considered as the ecosystems most at risk by the consequences of climate change. Wildfires are among one of the main drivers leading to losses in forested areas. The increasing availability of free remotely sensed data has enabled the precise locations of wildfires to be reliably monitored. A wildfire data inventory was created by integrating global positioning system (GPS) polygons with data collected from the moderate resolution imaging spectroradiometer (MODIS) thermal anomalies product between 2012 and 2017 for Amol County, northern Iran. The GPS polygon dataset from the state wildlife organization was gathered through extensive field surveys. The integrated inventory dataset, along with sixteen conditioning factors (topographic, meteorological, vegetation, anthropological, and hydrological factors), was used to evaluate the potential of different machine learning (ML) approaches for the spatial prediction of wildfire susceptibility. The applied ML approaches included an artificial neural network (ANN), support vector machines (SVM), and random forest (RF). All ML approaches were trained using 75% of the wildfire inventory dataset and tested using the remaining 25% of the dataset in the four-fold cross-validation (CV) procedure. The CV method is used for dealing with the randomness effects of the training and testing dataset selection on the performance of applied ML approaches. To validate the resulting wildfire susceptibility maps based on three different ML approaches and four different folds of inventory datasets, the true positive and false positive rates were calculated. In the following, the accuracy of each of the twelve resulting maps was assessed through the receiver operating characteristics (ROC) curve. The resulting CV accuracies were 74%, 79% and 88% for the ANN, SVM and RF, respectively.

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.

333 Background: Patients undergoing outpatient infusion chemotherapy for cancer are at risk for potentially preventable, unplanned acute care in the form of emergency department (ED) visits and hospital admissions. This can impact outcomes, patient decisions, and costs to the patient and healthcare system. To address this need, the Centers for Medicare & Medicaid Services developed the Chemotherapy Measure (OP-35). Recent randomized controlled data indicate that electronic health record (EHR)-based machine learning (ML) approaches accurately direct supportive care to reduce acute care during radiotherapy. As this may extend to systemic therapy, this study aims to develop and evaluate ML approaches to predict the risk of OP-35 qualifying, potentially preventable acute care within 30 days of infusional systemic therapy. Methods: This study included data from UCSF cancer patients receiving infusional chemotherapy from July 1, 2017, to February 11, 2021, (total 7,068 patients over 84,174 treatments). The data incorporated into the ML included 430 EHR-derived variables, including cancer diagnosis, therapeutic agents, laboratory values, vital signs, medications, and encounter history. Three ML approaches were trained to predict an OP-35 acute care risk following a systemic therapy infusion with least absolute shrinkage selection operator (LASSO), random forest, and gradient boosted trees (GBT; XGBoost) approaches. The models were trained on a subset (75% of patients; before October 12, 2019) of the dataset and validated on a mutually exclusive subset (25% patients; after October 12, 2019) based on the receiver operating characteristic (ROC) curves and calibration plots. Results: There were 1,651 total acute care visits (244 ED visits and 1,407 ED visits converted into hospitalization); 1,310 infusions included a qualifying acute care visit (200 with ED visits only, 0 direct hospital admissions, and 1,110 with both ED visit and hospitalization). Each ML approach demonstrated good performance in the internal validation cohort, with GBT (AUC 0.805) outpacing the random forest (0.750) and LASSO logistic regression (0.755) approaches. Visualization of calibration plots verified concordance between predicted and observed rates of acute care. All three models shared patient age and days elapsed since last treatment as important contributors. Conclusions: EHR-based ML approaches demonstrate high predictive ability for OP-35 qualifying acute care rates on a per-infusion basis, identifying 30-day potentially preventable acute care risk for patients undergoing chemotherapy. Prospective validation of these models is ongoing. Early prediction can facilitate interventional strategies which may reduce acute care, improve health outcomes, and reduce costs.

Collaborative robots, or cobots, are designed to work alongside humans and to alleviate their physical burdens, such as lifting heavy objects or performing tedious tasks. Ensuring the safety of human-robot interaction (HRI) is paramount for effective collaboration. To achieve this, it is essential to have a reliable dynamic model of the cobot that enables the implementation of torque control strategies. These strategies aim to achieve accurate motion while minimizing the amount of torque exerted by the robot. However, modeling the complex non-linear dynamics of cobots with elastic actuators poses a challenge for traditional analytical modeling techniques. Instead, cobot dynamic modeling needs to be learned through data-driven approaches, rather than analytical equation-driven modeling. In this study, we propose and evaluate three machine learning (ML) approaches based on bidirectional recurrent neural networks (BRNNs) for learning the inverse dynamic model of a cobot equipped with elastic actuators. We also provide our ML approaches with a representative training dataset of the cobot's joint positions, velocities, and corresponding torque values. The first ML approach uses a non-parametric configuration, while the other two implement semi-parametric configurations. All three ML approaches outperform the rigid-bodied dynamic model provided by the cobot's manufacturer in terms of torque precision while maintaining their generalization capabilities and real-time operation due to the optimized sample dataset size and network dimensions. Despite the similarity in torque estimation of these three configurations, the non-parametric configuration was specifically designed for worst-case scenarios where the robot dynamics are completely unknown. Finally, we validate the applicability of our ML approaches by integrating the worst-case non-parametric configuration as a controller within a feedforward loop. We verify the accuracy of the learned inverse dynamic model by comparing it to the actual cobot performance. Our non-parametric architecture outperforms the robot's default factory position controller in terms of accuracy.

Urban fabric characterization is very useful in urban design, planning, modeling and simulation. It is traditionally considered as a descriptive task mainly based on visual inspection of urban plans. Cartographic databases and geographic information systems (GIS) capabilities make possible the analytical formalization of this issue. This paper proposes a renewed approach to characterize urban fabrics using buildings’ footprints data. This characterization method handles both architectural form and urban open space morphology since urban space can be intuitively and simply divided into built-up areas (buildings) and non-built-up areas (open spaces). First, we propose to build a mesh of the open space (a morphologic tessellation) and then we formalize relevant urban morphology properties and translate them into a set of indicators (using some common-used indispensable indicators and proposing a new formulation or generalization of a few others). This first step produces a highly dimensional data set for each footprint characterizing both the building and its surrounding open space. This data set is then reduced and classified using a spatial clustering process, the self-organizing maps in this case. Our method only requires buildings’ footprints as input data. It can be applied on huge datasets and is independent from urban contexts. The results show that the classification produced is more faithful to ground truth (highlighting the variety of urban morphologic structures) than traditional descriptive characterizations generally lacking open space properties.KeywordsUrban fabricMorphologyBuildingsSelf-organizing maps

The determinants of open data (OD) in prediction using machine learning (ML) have been discussed in this study, which is done by reviewing current research scenario. As open government data (OGD) and social networking services (SNSs) have grown rapidly, OD is considered as the most significant trend for users to enhance their decision-making process. The purpose of the study was to identify the proliferation of OD in ML approaches in generating decisions through a systematic literature review (SLR) and mapping the outcomes in trends. In this systematic mapping study (SMS), the articles published between 2011 and 2020 in major online scientific databases, including IEEE Xplore, Scopus, ACM, Science Direct and Ebscohost were identified and analyzed. A total of 576 articles were found but only 72 articles were included after several selection process according to SLR. The results were presented and mapped based on the designed research questions (RQs). In addition, awareness of the current trend in the OD setting can contribute to the real impact on the computing society by providing the latest development and the need for future research, especially for those dealing with the OD and ML revolution.

Do Machine Learning Approaches Perform Better Than Regression Models in Mapping Studies? A Systematic Review.

This study quantifies the nonlinear driving force of urban morphological factors on canopy urban heat island intensity (CUHII) in Anhui Province, integrating relocated meteorological station data, remote sensing imagery, and machine learning frameworks. CUHII values exhibit a range of 0.06°C–1.12°C, with the built-up largest patch index (LPIbt, importance score = 0.25) and built-up area ratio (ARbt, 0.18) emerging as dominant drivers. Cropland coverage (ARc, Pearson’s r = −0.59) demonstrates significant cooling effects on urban thermal environments. The random forest (RF) model outperforms support vector regression (SVR) model, achieving training/test R2 values of 0.95/0.76 and RMSE of 0.04/0.08°C. This superiority highlights its capability to capture complex interactions between urban morphologies and local thermal environment. The research framework is innovatively adapted to a flipped classroom educational model: students not only replicate the machine learning workflow using the same dataset but also design comparative experiments to test how urban morphological indicators affect CUHI outputs, thereby deepening their understanding of both physical mechanisms of CUHI and the interpretability of machine learning modeling. This integration of cutting-edge climate research with hands-on educational practice bridges the gap between academic inquiry and practical skill development. The study provides a replicable methodological framework for urban climate research and its translation into educational applications.