Search Results (4,930)

Slope failures represent one of the most serious geotechnical hazards, which can have severe consequences for personnel, equipment, infrastructure, and other aspects of a mining operation. Deterministic and stochastic conventional methods of slope stability analysis are useful; however, some limitations in applicability may arise due to the inherent anisotropy of rock mass properties and rock mass interactions. In recent years, Machine Learning (ML) techniques have become powerful tools for improving prediction and risk assessment in slope stability analysis. This review provides a comprehensive overview of ML applications for analyzing slope stability and delves into the performance of each technique as well as the interrelationship between the geotechnical parameters of the rock mass. Supervised learning methods such as decision trees, support vector machines, random forests, gradient boosting, and neural networks have been applied by different authors to predict the safety factor and classify slopes. Unsupervised learning techniques such as clustering and Gaussian mixture models have also been applied to identify hidden patterns. The objective of this manuscript is to consolidate existing work by highlighting the advantages and limitations of different ML techniques, while identifying gaps that should be analyzed in future research. Full article

The sycamore lace bug Corythucha ciliata (Hemiptera: Tingidae), an invasive North American forest pest, owes its strong dispersal and adaptability to biological characteristics and symbiotic microbes, but the underlying mechanisms have not been fully elucidated. This study examined its outdoor-collected (LYGO) and indoor-reared (LYGI) populations using morphological observation, biological parameter assessment, and 16S rRNA sequencing. Key findings include: (1) Nymphs develop through five instars, with body size increasing significantly across stages; growth accelerated during 4th and 5th instars, reflecting a pattern of “low-instar accumulation and high-instar acceleration”. (2) Adult survival differed by sex, with females outliving males after 30 days; nymphs develop in 14.81 days, and each adult pair produced an average of 17 eggs, demonstrating a concentrated reproductive strategy; (3) Both populations shared dominant bacterial taxa (including the phyla Bacteroidota and Proteobacteria and the genus Cardinium) but diverged in non-dominant taxa; core microbial functions were conserved, while specific functions (e.g., glutathione S-transferase activity) varied. These results suggest a potential synergy between the insect’s biological characteristics (efficient development, concentrated reproduction) and the adaptive functions of its associated microbes in enhancing its invasiveness. The study supplements its basic biological data and offers a new view of its ecological adaptability. Full article

Forest and grassland fire behavior prediction is increasingly critical under climate change, as rising fire frequency and intensity threaten ecosystems and human societies worldwide. This paper reviews the status and future development trends of wildfire behavior modeling and prediction technologies. It provides a comprehensive overview of the evolution of models from empirical to physical and then to data-driven approaches, emphasizing the integration of multidisciplinary techniques such as machine learning and deep learning. While conventional physical models offer mechanistic insights, recent advancements in data-driven models have enabled the analysis of big data to uncover intricate nonlinear relationships. We underscore the necessity of integrating multiple models via complementary, weighted fusion and hybrid methods to bolster robustness across diverse situations. Ultimately, we advocate for the creation of intelligent forecast systems that leverage data from space, air and ground sources to provide multifaceted fire behavior predictions in regions and globally. Such systems would more effectively transform fire management from a reactive approach to a proactive strategy, thereby safeguarding global forest carbon sinks and promoting sustainable development in the years to come. By offering forward-looking insights and highlighting the importance of multidisciplinary approaches, this review serves as a valuable resource for researchers, practitioners, and policymakers, supporting informed decision-making and fostering interdisciplinary collaboration. Full article

The use of recycled coarse aggregate (RCA) concrete and polypropylene fibers (PPFs) presents a sustainable alternative in concrete production. However, the non-linear and interactive effects of RCA and PPF on both fresh and hardened properties are not yet fully quantified. This study employs Response Surface Methodology (RSM) and the Random Forest (RF) algorithm with K-fold cross-validation to predict the combined effect of using recycled coarse aggregate (RCA) as a partial replacement for natural coarse aggregate and polypropylene fiber (PPF) on the engineering properties of RCA-PPF concrete, addressing the critical need for a robust, data-driven modeling framework. A dataset of 144 tested samples obtained from literature was utilized to develop and validate the prediction models. Three input variables were considered in developing the proposed prediction models, namely, RCA, PPF, and curing age (Age). The examined responses were compressive strength (CS), tensile strength (TS), ultrasonic pulse velocity (UPV), and water absorption (WA). To assess the developed models, statistical metrics were calculated, and analysis of variance (ANOVA) was employed. Afterwards, the responses were optimized using optimization in RSM. The optimal results of responses by maximizing TS, CS, and UPV and minimizing WA were achieved at a PPF of 3% by volume of concrete and an RCA of approximately 100% replacing natural coarse aggregate, highlighting optimal reuse of recycled aggregate, with an AGE of 83.6 days. The RF model demonstrated superior performance, significantly outperforming the RSM model. Feature importance analysis via SHAP values was employed to identify the most effective parameters on the predictions. The results confirm that ML techniques provide a powerful and accurate tool for optimizing sustainable concrete mixes. Full article

Machine learning is emerging as a powerful tool across many scientific fields, including water resource management. In Morocco, growing challenges such as climate change, population growth, and high water demand—especially in agriculture—have led researchers to apply these techniques to water-related issues. This study reviews recent research conducted in Morocco, highlighting major trends, scientific contributions, and progress in machine learning applications for hydrological challenges. Following the PRISMA framework, a systematic search was carried out in the Scopus database, resulting in 103 relevant publications affiliated with Moroccan institutions. Using NVIVO and SPSS software, key themes were identified, including water quality, groundwater management, and groundwater level prediction. The most frequently used models include Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). This article presents a comparative analysis of nine highly cited Moroccan studies, focusing on application areas, models, parameters, and performance. Findings show a clear rise in AI-related hydrological research in Morocco, especially in water quality monitoring, smart irrigation optimization, and groundwater level forecasting. Full article

Forests play a pivotal role in the global carbon cycle, yet accurately simulating forest soil carbon dynamics remains a significant challenge for process-based models. This review systematically compares the mechanistic foundations of traditional models (e.g., Century, CLM5) with emerging microbial-explicit models (e.g., MEND), highlighting key differences in mathematical formulation (first-order kinetics vs. Michaelis–Menten kinetics), carbon pools partitioning (measurable vs. non-measurable experimentally), and the representation of soil carbon stabilization mechanisms (inherent recalcitrance, physical protection, and chemical protection). Despite advances in process-based models in predicting forest soil organic carbon (SOC), improving prediction accuracy, and assessing SOC response to climate change, current research still faces several challenges. These include difficulties in capturing depth-dependent variations in critical microbial parameters such as microbial carbon use efficiency (CUE), limited capacity to distinguish the relative contributions of aboveground and belowground litter inputs to SOC formation, and a general lack of long-term observational data across soil profiles. To address these limitations, this study emphasizes the importance of integrating remote sensing data and refining cross-scale simulation approaches. Such improvements are essential for enhancing model predictive accuracy and establishing a more robust theoretical basis for forest carbon management and climate change mitigation. Full article

The strong heterogeneity in and complex engineering conditions of deep shale gas reservoirs make productivity prediction challenging, especially in nascent blocks where data is scarce. This scarcity constitutes a critical research gap for the application of data-driven methods. To bridge this gap, we develop an interpretable framework by combining grey relational analysis (GRA) with three machine learning algorithms: Random Forest (RF), Support Vector Machine (SVR), and eXtreme Gradient Boosting (XGBoost). Utilizing small-sample data from 87 shale gas wells in the study area, eight key controlling factors were identified, namely, total fracturing fluid volume, proppant intensity, average tubing head pressure, pipeline transfer pressure, casing head pressure, ceramic proppant fraction, fluid placement intensity, and flowback recovery ratio. These factors were used to train, optimize, and validate a productivity prediction model tailored for deep shale gas horizontal wells. The results demonstrate that XGBoost delivers the highest predictive accuracy and generalization capability, achieving an R² of 0.907 for productivity prediction—surpassing RF and SVR by 12.11% and 131.38%, respectively. Integrating SHapley Additive exPlanations (SHAP) interpretability analysis further enabled immediate post-fracturing productivity assessment and engineering parameter optimization. This research provides a reliable, data-driven strategy for predicting productivity and optimizing operations within the studied block, offering a valuable template for development in geologically similar areas. Full article

Tourism demand forecasting has evolved into a wide variety of models, including time-series models that incorporate economic, environmental, and behavioral factors. Macao, one of the world’s most profitable gaming destinations, finds that gaming revenue is highly related to tourist arrivals. A forecast model for gaming tourism is essential for accurately predicting tourist arrivals. The challenge with ARIMA-type models is optimizing parameter selection in order to improve the accuracy of tourism demand forecasts. In this study, an enhanced version of SARIMAX, called SARIMAX-E, was developed to identify the most effective parameter combinations. By integrating data related to gaming revenue, weather, transportation, currency exchange rate, holidays, and seasonality into a single forecast model, this study examined the performance of different forecasting models, including the proposed SARIMAX-E model; ARIMA-type models (ARIMA, SARIMA, ARIMAX); and machine learning models (Transformer, LTSM, Random Forests, XGBoost). The results showed that the ARIMA family of models, including SARIMAX-E, ARIMAX, and SARIMA, was particularly well suited to tourism demand forecasting, as its members consistently ranked among the top performers in terms of error metrics. By applying multi-step predictions, LSTM outperforms most conventional approaches. Compared with all other models, the SARIMAX-E performed the best after applying the additional parameter grid. Full article

Urbanization imposes complex environmental gradients that threaten plant diversity and urban ecosystem integrity. Understanding the multifactorial drivers that govern species distribution in urban contexts is essential for biodiversity conservation and sustainable landscape planning. This study addresses this challenge by examining the environmental determinants of urban flora in a rapidly developing city. We integrated data from 397 floristic sampling sites and 13 environmental monitoring locations across Düzce, Türkiye. A multidimensional suite of environmental predictors—including microclimatic variables (soil temperature, moisture, light), edaphic properties (pH, EC (Electrical Conductivity), texture, carbonate content), precipitation chemistry (pH and major ions), macroclimatic parameters (CHELSA bioclimatic variables), and spatial metrics (elevation, proximity to urban and natural features)—was analyzed using nonlinear regression models and machine learning algorithms (RF (Random Forest), XGBoost, and SVR (Support Vector Regression)). Shannon diversity exhibited strong variation across land cover types, with the highest values in broad-leaved forests and pastures (>3.0) and lowest in construction and mining zones (<2.3). Species richness and evenness followed similar spatial trends. Evenness peaked in semi-natural habitats such as agricultural and riparian areas (~0.85). Random Forest outperformed other models in predictive accuracy. Elevation was the most influential predictor of Shannon diversity, while proximity to riparian zones best explained richness and evenness. Chloride concentrations in rainfall were also linked to species composition. When the models were recalibrated using only native species, they exhibited consistent patterns and maintained high predictive performance (Shannon R² ≈ 0.937474; Richness R² ≈ 0.855305; Evenness R² ≈ 0.631796). Full article

Graphite nodularity is a key indicator for evaluating the microstructure quality of ductile iron and plays a crucial role in ensuring product quality and enhancing manufacturing efficiency. Existing research often only focuses on a single type of feature and fails to utilize multi-source information in a coordinated manner. Single-feature methods are difficult to comprehensively capture microstructures, which limits the accuracy and robustness of the model. This study proposes a hybrid estimation model for the graphite nodularity of ductile cast iron based on multi-source feature extraction. A comprehensive feature engineering pipeline was established, incorporating geometric, color, and texture features extracted via Hue-Saturation-Value color space (HSV) histograms, gray level co-occurrence matrix (GLCM), Local Binary Pattern (LBP), and multi-scale Gabor filters. Dimensionality reduction was performed using Principal Component Analysis (PCA) to mitigate redundancy. An improved watershed algorithm combined with intelligent filtering was used for accurate particle segmentation. Several machine learning algorithms, including Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting Regressor (GBR), eXtreme Gradient Boosting (XGBoost) and Categorical Boosting (CatBoost), are applied to estimate graphite nodularity based on geometric features (GFs) and feature extraction. Experimental results demonstrate that the CatBoost model trained on fused features achieves high estimation accuracy and stability for geometric parameters, with R-squared (R²) exceeding 0.98. Furthermore, introducing geometric features into the fusion set enhances model generalization and suppresses overfitting. This framework offers an efficient and robust approach for intelligent analysis of metallographic images and provides valuable support for automated quality assessment in casting production. Full article

Objectives: This study evaluated the utility of complex morphometric analyses for predicting radiation pneumonitis (RP) and proposed a quantitative prognostic framework for patients with non-small cell lung cancer (NSCLC) undergoing curative-intent radiotherapy (RT). Imaging biomarkers, including box-counting fractal dimension (BoxFD), lacunarity, and minimum spanning tree fractal dimension (MSTFD), were assessed for their prognostic significance. Materials and Methods: We retrospectively analyzed 166 NSCLC patients who received curative-intent RT and had both pre-treatment and follow-up chest CT scans. Among them, 85 received RT alone and 81 underwent concurrent chemoradiotherapy (CCRT). Fractal features were measured to build a Random Forest model (RFM) predicting RP of grade ≥ 2, and the most important features were used to construct a decision tree model. Results: RP of grade ≥ 2 occurred in 19 patients (22.3%) in the RT alone group and 44 patients (54.3%) in the CCRT group. Lacunarity increased significantly post-RT in both groups, while BoxFD and MSTFD showed no significant changes. In the RFM, pre-RT MSTFD and lung dose parameters (V10 in RT alone; V5–V20 in CCRT) were identified as key predictors. Decision tree models based on these features achieved high predictive performance, with AUROC of 0.83 and 0.85, and F1 scores of 0.92 and 0.76 for RT alone and CCRT groups, respectively. Conclusions: Fractal imaging biomarkers demonstrated promising prognostic value for predicting grade ≥ 2 RP in NSCLC patients. The proposed decision tree model may serve as a practical tool for early identification of high-risk patients, facilitating personalized treatment strategies and informing future research. Full article

Understanding the mechanisms that maintain biodiversity is crucial for effective conservation in riverine ecosystems. However, the direct and indirect mechanisms by which land use patterns and water quality parameters influence plankton α- and β-diversity remain poorly elucidated. Here, we undertook a comprehensive survey of plankton communities across the Jialing River basin. Our results showed that Bacillariophyta and Chlorophyta were the dominant phytoplankton groups, whereas Protozoa and Copepoda predominated among zooplankton. Redundancy analysis identified dissolved oxygen and total phosphorus as key environmental factors shaping plankton community structure. Additionally, random forest models indicated that anthropogenic stressors exerted consistent effects on both α- and β-diversity of phytoplankton. Importantly, the decomposition of β-diversity revealed that species turnover constituted the major component, underscoring the importance of basin-scale management approaches. Structural equation modeling further demonstrated that land use practices predominantly affected phytoplankton β-diversity indirectly via water quality alterations, with a relatively weak direct effect. In contrast, neither the direct nor indirect effects of land use were significant for zooplankton communities. These findings suggest that phytoplankton may serve as more reliable bioindicators of anthropogenic disturbance than zooplankton in this freshwater system. Moreover, our findings highlight the central role of water quality in regulating phytoplankton diversity responses to environmental change. Consequently, we recommend that conservation strategies in the Jialing River basin focus on water quality monitoring and the mitigation of its ecological effects. Full article

The prolonged retention of senescent branches and needles (canopy litter) in Cunninghamia lanceolata canopies is an evolutionary adaptation, yet its impacts on stand microenvironment and understory succession remain poorly quantified. To address this gap, we conducted a 5-year field experiment across six planting densities (1800, 2400, 3000, 3600, 4200, and 4800 trees·ha⁻¹), aiming to evaluate the effects of canopy litter removal on canopy structure, forest light environment, and understory biodiversity. Results demonstrated that leaf area index (LAI) and mean tilt angle of the leaf (MTA) significantly increased with density (p < 0.05), leading to marked reductions in photosynthetic photon flux density (PPFD) and light transmittance (T). Canopy litter removal significantly reduced LAI across all densities after 4–5 years (p < 0.05) and consistently enhanced PPFD and transmittance (p < 0.01). MTA and light quality parameters (red:blue and red:far-red ratios) both exhibited variable responses to litter removal, driven by density and time interactions, with effects diminishing over time. Understory vegetation diversity exhibited pronounced temporal dynamics and density-dependent responses to canopy litter removal, with increases in species richness (S), Simpson diversity (D), and Shannon–Wiener diversity (H), while Pielou Evenness (J) responded more variably. The most notable increase in species richness occurred in the 4th year, when 21 new species were recorded, largely due to the expansion of light-demanding bamboos (e.g., Indocalamus tessellatus and Pleioblastus amarus), heliophilic grasses (e.g., Lophatherum gracile) and pioneer ferns (e.g., Pteris dispar and Microlepia hancei). Correlation analyses confirmed PPFD as a key positive driver of all diversity indices (p < 0.01), whereas LAI was significantly negatively correlated with PPFD, light transmittance, and understory diversity (p < 0.01). These findings demonstrate that strategic management of canopy litter incorporating stand density regulation can improve understory light availability, thereby facilitating heliophilic species recruitment and biodiversity enhancement in subtropical coniferous plantations. Full article

To reveal the hydraulic characteristics of a centrifugal pump with splitter blades during shutdown, a low specific speed closed impeller centrifugal pump is subjected to shutdown experiments under eight non-rated operating conditions in this paper. The transient evolution characteristics of five performance parameters with time are obtained, including rotational speed, flow rate, inlet and outlet pressures, and head. Meanwhile, the shutdown fitting models based on three machine learning models are developed. The results show that the integrated neural network model can more accurately predict the hydraulic performance of the physical pump during shutdown than the decision tree regression and random forest regression models. During the pre-mid period of the shutdown, the integrated neural network model predicts a maximum error of about 3.21% for the instantaneous flow rate and about 3.58% for the instantaneous head. This study provides a reference for the performance control of centrifugal pumps during transient operation. Full article

Rapid sand filtration is a critical step in the water treatment process, as its effectiveness directly impacts the supply of safe drinking water. However, optimising filtration processes in water treatment plants (WTPs) presents a significant challenge due to the varying operational parameters and conditions. This study applies explainable machine learning to enhance insights into predicting direct filtration operations at the Ålesund WTP in Norway. Three baseline models (Multiple Linear Regression, Support Vector Regression, and K-Nearest Neighbour (KNN)) and three ensemble models (Random Forest (RF), Extra Trees (ET), and XGBoost) were optimised using the GridSearchCV algorithm and implemented on seven filter units to predict their filtered water turbidity. The results indicate that ML models can reliably predict filtered water turbidity in WTPs, with Extra Trees models achieving the highest predictive performance (R² = 0.92). ET, RF, and KNN ranked as the three top-performing models using Alternative Technique for Order of Preference by Similarity to Ideal Solution (A-TOPSIS) ranking for the suite of algorithms used. The feature importance analysis ranked the filter runtime, flow rate, and bed level. SHAP interpretation of the best model provided actionable insights, revealing how operational adjustments during the ripening stage can help mitigate filter breakthroughs. These findings offer valuable guidance for plant operators and highlight the benefits of explainable machine learning in water quality management. Full article