The ultraviolet (UV) radiation environment consists of direct UV and diffuse UV components. The ratios of diffuse-to-direct UV for the UVB, UVA, and the erythema UV wavebands are influenced by clouds, aerosols, albedo, and surface reflectance, Rayleigh scattering, and solar zenith angle. At times, the relative proportion of diffuse UV may be higher than the direct UV, for example, on cloudy days or days with high atmospheric aerosols. Consequently, exposures due to diffuse UV radiation play a significant role in the UV exposure received by human subjects. Diffuse UV radiation contributes to the risk of skin cancer and sun-related eye disorders. Reducing personal exposure to diffuse UV by physical protection, including tree shade, purpose-built shade structures, protection by hats, and eyewear, is more difficult than reducing direct UV exposure due to the diffuse UV being incident from all directions. The UV index reported to the public represents the sum of the direct and the diffuse erythema UV, with no information provided specifically on the diffuse UV component. This paper reviews the factors that contribute to diffuse UV exposures affecting human populations. It examines diffuse UV modeling techniques, and broadband and spectral component measurements.

Abstract To date, no clinical scoring systems exist to quantify atopic dermatitis (AD) disease manifestations in relation to solar radiation exposure. This is clinically relevant, as an estimated 1.4–16% of cases of AD constitute photoaggravated atopic dermatitis. Here, we introduce a modification of the Eczema Area and Severity Index (EASI), termed the Photoaggravated Eczema Area and Severity Index (PEASI), a novel tool to provide a standardized measure of AD severity and extent in relation to solar radiation, and report preliminary reliability data. The PEASI adapts the EASI framework by replacing conventional region weighting factors with predefined photoaggravated region weighting factors (PRWFs). These are calculated by weighting four photoexposed regions according to solar irradiance scaled by surface area and assigned as 0.40 ×, 0.10 ×, 0.20 × and 0.30 × for the face and V-area of the neck and upper chest, dorsal neck, dorsal arms and dorsal hands, respectively. The original area and severity scoring is preserved. Reliability was assessed using intraclass correlation coefficient (ICC) 2 : 1 metrics. A photoaggravated regional score is calculated as the product of the PRWF and the corresponding severity and area scores. The PEASI score is obtained by summing the photoaggravated regional scores. As both the RWFs and PRWFs sum to unity, the PEASI and EASI share identical score ranges. Two rounds of reliability assessment involving six cases of AD and eight assessors (seven dermatologists and one photodermatology technician across four institutions) demonstrated moderate-to-good inter-rater reliability (round one ICC 0.81, 95% confidence interval 0.58–0.96; round two ICC 0.70, 95% confidence interval 0.40–0.94) and good intrarater reliability (median ICC 0.84, interquartile range 0.73–0.96). The PEASI is not designed to replace the EASI in patients with photoaggravated AD. Rather, it serves as an instrument for the identifi­cation and longitudinal monitoring of photoaggravated disease. Preliminary reliability assessments provide support for its use as a reproducible measure of AD severity and extent in relation to solar radiation.

BACKGROUND:Dermatological severity indices commonly use body surface area-based regional weightings to combine regional disease scores into an overall score. In photosensitive disease, however, disease activity often concentrates at highly photoexposed anatomical sites that constitute a limited proportion of total body surface area. This may introduce systematic bias by constraining the contribution of clinically important photoexposed regions to total severity scores. OBJECTIVES:To develop photoexposure region-weighting factors (PRWFs) as a standardised, photoexposure-informed approach to addressing surface area-related bias in photosensitive disease severity assessment. METHODS:Anatomical regions characteristically affected in photosensitive disease were defined through expert consensus and mapped onto a body surface model. Regional ultraviolet exposure was calculated using a computational model across walking, standing and sitting postures. Exposure calculations were combined across postures, integrated by regional surface area, normalised within the photoexposed assessment domain and rounded to derive clinically applicable PRWFs. Preliminary clinical reliability was assessed using an earlier PRWF-based modification of the Eczema Area and Severity Index in six image-based atopic dermatitis cases scored by eight assessors across four institutions. RESULTS:Five anatomical regions were included: the face, V-area of the neck and upper chest, dorsal neck, dorsal forearms and dorsal hands. Collectively, these regions accounted for 10.7% of total body surface area. Clinically rounded PRWFs were 0.3× for the face, 0.1× for the V-area, 0.1× for the dorsal neck, 0.3× for the dorsal forearms and 0.2× for the dorsal hands. The earlier PRWF-based modification of the Eczema Area and Severity Index showed good inter-rater reliability in the first assessment round and moderate reliability in the second (ICC 0.81 and 0.70, respectively), with good median intra-rater reliability (ICC 0.84). CONCLUSIONS:PRWFs provide a standardised framework for addressing surface area-related bias in photosensitive disease severity assessment by weighting anatomical regions according to ultraviolet exposure rather than surface area alone. Preliminary reliability findings support the reproducibility of PRWF-based clinical scoring, but prospective validation of the final PRWF framework is required before routine clinical or trial use.

Thermal stratification is a significant phenomenon driven by complex interconnected factors that reduce mixing between the top and the bottom layers, impacting oxygen and nutrient dispersion and potentially causing fish mortality. This study has assessed the non-mixing occurrence in river flow using a classification approach, developing a novel hybrid data-driven model from key datasets of the Darling River in Menindee, Australia. The influence of various input variables using the proposed model is investigated, including meteorological drivers, hydrological factors, key data generated by the one-dimensional process-based model named LAKEoneD, and Physics-Informed Neural Networks. The study also considers stratification indices based on the Schmidt stability and empirical river mixing criteria. Supervised machine learning methods were used to classify a given day as mixing or non-mixing conditions. The results showed that the proposed hybrid model integrating Support Vector Machines with key data generated by LAKEoneD outperformed benchmarking models. The study also employed explainable artificial intelligence analysis, suggesting that the minimum air temperature and relative humidity, as the model inputs, played a role in predicting non-mixing river flow conditions. Importantly, the maximum air temperature was another potential input that affected the river flow system, particularly near a fish death event. We conclude that the proposed model can be used as a scientific stratagem for future research in predicting fish and other aquatic organism health related to river flow dynamics, which has implications for environmental authorities guiding better water quality management in river systems.

Core mathematics courses are fundamental to the academic success of engineering students in higher education. These courses equip students with skills and knowledge applicable to their specialized fields. However, first-year engineering students often face significant challenges in mathematics due to a range of factors, including insufficient preparation, mathematics anxiety, and difficulty connecting theoretical concepts to real-life applications. The transition from secondary to tertiary mathematics remains a key area of educational research, with ongoing discussions about effective pedagogical approaches for teaching engineering mathematics. This study utilized a belief survey to gain general insights into the attitudes of first-year mathematics students towards the subject. In addition, it employed the activity theory framework to conduct a deeper exploration of the experiences of first-year engineering students, aiming to identify contradictions, or “tensions,” encountered within a flipped-classroom learning environment. Quantitative data were collected using surveys that assessed students’ self-reported confidence, competence, and knowledge development. Results from Friedman’s and Wilcoxon’s Signed-Rank Tests, conducted with a sample of 20 participants in 10 flipped-classroom sessions, statistically showed significant improvements in all three areas. All of Friedman’s test statistics were above 50, with p-values below 0.05, indicating meaningful progress. Similarly, Wilcoxon’s Signed-Rank Test results supported these findings, with p values under 0.05, leading to the rejection of the null hypothesis. The qualitative data, derived from student questionnaire comments and one-to-one interviews, elucidated critical aspects of flipped-classroom delivery. The analysis revealed emerging contradictions (“tensions”) that trigger “expansive learning”. These tensions encompassed the following: student expectation–curriculum structure; traditional versus novel delivery systems; self-regulation and accountability; group learning pace versus interactive learning; and the interplay between motivation and anxiety. These tensions are vital for academic staff and stakeholders to consider when designing and delivering a first-year mathematics course. Understanding these dynamics can lead to more effective, responsive teaching practices and support student success during this crucial transition phase.

Acute exposure effects of short-wavelength solar ultraviolet-B (UV-B) radiation can trigger skin-based diseases and eye health ailments in humans and animals, as well as disrupt photosynthetic or hormonal systems in plants. Within the UV wavebands, high levels of UV-B exposure are particularly severe and the leading cause of skin cancers. Therefore, accurate and explainable short-term UV-B forecasts are essential for effectively providing sun exposure information to the public and UV experts. To address this pressing issue, we developed an explainable hybrid TabNet framework optimized with the Optuna algorithm. The model was trained using predictors derived from satellite products and sky images for the experimental site in Toowoomba, Queensland, Australia. For model training, 3,863 data points were utilized from July 1, 2002 to February 29, 2004. The model development phase entailed dimensionality reduction using recursive feature elimination with cross-validation (RFECV) and principal component analysis (PCA) methods. The proposed model outperformed all competing counterparts, achieving comparatively high correlation coefficients of 0.908, 0.880, 0.868, and 0.868 for hourly, 2-hourly, 3-hourly, and 4-hourly forecast horizons, respectively. Explainable artificial intelligence (xAI) results, based on Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), indicate that the antecedent lagged memory of UV-B radiation and the solar zenith angle contribute significantly to UV-B predictions. Ozone effects and cloud cover conditions are also influential features in this respect. The superior capabilities of the newly designed hybrid explainable TabNet model affirm its potential for UV-B monitoring and mitigating the harmful sun exposure risks for the public and terrestrial life.

Wetlands are an important part of coastal ecosystems but are under increasing pressure from climate change-induced sea-level rise and flooding, in addition to development pressures associated with increasing human populations. The change in tidal events and their intensity due to sea-level rise is also reshaping and challenging the vitality of existing wetland systems, requiring more intensive localized studies to identify future-focused restoration and conservation strategies. To support this endeavor, this study utilizes tide gauge datasets from the Australian Bureau of Meteorology (BOM) for maximum sea-level (Hmax) prediction and Landsat Collection surface reflectance datasets obtained from the United States Geological Survey (USGS) database to detect and project patterns of change in the Maroochy River floodplain of Queensland, Australia. This study developed an efficient hybrid deep learning model combining a Convolutional Neural Network and Bidirectional Long Short-Term Memory (CNNBiLSTM) architecture for the prediction of maximum sea-level and tidal events. The proposed model significantly outperformed three benchmark models (Multiple Linear Regression (MLR), Support Vector Regression (SVR), and CatBoost) in achieving a high correlation coefficient (r = 0.9748) for maximum sea-level prediction. To further address the increasing frequency and intensity of tidal events linked to sea-level rise, a CNNBiLSTM classification model was also developed, achieving 96.72% accuracy in predicting extreme tidal occurrences. This study identified a significant positive linear increase in sea-level rise of 0.016 m/year between 2014 and 2024. Wetland change detection using Landsat imagery along the Maroochy River floodplain also identified a substantial vegetation loss of 395.64 hectares from 2009 to 2023. These findings highlight the strong potential of integrating deep learning and remote sensing for improved prediction and assessment of sea-level extremes and coastal ecosystem changes. The study outcomes provide valuable insights for informing not only conservation and restoration activities but also for providing localized projections of future change necessary for the progression of effective climate adaptation and mitigation strategies.

The impact of solar ultraviolet (UV) radiation on public health is severe and can cause sunburn, skin aging and cancer, immunosuppression, and eye damage. Minimization of exposure to solar UV is required in order to reduce the risks of these illnesses to the public. Greater public awareness and the prediction of ultraviolet index (UVI) is considered an essential task for the minimization of solar UV exposures. This research has designed an artificial intelligence (AI) model to predict the multistep solar UVI. The proposed model was based on the integration of convolutional neural networks with long short-term memory network (CLSTM) as the primary model to predict solar UVI, tested for Brisbane (27.47°S, 153.02°E), the capital city in Queensland, Australia. Solar zenith angle (SZA) data were used together with UVI as inputs for the CLSTM of different scales (i.e., 10-min, 30-min, and 60-min) UVI prediction. The CLSTM model was benchmarked against well-established AI models e.g., long short-term memory network (LSTM), convolutional neural network (CNN), Deep Neural Network (DNN), multilayer perceptron (MLP), extreme learning machine (ELM), random forest regression (RFR), Extreme Gradient Boosting (XGB), and Pro6UV Deterministic models. The experimental results showed that the CLSTM model outperformed these models with Root Mean Square Error (RMSE = 0.3817), Mean Absolute Error (MAE = 0.1887), and Relative Root Mean Square Error (RRMSE = 8.0086

Fluctuations in direct sunlight intensities (or sunflecks) are experienced in urban forest parklands. A novel application of an electronic sun journal (ESJ) was developed providing accessible, objective detection and analysis of sunflecks sampled at 50 Hz while walking through urban parkland forests in Toowoomba (27.57 degrees S 151.95 degrees E), Australia. A total of 654 sunflecks were detected during 12 walks. Sunfleck durations (SFD) ranged from 0.02 s to 102.5 s, with a median of 0.10 s and interquartile range of 0.04-0.28 s. The sunfleck intervals (SFI) ranged from 0.02 s to 115 s, with a median of 0.16 s and interquartile range of 0.06-0.62 s. Of the 10,983 sunfleck clusters, approximately 90% included two or four sunflecks per second, with the highest frequency cluster reaching eight. The distribution of the sunfleck clusters changed with different sun angles and azimuth as the sunlight passed through different parts of urban parklands. The developed method with the ESJ may be employed in the evaluation of sunfleck durations, intervals and clusters at eye level in other urban forest environments, adding to the developing interest as greenspaces play an increasing role in urban studies.

Sea level rise (SLR) attributed to the melting of ice caps and thermal expansion of seawater is of great global significance to vast populations of people residing along the world’s coastlines. The extent of SLR’s impact on physical coastal areas is determined by multiple factors such as geographical location, coastal structure, wetland vegetation and related oceanic changes. For coastal communities at risk of inundation and coastal erosion due to SLR, the modelling and projection of future sea levels can provide the information necessary to prepare and adapt to gradual sea level rise over several years. In the following study, a new model for predicting future sea levels is presented, which focusses on two tide gauge locations (Darwin and Milner Bay) in the Northern Territory (NT), Australia. Historical data from the Australian Bureau of Meteorology (BOM) from 1990 to 2022 are used for data training and prediction using artificial intelligence models and computation of mean sea level (MSL) linear projection. The study employs a new double data decomposition approach using Multivariate Variational Mode Decomposition (MVMD) and Successive Variational Mode Decomposition (SVMD) with dimensionality reduction techniques of Principal Component Analysis (PCA) for data modelling using four artificial intelligence models (Support Vector Regression (SVR), Adaptive Boosting Regressor (AdaBoost), Multilayer Perceptron (MLP), and Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN-BiGRU). It proposes a deep learning hybrid CNN-BiGRU model for sea level prediction, which is benchmarked by SVR, AdaBoost, and MLP. MVMD-SVMD-CNN-BiGRU hybrid models achieved the highest performance values of 0.9979 (d), 0.996 (NS), 0.9409 (L); and 0.998 (d), 0.9959 (NS), 0.9413 (L) for Milner Bay and Darwin, respectively. It also attained the lowest error values of 0.1016 (RMSE), 0.0782 (MABE), 2.3699 (RRMSE), and 2.4123 (MAPE) for Darwin and 0.0248 (RMSE), 0.0189 (MABE), 1.9901 (RRMSE), and 1.7486 (MAPE) for Milner Bay. The mean sea level (MSL) trend analysis showed a rise of 6.1 ± 1.1 mm and 5.6 ± 1.5 mm for Darwin and Milner Bay, respectively, from 1990 to 2022.

Water temperature (WT) is a crucial factor indicating the quality of water in the river system. Given the significant variability in water quality, it is vital to devise more precise methods to forecast temperature in river systems and assess the water quality. This study designs and evaluates a new explainable artificial intelligence and hybrid machine-learning framework tailored for hourly and daily surface WT predictions for case studies in the Menindee region, focusing on the Weir 32 site. The proposed hybrid framework was designed by coupling a nonstationary signal processing method of Multivariate Variational Mode Decomposition (MVMD) with a bidirectional long short-term memory network (BiLSTM). The study has also employed a combination of in situ measurements with gridded and simulation datasets in the testing phase to rigorously assess the predictive performance of the newly designed MVMD-BiLSTM alongside other benchmarked models. In accordance with the outcomes of the statistical score metrics and visual infographics of the predicted and observed WT, the objective model displayed superior predictive performance against other benchmarked models. For instance, the MVMD-BiLSTM model captured the lowest Root Mean Square Percentage Error (RMSPE) values of 9.70% and 6.34% for the hourly and daily forecasts, respectively, at Weir 32. Further application of this proposed model reproduced the overall dynamics of the daily WT in Burtundy (RMSPE = 7.88% and Mean Absolute Percentage Error (MAPE) = 5.78%) and Pooncarie (RMSPE = 8.39% and MAPE = 5.89%), confirming that the gridded data effectively capture the overall WT dynamics at these locations. The overall explainable artificial intelligence (xAI) results, based on Local Interpretable Model-Agnostic Explanations (LIME), indicate that air temperature (AT) was the most significant contributor towards predicting WT. The superior capabilities of the proposed MVMD-BiLSTM model through this case study consolidate its potential in forecasting WT.

Spectroradiometry, radiometry, and dosimetry are employed for the measurement of ultraviolet radiation (UVR) irradiance and non-ionizing exposure. Different types of UVR dosimeter have been developed for measuring personal and environmental UVR exposures since film dosimetry was pioneered in the 1970s. An important type of dosimeter is the thin film variant, which contains materials that undergo changes in optical absorbance when exposed to UVR. These changes can be measured at a specific wavelength using a spectrophotometer. Thin film dosimeters allow UVR exposure measurements on humans at various body sites during daily activities, as well as on plants, animals, and any sites of interest when utilized in a field environment. This review examines the properties and applications of five types of thin film UVR dosimeter that have different dynamic exposure limits and spectral responses. Polysulphone, with a spectral response approximating the human erythema action spectrum, was one of the first materials employed in thin film form for the measurement of UVR exposures up to 1 day, and up to 6 days with an extended dynamic range filter. Polyphenylene oxide has been characterized and employed for personal UVR exposure measurements up to approximately four summer days and has also been used for long-term underwater UVR exposures. Phenothiazine and 8-methoxypsoralen have been reported as suitable for the measurement of longer wavelength UVA exposures. Finally, polyvinyl chloride with an extended dynamic exposure range of over 3 weeks has been shown to have predominantly a spectral response in the UVB and extending up to 340 nm.

Tree shade, particularly shade that obscures direct sunlight near peak periods of midday solar exposure can have a pronounced effect on potentially harmful ultraviolet radiation, and in turn, strongly influence the maximum daily UV index (UVI). In this study, the seasonal influence of tree shade on the UVI is evaluated from 210 hemispherical sky view images collected alongside public walkways and footpaths from 10 residential Brisbane suburbs. The effective sidewalk UV index is calculated underneath planted tree canopies, adjacent residential gardens, buildings and background tree species. Results are presented with respect to seasonal variations in the diurnal solar elevation for each month of the year at Brisbane's latitude. The research also examines the total reduction in UVI due to the presence of individual tree species, showing reductions in the midday UVI of up to 91% of an equivalent unimpeded sky hemisphere when overhead tree canopies are present. Important footpath tree species for peak midday UVI mitigation include Pongamia pinnata, Xanthostemon chrysanthus, Senna siamea, and Libidibia ferrea. The planting and maintenance of existing tree species already growing alongside residential Brisbane streets will improve the shade characteristics of suburbs and enhance UV protection for local residents.

High-dose single exposures of long-wavelength ultraviolet-A (UV-A) radiation may trigger severe biological and skin tissue damage in humans and animals, as well as photosynthetic damage in plants. In humans, the highly abundant UV-A is also linked to an increased risk of skin cancer. This paper develops a new forecasting framework tailored for very short-term UV-A predictions using a Bayesian optimized ensemble Neural Basis Expansion Analysis for Interpretable Time Series (B-E-NBEATS) method, integrated with cloud cover predictors and the solar zenith angle. The design phase of the proposed model entails feature selection using an efficient neighborhood component analysis algorithm and hyperparameter tuning with a Bayesian optimizer. To further enhance the predictive performance and reliability, the B-E-NBEATS model is calibrated via uncertainty quantification by adopting an ensemble approach with single-point models trained on three key loss functions. The prescribed model generates interpretable forecasts of 20-minute ahead UV-A by empowering the ensemble members to learn seasonal and trend components in UV-A datasets. With respect to the four benchmark models, the statistical metrics and visual infographics of predicted and observed UV-A reveal a superior forecasting capability of the proposed B-E-NBEATS model. The model yields a comparatively high correlation coefficient of 0.910, 0.869, 0.933, and 0.900 for the spring, summer, autumn, and winter testing phases, respectively. The superior performance by the newly designed hybrid ensemble model ascertains its potential utility in UV-A monitoring and mitigating subsequent harmful exposure risk for the general public, and animal and plant life.

The Playground Shade Index (PSI) is introduced as a design metric for assessing the shade and solar ultraviolet (UV) protection provided by eight different cloth weave shade structures currently utilized in public playgrounds across a regional city located in southern Queensland, Australia. The PSI, expressing the ratio of available ambient solar UV exposure relative to the UV exposure received by a shaded 184 m2 playground surface over a whole day in midsummer and midwinter, is used to determine the best design and aspect of all eight existing structures. Unlike subjective shade audits that may only consider the type of shade structure, the number and characteristics of surrounding trees, and surface materials available at a given site, the PSI considers, in addition to previous factors, the available sky fraction and the direct solar UV contribution underneath the shade structure over a full day. By considering the in situ UV protection characteristics of the shade structure, the PSI has demonstrated its value as a robust design metric. Of the eight shade structure styles examined, this research presents the most likely structure best suited for UV protection over the two solar UV extremes in summer and winter, including optimal structure aspect.

Background and Objective: Exposure to solar ultraviolet (UV) radiation can cause malignant keratinocyte cancer and eye disease. Developing a user-friendly, portable, real-time solar UV alert system especially or wearable electronic mobile devices can help reduce the exposure to UV as a key measure for personal and occupational management of the UV risks. This research aims to design artificial intelligence-inspired early warning tool tailored for short-term forecasting of UV index (UVI) integrating satellite-derived and ground-based predictors for Australian hotspots receiving high UV exposures. The study further improves the trustworthiness of the newly designed tool using an explainable artificial intelligence approach. Methods: An enhanced joint hybrid explainable deep neural network model (called EJH-X-DNN) is constructed involving two phases of feature selection and hyperparameter tuning using Bayesian optimization. A compre-hensive assessment of EJH-X-DNN is conducted with six other competing benchmarked models. The proposed model is explained locally and globally using robust model-agnostic explainable artificial intelligence frame-works such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley additive explanations (SHAP), and permutation feature importance (PFI). Results: The newly proposed model outperformed all benchmarked models for forecasting hourly horizons UVI, with correlation coefficients of 0.900, 0.960, 0.897, and 0.913, respectively, for Darwin, Alice Springs, Townsville, and Emerald hotspots. According to the combined local and global explainable model outcomes, the site-based results indicate that antecedent lagged memory of UVI and solar zenith angle are influential features. Predictions made by EJH-X-DNN model are strongly influenced by factors such as ozone effect, cloud conditions, and precipitation.Conclusion: With its superiority and skillful interpretation, the UVI prediction system reaffirms its benefits for providing real-time UV alerts to mitigate risks of skin and eye health complications, reducing healthcare costs and contributing to outdoor exposure policy.

Abstract The impact of ultraviolet (UV) radiation on public health is severe and can cause sunburn, skin aging and cancer, immunosuppression, and eye damage. Minimization of exposure to solar UV is required in order to reduce the risks of these illnesses to the public. Greater public awareness and a prediction of the ultraviolet index (UVI) is considered an essential task for the minimization of solar UV exposures. This research has designed artificial intelligence based deep learning models to predict multistep UVI index. It has developed a convolutional neural network integrated with long short-term memory network (CLSTM) as the main model to forecast UVI for Brisbane with latitude − 27.47 and longitude 153.02, the capital city of Queensland, Australia. Solar zenith angle (SZA) data were used together with UVI as inputs in the CLSTM for 10-min, 30-min and 60-min UVI prediction. The CLSTM model was benchmarked against long short-term memory network (LSTM), convolutional neural network (CNN), Deep Neural Network (DNN), multilayer perceptron (MLP), extreme learning machine (ELM), random forest regression (RFR), Extreme Gradient Boosting (XGB), and Pro6UV Deterministic models. The experimental results showed that the CLSTM model outperformed these models with RMSE = 0.3817, MAE = 0.1887, RRMSE = 8.0086%, MAPE = 4.6172% and APB = 3.9586 for 10-min prediction. In addition to that, these metrics for 30-min and 60-min prediction were RMSE = 0.4866/0.5146, MAE = 0.2763/0.3038, RRMSE = 10.4860%/11.5840%, MAPE = 8.1037%/9.6558% and APB = 5.9546/6.8386, respectively. Thus, the CLSTM model can yield improved UVI prediction for both the public and the government agencies.

Skin cancer, the most prevalent cancer in Caucasians residing at low latitudes, can primarily be prevented by avoiding overexposure to sunlight. Serial cross-sectional observations were conducted at an outdoor motorsport event held in Townsville, Queensland each July (Southern winter) to determine whether sun-protection habits changed over time. Most (71.1%) of the 1337 attendees observed (97.6% lightly pigmented skin, 64.0% male) wore a hat (any style shading the face), while few (18.5%) wore three-quarter or full-length sleeves. While hat-wearing rates (any style) were similar in 2009 (326, 72.6%) and 2013 (625, 70.4%), the use of sun-protective styles (wide-brimmed/bucket/legionnaires) decreased from 29.2% to 18.6% over the same period, primarily because the use of sun-protective hats halved (from 28.7% to 14.0%) among females, while decreasing from 29.4% to 21.1% in males. Although relatively few individuals wore sun-protective (three-quarter-length or full-length) sleeves regardless of year (OR = 0.117, P < 0.0001), encouragingly, the use of sun-protective sleeves more than doubled between 2009 (10.5%) and 2013 (22.5%). Interestingly females, albeit the minority, at this sporting event were less likely to wear a hat (OR = 0.473, P < 0.0001) than males. These findings highlight the need for continued momentum toward skin cancer primary prevention through sun protection with a dedicated focus on outdoor sporting settings.

Harmful exposure to erythemally-effective ultraviolet radiation (UVR) poses high health risks such as malignant keratinocyte cancers and eye-related diseases. Delivering short-term forecasts of the solar ultraviolet index (UVI) is an effective way to advise UVR exposure information to the public at risk. This research reports on a novel framework built to forecast UVI, integrating antecedent lagged memory of cloud statistical properties and the solar zenith angle (SZA). To produce the forecasts at multi-step horizon we design a 3-phase hybrid convolutional long short-term memory network (W-O-convLSTM) model, validated with Queensland-based datasets in near real-time ( i.e ., 10-minute, 20-minute, 30-minute and 1 hour forecast horizon). Our approach in optimizing the performance also entails a robust selective filtering method using the BorutaShap algorithm, data decomposition with stationary wavelet transformation and hyperparameter optimization using the Optuna algorithm. We assess the performance of the proposed W-O-convLSTM model alongside the baseline and benchmark models. The captured results, through statistical metrics and visual infographics, elucidate the superior performance of the objective model in short-term UVI forecasting. For instance, at a 10-minute forecast horizon, our objective model yields a relatively high correlation coefficient of ~0.961 in the autumn, 0.909 in the summer, 0.926 in the spring and 0.936 in the winter season. Overall, the proposed O-convLSTM model outperforms its competing counterpart models for all forecast horizons with the lowest absolute forecast error. The robustness of our newly proposed model avers its practical utility in delivering sun-protection behavior recommendations that can mitigate UV-exposure-related public health risk. We also recommend that future integration of aerosol and ozone effects with cloud cover data can enhance our forecasting framework for wider applications in solar energy or skin health monitoring systems.