Hazard Prediction Research Articles

ProbSevere Version 3: Improved Exploitation of Data Fusion and Machine Learning for Nowcasting Severe Weather

Abstract National Oceanic and Atmospheric Administration (NOAA)/Cooperative Institute for Meteorological Satellite Studies (CIMSS) ProbSevere, or the “probability of severe” models, provide next-hour probabilistic guidance on severe weather in the United States (large hail, strong wind gusts, and tornadoes) using machine learning and meteorological data from remotely sensed platforms and short-term numerical weather models. ProbSevere has been widely used by NOAA’s National Weather Service (NWS) since 2016. ProbSevere version 3 employs multiplatform, multiscale storm object identification and tracking to collect storm features and then uses gradient boosting decision trees to make predictions of convective hazards from the extracted predictors. ProbSevere v3 was trained, validated, and tested on data from 2018 to 2023. Results demonstrate improved performance over ProbSevere v2 for the majority of the United States across all seasons, spanning a wide range of meteorological regimes. The greatest improvements are for the hail, wind, and any severe models, whereas the tornado model demonstrated modest improvement. ProbSevere v3 models were evaluated by NWS forecasters in simulated real-time experiments from 2021 to 2023. The majority of forecasters preferred ProbSevere v3 over v2 due to improved confidence in predictions and greater lead times for the issuance of severe weather warnings. An analysis of predictor importance revealed several radar, lightning, satellite, and numerical model fields that strongly contribute to the model predictions, which is consistent with past research and knowledge of severe thunderstorm forecasting. This reinforces the importance of environmental data fusion for nowcasting severe weather associated with midlatitude convection. Significance Statement This study details the updates made to a U.S.-wide, real-time, probabilistic severe-weather guidance system aimed to improve forecaster confidence and the accuracy of the U.S. National Weather Service severe weather warnings. An evaluation of the system demonstrated improved performance over the operational predecessor, which was driven by radar, ground-based lightning, satellite, and numerical model data sources.

Improvement of the Typhoon Damage Prediction System for Electric Power Distribution Equipment (RAMPT): Proposal of a Correction Method Considering the Tree and Information of Landslide Hazard Prediction

Improvement of the Typhoon Damage Prediction System for Electric Power Distribution Equipment (RAMPT): Proposal of a Correction Method Considering the Tree and Information of Landslide Hazard Prediction

Optimizing rainfall-triggered landslide thresholds for daily landslide hazard warning in the Three Gorges Reservoir area

Abstract. Rainfall is intrinsically linked to the occurrence of landslide catastrophes. Identifying the most suitable rainfall threshold model for an area is crucial for establishing effective daily landslide hazard warnings, which are essential for the precise prevention and management of local landslides. This study introduces a novel approach that utilizes multilayer perceptron (MLP) regression to calculate rainfall thresholds for 453 rainfall-induced landslides. This research represents the first attempt to integrate MLP and ordinary least squares methods for determining the optimal rainfall threshold model tailored to distinct subregions, categorized by topographical and climatic conditions. Additionally, an innovative application of a three-dimensional convolutional neural network (CNN-3D) model is introduced to enhance the accuracy of landslide susceptibility predictions. Finally, a comprehensive methodology is developed to integrate daily rainfall warning levels with landslide susceptibility predictions using a superposition matrix, thus offering daily landslide hazard warning results for the study area. The key findings of this study are as follows. (1) The optimal rainfall threshold models and calculation methods vary across different subregions, underscoring the necessity for tailored approaches. (2) The CNN-3D model substantially improves the accuracy of landslide susceptibility predictions. (3) The daily landslide hazard warnings were validated using anticipated rainfall data from 19 July 2020, thereby demonstrating the reliability of both the landslide hazard warning results and the rainfall threshold model. This study presents a substantial advancement in the precise prediction and management of landslide hazards by employing innovative modeling techniques.

Advanced simulation of combustion characteristics for hazardous nitrogenous compounds using multi-component gaseous fuels

Nitrogen-containing compounds are widely used as raw materials or intermediates in industries such as pharmaceuticals, dyes, explosives, and plastics. However, there is a lack of reliable and effective research methods for accurately predicting the consequences of accidents involving hazardous nitrogenous chemicals. This paper presents a novel method for simulating the combustion characteristics of nitrogen-containing hazardous chemicals, such as Hexogen (RDX) and Octogen (HMX), using multi-component gaseous small molecule fuels. The method relies on a theoretical modeling approach and numerical simulation to predict the behavior of intermediate combustion products. Key advancements include establishing a standard modeling method identifying 11 different small molecule components, and creating predictive model libraries through combinatorial methods. This approach moves away from traditional target matching by calculating proportion coefficients for each component based on their contribution to ignition characteristics. The feasibility and accuracy of this method were validated through experiments using a microscale calorimeter (MCC), demonstrating a high correlation (0.9981) between experimental results and model predictions. This method was found particularly effective for real-time prediction of thermal hazards in high-rise building scenarios, exemplified by 2-Ethylhexyl nitrate (EHN). The paper concludes with the identification of optimal multi-component models for RDX and HMX, highlighting the significant role of hydrogen cyanide (HCN) and unsaturated hydrocarbons in these models.

Observed Associations between Fire Danger and Climate Modes and Their Representation in ACCESS-S2

Abstract The increasing frequency and severity of wildfires in Australia, driven by climate change, pose a significant threat to ecosystems, lives, and property. This study examines the impact of climate drivers, specifically El Niño–Southern Oscillation (ENSO), Indian Ocean dipole (IOD), Southern Annular Mode (SAM), Madden–Julian oscillation (MJO), and two modes of persistent high pressure in the Australia–Pacific region, on extreme fire danger. By analyzing observed and simulated fire danger in relation to these climate drivers, we aim to enhance our understanding of climate–fire mechanisms and contribute to Australia’s bushfire preparedness. Our findings indicate that all assessed drivers influence extreme fire danger, with key influences related to the drivers’ established relationships with rainfall and temperature. El Niño, positive IOD, and negative SAM events generally increase extreme fire danger across most of Australia and in most seasons. The two modes of Australian blocking exhibit similar effects, varying spatially. Specific phases of the MJO have significant seasonal relationships with fire danger. In some instances, increased fire danger is not directly linked to temperature or precipitation changes but rather driven by remote teleconnections, airflow, or pressure anomalies. Evaluating the accuracy of weather and climate forecasting systems in representing these relationships is crucial for the effective prediction and mitigation of fire hazards. The leading Australian climate simulation model effectively reproduces observed relationships but reveals biases in capturing certain aspects of climate variability. Advancements in this field would enhance fire weather forecasts, including those by the Australian Bureau of Meteorology with lead times of up to 4 months. Significance Statement This assessment of climate–fire relationships and modeling accuracy is pivotal in understanding the factors behind severe fire events and improving future predictions and mitigation. Prior research has already established links between elevated fire weather conditions and these climate drivers, highlighting their potential for predicting severe fire events. This study aims to deepen our comprehension of the factors driving severe fire events and facilitate improved bushfire risk management in Australia.

Design of a hazard prediction system with intelligent multimodal fusion based on artificial intelligence & internet of things technology: taking a crib as an example.

How to design an intelligent multimodal fusion hazard prediction system using AIoT (Artificial Intelligence & Internet of Things) technology to predict some potential dangers. This article will provide some ideas and methods. This article designs an intelligent multimodal fusion hazard prediction system based on AIoT technology. The system mainly consists of an IoT hardware device and an AI multimodal and multi-dimensional Hazard Prediction Algorithm. This article will take baby cribs as an example, using this system to empower traditional baby cribs and transform them into intelligent baby cribs. In this example, the system can detect the real-time status of the baby and predict upcoming dangers, including kicking the quilt, wetting the bed, fever, crying, climbing over the crib, and turning over. Assuming that intelligent systems can detect the status of infants in real-time and make predictions before potential dangers occur, to promptly alert parents. Perhaps it can prevent some irreversible dangers from occurring. This system solves the pain point problem of parents having to take care of their babies after working hard. In this scenario, the system provides a design scheme for an intelligent multimodal fusion hazard prediction system with a temporary care function. The application of this system to baby cribs not only reduces the burden on parents but also ensures the safety and comfort of the baby. At the same time, the system has transferability, and its design concept can be transferred to other application scenarios, such as hospital care for infants, young children, or elderly patients, as well as childcare stations for abandoned children in society. This innovative system design scheme has a positive significance for family harmony and social development.

Examining the contribution of lithology and precipitation to the performance of earthquake-induced landslide hazard prediction

Earthquake-induced landslides (EQIL) are one of the most catastrophic geological hazards. Immediate and swift evaluation of EQIL hazard in the aftermath of an earthquake is critically important and of substantial practical value for disaster reduction. The selection of influencing factor layers is crucial when using machine learning methods to predict EQIL hazard. As important input factors for EQIL hazard models, lithology and precipitation are extensively employed in forecasting EQIL hazard. However, few work explored whether these layers can improve the accuracy of EQIL hazard predictions. With Random Forest (RF) models, we employed a traditional and a state-of-the-art sampling strategy to assess EQIL modelling with and without lithology and precipitation data for the 2022 Luding earthquake in China. First, by excluding both factors, we used eight other influencing factors (land use, slope aspect, slope, elevation, distance to faults, distance to rivers, NDVI, and peak ground acceleration) to generate a landslide hazard map. Second, lithology and precipitation were separately added to the original EQIL hazard models. The results indicate that neither lithology nor precipitation have positive effects on the prediction of EQIL for both sampling strategies. The high-risk areas (or low-risk areas) tend to cluster within certain lithology types or precipitation ranges, which significantly affects the accuracy of the hazard map. Additionally, the model with the state-of-the-art sampling strategy deteriorates more than the model with the traditional sampling strategy. We believe this is very likely due to the strong spatial clustering of negative sample points caused by the latest sampling strategy. Our findings will contribute to the assessment of post-earthquake landslide hazards and the advancement of emergency disaster mitigation efforts.

Accelerated hazard prediction based on age time-scale for women diagnosed with breast cancer using a deep learning method

Breast cancer is the most common cancer in women. Previous studies have investigated estimating and predicting the proportional hazard rates and survival in breast cancer. This study deals with predicting accelerated hazards (AH) rate based on age categories in breast cancer patients using deep learning methods. The AH has a time-dependent structure whose rate changes according to time and variable effects. We have collected data related to 1225 female patients with breast cancer at the Mandarin University of Medical Sciences. The patients' demographic and clinical characteristics including family history, age, history of tobacco use, hysterectomy, first menstruation age, gravida, number of breastfeeding, disease grade, marital status, and survival status have been recorded. Initially, we dealt with predicting three age groups of patients: ≤ 40, 41–60, and ≥ 61 years. Then, the prediction of accelerated risk value based on age categories for each breast cancer patient through deep learning and the importance of variables using LightGBM is discussed. Improving clinical management and treatment of breast cancer requires advanced methods such as time-dependent AH calculation. When the behavioral effect is assumed as a time scale change between hazard functions, the AH model is more appropriate for randomized clinical trials. The study results demonstrate the proper performance of the proposed model for predicting AH by age categories based on breast cancer patients' demographic and clinical characteristics.

Mechanism and controlling factors of mass transport complexes migration: A case study of the mass transport complexes in the taranaki deep water basin, New Zealand

Mass transport Complexes (MTCs) form significant sediment accumulations in continental slopes, hold key insights for natural hazard prediction and offshore oil exploration. This paper uses high-definition 3D seismic data to reconstruct the seismic geomorphology and sedimentary dynamics of MTCs, meticulously exploring the depositional systems of the Tanaraki Basin, New Zealand. It deciphers by kinematic notation, seismic faciess, quantifies megaclast morphological characteristics, in conjunction with the basal slope and channel structure development as the migration or kinematics of MTCs. Five seismic facies categories and dynamic traits—compression ridges, thrust faults, slides, grooves and slope terraces are distinguished in MTCs. Based on attributes maps and geomorphological interpretations, MTCs is segmented into four zones, showing combined effects of levée, basal slopes, and megaclast clusters on its migration. Lithological and topographical variations along these features modulate erosion properties and MTCs mobility, with base height shifts guiding local migration trajectories. The results of megaclast parameters in Zones 1 and 3 tune our understanding of stress patterns and directionality shifts, highlighting the complex dynamics at play. Notably, the differential motion triggered by levees instigates longitudinal shear zones. At critical migration disparities, MTCs fracture at these weak points, discharging pore pressure and filling fractures with fines, birthing “promontory” formations marked by low-amplitude fills. This work, therefore, establishes a groundbreaking migratory model that synthesizes the impacts of levees height, rock type variability, and megaclasts accumulation intensity, depicting a fragmented migration pattern. This study not only enriches our grasp of MTCs behavior in deep-water contexts but also furnishes a robust scientific foundation and predictive tool for gauging the hazards that MTCs may pose to underwater structures, thus carrying substantial theoretical and applied significance.

Landslide Hazard Prediction Based on UAV Remote Sensing and Discrete Element Model Simulation—Case from the Zhuangguoyu Landslide in Northern China

Rainfall-triggered landslides generally pose a high risk due to their sudden initiation, massive impact force, and energy. It is, therefore, necessary to perform accurate and timely hazard prediction for these landslides. Most studies have focused on the hazard assessment and verification of landslides that have occurred, which were essentially back-analyses rather than predictions. To overcome this drawback, a framework aimed at forecasting landslide hazards by combining UAV remote sensing and numerical simulation was proposed in this study. A slow-moving landslide identified by SBAS-InSAR in Tianjin city of northern China was taken as a case study to clarify its application. A UAV with laser scanning techniques was utilized to obtain high-resolution topography data. Then, extreme rainfall with a given return period was determined based on the Gumbel distribution. The Particle Flow Code (PFC), a discrete element model, was also applied to simulate the runout process after slope failure under rainfall and earthquake scenarios. The results showed that the extreme rainfall for three continuous days in the study area was 151.5 mm (P = 5%), 184.6 mm (P = 2%), and 209.3 mm (P = 1%), respectively. Both extreme rainfall and earthquake scenarios could induce slope failure, and the failure probabilities revealed by a seepage–mechanic interaction simulation in Geostudio reached 82.9% (earthquake scenario) and 92.5% (extreme rainfall). The landslide hazard under a given scenario was assessed by kinetic indicators during the PFC simulation. The landslide runout analysis indicated that the landslide had a velocity of max 23.4 m/s under rainfall scenarios, whereas this reached 19.8 m/s under earthquake scenarios. In addition, a comparison regarding particle displacement also showed that the landslide hazard under rainfall scenarios was worse than that under earthquake scenarios. The modeling strategy incorporated spatial and temporal probabilities and runout hazard analyses, even though landslide hazard mapping was not actually achieved. The present framework can predict the areas threatened by landslides under specific scenarios, and holds substantial scientific reference value for effective landslide prevention and control strategies.

HyG: A hydraulic geometry dataset derived from historical stream gage measurements across the conterminous US

Regional- and continental-scale hydrologic models are increasingly important forecasting tools, yet they rely on highly variable channel parameters (e.g. width, depth, hydraulic resistance) that remain unquantified for millions of stream reaches across the country. Existing hydrologic models utilize over-simplified channel geometries that directly impact the accuracy of streamflow estimates, with cascading effects for water resource and hazard prediction. Here, we present a hydraulic geometry dataset, termed ‘HyG’, derived from discharge field measurements at U.S. Geological Survey (USGS) stream gages across the conterminous United States (CONUS). The HyG dataset includes (1) at-a-station hydraulic geometry parameters, (2) at-a-station hydraulic resistance (Manning’s n) calculated from the Manning equation, (3) daily discharge percentiles, and (4) regionalized downstream hydraulic geometry parameters based on HUC4 (Hydrologic Unit Code 4), derived from a total of 4,051,682 individual measurements from 66,841 total gages. The regionalized HyG dataset can be used directly to improve channel representations in models over CONUS. The original HyG relationships can also be regionalized for finer scales if required.

VERMEER FCM: A tool integrating exposure and hazard modelling for chemicals migrating from food contact materials

A new tool, VERMEER FCM, was developed to support the risk assessment of single organic chemicals migrating from plastic food contact materials (FCM). The freely available tool is integrated into MERLIN-Expo and has been designed in line with Regulation (EU) No 10/2011 for plastic FCM. Overall, the tool consists of three modules that allow (i) to model the migration of chemicals into food, (ii) to predict toxicological endpoints relevant to risk assessment of FCM chemicals, and (iii) to automatically check whether the chemical of interest is included in Regulation (EU) No 10/2011. To apply the VERMEER FCM tool, users need to provide information regarding the chemical(s) of interest, the FCM, the food and other parameters (e.g. contact time and temperature). The three modules can be run either separately or in combination. Migration is predicted by a recently developed migration model, whereas hazard predictions for genotoxicity, subchronic toxicity, reproductive and developmental toxicity and carcinogenicity are provided by QSAR models selected from the publicly available VEGA HUB. The major novelty of the tool is that it combines information on hazard and exposure (i.e. migration) with regulatory information. Several case studies were performed to demonstrate the application of the tool.

Decoding Adverse Effects of Organic Contaminants in the Aquatic Environment: A Meta-analysis of Species Sensitivity, Hazard Prediction, and Ecological Risk Assessment.

Aquatic organisms in the environment are frequently exposed to a variety of organic chemicals, while these biological species may show different sensitivities to different chemical groups present in the environment. This study evaluated species sensitivity, hazards, and risks of six classes of organic chemicals in the aquatic environment. None of the taxonomic groups were the most sensitive or tolerant to all chemicals, as one group sensitive to one class of chemicals might possess adaptations to other chemical groups. Polychlorinated biphenyls were generally the most toxic chemical group, followed by polybrominated diphenyl ethers, polycyclic aromatic hydrocarbons, and pharmaceuticals and personal care products, while per- and polyfluoroalkyl substances and phthalate esters were the less toxic chemical groups. The hazard of organic chemicals was closely related to their physicochemical properties, including hydrophobicity and molecular weight. It was shown that 20% of the evaluated chemicals exhibited medium or high ecological risks with the worst-case scenario in the Pearl River Estuary. This novel work represented a comprehensive comparison of chemical hazards and species sensitivity among different classes of organic chemicals, and the reported results herein have provided scientific evidence for ecological risk assessment and water quality management to protect aquatic ecosystems against organic chemicals.

Crustal and uppermost mantle S-velocity structure of the Seoul metropolitan area on the Korean Peninsula from Helmholtz tomography

The Seoul metropolitan area, the most densely populated part of the Korean Peninsula, features complex subsurface structures and seismogenic faults, though their characteristics remain ambiguous due to low seismicity and limitations in fault investigation. High-resolution velocity models can provide constraints for identifying subsurface faults by detecting elongated low-velocity anomalies along fault zones. Recently, a dense seismic network was deployed in this area, facilitating the use of Helmholtz tomography, an array-based method that accounts for finite-frequency effects. Utilizing Helmholtz tomography, we obtained a high-resolution S-wave velocity model down to a depth of 50 km with waveform data recorded at 74 broadband seismic stations. We found that a linear low-velocity anomaly along the Pocheon fault extends to the uppermost mantle, with an increasing width with depth. In contrast, the Dongducheon fault, which traverses Seoul from north to south, is not well imaged, indicating its current weak activity. Another linear low-velocity anomaly extends southwest through Seoul from northern Seoul, potentially representing the extension of the Pocheon fault based on similar strike and dip directions. Additionally, a large lateral low-velocity anomaly is identified in the lower crust beneath the northern part of the Seoul metropolitan area, interpreted as a ductile décollement, connected with the Pocheon, Wangsukcheon, and possibly Gyeonggang faults. This study successfully identified the extensions and orientations of subsurface faults beneath the Seoul metropolitan area down to the uppermost mantle, which is critical for seismic hazard predictions and earthquake simulations in this highly populated area.

Evaluating Machine Learning–Based Probabilistic Convective Hazard Forecasts Using The HRRR: Quantifying Hazard Predictability and Sensitivity to Training Choices

Abstract The High-Resolution Rapid Refresh (HRRR) model provides hourly updating forecasts of convective-scale phenomena, which can be used to infer the potential for convective hazards (e.g., tornadoes, hail, and wind gusts), across the United States. We used deterministic 2019–20 HRRR, version 4 (HRRRv4), forecasts to train neural networks (NNs) to generate 4-hourly probabilistic convective hazard forecasts [neural network probability forecasts (NNPFs)] for HRRRv4 initializations in 2021, using storm reports as ground truth. The NNPFs were compared to the skill of a smoothed updraft helicity (UH) baseline to quantify the benefit of the NNs. NNPF skill varied by initialization time and time of day but was all superior to the UH forecast. NNPFs valid at hours between 1800 and 0000 UTC were most skillful in aggregate, significantly exceeding the baseline forecast skill. Overnight NNPFs (i.e., valid 0600–1200 UTC) were least skillful, indicating a diurnal cycle in hazard predictability that was present across all HRRRv4 initializations. We explored the sensitivity of HRRRv4 NNPF skill to NN training choices. Including an additional year of 2021 HRRRv4 forecasts for training slightly improved skill for 2022 HRRRv4 NNPFs, while reducing the training dataset size by 40% using only forecasts with storm reports was not detrimental to forecast skill. Finally, NNs trained with 2018–20 HRRRv3 forecasts led to a reduction in NNPF skill when applied to 2021 HRRRv4 forecasts. In addition to documenting practical predictability challenges with convective hazard prediction, these findings reinforce the need for a consistent model configuration for optimal results when training NNs and provide best practices when constructing a training dataset with operational convection-allowing model forecasts. Significance Statement Convective hazards, such as hail and tornadoes, are often challenging to predict. To improve hazard predictions, we used machine learning (ML) to generate forecasts of convective hazards across the United States leveraging forecasts of prior events. The ML hazard forecasts were consistently better than a non-ML approach and varied in skill based on the time of day, with nighttime forecasts being particularly challenging. ML forecasts of wind gusts and hail were more skillful than tornadoes. Different strategies of constructing the dataset of prior events led to differences in forecast performance; thus, this work provides recommendations for how to assemble these datasets and train ML models to generate improved forecasts of severe weather events.

Predictors of Durable Remission After Successful Surgery for Cushing Disease: Results From the Multicenter RAPID Registry.

Cushing disease (CD) affects mortality and quality of life along with limited long-term remission, underscoring the need to better identify recurrence risk. The identification of surgical or imaging predictors for CD remission after transsphenoidal surgery has yielded some inconsistent results and has been limited by single-center, single-surgeon, or meta-analyses studies. We sought to evaluate the multicenter Registry of Adenomas of the Pituitary and Related Disorders (RAPID) database of academic US pituitary centers to assess whether robust nonhormonal recurrence predictors could be elucidated. Patients with treated CD from 2011 to 2023 were included. The perioperative and long-term characteristics of CD patients with and without recurrence were assessed using univariable and multivariable analyses. Of 383 patients with CD from 26 surgeons achieving postoperative remission, 288 (75.2%) maintained remission at last follow-up while 95 (24.8%) showed recurrence (median time to recurrence 9.99 ± 1.34 years). Patients with recurrence required longer postoperative hospital stays (5 ± 3 vs 4 ± 2 days, P = .002), had larger average tumor volumes (1.76 ± 2.53 cm 3 vs 0.49 ± 1.17 cm 3 , P = .0001), and more often previously failed prior treatment (31.1% vs 14.9%, P = .001) mostly being prior surgery. Multivariable hazard prediction models for tumor recurrence found younger age (odds ratio [OR] = 0.95, P = .002) and Knosp grade of 0 (OR = 0.09, reference Knosp grade 4, P = .03) to be protective against recurrence. Comparison of Knosp grade 0 to 2 vs 3 to 4 showed that lower grades had reduced risk of recurrence (OR = 0.27, P = .04). Other factors such as length of stay, surgeon experience, prior tumor treatment, and Knosp grades 1, 2, or 3 failed to reach levels of statistical significance in multivariable analysis. This multicenter study centers suggests that the strongest predictors of recurrence include tumor size/invasion and age. This insight can help with patient counseling and prognostication. Long-term follow-up is necessary for patients, and early treatment of small tumors may improve outcomes.

Development of hazard prediction test and interventions for two-wheeled electric vehicle riders in China

Objective This paper aimed to develop a hazard prediction test and enhance two-wheeled electric vehicle (TWEV) riders’ hazard perception and prediction capabilities via interventions by executing two distinct studies. Study 1 aimed to develop and validate a hazard prediction test. Study 2 evaluated the efficacy of two interventions, self-commentary and what happens next (WHN), integrating expert commentary. Method For Study 1, a video-based hazard prediction test was developed through video recording and clipping, with participants categorized into high and low prediction ability groups for experimentation. Data analysis employed the receiver operating characteristic (ROC) curve. Study 2 categorized participants into four groups: self-commentary with licenses (SCL), self-commentary without licenses (SCNL), WHN with licenses (WHNL), and WHN without licenses (WHNNL), for conducting a one-week intervention experiment. Data collected from participants’ pre-intervention, post-intervention, and aftereffect tests were subjected to repeated measures analysis of variance (ANOVA). Results Analysis of the ROC curve indicated the test can distinguish the riders with different hazard prediction levels. ANOVA results demonstrated that the measurement time had a significant positive effect on scores (p < 0.001). Both interventions significantly improved hazard prediction ability (p < 0.05), and the effect persisted one week after administration. The effect of the WHN intervention was significantly greater than the self-commentary method across all time points. Conclusion The hazard prediction test developed in this study could assess riders’ hazard prediction ability, with the identified interventions demonstrating effectiveness in enhancing this ability. These findings suggested potential application in future qualification tests for TWEV riders, contributing to enhanced traffic safety awareness among TWEV riders in China, thus advancing overall traffic safety.

Rational frequency range and criteria for diagnosing endogenous fire zones in coal massifs by using the georadiolocation method

Relevance. The necessity to improve the accuracy of analysis and prediction of potential fire hazard of rock-coal massifs by using electromagnetic methods of endogenous fire detection. Taking into consideration that the increase in coal temperature changes a number of its parameters, such as dielectric permittivity and electrical resistivity, it is reasonable to use the method of electromagnetic reconnaissance in locating the focus of fire. Aim. To analyze the theoretical and practical knowledge about the anomalies formed in the area of spontaneous combustion and to evaluate the effectiveness of electromagnetic methods for locating the spontaneous combustion zones of a coal massif. Objects. Physical parameters of the ignition zone of the coal massif, such as dielectric permittivity and electrical resistivity, as well as the range of the GPR central frequency, allowing clearly defining the boundaries of the ignited zone. Method. Reviewing the proposed methods of determining the parameters serving for correct location of the fire zone. For GPR it is necessary to determine the center frequency of the standard antenna unit and resolution, then to estimate the rational frequency range of GPR. Results. Allow us to draw conclusions about the methods used to determine the rational range of GPR center frequency – it can be calculated by solving the system of equations of the signal attenuation function and energy potential of GPR, by the experimental value of the target function, including the depth and detail of sounding as a function of frequency, or on the basis of a complex parameter of GPR, including the radiated power of the antenna, the number of accumulations and the reflection coefficient from the boundaries. Taking into account such physical features of the fire zone as drying the rock-angle massif and the shape of the anomalous zone, the rational range of the center frequency for the GPR "OKO-2" was determined.

Perspectives on Advancing Multimodal Learning in Environmental Science and Engineering Studies.

The environment faces increasing anthropogenic impacts, resulting in a rapid increase in environmental issues that undermine the natural capital essential for human wellbeing. These issues are complex and often influenced by various factors represented by data with different modalities. While machine learning (ML) provides data-driven tools for addressing the environmental issues, the current ML models in environmental science and engineering (ES&E) often neglect the utilization of multimodal data. With the advancement in deep learning, multimodal learning (MML) holds promise for comprehensive descriptions of the environmental issues by harnessing data from diverse modalities. This advancement has the potential to significantly elevate the accuracy and robustness of prediction models in ES&E studies, providing enhanced solutions for various environmental modeling tasks. This perspective summarizes MML methodologies and proposes potential applications of MML models in ES&E studies, including environmental quality assessment, prediction of chemical hazards, and optimization of pollution control techniques. Additionally, we discuss the challenges associated with implementing MML in ES&E and propose future research directions in this domain.

Prediction of coal and gas outburst hazard using kernel principal component analysis and an enhanced extreme learning machine approach

In order to enhance the accuracy and efficiency of coal and gas outburst disaster risk prediction, a novel approach combining kernel principal component analysis (KPCA) with an improved whale optimization algorithm (IWOA) optimized extreme learning machine (ELM) is proposed for precise forecasting of coal and gas outburst disasters in mines. Firstly, based on the influencing factors of coal and gas outburst disasters, nine coupling indexes are selected, including gas pressure, geological structure, initial velocity of gas emission, and coal structure type. The correlation between each index was analyzed using the Pearson correlation coefficient matrix in SPSS 27 software, followed by extraction of the principal components of the original data through kernel principal component analysis (KPCA). The whale optimization algorithm (WOA) was enhanced by incorporating adaptive weight, variable helix position update, and optimal neighborhood disturbance to augment its performance. The improved Whale Optimization Algorithm (IWOA) is subsequently employed to optimize the weight ф of the Extreme Learning Machine (ELM) input layer and the threshold g of the hidden layer, thereby enhancing its predictive accuracy and mitigating to some extent the issue of "over-fitting" associated with ELM. The principal components extracted by KPCA were utilized as input, while the outburst risk grade served as output. Subsequently, a comparative analysis was conducted between these results and those obtained from WOA-SVC, PSO-BPNN, and SSA-RF models. The IWOA-ELM model accurately predicts the risk grade of coal and gas outburst disasters, with results consistent with actual situations. Compared to other models tested, the model's performance showed an increase in Ac by 0.2, 0.3, and 0.2 respectively; P increased by 0.15, 0.2167, and 0.1333 respectively; R increased by 0.25, 0.3, and 0.2333 respectively; F1-Score increased by 0.2031, 0.2607, and 0.1864 respectively; Kappa coefficient k increased by 0.3226, 0.4762 and 0.3175, respectively. The practicality and stability of the IWOA-ELM model were verified through its application in a Shanxi Province coal mine where predicted values matched actual values exactly. This indicates that this model is more suitable for predicting coal and gas outburst disaster risks.