Search Results (216)

Oil palm plantations play an important role in agricultural production and carbon storage in tropical regions. The accurate estimation of aboveground carbon (AGC) is essential for sustainable plantation management, climate change mitigation, and carbon monitoring. Although field measurements provide reliable estimates, they are often time-consuming, labor-intensive, and costly, particularly over large plantation areas. Recent advances in remote sensing and machine learning offer efficient alternatives for AGC estimation using satellite imagery. In this study, we developed a machine learning framework for AGC estimation in oil palm plantations using Sentinel-2 multispectral imagery and Sentinel-1 synthetic aperture radar (SAR) data. Field measurements were integrated with spectral variables, vegetation indices, and SAR-derived parameters extracted from satellite data. A hybrid feature selection approach combining Pearson correlation, mutual information and mRMR was used to identify the most relevant variables. Six machine learning algorithms were evaluated, including Linear Regression, Random Forest, XGBoost, Gradient Boosting, LightGBM, and Extra Trees. Because the 160 observations comprise sixteen 10 m × 10 m grid cells nested within ten 40 m × 40 m field plots, model performance was assessed with leave-one-plot-out cross-validation: all sixteen cells of a plot were held out together, and the hybrid feature selection was repeated inside every fold using only that fold’s training plots. Performance was measured on pooled out-of-fold predictions using R², root mean squared error (RMSE), and average absolute relative error (AARE%). Under this spatially independent design the combined Sentinel-1 + Sentinel-2 dataset gave the highest accuracy (R² = 0.7950, RMSE = 4.14 t C ha⁻¹, AARE = 33.53%), followed by Sentinel-1 alone (R² = 0.7631, RMSE = 4.46 t C ha⁻¹) and Sentinel-2 alone (R² = 0.6108, RMSE = 5.71 t C ha⁻¹). Linear Regression and Extra Trees were the most robust models, whereas the boosted ensembles did not generalize to unseen plots. Repeating the evaluation with an ungrouped random split of the same data inflated R² by up to 0.70, showing that a large part of the accuracy obtainable under that design reflects within-plot spatial autocorrelation rather than predictive skill. These findings indicate that optical-SAR imagery combined with machine learning can provide useful AGC estimates in oil palm plantations, and that spatially independent validation is essential for reporting them honestly. The proposed framework can be used to support plantation-scale carbon mapping, monitoring, and carbon stock assessment, subject to further calibration and independent validation across additional plantations. Full article

Waste cooking oil (WCO) was investigated as a waste-derived reactive precursor for a cured organic binder in highly mineral-filled composites containing turmeric. Ten formulations selected from a broader experimental screening were prepared from WCO, sulfuric acid, quartz sand, and turmeric added at 1–7% relative to the dry mass of quartz sand. Formulation-specific thermal curing was conducted at 190–210 °C for 12–20 h. Because the binder content, acid-to-binder ratio, turmeric content, curing temperature, and curing time varied simultaneously, the study was designed as an exploratory multifactorial screening rather than as a controlled assessment of individual processing variables. FTIR, ¹H NMR analysis of acetone-soluble constituents, TGA, and SEM-EDS were combined with mechanical screening, water-absorption, contact-angle, and microbiological measurements. Bending and splitting tensile strengths ranged from 1.15 to 2.42 MPa and from 0.30 to 0.52 MPa, respectively. Water absorption ranged from approximately 4.8% to 9.0%, while water contact angles exceeded 90° for all investigated formulations. Selected formulations reduced the surviving fraction by more than 90% for Staphylococcus epidermidis and by approximately 70% for Pseudomonas aeruginosa under the applied suspension-assay conditions. The estimated C₅₀ values of 60.6–83.3 mg mL⁻¹ indicated measurable concentration-dependent responses at relatively high nominal composite concentrations. The available results support curing-associated transformation and consolidation of the WCO-derived binder phase but do not quantify crosslink density or retained organic content. Because no matched turmeric-free composite or surface/eluate pH measurements were available, the biological effects are attributed to the complete composite formulations rather than specifically to turmeric or intact curcumin. The results provide an exploratory basis for the further development of waste-derived, non-load-bearing polymer–mineral composites with functional surface and biological properties. Full article

Economically motivated adulteration of olive oil, coffee and fruit juice is a persistent food-fraud problem for which Fourier-transform infrared (FTIR) spectroscopy with chemometrics offers rapid screening. Linear partial least squares (PLS) is interpretable but cannot capture non-linear mixing; neural networks add flexibility at the cost of becoming black boxes. We evaluated a Kolmogorov–Arnold network (KAN), which places learnable univariate functions on its edges and is therefore intrinsically interpretable, against PLS, support-vector regression, random forests, a multilayer perceptron and a one-dimensional convolutional network on three attenuated total reflectance (ATR)–FTIR datasets (olive oil + sunflower oil, coffee + malt flour, orange juice + apple juice; approximately 350, 400 and 400 spectra). All models were compared under identical, leakage-free validation that splits spectra by physical sample. The compact KAN was consistently competitive (cross-validated coefficients of determination (R²) = 0.86, 0.93 and 0.69) and yielded closed-form equations whose variables map to recognised vibrational bands and whose importance ranking agrees with SHapley Additive exPlanations (SHAP; Spearman ρ = 0.86–0.90); symbolic conversion costs no accuracy. We also report the following limits: PLS was strongest where the chemistry was linear (coffee) and the multilayer perceptron was strongest on fruit juice, whose equation is the weakest (R² = 0.47–0.75 across seeds); a parameter-matched perceptron matched the KAN’s accuracy; and leave-one-brand-out validation degraded every model. The KAN is therefore a promising, compact and genuinely transparent alternative under controlled multi-matrix conditions, not a deployment-ready method. Full article

Photovoltaic (PV)/biomass systems offer stable/continuous power by overcoming solar-energy intermittency with biomass dispatchable energy. Considering gaps in the scientific literature, this article sets out to present information on PV/biomass installations and the eco-profiles of different feedstocks for biogas generation. To this end, this article is split into two parts. The first one outlines some key elements of the literature on PV/biomass systems, highlighting factors that determine feasibility and performance. The second one presents the eco-profiles of three feedstocks. The methodology is based on literature review and Life-Cycle Assessment (LCA). Regarding the first part, the results show that the majority of the prior research placed emphasis on techno-economic analysis and the design/modelling of PV/biomass systems, and there is a dearth of LCA studies on PV/biomass installations. As for the second part, the findings demonstrate that, among the feedstocks examined (manure; waste cooking oil; grass), in most categories, animal waste shows the highest environmental impacts. For instance, considering the total impact of these three feedstocks and based on Environmental Product Declaration (EPD), the results indicate that, in many categories, manure surpasses the percentage values of 40%. Grass exhibits minor percentage shares, with the exception of the “Eutrophication” (54%) and “Acidification” (33%) categories. Full article

Recycled micro-surfacing is a sustainable pavement maintenance technique, yet using fine Reclaimed Asphalt Pavement (RAP) is challenging due to aged asphalt and particle agglomeration. This study aimed to develop cold recycled micro-surfacing with waste edible oil (WEO) and Waterborne Epoxy Resin (WER)-modified emulsified asphalt and proposed a novel pre-regeneration method using ultrasonic–mechanical mixing for fine RAP with WEO before preparing mixtures. Molecular dynamics (MD) simulation and Dynamic Shear Rheometer (DSR) tests were conducted to assess rejuvenator diffusion and rheological recovery. In addition, mixtures with 0–25% WER were tested for wear, rutting, low-temperature splitting, and water resistance to optimize the WEO content, mixing time, and WER dosage. The results of MD simulation showed that WEO diffused faster than aged asphalt molecules and mutually interacted. DSR results indicated that 4% WEO (by mass of aged asphalt) gradually restored the complex modulus and phase angle to the levels of matrix asphalt. The recycled mixtures with 4 min ultrasonic–mechanical mixing had a minimum WTAT of 136.86 g/m², which was a 9.6% decrease compared to the mixture without ultrasonic–mechanical mixing. The 1 h WTAT, PVD, PLD, 6d WTAT, and tensile strength of recycled mixtures with 20% WER were improved by 72.6%, 68.9%, 68.8%, 75.0%, and 88.7% compared with those of the matrix asphalt mixtures. Although WER weakened the low-temperature performance of the mixtures, the tensile strain was smaller than the maximum specification requirement of 2500 με when the WER content was less than 20%. In summary, pre-regeneration with 0.4% WEO (by mass of mixtures) and 4 min ultrasonic–mechanical mixing effectively activated the fine RAP. Considering the balance of properties of fine RAP micro-surfacing mixtures, the optimum dosage of 20% WER was recommended to provide sustainable high-performance cold recycled micro-surfacing. Full article

Commodity prices are notoriously hard to forecast, and whether the returns of commodity exchange-traded funds (ETFs) can be predicted remains an open question. We compare three deep learning models, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Transformer, for forecasting the returns of six Deutsche Bank commodity ETFs covering agriculture (DBA), base metals (DBB), broad commodities (DBC), energy (DBE), oil (DBO), and precious metals (DBP). Using daily price data from January 2007 to December 2025, we predict daytime returns (open to close) and overnight returns (previous close to open) separately, over five horizons of 1, 5, 30, 60, and 180 trading days. Each model sees a 20-day window of price-based features, returns, rolling averages and volatilities, momentum, and recent lags, built from all six ETFs. All models are trained on a strict chronological split and judged by two simple, decision-oriented measures: how often they call the direction correctly, and the risk-adjusted return (annualized Sharpe ratio) of a stylized long–short strategy that ignores transaction costs. Formal significance tests with HAC corrections for overlapping targets, bootstrap confidence intervals, and comparisons with ARIMA, random forest, and simpler benchmarks corroborate strong predictability in overnight DBP and daytime DBB at medium horizons. Predictability turns out to be highly specific to the asset, the trading session, and the horizon. Overnight returns of the precious metals ETF (DBP) are by far the most predictable: the correct direction is called 71.6% of the time at 60 days and 76.7% at 180 days, with Sharpe ratios reaching about 15. Base metals (DBB) daytime returns are predictable at 30 days and oil (DBO) daytime returns at 180 days, whereas one-day-ahead forecasts and agricultural returns (DBA) stay essentially unpredictable. The Transformer has a slight edge at longer horizons and the GRU at shorter ones. Key directional accuracy and Sharpe ratio results are confirmed by Newey–West HAC significance tests and Diebold–Mariano forecast comparison tests with the Harvey–Leybourne–Newbold small-sample correction; HAC standard errors at the 180-day horizon exceed naïve OLS errors by a factor of approximately 7.4, and we explicitly flag results that do not survive this correction. A three-fold expanding walk-forward validation scheme corroborates the main findings, with DBP overnight and DBO daytime predictability persisting across all evaluation windows. Deep learning architectures statistically and economically outperform logistic regression, ridge regression, and momentum baselines on the most predictable configurations. An anomalous failure of all models on DBA daytime returns at the 180-day horizon is diagnosed as a regime-driven artefact associated with post-2021 commodity inflation, not a general feature of agricultural return dynamics. The broader lesson is that splitting returns into daytime and overnight components exposes predictable structure that conventional close-to-close returns hide. Full article

Oil-well anomaly monitoring supports safe and efficient oil-and-gas production, but delayed recognition of abnormal operating states can reduce lifting efficiency, trigger costly interventions, and increase operational risk. Existing data-driven detectors are also vulnerable to optimistic estimates when segmentation, normalization, and train–test splitting leak information across source files. This study presents ALSTMResNet, an application-oriented active-learning workflow built on an LSTMResNet backbone for one-step-ahead anomaly screening under partial labels. The workflow converts real 3W well records into leakage-aware file-wise splits, train-only standardized sliding windows, and a fixed 15-channel representation that combines process measurements with temporal covariates; active learning is used only during training to select additional labels while leaving the deployed backbone unchanged. Experiments on the retained benchmark split obtain an $F_1$-score of 0.9354, and five repeated file-wise trials give an average $F_1$-score of $0.8661\pm 0.0666$ while reducing retraining time relative to the full-data backbone. Label-budget and acquisition-policy analyses show that the workflow remains competitive under constrained labels, although uncertainty, entropy, margin, least-confidence, and random querying have limited separation in the present binary setting. These results indicate that ALSTMResNet can support cost-aware oil-well anomaly monitoring when labels are partially available and retraining resources are constrained. Full article

Handwritten identification marks on steel plate end faces are important for material traceability, inventory checking, and production scheduling in large steel storage yards. Their localization remains challenging because field images often contain uneven illumination, specular reflection, rust, oil contamination, densely adjacent targets, and arbitrary target orientations. This study presents an application-oriented pipeline for oriented localization of handwritten marks on densely stacked steel plates. The pipeline combines task-oriented image enhancement, high-resolution sliding-window inference, and a YOLOv11 oriented bounding-box detector (YOLOv11-OBB) adapted with attention enhancement, adjusted multi-scale fusion, and Scylla-IoU (SIoU)-based box regression. A real steel-yard dataset was annotated with oriented bounding boxes and split at the source-image level before patch extraction. The held-out evaluation subset was used both for checkpoint selection and final performance reporting under the same protocol. On this dataset, the final detector achieved 89.9% precision, 88.3% recall, 91.8% mAP@0.5, and 72.0% mAP@0.5:0.95. These results support the practical value of oriented localization and high-resolution inference for weak handwritten regions in complex industrial scenes. Broader detector benchmarking and downstream recognition performance remain to be validated in future work. Full article

Preferential flow paths and ineffective water circulation are difficult to quantify in ultra-high water-cut reservoirs because long-term waterflooding intensifies dynamic heterogeneity and oil–water flow interactions. This study develops a displacement unit (DU)-scale method that integrates dynamic liquid-volume splitting, saturation tracking, and techno-economic water-cut evaluation while considering time-varying reservoir properties. The method was applied to a typical ultra-high water-cut block in the Daqing Oilfield to characterize the temporal evolution of preferential flow paths. A total of 902 DUs were delineated from streamline envelopes, and validation with production profile data from representative wells showed an accuracy exceeding 82%. Under an oil price of 60 USD/bbl, the proposed economic water-cut criterion identified 368 economically strong preferential-flow DUs, accounting for 40.79% of all DUs. Two indicators, the water-cut profit–loss margin (Δf_w) and oil displacement efficiency (E_d), were then used to establish a Δf_w-E_d classification matrix. The DUs were divided into four types: economically ineffective strong-channeling units, channeling units with remaining potential, mature stable production units, and homogeneous units. The results support differentiated control measures, such as channel plugging, profile control, cyclic waterflooding, and fluid-rate optimization, for improving waterflood management in mature reservoirs. Full article

The scarcity of natural aggregates and the accumulation of oil sludge in desert regions pose critical challenges for highway construction. Although aeolian sand and oil sludge pyrolysis residue have been studied individually as construction materials, their combined use in foamed lightweight soil remains unexplored. This study addresses this gap by developing a novel foamed lightweight soil termed SOFS, which is created through the synergistic modification of aeolian sand and oil sludge pyrolysis residue. A six-factor, five-level orthogonal array (L25) was employed to systematically investigate the effects of residue content, sand content, foam-to-slurry ratio, foaming agent dilution, water-to-solid ratio, and mixing time. The evaluated properties included physical properties (fluidity and wet density), mechanical properties (compressive, splitting tensile, and flexural strength), and durability (wet–dry and freeze–thaw resistance). Scanning electron microscopy was used to examine the microstructural mechanisms. Variance and range analysis identified the optimal mixture, designated H14, which achieved 28-day compressive, splitting tensile, and flexural strengths of 3.75 MPa, 2.21 MPa, and 0.9 MPa, respectively, thereby meeting desert roadbed requirements. Compared with conventional materials, H14 exhibited superior durability, with strength losses of only 16.3% in compressive strength and 19.1% in splitting tensile strength after 25 cycles. Microstructural analysis revealed a dense C-S-H gel network encapsulating the solid waste particles, with nanoscale Al- and Cl-rich crystalline phases observed at interfacial pores—a phenomenon that has rarely been documented in previous studies. These findings provide a theoretical and technical foundation for solid waste valorization and the development of sustainable desert infrastructure. Full article

Pipelines remain the primary mode of oil and gas transportation but are vulnerable to leaks that pose environmental and safety risks, particularly in two-phase flow systems. Conventional detection methods often struggle under transient multiphase conditions, while many data-driven studies rely on static evaluation metrics that do not reflect continuous monitoring requirements. This study develops a machine learning framework for leak detection using OLGA-simulated datasets from a previously published study, comprising approximately 180,000 labelled samples across nine leak scenarios and one no-leak case. Pressure, temperature, and mass-flow variables were enhanced through feature engineering to capture nonlinear leak behaviour. Random forest and extreme gradient boosting (XGBoost) classifiers were trained using an 80/20 stratified split with synthetic minority oversampling technique (SMOTE)-based balancing applied only to training data. XGBoost achieved 99.2% accuracy and reduced false positives by 53% relative to random forest while maintaining near-zero false negatives. A sliding-window suspicion framework extended static classification into time-dependent detection, producing delays of between 9.81 s and 82.04 s with zero false alarms in the no-leak scenario. Physical validation using pressure, flow, and fast Fourier transform (FFT) analysis confirmed that detections correspond to genuine hydraulic disturbances, demonstrating the reliability and physical credibility of the proposed framework. Full article

Polymer-augmented waterflooding is a key enhanced oil recovery technique whose simulation remains computationally demanding at a high spatial resolution. This paper presents a fully GPU-resident parallel solver for the one-dimensional Buckley–Leverett polymer-flooding problem within an Implicit-Pressure–Explicit-Saturation framework. The solver combines Jacobi iteration for pressure, first-order upwind flux splitting for saturation, and a first-order upwind flux-splitting update for polymer mass with explicit concentration recovery inside a coupled Picard–IMPES iteration. Two CUDA implementations are compared: a global-memory baseline and a shared-memory variant that stages a per-block pressure tile with halo cells on chip. Both kernels were profiled on an NVIDIA GeForce RTX 2080 Ti over problem sizes from $N=65,536$ to $N=67,108,864$ and block sizes 128, 256, 512, and 1024. The two GPU implementations match the serial reference within $2\times {10}^{-8}$, and peak speed-ups are $20.2\times$ (global) and $20.1\times$ (shared). Per-kernel Nsight Compute profiling classifies every kernel in both builds as compute-bound: SM throughput is 54–83% of peak and DRAM throughput 3–29% of peak. The bottleneck is the FP64 pipeline of consumer Turing hardware (FP64 throughput is one thirty-second of FP32); three FP64 divisions per cell, from inline polymer-modified mobility recomputation, saturate the FP64 unit. Shared-memory tiling cannot improve performance because it acts on memory traffic rather than on compute throughput. The result therefore characterizes a specific regime, namely FP64 one-dimensional, low-reuse transport stencils on consumer-class NVIDIA GPUs with reduced FP64 throughput, and is not a universal property of CUDA shared memory. Full article

Asphalt pavements are prone to the formation of microcracks due to aging under environmental factors, and microcapsule-based self-healing technology represents an effective means of preventive maintenance. In this study, corn oil, a renewable and environmentally friendly material, was selected as the asphalt rejuvenator to prepare corn oil microcapsules via in situ polymerization, and the self-healing performance of corn oil microcapsule-modified asphalt was investigated. By analyzing the effects of corn oil microcapsules on the high-temperature performance, salt resistance, chemical structure, and microscopic morphology of asphalt, as well as the influence of temperature, time, and corn oil microcapsule content on the self-healing performance of asphalt mixtures, the self-healing mechanism of corn oil microcapsule-modified asphalt was elucidated at both the microscopic and macroscopic levels. The results showed that during the preparation of corn oil microcapsules, the optimal molar ratio of M_F:M_(M+U) was 2.5, with an emulsification rate of 1.2 kr/min. The prepared corn oil microcapsules exhibited high yield and good encapsulation efficiency, possessed excellent high-temperature resistance that met the requirements of the asphalt mixing stage, and showed superior salt resistance. FTIR analysis confirmed the successful incorporation of microcapsules into the asphalt system. Atomic force microscopy (AFM) observations revealed that the microcapsules mitigated microscopic surface damage caused by aging. The healing index of the asphalt mixtures incorporating corn oil microcapsules increased with prolonged healing time and elevated temperature. By establishing the relationship between the healing index and the content of corn oil microcapsules, the recommended content of corn oil microcapsules within the tested range is 6 wt%. This study elucidates the self-healing mechanism of corn oil microcapsule-modified asphalt from both microscopic (surface parameter recovery) and macroscopic (mechanical property restoration) scales, providing a scientific basis for the application of microcapsule technology in green and sustainable asphalt pavement maintenance. Full article

Brent crude oil prices are strategically important due to their sensitivity to geopolitical developments, financial market stress, and global monetary conditions. This study examines whether strategic risk indicators improve the forecasting performance of Brent crude oil returns within an integrated econometric and machine learning framework. Monthly data from January 2001 to December 2025 are employed, using the Global Geopolitical Risk Index (GPR), the CBOE Volatility Index (VIX), and the U.S. 10-year Treasury yield (DGS10) as key explanatory variables. Methodologically, the analysis first estimates benchmark econometric models, including ARIMAX (AutoRegressive Integrated Moving Average with Explanatory Variable) and ARIMAX-gjrGARCH (Glosten-Jagannathan-Runkle Generalized Autoregressive Conditional Heteroscedasticity, and then implements machine learning models, namely XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), and Random Forest, to capture potential nonlinear relationships. Using sMAPE (Symmetric Mean Absolute Percentage Error), forecast performance is assessed over multiple forecast horizons under a rolling-origin framework. Across several forecasting horizons and train-test split configurations, the empirical results consistently show that machine learning techniques, especially LightGBM, offer superior out-of-sample forecasting accuracy. These findings suggest that the dynamics of Brent crude oil returns are influenced by complex and nonlinear relationships between macro-financial conditions, financial uncertainty, and geopolitical risk. The study concludes that flexible data-driven forecasting frameworks offer stronger predictive performance than benchmark econometric models under strategic risk conditions and provide useful implications for energy market risk management and policy decision-making. Full article

Using daily data from Investing.com South Africa, this study investigates the forecasting performance of four Rand currency rate markets (EUR/ZAR, CHF/ZAR, BRL/ZAR, and CNY/ZAR) from 13 February 2018 until 24 February 2025. The predictive fitness of three competing models, Support Vector Regression (SVR), Principal Component Regression (PCR), and eXtreme Gradient Boosting (XGBoost), is explored between 80%/20% and 95%/5% training-testing splits. Forecasting accuracy is evaluated based on evaluation errors, i.e., Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The Diebold–Mariano test is employed to check for statistical significance. Empirical results show that the linear SVR model outperforms PCR across all markets, while XGBoost achieves competitive predictive accuracy on average; the trade-offs between SVR and XGBoost are often very small. The data indicate that linear kernel methods provide a robust prediction pipeline, especially when macroeconomic factors (gold, oil, platinum prices, and the USD/ZAR exchange rate) and calendar-based factors are taken into account, and offer a strong framework for predicting daily exchange rate fluctuations. The results of this research provide practitioners (traders, risk managers, and policymakers) with insights into the relative efficiency of the kernel vs. ensemble learning approaches for forecasting the value of emerging-market currencies in the presence of structural volatility. Full article