Search Results (1,530)

Accurately estimating village-level winter wheat yield in coastal saline–alkali farmland is challenging because this region has strong spatial differences and multiple environmental stresses. In this study, Huanghua City, Hebei Province, was selected as a typical coastal saline–alkali area. Sentinel-2 images, climate factors, and topographic variables, including elevation, topographic wetness index, distance to the coastline, and distance to water systems, were combined to build a phenology-guided feature set for winter wheat yield prediction in coastal areas. The results showed that Phenology-Guided Feature Integration XGBoost achieved an R² of 0.6382 and an RMSE of 450.15 kg/ha, which was slightly better than Gradient Boosting (R² = 0.6256) and Random Forest (R² = 0.6098), and clearly better than SVR (R² = 0.4792), Ridge regression (R² = 0.4582), and a single Decision Tree (R² = 0.3088). Then, a three-stage branch was designed to identify the main drivers of SI, NDVI, and winter wheat yield at different stages, helping explain how environmental constraints and vegetation responses jointly affect final yield. The Three-Stage Fusion XGBoost Model achieved an R² of 0.6439, an RMSE of 446.24 kg/ha, and an MAE of 363.38 kg/ha, showing a slight improvement in prediction accuracy. SHAP analysis showed that SI, distance-related factors, elevation, TWI, and NDVI were important drivers of winter wheat yield variation. Spatial prediction results showed higher winter wheat yield in inland areas (5145 kg/ha) and lower yield in coastal areas (4198 kg/ha). This framework supports village-scale winter wheat yield prediction in coastal saline–alkali farmland and improves model interpretability. Full article

Cadmium (Cd) contamination in soil poses a serious threat to crop quality. Biochar is widely regarded as an effective amendment that can reduce Cd bioavailability and limit Cd uptake by crops. However, studies on the rapid and nondestructive evaluation of crop physiological responses under biochar-mediated alleviation of Cd stress remain insufficient. Spectral modeling methods can enable rapid and nondestructive monitoring of crop physiological status. In this preliminary experiment, Zhengdan 958 maize seedlings grown in Cd-contaminated soil were subjected to five biochar application rates: 0, 10, 30, 50, and 70 g/pot, designated as CK, A1, A3, A5, and A7, respectively. The study established a non-destructive spectral detection model for relative chlorophyll content expressed as SPAD values of maize leaves to achieve spectral inversion of leaf physiological information. The alleviating effect of biochar on Cd stress was evaluated by analyzing SPAD values and Cd accumulation in roots, stems, and leaves. The original spectral data underwent preprocessing steps including multivariate scattering correction, standard normal variable transformation, normalization, trend removal, first-order derivative transformation, and second-order derivative transformation. The effectiveness of different preprocessing methods was compared using partial least squares regression. Feature bands were identified via Pearson correlation analysis, and support vector regression models were established based on genetic algorithm (GA), particle swarm optimization (PSO), and grid search optimization. The results demonstrated that biochar application significantly increased the SPAD values of corn leaves (r = 0.879) and reduced the proportion of bioavailable Cd in soil, with the A7 treatment showing the most substantial decrease (30%). This indicates that biochar effectively mitigates Cd’s inhibitory effect on chlorophyll synthesis, with the alleviation effect enhancing as biochar application rates increased. Validation of the partial least squares regression model revealed that detrended spectra achieved optimal predictive performance (R²c = 0.94, RMSEC = 0.82, R²p = 0.88, RMSEP = 1.15), leading to the development of three optimized support vector regression models: GA-SVR, PSO-SVR, and GS-SVR. The GA-SVR model with a sigmoid kernel demonstrated the best internal validation performance for predicting SPAD values in maize leaves (R²c = 0.95, RMSEC = 0.24; R²p = 0.75, RMSEP = 1.63). This study provides preliminary theoretical support and technical reference for rapid spectral detection of the physiological status of maize under biochar-mediated mitigation of cadmium stress. Full article

Accurate prediction of surface roughness and cutting forces in milling aluminum alloys remains challenging under data-scarce conditions, where limited experimental data restricts the application of conventional machine learning models. This study addresses this gap by developing a systematic machine learning framework using 108 milling experiments (repeated to 216 tests) on aluminum alloys AA2024-T351 and AA6061-T6. Five primary machining inputs—material type, spindle speed, feed rate, depth of cut, and tool coating—were used. Through feature engineering, 35 interaction features were generated to capture non-linear relationships. A two-step preprocessing strategy was applied: Winsorization at the 5th and 95th percentiles to handle outliers, followed by hybrid scaling combining RobustScaler and MinMaxScaler. Eight machine learning algorithms, including XGBoost, NGBoost, LightGBM, CatBoost, Random Forest, MLP, SVR, and Least Squares Boosting, were developed and hyperparameter-optimized using the Optuna framework with Tree-structured Parzen Estimator. Models were evaluated using R², MAE, and RMSE on a 70/15/15 train–validation–test split. Results demonstrate that XGBoost achieved the highest predictive accuracy for surface roughness (Ra) (R² = 0.99829) and for resultant cutting force (FN) (R² = 0.997). Feed rate was identified as the dominant machining parameter, accounting for 87.7% of the total importance in predicting surface roughness. SHAP analysis confirmed that engineered interaction features—particularly Feed_Coating and Material_Feed—carry strong physical relevance. Additionally, NGBoost enabled probabilistic regression, providing uncertainty estimates. The proposed framework proves highly effective for multi-output prediction in machining under limited data, offering a robust, interpretable, and industry-ready solution for quality control in aluminum alloy milling operations. Full article

Soil salinization severely restricts ecosystem stability and the sustainable development of agricultural productivity. However, current understanding of the spectral–salinity quantitative relationships under the influence of surface cracking still remains limited. To address this gap, this study collected hyperspectral reflectance data (350–2500 nm) from salt-affected soil in both cracked and uncracked surface conditions across the Songnen Plain, and applied fractional-order differentiation (FOD) processing with orders ranging from 0 to 2 and a step size of 0.1. Based on this, 14 types of FOD spectral indices were constructed, incorporating one-dimensional (1D), two-dimensional (2D), and three-dimensional (3D) structures. For each spectral index, the optimal fractional order and corresponding band combinations were first selected through Pearson correlation analysis for pH and EC under both surface conditions; subsequently, feature selection was performed using XGBoost-SHAP explainable analysis among the 14 optimal indices across different dimensions. Furthermore, the predictive performance of four modeling methods, including partial least squares regression (PLSR), Gaussian process regression (GPR), support vector regression (SVR), and random forest regression (RFR), was evaluated. The results showed that FOD transformations significantly enhanced correlations with EC and pH compared to raw reflectance. All prediction models demonstrated higher prediction accuracy under cracked surface conditions than uncracked surface conditions, indicating that desiccation cracks positively modulate spectral signals to enhance salinity information expression. Across different surface states, model performance generally followed the ranking: PLSR > GPR > SVR > RFR, with PLSR achieving the best predictions for EC and pH under cracked surfaces (R² of 0.88 and 0.76, RMSE of 0.29 dS/m and 0.35). This study not only deepens the understanding of fractional-order spectral response mechanisms in saline–alkali soils but also provides methodological support for regional monitoring of soil salinization. Full article

Individual biochemical indicators are insufficient for comprehensive tomato food flavor quality assessment, necessitating multi-parameter models of the core soluble taste matrix. We hypothesized that age stratification of trained sensory assessors would expose differential biochemical variable importance profiles in flavor quality prediction. Accordingly, this study aimed to: (1) construct and compare multiple regression models linking eight biochemical indicators to sensory scores, (2) identify key quality drivers via feature selection, and (3) examine whether age stratification alters the identified sensory drivers. Eight baseline taste indicators across 62 tomato cultivars were evaluated by 30 age-stratified trained sensory panelists (<40 and ≥40 years), using cross-validation to ensure model robustness against small-sample constraints. Partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and Boruta were applied. Random forest achieved the best performance (R² = 0.82). In the full panel model, key variables were fructose, total free amino acids, and vitamin C. After age stratification, the under-40 group retained these variables, whereas the ≥40 group replaced vitamin C with soluble solids. Fructose and total free amino acids were consistently robust drivers, while total acidity remained least important. Deploying the RF–Boruta framework within an age-stratified context provides a structured analytical framework for investigating flavor perception from biochemical data. These findings suggest that fructose and total free amino acids represent highly robust candidate indicators for flavor quality prediction, while age-stratified variances suggest the utility of integrating demographic-specific metrics into precision breeding frameworks. Full article

To eliminate the complex nonlinear mixing relationships among spectral features in near-infrared (NIR) quantitative analysis, and to overcome the limitations of principal component analysis (PCA), which relies solely on covariance structure and linear assumptions and is therefore incapable of effectively handling nonlinear signals, this study employs kernel-independent component analysis (KICA), for nonlinear feature extraction from NIR spectra, combined with a regression model to achieve rapid detection of tannin content in sorghum grains. KICA effectively separates nonlinearly mixed source signals by mapping spectral data into a high-dimensional feature space via the kernel trick. The prediction model built on KICA-extracted features and support vector regression (SVR) consistently delivered the highest test-set prediction accuracy and exhibited the smallest training-to-test R² gap among all evaluated models across repeated random splits, confirming its superiority over PCA-based feature extraction methods and standalone SVR, and its competitive performance relative to ICA-based methods, in both predictive accuracy and generalization capability. Additionally, KICA yielded a lower reconstruction error for the original spectra, indicating its ability to more completely retain the nonlinear informative content of the spectral data. By calculating the mean absolute coefficient of each independent component, it was found that the component with the highest contribution was strongly correlated with the wavelength range near the characteristic absorption peaks of tannin, thereby enhancing the chemical interpretability of the features. On a publicly available corn NIR dataset, the proposed method also achieved superior prediction results compared with benchmark methods, validating its generalization capability across different sample types and quality attributes. This study confirms the feasibility of introducing nonlinear blind source separation via KICA into NIR quantitative analysis, offering a promising approach for spectral feature extraction in the rapid quality assessment of agricultural products with complex matrices. Full article

Accurate high-resolution mapping of soil organic carbon (SOC) is essential for agricultural management and carbon pool assessment in arid lakeside oases, a fragile aquatic-terrestrial transition ecosystem. However, targeted high-precision SOC mapping for typical lakeside oases remains insufficient: existing models have poor adaptability to the highly fragmented oasis landscapes, and fine-resolution SOC spatial products for the representative Bosten Lake oasis are lacking. To address this inadequacy, we integrated Sentinel-2 imagery with topographic, bioclimatic, and spectral environmental covariates and developed four machine learning models (Random Forest, XGBoost, SVR with RBF kernel, Cubist) for SOC prediction, based on 153 topsoil samples (0–20 cm) collected via stratified random sampling in the study area. Model performance was validated through 5-fold cross-validation, the optimal model was selected for 10 m resolution SOC mapping, and dominant driving factors were identified via SHAP analysis. The results showed that SOC content in the study area ranged from 2.37 to 20.63 g·kg⁻¹ (mean = 10.59 g·kg⁻¹), with moderate spatial variability (CV = 34.86%). The Cubist model achieved the highest mapping accuracy (R² = 0.8166, RMSE = 1.5812 g·kg⁻¹, MAE = 0.9247 g·kg⁻¹). The generated high-resolution SOC map clearly revealed a spatial pattern of high values in the eastern well-irrigated cropland and low values in bare and salinized areas at the oasis edge. The Bare Soil Index (BSI), surface roughness, and Normalized Difference Red Edge Index 1 (NDRE1) were the dominant factors controlling SOC spatial distribution. This study mitigates the inadequacy of high-precision SOC mapping in typical arid lakeside oases, and the proposed framework is readily applicable to other fragmented arid landscapes worldwide and provides reliable spatial data and a scalable technical framework for precision agriculture and sustainable land management in similar fragile ecosystems. Full article

Decametric-resolution leaf area index (LAI) is an essential parameter for fine-scale crop growth monitoring and ecosystem modeling. Prior-guided approaches using existing hectometric-resolution LAI products have demonstrated potential in large-scale decametric-resolution LAI estimation. However, within such approaches, the impacts of algorithm selection and band combination on retrieval accuracy remain insufficiently quantified, and the lack of model interpretability limits methodological transferability. To address these challenges, a multi-source data integration (MSDI) framework is developed to systematically assess the sensitivity of prior-guided LAI estimation to retrieval algorithms and spectral bands using Sentinel-2 imagery. In addition, Shapley Additive Explanations (SHAP) is employed to quantify the contributions of individual bands and interpret model behavior. The MSDI LAI was evaluated using ground LAI measurements and compared with Simplified Level 2 Product Prototype Processor (SL2P)-derived LAI and MODIS LAI products. The results indicated that Support Vector Regression (SVR) achieved the best performance in LAI estimation among six machine learning algorithms, likely due to its robustness in modeling nonlinear relationships across different training samples. Band optimization further reduced estimation uncertainty by >24% and increased R² by >44% for SVR-derived LAI estimates. Moreover, MSDI outperformed SL2P, especially at 20 m resolution, with Bias, RMSE, and R² values of 0.26, 0.76, and 0.71, respectively. Meanwhile, MSDI LAI exhibited a similar spatial distribution to MODIS LAI while providing substantially enhanced spatial detail and accuracy. SHAP analysis revealed that red-edge (RE) and shortwave-infrared (SWIR) bands contributed the most to LAI prediction, consistent with their sensitivity to vegetation canopy biophysical properties. Overall, this study highlights the importance of retrieval strategy optimization and model interpretability for improving prior-guided decametric-resolution LAI estimation and offers practical guidance for generating consistent LAI estimations across various scales. Full article

In this study, the milling performance of Inconel 718 alloys produced by forging (WP1), Inconel 718 produced by Selective Laser Melting (SLM) (WP2), and Inconel 718 (WP3) subjected to heat treatment after SLM, under different cooling/lubrication conditions, was evaluated using experimental and artificial intelligence-based approaches. Microstructural analysis showed a homogeneous fine-grained structure in WP1, while WP2 exhibited dendritic features and porosity. Heat treatment improved the microstructural homogeneity of WP3. The hardness values of WP1, WP2, and WP3 were 457 Hv, 303.33 Hv, and 391 Hv, respectively. Milling experiments yielded cutting forces of 336.5–1185.9 N, surface roughness values of 0.22–1.39 µm, and cutting temperatures of 168–658 °C. Compared with dry machining, MQL reduced average cutting force and cutting temperature by 15.5% and 18.65%, respectively, while improving tool wear and surface integrity. Machine learning models including LR, DTR, SVR, and GPR were developed to predict machining responses. GPR provided the highest prediction accuracy, achieving 98.72% for cutting force and 98.99% for cutting temperature. The results demonstrate that manufacturing route and cooling strategy significantly affect the machinability of Inconel 718 and that machine learning techniques can effectively support machining process optimization. Full article

Alternative-fuel engines, such as diesel–compressed natural gas (CNG) dual fuel systems, exhibit increased cycle-to-cycle combustion variability, placing demanding requirements on the accuracy and robustness of prediction models for key combustion parameters. Echo state networks (ESNs), owing to their reservoir computing architecture, can capture nonlinear temporal dynamics, yet their performance is sensitive to reservoir hyperparameters, and the conventional linear readout trained by minimizing mean squared error is susceptible to outliers in noisy observations. This paper proposes a robust ESN framework based on the equilibrium optimizer (EO), termed EO-Robust-ESN, that automatically searches for key model hyperparameters and replaces the conventional squared loss with the $ϵ$-insensitive loss by adopting linear support vector regression (SVR) to train the readout weights, thereby enhancing prediction robustness under noisy conditions. Results on the Mackey–Glass chaotic time series benchmark and a peak in-cylinder pressure series from a diesel–CNG dual fuel engine demonstrate that EO significantly outperforms the genetic algorithm and manual tuning on the Mackey–Glass benchmark, reducing the mean RMSE by approximately 5.6% relative to GA, and achieves comparable accuracy with higher search stability on the $P_{max}$ series. The $ϵ$-insensitive SVR readout further reduces prediction errors, with the MSE on the noisy $P_{max}$ series reduced by approximately 42% compared with the ridge regression readout, suggesting that the proposed framework provides an effective data-driven tool for robust combustion prediction in alternative-fuel engines. Full article

Introduction: Day-to-day fluctuations in heart rate variability (HRV) are widely used to infer autonomic recovery in endurance athletes. However, the extent to which HRV can be forecast one day ahead from readily available external and internal training-load metrics remains unclear. In this study, we evaluated whether machine learning models can predict next-day HRV in competitive cyclists using the two load descriptors most commonly collected in practice: external load quantified as total mechanical work in kilojoules (kJ) and internal load quantified as session rating of perceived exertion (RPE). Methods: Seven male competitive endurance cyclists were monitored daily for sixteen weeks, yielding 590 athlete-days of longitudinal data (seven independent time series). Two machine learning approaches—support vector regression (SVR) and extreme gradient boosting (XGBoost)—were compared with a conventional autoregressive model with exogenous inputs (ARX) as a traditional time-series benchmark. Each model was trained individually per athlete under two predictor scenarios (using past HRV-only or past HRV plus kJ and RPE) and across multiple lag orders (1, 4, 7, 10 and 14 days), with forecasting accuracy expressed as root mean squared error (RMSE). Results: Across all athletes, adding kJ and RPE to the past HRV produced only modest reductions in RMSE relative to HRV-only models. XGBoost achieved the lowest one-step-ahead RMSE at short lag, while all models converged at longer lag orders. Predictive accuracy differed markedly between athletes, reflecting the well-known individual nature of autonomic responses. Conclusions: These findings suggest that the two routinely collected load descriptors examined here—total work (kJ) and RPE—add limited information beyond recent HRV history for forecasting next-day HRV, and that broader contextual variables are likely required to meaningfully improve athlete monitoring. Full article

Unmanned Aerial Vehicle (UAV)-based remote sensing using high-throughput spectral imaging has emerged as an effective non-destructive alternative for large-scale agricultural monitoring. This study evaluates the performance of UAV-based multispectral (MSI) and hyperspectral (HSI) imaging combined with machine learning for estimating in-season nitrogen uptake in spring wheat and canola. Field trials were conducted at irrigated and non-irrigated sites in southern and central Alberta, Canada, respectively, over three growing seasons (2023–2025). Coincident with ground-truth tissue sampling, aerial imagery was collected and processed to train and validate six machine learning models, using ~520 matchups per crop. All models successfully estimated nitrogen uptake across years and locations, although performance varied by sensor and data types. For canola, ANN produced the highest MSI-based accuracy (R² = 0.83, RMSE = 0.5%), whereas HSI data improved prediction performance, with SVR achieving the best results (R² = 0.90, RMSE = 0.40%). In wheat, ANN yielded the highest accuracy for both MSI and HSI data (R² = 0.77, RMSE = 0.54% for MSI; R² = 0.8, RMSE = 0.48% for HSI). These findings demonstrate that UAV-based spectral imaging combined with machine learning provides a reliable and scalable approach for non-destructive nitrogen uptake estimation. Although MSI sensors produced strong predictive performance, the enhanced spectral resolution of HSI data consistently improved estimation accuracy for both crops across varied growing conditions. Full article

Rice brown spot, caused by Bipolaris oryzae, is an important constraint for rice production and requires timely field-scale monitoring. This study evaluated the use of multispectral bands acquired with a UAV-mounted sensor, together with vegetation indices, combined with machine-learning models to estimate rice brown spot severity under field conditions in Lambayeque and Cajamarca, Peru. A total of 37 sampling observations were collected across the vegetative, flowering, and milk-ripening stages. Spectral variables were extracted from UAV orthomosaics and related to field-based disease severity assessments. The strongest correlations with severity were observed for NDRE (r = −0.83) and NPCI (r = 0.77). Three regression models were evaluated using leave-one-out cross-validation (LOOCV): support vector regression with radial basis function kernel (SVR-rbf), support vector regression with linear kernel (SVR-linear), and Random Forest (RF). The SVR-linear model showed the lowest prediction error using NDRE, GREEN, and BLUE as predictors (R²_CV = 0.76; RMSE_CV = 1.31), although its performance was very similar to that of SVR-rbf and RF. These results indicate that UAV-derived multispectral information can support plot-level estimation of rice brown spot severity. However, model performance should be interpreted cautiously because of the small dataset, heterogeneous disease conditions, and moderate prediction accuracy. Further studies with larger and independent datasets are needed to improve robustness and transferability. Full article

Accurate short-term power forecasting is essential for enhancing the efficiency and reliability of energy systems. Nonetheless, conventional techniques for forecasting struggle to detect nonlinear patterns in power time series, as maintaining both stability and accuracy in predictions is tough. This research presents a unique prediction framework that integrates a Multilayer Perceptron (MLP) with survivor-based evolutionary selection strategies. The proposed neural network architecture comprises three hidden layers containing 32, 16, and 8 neurons, respectively. This enables the network to extract features while preserving essential information progressively. A Survivor selection process is employed to enhance the model’s efficacy. This approach retains the optimal training models for subsequent training phases. This technique enhances both predictive accuracy and training efficiency. The amalgamation of Survivor-based selection methodologies with MLP architectures for short-term power generation forecasting is overlooked in the existing literature, although it holds promise. Thus, the proposed model is evaluated against established baselines, including Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR). The results from 30 distinct trials indicate that the proposed MLP (32-16-8) combined with the Survivor approach exhibits the minimal prediction errors, with a mean absolute error (MAE) of 5.3588 and a root mean square error (RMSE) of 10.0216. This strategy is superior in minimizing errors compared to alternative methods. Furthermore, statistical analyses utilizing the Wilcoxon signed-rank test and paired t-test indicate that the proposed method significantly outperforms SVR and RF, while displaying performance comparable to LR. The findings indicate that including a Survivor-based selection mechanism in the MLP training process is an effective and reliable method for forecasting short-term generation power. Full article

In cold hydrogenation processes, bent pipes are highly susceptible to severe localized erosion under hydrogen–silica powder gas–solid two-phase flow. However, high-fidelity numerical simulations are computationally expensive and thus inadequate for rapid assessment under multiple operating conditions. To overcome this limitation, an MI-UK-GPR-based method is proposed for predicting the erosion rate of cold hydrogenation bent pipes. Based on a validated CFD model, six input variables, namely pipe inner diameter, curvature ratio, bend angle, particle mass flow rate, particle size, and particle velocity, were selected. Latin hypercube sampling was employed to generate parameter combinations, and the corresponding maximum erosion rates were obtained through high-fidelity CFD simulations to construct an LHS-CFD sample database. The input variables were then normalized, and the maximum erosion rates were log-transformed. On this basis, an MI-UK-GPR model integrating a mechanistic trend term with a Gaussian process residual term was developed to capture both the global trend of erosion peaks and local nonlinear deviations. Model performance was assessed using leave-one-out cross-validation with MAE, RMSE, MAPE, R², and PICP as evaluation metrics. The results show that, under leave-one-out cross-validation, the proposed MI-UK-GPR model achieved an MAE of 7.10 × 10⁻⁵, an RMSE of 1.29 × 10⁻⁴, a MAPE of 14.53%, an R² of 0.9573, and a PICP of 88.33%, outperforming RSM, SVR, and ordinary GPR in terms of overall prediction performance. In addition, for 50 independent operating conditions, the total computational time of parameterized CFD batch simulations was 5083.51 s, whereas the trained MI-UK-GPR model required only 0.004860 s, corresponding to a speedup of approximately 1.05 × 10⁶. Overall, the proposed method provides a physically consistent, uncertainty-aware, and computationally efficient framework for rapid erosion assessment of cold hydrogenation elbows under multiple operating conditions. Full article