Search Results (2,844)

Accurate stem-volume estimation is fundamental for urban tree inventory and management, but equations developed for forest-grown trees may not be directly suitable for open-grown urban trees with altered stem form and height–diameter relationships. This study developed species-specific, model-assisted stem-volume equations for four dominant urban broad-leaved species in Beijing, China: Quercus mongolica, Sophora japonica, Ginkgo biloba, and Populus davidiana. A total of 2679 standing trees from 535 plots were used for model development and evaluation. The diameter at breast height and ground diameter were field-measured, whereas tree height was obtained as a photogrammetry-derived non-destructive measurement using a handheld tree-measurement superstation. Bivariate DBH–height models, DBH-based linked models, and ground-diameter-based chained models were fitted using weighted nonlinear least squares. Model performance was assessed using validation statistics, 10-fold cross-validation, Monte Carlo uncertainty propagation, and an independent destructive reference dataset of 55 felled trees with section-measured stem volume. Across species, the bivariate models performed best, with mean percent standard errors of 8.68%–16.24%, compared with 9.76%–20.25% for DBH-based linked models and 15.13%–28.56% for ground-diameter-based models. Destructive reference validation showed acceptable agreement within the available validation dataset, with relative RMSE values of 2.30%–5.03% and relative bias values of 0.51%–2.51%. Monte Carlo simulation indicated species-specific propagation of photogrammetric height error, with the lowest average volume fluctuation in Ginkgo biloba. These results suggest that handheld photogrammetry combined with species-specific modelling provides a practical and uncertainty-aware basis for urban stem-volume estimation. This study directly estimates stem volume rather than biomass or carbon stock, and the equations may support future biomass- and carbon-related assessments when combined with appropriate conversion parameters. Full article

Coral sand dissolution may weaken particle strength and compromise the foundation stability of reclaimed reef islands. However, its dissolution mechanisms and associated effects under saline–freshwater conditions remain poorly quantified. This study combined dissolution experiments, inverse hydrogeochemical modeling, statistical analysis, machine learning, and multiscale characterization to identify dominant mechanisms, quantify their contributions, determine key factors, and evaluate alterations in reef island groundwater. Results demonstrated that the dissolution capacity of coral sand (q) ranged from 0.04 to 0.24 mg, increasing with salinity but decreasing with pH and particle size. Coral sand dissolution was mainly controlled by carbonic-acid-mediated dissolution and Ca-Na cation exchange. The cation exchange contribution (p) reached 63–95% under alkaline conditions and increased with pH, salinity, and particle size. Random Forest accurately predicted q and p, with R² values of 0.875 and 0.980, respectively. SHAP analysis identified salinity and pH as the dominant predictors of q and p, respectively. With increasing q, the relative aragonite content decreased, whereas calcite content increased; particle surfaces became rougher, BET specific surface area and porosity increased by 5–28% and 2–10.5%, respectively, and single-particle compressive strength decreased by 70–87%. These findings provide a theoretical basis for assessing stability and reinforcing coral sand foundations on artificial islands. Full article

Land use/land cover (LULC) is one of the core driving factors affecting terrestrial ecosystem carbon storage and exacerbating global warming. As an area with the most intense land–sea interactions, China’s coastal zone has experienced drastic LULC transition and carbon storage fluctuations during the rapid urbanization process. Based on the InVEST model, this study analyzes the spatiotemporal dynamics of LULC and carbon storage (CS) in China’s coastal regions from 2000 to 2024, and simulated multi-scenario carbon storage trajectories for 2050 integrating the SSP-RCP scenarios of the Coupled Model Intercomparison Project Phase 6 (CMIP6). Furthermore, the XGBoost-SHAP and generalized additive models (GAMs) were introduced to deeply analyze the nonlinear characteristics and temporal heterogeneity of the driving mechanisms of CS evolution. The results show the following: (1) During the study period, the LULC structure of the coastal region was dominated by cropland and forestland consistently accounting for over 85%, but exhibited a competitive pattern characterized by the continuous expansion of built-up land severely squeezing ecological spaces. (2) The total regional CS showed an overall phased downward trend, accompanied by increasing fragmentation of high carbon sink areas. Notably, as the core carbon pool, the reduction in forest area was the dominant factor causing regional net carbon losses. (3) CS remained relatively stable under SSP1-2.6, representing a sustainable development pathway with low greenhouse gas emissions. In contrast, SSP2-4.5, SSP3-7.0, and SSP5-8.5 exhibited more pronounced declines in carbon storage by 2050, indicating that SSP1-2.6 is the most favorable pathway for maintaining long-term carbon storage stability in China’s coastal regions. (4) The driving mechanism of CS has undergone a profound shift from being dominated by natural ecological baselines to human activities. Land use intensity (LUI) has emerged as the strongest predictor in the model, and the nonlinear impacts of human activities have grown increasingly complex over time. This study highlights the complex impacts of high-intensity human disturbances on the coastal carbon cycle, providing a scientific basis for formulating differentiated carbon management strategies and adaptive spatial land-use planning oriented toward the “Dual Carbon” goals. Full article

In casting processes, mechanical properties such as hardness are highly sensitive to both chemical composition and process parameters, making parameter design a complex and uncertain task during the embodiment stage of engineering design. Conventional trial-and-error-based approaches are often costly, time-consuming, and impractical in industrial environments. To address these challenges, this study proposes an optimized fuzzy artificial neural network (FANN)-based decision-support approach for hardness-oriented parameter design in a casting process. The developed model uses chemical composition variables, including carbon, silicon, manganese, phosphorus, sulfur, chromium, copper, and tin, together with process parameters such as casting temperature and casting time as inputs, while Brinell hardness is considered as the output. A dataset consisting of 170 experimental casting samples was employed; 128 samples were used for model development and hyperparameter selection, and 42 samples were reserved as an independent final test set. The proposed model was implemented as a scaled direct FANN weighted ensemble, in which fuzzified input variables were used to predict standardized continuous hardness values. A total of 300 FANN configurations were evaluated using five-fold cross-validation, and the five best-performing configurations were combined through RMSE-based weighted ensemble averaging. The final model was compared with Random Forest, Linear Regression, Ridge Regression, and SVR-RBF models using MSE, RMSE, MAE, R², MAPE, normalized RMSE, and ±5% prediction success rate. The results showed that the optimized FANN ensemble achieved the lowest mean RMSE in the full-data five-fold cross-validation analysis, slightly outperforming the Random Forest benchmark. In the independent final test set, Random Forest produced the lowest prediction error, whereas the proposed FANN ensemble remained competitive and achieved the same ±5% prediction success rate as Random Forest, Linear Regression, and Ridge Regression. Furthermore, a target-hardness case study demonstrated that the proposed approach could identify candidate casting conditions very close to a desired hardness level, with the nearest prediction reaching 202.985 HB for a target value of 203 HB. These findings indicate that the proposed FANN-based framework can serve not only as a hardness prediction model but also as a practical fuzzy decision-support tool for target-hardness-oriented parameter design in casting processes. Full article

Soil organic carbon (SOC) plays a critical role in climate regulation, soil fertility, and ecosystem resilience, making its accurate spatial quantification essential for sustainable land management and greenhouse gas (GHG) reporting. However, mapping SOC in heterogeneous agroforestry systems remains challenging due to vegetation cover and landscape complexity. In this study, we develop and evaluate a hybrid bare soil modelling- Digital Soil Mapping supported by ML framework to generate high-resolution soil properties predictions in Mediterranean agroforestry systems (Extremadura, Spain). A dual modelling approach was implemented, combining (i) Bare Soil modelling using Sentinel-2 multi-temporal reflectance composites and (ii) Digital Soil Mapping (DSM) supported by environmental covariates (climate, terrain, vegetation) following the SCORPAN framework. Machine learning models, namely Quantile Regression Forests (QRF) and Extreme Gradient Boosting (XGBoost), were applied and optimised using automated hyperparameter tuning (FLAML). A total of 107 LUCAS topsoil samples and 36 complementary points from the Forest ICP Level I were used for calibration and validation, with a 70/30 train–test split. Results show that Sentinel-2-based modelling can effectively capture SOC spatial variability in bare soil conditions, while DSM improves predictions in vegetated areas. Model performance reached R² values up to 0.76 (QRF, pH) and RMSE as low as 0.03 (XGBoost, N), with uncertainty quantified using the Prediction Interval Ratio (PIR) and performance further supported by RPIQ values up to 3.15. However, prediction accuracy remains sensitive to vegetation structure and sample density. The proposed framework provides a scalable and uncertainty-aware approach for SOC mapping, supporting Tier-3 GHG inventories and emerging Monitoring, Reporting, and Verification (MRV) systems. The results highlight the importance of integrating multi-source datasets and hybrid modelling strategies for reliable SOC estimation in complex landscapes. Full article

With the adoption of more ambitious emission reduction strategies in the shipping industry by the International Maritime Organization and the resulting stricter greenhouse gas emission reduction requirements, it is particularly important for all stakeholders in the global maritime shipping industry to assess the energy efficiency of shipping vessels. Forming predictive capabilities for ship fuel consumption and Carbon Intensity Indicator (CII) annual ratings, for example, are two important works. This article adopted 14 different algorithms in three categories of data-driven approaches, i.e., statistics, machine learning and deep learning, including polynomial regression, ridge regression, adaptive boosting, categorical boosting, elastic net, etc., and built the ship fuel consumption prediction model using ship noon report as the data source. The prediction accuracy and computational efficiency of model training were compared based on metrics of coefficient of determination, mean absolute percentage error and floating-point operations per amount of training data. Cross-validations were performed for all 14 algorithms to analyze their sensitivities to their respective tuned parameters. Comparisons indicated that algorithms of the statistics approach were sensitive to the quality of the data source, compared with the machine learning and the deep learning approaches. The accuracy of the elastic net algorithm was sensitive to the tuned parameters. Two algorithms, light gradient boosting machine and random forest, were selected based on their performances of prediction accuracy and computational efficiency of model training. Then, the selected algorithms were separately combined with long short-term memory as the time-series prediction algorithm to form their respective coupled framework. Both of the coupled frameworks achieved successful prediction of the CII annual discriminant and rating of the studied ships. The prediction accuracy was validated to be sufficient. Full article

Reliable carbon emission data are essential for the effective operation of emissions trading systems (ETS), especially as China’s ETS expands to include energy-intensive industries. This study proposes a hybrid, risk-based anomaly detection framework for high-frequency CO₂ emission data by cross-validating material-based emissions with flue gas-based monitoring data. Under normal operating conditions, the ratio of material-based to flue gas-based emissions is expected to remain within a relatively stable distribution. Potential high-risk periods can therefore be identified when this relationship is distorted or when local temporal patterns deviate from expected behavior. The framework combines Hartigan’s dip test with a window-based Random Forest (RF) classifier, which is suitable for continuous monitoring data that may exhibit temporal dependence. The framework was evaluated using 15-min CO₂ emission data from a cement production facility, with simulations of anomaly magnitude, duration, and mode. Results show that the dip test performs well for long-lasting or strong anomalies, whereas the RF model is more sensitive to subtle, short-term deviations. In the integrated framework, 94.7% of anomalous periods were detected by at least one method and flagged as potential data-quality risks, whereas normal periods were not flagged, supporting its use to prioritize verification efforts. Full article

Forest carbon assessment requires methods that capture the combined effects of stand structure, site conditions, carbon pools, operational emissions, and circular-economy processes. This study aimed to develop and optimize hybrid machine learning models for predicting the gross CO₂e (carbon dioxide equivalent) balance of Polish forest stands using measurable stand- and site-related variables. The research was based on a primary dataset describing forest management in major Polish macroregions in 2020–2024. After data cleaning and preprocessing, multiple machine learning algorithms, including ensemble, boosting, neural, and hybrid models, were trained, validated, and tested. Model performance was assessed using standard regression metrics, overfitting diagnostics, learning curves, and SHAP (Shapley Additive Explanations). Most models achieved high predictive accuracy, with six of ten algorithms reaching R² values above 0.90 on the test set. The reduction in strongly correlated variables helped limit multicollinearity and excessive overlap between predictors and the target variable, supporting a more reliable interpretation of model performance. The CatBoost algorithm achieved the highest predictive performance on the test set (R² = 0.948), while also recording the lowest root mean squared error (RMSE = 152.242). However, the Decision Tree demonstrated the weakest generalization performance (R² = 0.806) on the test set. SHAP analysis identified tree height as the most influential predictor, followed by tree age, number of trees, species composition, and selected habitat features. The novelty of the study lies in integrating hybrid machine learning, interpretable modelling, and circular-economy-related carbon balance components into a single framework for rapid and operational forest carbon assessment in Polish forest stands. Full article

Biomass valorization plays a vital role in achieving carbon neutrality and circular economy frameworks. Owing to its carbon-rich structure, biomass represents a promising feedstock to produce bio-based hydrocarbons via biological and thermochemical pathways. While biological conversion routes have been extensively studied, their deployment at commercial scale is constrained by high capital costs and low product yields. In contrast, thermochemical conversion technologies are increasingly being explored as viable large-scale biomass valorization routes. This review presents a comprehensive assessment of thermochemical pathways, with particular emphasis on hydrothermal liquefaction (HTL). The review identifies hydrothermal liquefaction (HTL) as a strategically advantageous route for wet and heterogeneous biomass valorization, due to simultaneous yields of liquid biocrude, and solid hydrochar. The review emphasizes the application of biocrude upgradation processes like hydrodeoxygenation under biphasic solvent systems using sulfided NiMo and CoMo catalysts. Further, the review also establishes hydrochar as a tunable functional material rather than a mere byproduct for applications in fields of energy production, soil amendment, and heterogeneous catalysis. The review article examines technology readiness levels of different biomass valorization techniques, and suggests that while combustion, anaerobic digestion, torrefaction, and transesterification are commercially mature, HTL and carbon capture utilization and storage (CCUS)-integrated fuel synthesis pathways remain at intermediate readiness. Additionally, the review carries out an in-depth study on artificial intelligence and machine learning (AI and ML) applications in biomass valorization, where it observes that Tree-based ensemble models, particularly Random Forest and XGBoost, show strong performance for several HTL prediction tasks, while Gaussian Process Regression and neural network–Bayesian optimization approaches provide additional advantages for uncertainty estimation and process-level optimization. Finally, the future research opportunities in biomass valorization and AI/ML application in HTL-process optimization have been identified for improving the bio-based fuel production techniques. Full article

Aboveground biomass (AGB) mapping is fundamental to tropical forest carbon monitoring, yet national-scale estimation remains challenging because field plots are sparse and model performance is often sensitive to predictor choice and validation design. This study assessed whether geospatial embeddings improve national AGB mapping in Guyana when combined with environmental and topographic predictors. Predictor selection was undertaken using repeated grouped resampling at the plot-cluster level, and model performance was evaluated across 100 independent train–test repeats. Three final random forest models were compared. The environmental baseline model (Env + SRTM-derived elevation; 8 predictors) achieved a mean R² of 0.179, an RMSE of 148.5 Mg/ha and a relative RMSE of 36.1%. A retained 8-predictor model combining environmental variables with a selected embedding subset (Env + Emb*) improved performance slightly, with a mean R² of 0.189, an RMSE of 147.6 Mg/ha and a relative RMSE of 35.9%. The best performance was obtained with a 22-variable full-stack model combining environmental, topographic and embedding predictors, after all Sentinel-2 predictors had been eliminated during feature selection; this model achieved a mean R² of 0.203, an RMSE of 146.3 Mg/ha and a relative RMSE of 35.5%. Across models, isothermality, a measure of how day-to-night temperature variation compares to annual temperature variation, and precipitation of the coldest quarter were consistently the most influential predictors. Mean ensemble coefficient of variation, representing relative model disagreement, ranged from 0.336 to 0.361. These results indicate that geospatial embeddings provide useful complementary information, but predictive performance remained modest overall, with the best model explaining only about one-fifth of plot-level AGB variance. The resulting maps are therefore best interpreted as broad-scale decision-support products rather than high-precision local estimates of AGB. Full article

Soil microbial carbon use efficiency (CUE) is a pivotal determinant of soil carbon sequestration, yet how forest quality gradients regulate CUE through the interplay of mineral-microbial interactions in subtropical conifer ecosystems remains poorly understood. To address this, we examined the CUE response and its drivers across a forest quality gradient (high-quality to poor-quality stands) in subtropical coniferous forests in China. Soil mineral composition (including soil texture and the contents of Fe₂O₃, CaO, and MgO), physicochemical properties, microbial community diversity, and CUE were quantified. The results showed that CUE decreased by 2.7%, from 0.533 in high-quality stands to 0.519 in low-quality stands. Concurrently, soil organic carbon (SOC), nutrient availability, and microbial diversity exhibited consistent declining trends along the forest quality gradient. The CUE showed a significant positive correlation with SOC (r > 0.90, p < 0.001). Structural equation modeling and random forest revealed that microbial diversity was the most dominant correlated factor of CUE (the total effects on CUE = 0.932), followed by SOC. However, soil minerals indirectly influenced CUE via SOC. These findings highlight microbial diversity as the dominant observed correlate of CUE across forest quality gradients. This study not only deepens the understanding of the microbial mechanisms underlying soil carbon dynamics in subtropical forests but also provides key scientific basis for ecological restoration of poor-quality forests and nature-based climate solutions. Full article

Accurate assessment of carbon storage dynamics and their driving factors is important for ecological sustainability and land management on the Loess Plateau under China’s dual carbon goals. In this study, the InVEST and PLUS models were integrated to evaluate carbon storage changes from 2000 to 2020 and simulate future carbon storage patterns for 2030 under four development scenarios, including natural development (ND), rapid development (RD), cropland protection (CP), and ecological protection (EP). In addition, the XGBoost-SHAP framework was employed to identify the dominant drivers and nonlinear response relationships controlling spatial variation in carbon storage. During 2000–2020, ecosystem carbon storage across the Loess Plateau generally increased, rising from 5.780 Pg to 5.893 Pg. Spatially, carbon storage displayed a pronounced pattern characterized by higher levels in the southeast and lower levels in the northwest, aligning with forest–grassland restoration belts. Scenario simulations showed that EP produced the largest carbon storage gain, with total carbon storage projected to reach 5.962 Pg in 2030. In contrast, RD reduced carbon storage to 5.858 Pg because of intensive construction land expansion. XGBoost-SHAP results identified net primary productivity (NPP) as the most influential factor controlling spatial variation in carbon storage, accounting for 57.3% of the total explanatory importance, whereas soil erosion (SE) exhibited a strong negative effect on carbon storage. Population density (POPD) also exerted a negative effect, whereas gross domestic product (GDP) showed positive contributions in economically developed counties. These findings enhance understanding of the spatial response characteristics of carbon storage under environmental gradients and human disturbance across the Loess Plateau. They further provide scientific support for differentiated ecological management and regionally adapted carbon mitigation planning. Full article

Grain for Green, as an important ecological restoration method, profoundly affects soil nitrogen (N) cycling by altering the soil physicochemical properties and microbial community. Soil nitrogen mineralization is a key process in the terrestrial N cycle. However, the dynamics and underlying driving mechanisms of soil N mineralization rate (Rmin) that respond to afforestation remain unclear. In this study, we selected a typical afforestation sequence in Northeast China, including farmland (F), 21-year-old larch plantation (L21), 42-year-old larch plantation (L42), and natural larch forest (NL). The soil Rmin, associated soil physicochemical properties, and microbial community characteristics were determined to explore the effects of afforestation on soil Rmin and its potential mechanisms of action. The results suggested that soil Rmin was ranked in the order of L42 (0.41 mg kg⁻¹ d⁻¹) > F (0.39 mg kg⁻¹ d⁻¹) > L21 (0.23 mg kg⁻¹ d⁻¹) (p < 0.05) along the afforestation sequence, with no significant difference between L42 and F. Compared to the L42, the NL exhibited significantly lower soil Rmin (0.23 mg kg⁻¹ d⁻¹) (p < 0.05). The changes in soil Rmin during the afforestation were significantly positively related to soil total N (TN) and organic carbon (SOC) concentrations, but significantly negatively related to pH (p < 0.05). Furthermore, the abundances of Proteobacteria and Acidobacteria (bacteria) and Ascomycota (fungi) were also closely correlated with soil Rmin. Structural equation modeling (SEM) analysis further indicated that the afforestation mainly regulated soil Rmin by altering soil temperature (ST) and NH₄⁺-N content. Meanwhile, soil NH₄⁺-N content could also exert a significantly positive effect on soil Rmin by influencing the microbial community. In conclusion, afforestation effectively altered soil Rmin, which was even higher in the plantation than in natural forests. This finding further enhances our understanding of forest restoration and land management practices on soil N cycling in temperate regions. Full article

Soil organic carbon (SOC) is closely linked to soil fertility, agricultural carbon cycling, and the functioning of cotton field ecosystems, and it provides essential information for sustainable soil management. Rapid and accurate SOC estimation is therefore important for assessing carbon sequestration potential and supporting low-carbon agricultural management. This study focused on cotton fields in northern Shawan City and used optical imagery, Synthetic Aperture Radar (SAR) imagery, and 140 ground-collected SOC samples to estimate SOC content with three machine learning models: Random Forest (RF), Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (XGBoost). The Kennard–Stone algorithm was applied to partition the 140 SOC samples into training and validation subsets at a 7:3 ratio, ensuring a more representative distribution of samples. Model performance was evaluated using the coefficient of determination (R²) and root mean square error (RMSE), and SHapley Additive exPlanations (SHAP) was used to interpret feature contributions and SOC spatial variability. The results showed that: (1) optical features performed better than SAR features, while fused optical-SAR features achieved the highest accuracy; (2) XGBoost consistently outperformed RF and LightGBM, with the optimal model achieving R² = 0.726 and RMSE = 1.252% on the validation set; (3) SHAP analysis confirmed the dominant contribution of optical features to SOC estimation; and (4) the predicted SOC distribution showed higher values in the central study area, lower values in the northern and southern parts, and high-value zones mainly along both sides of the Manas River. By comparing optical, SAR, and fused features for SOC estimation in arid-zone cotton fields, this study provides methodological support for rapid SOC monitoring and sustainable soil management, and offers practical guidance for variable-rate fertilization and soil carbon sequestration planning along the Manas River corridor. Full article

Urban canopy height is an essential indicator for characterizing vegetation structure and carbon sequestration, yet satellite LiDAR often lacks sufficient spatial resolution, airborne LiDAR is costly, and SAR has limited sensitivity to vegetation structure. This study proposes a canopy height inversion framework using high-resolution stereo pairs from the Gaofen-7 (GF-7) satellite. A 0.65 m Digital Surface Model (DSM) was generated from GF-7 data, and a relative surface height was derived by differencing the GF-7 DSM from a coarse 30 m DSM reference. Key features were selected via Boruta and Random Forest Recursive Feature Elimination (RF-RFE), and six models—linear, polynomial, support vector machine, backpropagation neural network, XGBoost, and RF—were compared. The results showed that the Boruta feature set improved average R² by 8.2%. Among all models, RF performed best (test set R² = 0.71, RMSE = 1.70 m) and exhibited the strongest resistance to overfitting. Canopy heights within Beijing’s Fifth Ring Road showed an “outer-high, inner-low” pattern: large parks exceeded 30 m, while the Central Business District remained below 3 m. GF-7 stereo pairs enable efficient and cost-effective retrieval of canopy height in fragmented urban green spaces, supporting ecological parameter quantification and urban green-space management. Full article