Search Results (122)

Wildfires are increasing in frequency and severity, with Australia’s 2019–2020 Black Summer burning over 18 million hectares. Accurate prediction of wildfire behavior is essential for effective risk assessment and emergency response. This study presents a machine learning framework for predicting wildfire dynamics across Australia’s seven regions using the IBM wildfire dataset. Various Machine Learning (ML) models were evaluated to forecast three key indicators: Fire Area (km²), Fire Brightness Temperature (K), and Fire Radiative Power (MW). Lasso Regression consistently outperformed the other models, achieving an average RMSE of 0.04201 and R² of 0.29355. Performance varied across regions, with stronger results in areas like New South Wales and Queensland, likely influenced by differences in topography, microclimate, and vegetation. However, limitations include the exclusion of ignition sources such as lightning and human activity, which are critical for capturing the environment accurately and improving predictive accuracy. Future work will integrate these factors alongside more detailed weather and vegetation data. Practical implementation may face challenges related to real-time data availability, system integration, and response coordination, but this approach offers promising potential for operational wildfire decision support. Full article

Wildfires are becoming more frequent and widespread, posing a threat to European ecosystems. Recent findings quantified a large fraction of Europe’s burnt areas within Natura 2000 protected area sites. This study analyzed total wildfire events and burnt areas in Greece. The frequency of protected area burn percentages per fire event and their trend over time were quantified. The mean protected area percentage of burn per fire event across other Mediterranean countries was compared. Results indicated an increase in the total number of wildfire events over time, while total burnt area was highest in recent years but generally varied. Forest-type vegetation burn exhibits no trend over time with the exception being that the transitional vegetation percentage of burn per wildfire is increasing, while agricultural land is decreasing. The protected area percentage of burn per wildfire is not related with total area burn. The majority of the high percentage protected area burns derive mainly from small or medium total area burn wildfires. More than a third of wildfires burned exclusively (100%) Natura protected area surfaces. Protected area percent per burn is increasing over time. This increase is not related to the increased total burnt area. Protected area percent per burn is considerably higher in Greece in comparison to Italy, Spain, and Portugal. Protected area percent per burn is increasing over time in Greece and with a slower slope in Portugal, while it has no monotonic trend in Italy and Spain. Reserves face increasing burn frequency, necessitating effective management strategies to conserve them. Climate change exacerbates total wildfires or surface area burned but cannot entirely explain the steep increase in protected area percent per burn. While a legislative framework preventing arson exists, management measures need to further improve the efficacy and clarity of legislation. High-power electricity networks and wind and solar energy facilities are often causes of wildfires and should receive low priority or not be licensed in Natura areas. Full article

Simulated data created in silico using a previously reported method were sampled by bootstrapping to generate data sets for training multiple copies of an ensemble learner (i.e., a machine learning (ML) method). The posterior probabilities of class membership obtained by applying the ensemble of ML models to previously unseen validation data were fitted to a beta distribution. The shape parameters for the fitted distribution were used to calculate the subjective opinion of sample membership into one of two mutually exclusive classes. The subjective opinion consists of belief, disbelief and uncertainty masses. A subjective opinion for each validation sample allows identification of high-uncertainty predictions. The projected probabilities of the validation opinions were used to calculate log-likelihood ratio scores and generate receiver operating characteristic (ROC) curves from which an opinion-supported decision can be made. Three very different ML models, linear discriminant analysis (LDA), random forest (RF), and support vector machines (SVM) were applied to the two-state classification problem in the analysis of forensic fire debris samples. For each ML method, a set of 100 ML models was trained on data sets bootstrapped from 60,000 in silico samples. The impact of training data set size on opinion uncertainty and ROC area under the curve (AUC) were studied. The median uncertainty for the validation data was smallest for LDA ML and largest for the SVM ML. The median uncertainty continually decreased as the size of the training data set increased for all ML.The AUC for ROC curves based on projected probabilities was largest for the RF model and smallest for the LDA method. The ROC AUC was statistically unchanged for LDA at training data sets exceeding 200 samples; however, the AUC increased with increasing sample size for the RF and SVM methods. The SVM method, the slowest to train, was limited to a maximum of 20,000 training samples. All three ML methods showed increasing performance when the validation data was limited to higher ignitable liquid contributions. An ensemble of 100 RF ML models, each trained on 60,000 in silico samples, performed the best with a median uncertainty of 1.39x${10}^{-2}$ and ROC AUC of 0.849 for all validation samples. Full article

This article presents a review of several non-exclusive pathways for the sequestration of soil organic carbon, which can be classified into two large classical groups: the modification of plant and microbial macromolecules and the abiotic and microbial neoformation of humic substances. Classical studies have established a causal relationship between aromatic structures and the stability of soil humus (traditional hypotheses regarding lignin and aromatic microbial metabolites as primary precursors for soil organic matter). However, further evidence has emerged that underscores the significance of humification mechanisms based solely on aliphatics. The precursors may be carbohydrates, which may be transformed by the effects of fire or catalytic dehydration reactions in soil. Furthermore, humic-type structures may be formed through the condensation of unsaturated fatty acids or the alteration of aliphatic biomacromolecules, such as cutins, suberins, and non-hydrolysable plant polyesters. In addition to the intrinsic value of understanding the potential for carbon sequestration in diverse soil types, biogeochemical models of the carbon cycle necessitate the assessment of the total quantity, nature, provenance, and resilience of the sequestered organic matter. This emphasises the necessity of applying specific techniques to gain insights into their molecular structures. The application of appropriate analytical techniques to soil organic matter, including sequential chemolysis or thermal degradation combined with isotopic analysis and high-resolution mass spectrometry, derivative spectroscopy (visible and infrared), or ¹³C magnetic resonance after selective degradation, enables the simultaneous assessment of the concurrent biophysicochemical stabilisation mechanisms of C in soils. Full article

Principal component analysis (PCA) is a widely applied multivariate statistical technique across scientific disciplines, with forestry being one of its most dynamic areas of use. Its primary strength lies in reducing data dimensionality and classifying parameters within complex ecological datasets. This study provides the first comprehensive bibliometric and literature review focused exclusively on PCA applications in forestry. A total of 96 articles published between 1993 and 2024 were analyzed using the Web of Science database and visualized using VOSviewer software, version 1.6.20. The bibliometric analysis revealed that the most active scientific fields were environmental sciences, forestry, and engineering, and the most frequently published journals were Forests and Sustainability. Contributions came from 198 authors across 44 countries, with China, Spain, and Brazil identified as leading contributors. PCA has been employed in a wide range of forestry applications, including species classification, biomass modeling, environmental impact assessment, and forest structure analysis. It is increasingly used to support decision-making in forest management, biodiversity conservation, and habitat evaluation. In recent years, emerging research has demonstrated innovative integrations of PCA with advanced technologies such as hyperspectral imaging, LiDAR, unmanned aerial vehicles (UAVs), and remote sensing platforms. These integrations have led to substantial improvements in forest fire detection, disease monitoring, and species discrimination. Furthermore, PCA has been combined with other analytical methods and machine learning models—including Lasso regression, support vector machines, and deep learning algorithms—resulting in enhanced data classification, feature extraction, and ecological modeling accuracy. These hybrid approaches underscore PCA’s adaptability and relevance in addressing contemporary challenges in forestry research. By systematically mapping the evolution, distribution, and methodological innovations associated with PCA, this study fills a critical gap in the literature. It offers a foundational reference for researchers and practitioners, highlighting both current trends and future directions for leveraging PCA in forest science and environmental monitoring. Full article

Wildfires critically affect ecosystems, carbon cycles, and public health. COVID-19 restrictions provided a unique opportunity to study human activity’s role in wildfire regimes. This study presents a comprehensive evaluation of pandemic-induced wildfire regime changes across global fire-prone regions. Using MODIS data (2010–2022), we analyzed fire patterns during the pandemic (2020–2022) against pre-pandemic baselines. Key findings include: (a) A 22% global decline in wildfire hotspots during 2020–2022 compared to 2015–2019, with the most pronounced reduction occurring in 2022; (b) Contrasting regional trends: reduced fire activity in tropical zones versus intensified burning in boreal regions; (c) Stark national disparities, exemplified by Russia’s net increase of 59,990 hotspots versus Australia’s decrease of 60,380 in 2020; (d) Seasonal shifts characterized by December declines linked to mobility restrictions, while northern summer fires persisted due to climate-driven factors. Notably, although climatic factors predominantly govern fire regimes in northern latitudes, anthropogenic ignition sources such as agricultural burning and accidental fires substantially contribute to both fire incidence and associated emissions. The pandemic period demonstrated that while human activity restrictions reduced ignition sources in tropical regions, fire activity in boreal ecosystems during these years exhibited persistent correlations with climatic variables, reinforcing climate’s pivotal—though not exclusive—role in shaping fire regimes. This underscores the need for integrated wildfire management strategies that address both human and climatic factors through regionally tailored approaches. Future research should explore long-term shifts and adaptive management frameworks. Full article

The possibility of collecting new archaeological elements useful in reconstructing the dynamics of population, production and commercial activities in the Bronze Age at the edge of the central-southern Venice Lagoon was provided between 2023 and 2024 thanks to an intervention of rescue archaeology planned during some water restoration works in the Giare–Mira area. Three small excavations revealed, approximately one meter below the current surface and covered by alluvial sediments, a rather complex palimpsest dated to the late Recent and the early Final Bronze Age. Three large circular pits containing exclusively purified grey/blue clay and very rare inclusions of vegetable fibres, and many large, fired clay vessels’ bases, walls and rims clustered in concentrated assemblages and random deposits point to potential on-site production. Two pyro-technological structures, one characterised by a sub-circular combustion chamber and a long inlet channel/praefurnium, and the second one with a sub-rectangular shape with arched niches along its southern side, complete the exceptional context here discovered. To analyse the relationship between the site and the natural sedimentary succession and to evaluate the possible extension of this site, three electrical resistivity tomography (ERT) and low-frequency electromagnetic (FDEM) measurements were collected. Several manual core drillings associated with remote sensing integrated the geophysical data in the analysis of the geomorphological evolution of this area, clearly related to different phases of fluvial activity, in a framework of continuous relative sea level rise. The typology and chronology of the archaeological structures and materials, currently undergoing further analyses, support the interpretation of the site as a late Recent/early Final Bronze Age productive site. Geophysical and geomorphological data provide information on the palaeoenvironmental setting, suggesting that the site was located on a fine-grained, stable alluvial plain at a distance of a few kilometres from the lagoon shore to the south-east and the course of the Brenta River to the north. The archaeological site was buried by fine-grained floodplain deposits attributed to the Brenta River. The good preservation of the archaeological structures buried by fluvial sediments suggests that the site was abandoned soon before sedimentation started. Full article

Forest fires pose significant threats to ecosystems, economies, and human lives. However, existing forest fire risk assessments are over-reliant on field data and expert-derived indices. Here, we assessed the nationwide forest fire risk in South Korea using a dataset of 2289 and 4578 fire and non-fire events between 2020 and 2023. Twelve remote sensing-based environmental variables were exclusively derived from Google Earth Engine, including climate, vegetation, topographic, and socio-environmental factors. After removing the snow equivalent variable owing to high collinearity, we trained three machine learning models: random forest, XGBoost, and artificial neural network, and evaluated their ability to predict forest fire risks. XGBoost showed the best performance (F1 = 0.511; AUC = 0.76), followed by random forest (F1 = 0.496) and artificial neural network (F1 = 0.468). DEM, NDVI, and population density consistently ranked as the most influential predictors. Spatial prediction maps from each model revealed consistent high-risk areas with some local prediction differences. These findings demonstrate the potential of integrating cloud-based remote sensing with machine learning for large-scale, high-resolution forest fire risk modeling and have implications for early warning systems and effective fire management in vulnerable regions. Future predictions can be improved by incorporating seasonal, real-time meteorological, and human activity data. Full article

The prolonged operation of thermal power plants inevitably leads to component aging and a gradual decline in performance. This deterioration increases the gross heat rate and reduces electrical output, resulting in higher fuel consumption and lower electricity production. Consequently, these issues can cause significant financial losses and threaten the plant’s competitiveness. This paper presents a comprehensive methodology for improving the performance of existing plants. The methodology consists of two crucial elements: steam turbine testing and numerical simulation of the process. The tests should be comprehensive to ensure accurate measurements and reliable conclusions. The developed method for process simulation enables the calculation of overall performance, like specific heat rate and thermal efficiency, as well as the performance of individual components under various operational conditions. Comparing numerical results with experimental data can effectively identify operational problems. Based on these findings, targeted overhauls and other corrective measures can substantially improve the plant’s thermal efficiency and financial performance. The system was demonstrated through a case study of a 120 MW coal-fired steam turbine. The test revealed that it consumes more than 10% additional heat compared to its original design specifications. The analysis identified operational issues and recommended improvement measures, focusing exclusively on the steam turbine set while excluding the boiler. Full article

This study investigates the latency of lightning-caused fires in the boreal coniferous forests of the Greater Khingan Mountains, employing advanced machine learning techniques to analyze the relationship between meteorological factors, lightning characteristics, and fire ignition and smoldering processes. Using the Random Forest Model (RFM) combined with Recursive Feature Elimination with Cross-Validation (RFECV) and SHapley Additive exPlanations (SHAP), the study identifies key factors influencing fire latency. Two methods, Min distance and Min latency, were used to determine ignition lightning, with the Min distance method proving more reliable. The results show that lightning-caused fires cluster spatially and peak temporally between May and July, aligning with lightning activity. The Fine Fuel Moisture Code (FFMC) and precipitation were identified as the most influential factors. This study underscores the importance of fuel moisture and weather conditions in determining latency of lightning-caused fire, offering valuable insights for enhancing early warning systems. Despite limitations in data resolution and the exclusion of topographic factors, this study advances our understanding of lightning-fire latency mechanisms and provides a foundation for more effective wildfire management strategies under climate change. Full article

Seasonally dry mature and old-growth (MOG) forests in the western USA face increasing threats from catastrophic wildfire and drought due to historical fire exclusion and climate change. The Emerald Point forest at Lake Tahoe in the Sierra Nevada of California, one of the last remaining old-growth stands at lake level, is at high risk due to elevated fuels and tree densities. The stand supports huge trees and the highest tree diversity in the Lake Tahoe Basin and protects important raptor habitat. In this study, we simulate forest response to vegetation management and wildfire to assess the impacts of four fuel-reduction scenarios on fire behavior and stand resilience at Emerald Point. Results: Our results demonstrate that restorative forest management can greatly improve an MOG forest’s resistance to catastrophic fire. Thinning to the natural range of variation for density, basal area, and fuel loads, followed by a prescribed burn, was most effective at reducing large-tree mortality, maintaining basal area, and retaining live tree carbon post-wildfire, while reducing secondary impacts. Conclusions: Our findings highlight the value of proactive management in protecting old-growth forests in seasonally dry regions from severe fire events, while also enhancing their ecological integrity and biodiversity. Full article

In this paper, we examine an ultra-compact on-chip balanced filter based on novel hybrid resonators (NHRs) comprising short transmission line sections (STLSs) and series LC blocks using low-temperature co-fired ceramic (LTCC) technology. Based on a rigorous theoretical analysis, the proposed NHR demonstrates the potential for intrinsic ultra-wideband differential-mode (DM) and common-mode (CM) suppression without any additional suppressing structures. Furthermore, the resonance of NHRs was determined by four degrees of freedom, providing flexibility for miniaturization. Theoretical extensions of the Nth-order topology can be easily achieved by the simple coupling schemes that occur exclusively between STLSs. For verification, a balanced filter covering the 5G band n78 with an area of 0.065λ_g × 0.072λ_g was designed using the proposed optimization-based design procedure. An ultra-low insertion loss of 0.8 dB was obtained. The quasi-full CM stopband with a 20 dB rejection level ranged from 0 to 12.9 GHz. And the ultra-wide upper DM stopband with a 20 dB rejection level ranged from 4.4 to 11.5 GHz. Good agreement between the theoretical, simulated, and measured results indicate the validity of the proposed design principle. Full article

Ensuring firefighter safety during oil tank fires is paramount, given the substantial risks posed by thermal radiation. This study employs both the Fire Dynamics Simulator (FDS) and Areal Locations of Hazardous Atmospheres (ALOHA) software to simulate a severe oil tank fire scenario at the Zhushan Branch Power Plant, where two heavy oil tanks and multiple light oil tanks are located. The simulation framework divides the combustion scenario into 22.4 million grids with a grid size of 0.5 m, allowing a fine-resolution assessment of thermal radiation. Assuming a worst-case scenario involving n-Heptane combustion, the FDS simulation calculates essential parameters, including temperature, velocity, and soot distribution fields, and suggests a minimum safe firefighting distance of 22 m (equivalent to one tank diameter, 1D) for those equipped with personal protective equipment when exposed to a 5 kW/m² heat flux. Meanwhile, ALOHA modeling extends the safety assessment, recommending a downwind safety distance of 62 m (approximately 2D) to establish a preliminary exclusion zone, crucial in early emergency response when data may be incomplete. Additionally, a grid sensitivity analysis was conducted to validate the accuracy of the numerical results. This study underscores the importance of coupling FDS and ALOHA outputs to develop a balanced, adaptive approach to firefighter safety, optimizing response protocols for high-risk environments. The results provide essential guidance for establishing safety zones, advancing standards within fire protection and emergency response, and supporting strategy development for large-scale oil and petrochemical storage facilities. Full article

Background: Although computational models are advancing air quality prediction, achieving the desired performance or accuracy of prediction remains a gap, which impacts the implementation of machine learning (ML) air quality prediction models. Several models have been employed and some hybridized to enhance air quality and air quality index predictions. The objective of this paper is to systematically review machine and deep learning techniques for spatiotemporal air prediction challenges. Methods: In this review, a methodological framework based on PRISMA flow was utilized in which the initial search terms were defined to guide the literature search strategy in online data sources (Scopus and Google Scholar). The inclusion criteria are articles published in the English language, document type (articles and conference papers), and source type (journal and conference proceedings). The exclusion criteria are book series and books. The authors’ search strategy was complemented with ChatGPT-generated keywords to reduce the risk of bias. Report synthesis was achieved by keyword grouping using Microsoft Excel, leading to keyword sorting in ascending order for easy identification of similar and dissimilar keywords. Three independent researchers were used in this research to avoid bias in data collection and synthesis. Articles were retrieved on 27 July 2024. Results: Out of 374 articles, 80 were selected as they were in line with the scope of the study. The review identified the combination of a machine learning technique and deep learning techniques for data limitations and processing of the nonlinear characteristics of air pollutants. ML models, such as random forest, and decision tree classifier were among the commonly used models for air quality index and air quality predictions, with promising performance results. Deep learning models are promising due to the hyper-parameter components, which consist of activation functions suitable for nonlinear spatiotemporal data. The emergence of low-cost devices for data limitations is highlighted, in addition to the use of transfer learning and federated learning models. Again, it is highlighted that military activities and fires impact the O₃ concentration, and the best-performing models highlighted in this review could be helpful in developing predictive models for air quality prediction in areas with heavy military activities. Limitation: This review acknowledges methodological challenges in terms of data collection sources, as there are equally relevant materials on other online data sources. Again, the choice and use of keywords for the initial search and the creation of subsequent filter keywords limit the collection of other relevant research articles. Full article

Throughout history, natural stone has been a crucial building material due to its strength, durability, and aesthetic qualities. Today, it continues to be a valuable resource, representing both a cultural heritage asset and a significant economic material. However, the increasing frequency of heat waves and fires driven by climate change poses a growing threat to stone building materials. This paper reviews the scientific attention given to the effects of high temperatures on Global Heritage Stone Resources (GHSRs), an international classification designed to enhance the recognition and status of building stones. Through a systematic SCOPUS search with refined filtering criteria, the study aims to quantify the existing research on these heritage stones. The search applied the standardized lithotype terms from GHSR publications to ensure consistency, followed by the exclusion of irrelevant terms when identified. Additionally, a relevance filter was applied to restrict the number of articles per lithotype and ensure that only the most pertinent studies were considered. Key findings from the literature reveal that exposure to high temperatures (ranging from 200 °C to 900 °C) significantly affected the studied GHSRs, leading to thermal micro-fissuring, increased porosity, and changes in water absorption, which compromise the mechanical properties of the stones. Moreover, these conditions can result in irreversible chemical transformations, exacerbating the deterioration of cultural heritage assets. The study emphasizes the critical need for research to better understand how these stone materials behave when exposed to high temperatures. It also provides a relevant framework for future investigations aimed at predicting and mitigating the effects of external threats such as fires. Full article