Search Results (448)

This study presents the deployment of Machine Learning (ML) models on low-cost edge devices (ESP32) for real-time water quality prediction in tilapia aquaculture. A compact monitoring and control system was developed with low-cost sensors to capture key environmental parameters under field conditions in Northern Thailand. Three ML models—Multiple Linear Regression (MLR), Decision Tree Regression (DTR), and Random Forest Regression (RFR)—were evaluated. RFR achieved the highest accuracy (R² > 0.80), while MLR, with moderate performance (R² ≈ 0.65–0.72), was identified as the most practical choice for ESP32 deployment due to its computational efficiency and offline operability. The system integrates sensing, prediction, and actuation, enabling autonomous regulation of dissolved oxygen and pH without constant cloud connectivity. Field validation demonstrated the system’s ability to maintain DO within biologically safe ranges and stabilize pH within an hour, supporting fish health and reducing production risks. These findings underline the potential of Edge AIoT as a scalable solution for small-scale aquaculture in resource-limited contexts. Future work will expand seasonal data coverage, explore federated learning approaches, and include economic assessments to ensure long-term robustness and sustainability. Full article

Land Surface Temperature (LST) is a critical parameter for analyzing urban heat islands, surface–atmosphere interactions, and environmental management. This study enhances the temporal resolution of LST data by leveraging machine learning and deep learning models. A novel methodology was developed using Landsat 8 thermal data and Sentinel-2 multispectral imagery to predict LST at finer temporal intervals in an urban setting. Although Sentinel-2 lacks a thermal band, its high-resolution multispectral data, when integrated with Landsat 8 thermal observations, provide valuable complementary information for LST estimation. Several models were employed for LST prediction, including Random Forest Regression (RFR), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Gated Recurrent Unit (GRU). Model performance was assessed using the coefficient of determination (R²) and Mean Absolute Error (MAE). The CNN model demonstrated the highest predictive capability, achieving an R² of 74.81% and an MAE of 1.588 °C. Feature importance analysis highlighted the role of spectral bands, spectral indices, topographic parameters, and land cover data in capturing the dynamic complexity of LST variations and directional patterns. A refined CNN model, trained with the features exhibiting the highest correlation with the reference LST, achieved an improved R² of 84.48% and an MAE of 1.19 °C. These results underscore the importance of a comprehensive analysis of the factors influencing LST, as well as the need to consider the specific characteristics of the study area. Additionally, a modified TsHARP approach was applied to enhance spatial resolution, though its accuracy remained lower than that of the CNN model. The study was conducted in Tehran, a rapidly urbanizing metropolis facing rising temperatures, heavy traffic congestion, rapid horizontal expansion, and low energy efficiency. The findings contribute to urban environmental management by providing high-temporal-resolution LST data, essential for mitigating urban heat islands and improving climate resilience. Full article

With the advancement of coal mine electrical equipment toward larger scale, higher complexity, and greater intelligence, traditional temperature rise monitoring methods have revealed critical limitations such as intrusive measurement, low spatial resolution, and delayed response. This study proposes a novel cross-media infrared measurement method combined with temperature rise characteristic analysis to overcome these challenges. First, a cross-media measurement principle is introduced, which uses the enclosure surface temperature as a proxy for the internal heat source temperature, thereby enabling non-invasive internal temperature rise measurement. Second, a non-contact, infrared thermography-based array-sensing measurement approach is adopted, facilitating the transition from traditional single-point temperature measurement to full-field thermal mapping with high spatial resolution. Furthermore, a multi-source data perception method is established by integrating infrared thermography with real-time operating current and ambient temperature, significantly enhancing the comprehensiveness and timeliness of thermal state monitoring. A hybrid prediction model combining Support Vector Regression (SVR) and Random Forest Regression (RFR) is developed, which effectively improves the prediction accuracy of the maximum internal temperature—particularly addressing the issue of weak surface temperature features during low heating stages. The experimental results demonstrate that the proposed method achieves high accuracy and stability across varying operating currents, with a root mean square error of 0.741 °C, a mean absolute error of 0.464 °C, and a mean absolute percentage error of 0.802%. This work provides an effective non-contact solution for real-time temperature rise monitoring and risk prevention in coal mine electrical equipment. Full article

Despite successful land reclamation efforts, post-mining areas are still prone to secondary effects of mineral extraction. These effects include surface deformations, damage to infrastructure and buildings, and periodic or permanent changes to surface water resources. This study focused on analyzing a former copper mine in southwest Poland in terms of surface water changes, which may be caused by the restoration of groundwater conditions in the region after mine closure. The main objective of the study was to detect areas with statistically significant changes in surface water between 2015 and 2024, as well as to identify the main factors influencing the observed changes. The methodology integrated open remote sensing datasets from Landsat and Sentinel-1 missions for deriving spectral indices—Modified Normalized Difference Water Index (MNDWI) and Normalized Difference Moisture Index (NDMI), as well as Surface Soil Moisture index (SSM); spatial statistics methods, including Emerging Hot Spot analysis; and regression models—Random Forest Regression (RFR) and Geographically Weighted Regression (GWR). The results obtained indicated a general increase in vegetation water content, a reduction in the extent of surface water, and minor soil moisture changes during the analyzed period. The Emerging Hot Spot analysis revealed a number of new hot spots, indicating regions with statistically significant increases in surface water content in the study area. Out of the investigated regression models, global regression (RFR) outperformed local (GWR) models, with R2 ranging between 74.7% and 87.3% for the studied dependent variables. The most important factors in terms of influence were the distance from groundwater wells, surface topography, vegetation conditions and distance from active mining areas, while surface geology conditions and permeability had the least importance in the regression models. Overall, this study offers a comprehensive framework for integrating multi-source data to support the analysis of environmental changes in post-mining regions. Full article

Cow behavior recognition constitutes a fundamental element of effective cow health monitoring and intelligent farming systems. Within large-scale cow farming environments, several critical challenges persist, including the difficulty in accurately capturing behavioral feature information, substantial variations in multi-scale features, and high inter-class similarity among different cow behaviors. To address these limitations, this study introduces an enhanced target detection algorithm for cow behavior recognition, termed RFR-YOLO, which is developed upon the YOLOv11n framework. A well-structured dataset encompassing nine distinct cow behaviors—namely, lying, standing, walking, eating, drinking, licking, grooming, estrus, and limping—is constructed, comprising a total of 13,224 labeled samples. The proposed algorithm incorporates three major technical improvements: First, an Inverted Dilated Convolution module (Region Semantic Inverted Convolution, RsiConv) is designed and seamlessly integrated with the C3K2 module to form the C3K2_Rsi module, which effectively reduces computational overhead while enhancing feature representation. Second, a Four-branch Multi-scale Dilated Attention mechanism (Four Multi-Scale Dilated Attention, FMSDA) is incorporated into the network architecture, enabling the scale-specific features to align with the corresponding receptive fields, thereby improving the model’s capacity to capture multi-scale characteristics. Third, a Reparameterized Generalized Residual Feature Pyramid Network (Reparameterized Generalized Residual-FPN, RepGRFPN) is introduced as the Neck component, allowing for the features to propagate through differentiated pathways and enabling flexible control over multi-scale feature expression, thereby facilitating efficient feature fusion and mitigating the impact of behavioral similarity. The experimental results demonstrate that RFR-YOLO achieves precision, recall, mAP50, and mAP50:95 values of 95.9%, 91.2%, 94.9%, and 85.2%, respectively, representing performance gains of 5.5%, 5%, 5.6%, and 3.5% over the baseline model. Despite a marginal increase in computational complexity of 1.4G, the algorithm retains a high detection speed of 147.6 frames per second. The proposed RFR-YOLO algorithm significantly improves the accuracy and robustness of target detection in group cow farming scenarios. Full article

This paper examines how smart city technologies can help promote sustainability in China by cutting energy use and carbon footprint, as well as how smart city technologies can help achieve urban sustainability. With the help of Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost) approaches to machine learning (ML), Long Short-Term Memory (LSTM), graph neural networks (GNNs) and SHapley Additive exPlanations (SHAP) value analysis, we have predicted urban energy consumption and have revealed the most powerful emission drivers. The findings indicate that smart grids could decrease energy use by 15 percent and renewable energy integration decreases per capita emissions by about 12 percent. The predictive model’s outstanding performance (R² = 0.996; RMSE = 13.63) confirms the reliability of the predictions. The major contributors to emissions, based on the SHAP analysis, are water heating and urban central heating systems, highlighting the critical significance of upgrading heating systems. Monte Carlo simulations and sensitivity analysis also illustrate that the possibility of optimization of heating infrastructure has the most significant potential of reducing the emissions. These results show that although renewable energy is needed, it is impossible to achieve a high level of de-carbonization without implementing ML-based prediction, smart grids, and building improvements on an integrated basis as part of urban development approaches. Full article

Soil moisture plays a critical role in the global water cycle, the exchange of matter and energy within ecosystems, and the movement of water in plants. Accurate monitoring of soil moisture is essential for drought early warning systems, irrigation decision-making, and crop growth assessment. The use of drone-based multispectral remote sensing technology for estimating the soil moisture content offers advantages such as wide coverage, high accuracy, and efficiency. However, the soil background can often interfere with the accuracy of these estimations. In specific environments, such as areas with strong winds, removing soil background noise may not necessarily enhance the precision of estimates. This study utilizes unmanned aerial vehicle (UAV) multispectral imagery and employs a vegetation index threshold method to remove soil background noise. It systematically analyzes the response relationship between spectral reflectance, spectral indices, and the soil moisture content in the top 0–10 cm layer of alfalfa; constructs K-Nearest Neighbors (KNN), Random Forest Regression (RFR), ridge regression (RR), and XG-Boost inversion models; and comprehensively evaluates model performance. The results indicate the following: (1) The XG-Boost model validation set had the highest R² value (0.812) when spectral reflectance was used as the input variable, which was significantly better than the other models (R² = 0.465 to 0.770), and the RFR model validation set had the highest R² value when the spectral index was used as the input variable (0.632), which was significantly better than the other models (R² = 0.366 to 0.535). (2) After removing soil background noise, the accuracy of the soil moisture estimates for each model did not show significant changes; specifically, the R² value for the XG-Boost model decreased to 0.803 when using spectral reflectance as the input, and the R² value for the RFR model dropped to 0.628 when using spectral indices. (3) Before and after removing the soil background noise, the spectral reflectance can provide more accurate data support for the inversion of the soil moisture content than the spectral index, and the XG-Boost model is the most effective in the inversion of the soil moisture content when using the spectral reflectance as the input variable. The research findings provide both theoretical and technical support for the retrieval of the surface soil moisture content in alfalfa using drone-based multispectral remote sensing. Additionally, they offer evidence that validates large-scale soil moisture remote sensing monitoring. Full article

Soil–structure contacts often govern deformation and stability in foundations and buried infrastructure. Rubber waste is used in soil mixtures to enhance geotechnical performance and promote environmental sustainability. This study investigates the peak and residual shear strength of sand–steel interfaces, where the sand is mixed with recycled rubber. It also develops predictive machine learning (ML) models based on the experimental data. Two silica sands, medium and coarse, were mixed with two rubber gradations; however, Rubber B was included only in limited comparative tests at a fixed content. Ring-shear tests were performed against smooth and rough steel plates under normal stresses of 25 to 200 kPa to capture the full τ–δ response. Nine input variables were considered: median particle size (D₅₀), regularity index (RI), porosity (n), coefficients of uniformity (C_u) and curvature (C_c), rubber content (RC), applied normal stress (σ_n), normalised roughness (R_n), and surface hardness (HD). These variables were used to train multiple linear regression (MLR) and random forest regression (RFR) models. The models were trained and validated on 96 experimental data points derived from ring-shear tests across varied material and loading conditions. The machine learning models facilitated the exploration of complex, non-linear relationships between the input variables and both peak and residual interfacial shear strength. Experimental findings demonstrated that particle size compatibility, rubber content, and surface roughness significantly influence interface behaviour, with optimal conditions varying depending on the surface type. Moderate inclusion of rubber was found to enhance strength under certain conditions, while excessive content could lead to performance reduction. The MLR model demonstrated superior generalisation in predicting peak strength, whereas the RFR model yielded higher accuracy for residual strength. Feature importance analyses from both models identified the most influential parameters governing the shear response at the sand–steel interface. Full article

Computing the temporal variation in clearwater scour depth around abutments is important for bridge foundation design. To reach the equilibrium scour depth at bridge abutments takes a very long time. However, the corresponding times under prototype conditions can yield values significantly greater than the time to reach the design flood peak. Therefore, estimating the temporal variation in scour depth is necessary. This study evaluates multiple machine learning (ML) models to identify the most accurate method for predicting scour depth (Ds) over time using experimental data. The dataset of 3275 records, including flow depth (Y), abutment length (L), channel width (B), velocity (V), time (t), sediment size (d₅₀), and Ds, was used to train and test Linear Regression (LR), Random Forest Regressor (RFR), Support Vector Regression (SVR), Gradient Boosting (GBR), XGBoost, LightGBM, and KNN models. Results demonstrated the superior performance of AI-based models over conventional regression. The RFR model achieved the highest accuracy (R² = 0.9956, Accuracy = 99.73%), followed by KNN and GBR. In contrast, the conventional LR model performed poorly (R² = 0.4547, Accuracy = 57.39%). This study confirms the significant potential of ML, particularly ensemble methods, to provide highly reliable scour predictions, offering a robust tool for enhancing bridge design and safety. Full article

Active vibration control designs for journal bearings have improved rotordynamic stability and led to advancements in adjustable bearing types that enable precise control of bearing geometry. In this study, optimized machine learning (ML) algorithms were modeled and implemented to accurately predict the static performance envelope of a four-pad active journal bearing with features of controlling the radial and tilt positions of pads in real time. ML models developed for the adjustable bearing system help predict its behavior as a function of three key input parameters such as the eccentricity ratio and radial and tilt positions of pads. Four supervised regression models, such as Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and a feedforward Artificial Neural Network (ANN), were chosen for their demonstrated ability to capture complex nonlinear patterns and their robustness against overfitting in such tribological applications. Hyperparameter tuning for each model was performed using the Optuna framework, which applies Bayesian optimization to efficiently determine the best parameter settings. The Optuna-optimized ensemble and neural network models were used to identify the optimal combinations of input variables that maximize the static performance envelope of the active bearing system with geometric adjustments. Full article

The dynamic metabolic landscape underlying goose meat quality deterioration during refrigerated storage remains incompletely elucidated. Here, ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS)-based widely targeted metabolomics was employed to characterize metabolic profiling in refrigerated goose meat. Orthogonal partial least squares discriminant analysis (OPLS-DA) revealed 211 differential metabolites, while random forest regression (RFR) identified 30 candidate biomarkers. Seven metabolites, including xanthine, oxidized glutathione, and inosine 5′-monophosphate, exhibited significant correlations with total volatile basic nitrogen (TVB-N). By integrating potential biomarkers, metabolic pathways involving purines, amino acids, and sugars were identified as underlying mechanisms of goose meat spoilage. Notably, through comprehensive analysis of time-dependent correlations between physicochemical properties and metabolic profiles, a temporal threshold for quality deterioration in refrigerated goose meat was identified as day 5. These findings deepen our understanding of metabolite variations in refrigerated goose meat and provide a basis for optimizing storage protocols. The identified biomarkers may enable rapid detection kits and smart packaging systems for poultry industry applications. Full article

Blood glucose monitoring is crucial for the daily management of diabetic patients. In this study, we developed a differential absorbance and photoplethysmography (PPG)-based non-invasive blood glucose measurement system (NIBGMS) using visible–near-infrared (Vis-NIR) light. Three light-emitting diodes (LEDs) (625 nm, 850 nm, and 940 nm) and three photodetectors (PDs) with different source–detector separation distances were used to detect the differential absorbance of tissues at different depths and PPG signals of the index finger. A spatiotemporal multimodal fused long short-term memory (STMF-LSTM) model was developed to improve the prediction accuracy of blood glucose levels by multimodal fusion of optical spatial information (differential absorbance and PPG signals) and glucose temporal information. The validity of the NIBGMS was preliminarily verified using multilayer perceptron (MLP), support vector regression (SVR), random forest regression (RFR), and extreme gradient boosting (XG Boost) models on datasets collected from 15 non-diabetic subjects and 3 type-2 diabetic subjects, with a total of 805 samples. Additionally, a continuous dataset consisting 272 samples from four non-diabetic subjects was used to validate the developed STMF-LSTM model. The results demonstrate that the STMF-LSTM model indicated improved prediction performance with a root mean square error (RMSE) of 0.811 mmol/L and a percentage of 100% for Parkes error grid analysis (EGA) Zone A and B in 8-fold cross validation. Therefore, the developed NIBGMS and STMF-LSTM model show potential in practical non-invasive blood glucose monitoring. Full article

Drag embedment anchors (DEAs) play a vital role in maintaining the stability and safety of offshore structures, including floating wind turbines, oil rigs, and marine renewable energy systems. Accurate prediction of anchor performance is essential for optimizing mooring system designs, reducing costs, and minimizing risks in challenging marine environments. By leveraging advanced machine learning techniques, this research provides innovative solutions to longstanding challenges in geotechnical engineering, paving the way for more efficient and reliable offshore operations. The findings contribute significantly to developing sustainable marine infrastructure while addressing the growing global demand for renewable energy solutions in coastal and deep-water environments. This current study evaluated tree-based machine learning algorithms, e.g., decision tree regression (DTR) and random forest regression (RFR), to predict the holding capacity and efficiency of DEAs in sand seabed. To train and validate the results of machine learning models, the K-fold cross-validation method, with K = 5, was utilized. Eleven geotechnical and geometric parameters, including sand friction angle (φ), fluke-shank angle (α), and anchor dimensions, were analyzed using 23 model configurations. Results demonstrated that RFR outperformed DTR, achieving the highest accuracy for capacity prediction (R = 0.985, RMSE = 344.577 KN) and for efficiency (R = 0.977, RMSE = 0.821 KN). Key findings revealed that soil strength dominated capacity, while fluke-shank angle critically influenced efficiency. Single-parameter models failed to capture complex soil-anchor interactions, underscoring the necessity of multivariate analysis. The ensemble approach of RFR provided superior generalization across diverse seabed conditions, maintaining errors within ±10% for capacity and ±5% for efficiency. Full article

Timely and accurate monitoring of crop nitrogen (N) status is essential for precision agriculture. UAV-based hyperspectral remote sensing offers high-resolution data for estimating plant nitrogen concentration (PNC), but its cost and complexity limit large-scale application. This study compares the performance of UAV hyperspectral data (S185 sensor) with simulated multispectral data from DJI Phantom 4 Multispectral (P4M), PlanetScope (PS), and Sentinel-2A (S2) in estimating winter wheat PNC. Spectral data were collected across six growth stages over two seasons and resampled to match the spectral characteristics of the three multispectral sensors. Three variable selection strategies (one-dimensional (1D) spectral reflectance, optimized two-dimensional (2D), and three-dimensional (3D) spectral indices) were combined with Random Forest Regression (RFR), Support Vector Machine Regression (SVMR), and Partial Least Squares Regression (PLSR) to build PNC prediction models. Results showed that, while hyperspectral data yielded slightly higher accuracy, optimized multispectral indices, particularly from PS and S2, achieved comparable performance. Among models, SVM and RFR showed consistent effectiveness across strategies. These findings highlight the potential of low-cost multispectral platforms for practical crop N monitoring. Future work should validate these models using real satellite imagery and explore multi-source data fusion with advanced learning algorithms. Full article

To address the problems of traditional methods that rely on destructive sampling, the poor adaptability of fixed equipment, and the susceptibility of single-view angle measurements to occlusions, a non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed. Based on the Structure-from-Motion Multi-View Stereo (SFM-MVS) algorithms, a high-precision three-dimensional point cloud model was reconstructed from multi-view RGB image sequences, and 12 phenotypic parameters, such as plant height, crown width, were accurately extracted. Through regression analyses of plant height, crown width, and crown height, and the R² values were 0.98, 0.99, and 0.99, respectively, the RMSE values were 2.26 mm, 1.74 mm, and 1.69 mm, respectively. On this basis, four biomass prediction models were developed using Adaptive Boosting (AdaBoost), Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), and Random Forest Regression (RFR). The results indicated that the RFR model based on the projected convex hull area, point cloud convex hull surface area, and projected convex hull perimeter performed the best, with an R² of 0.90, an RMSE of 2.63 g, and an RMSEn of 9.53%, indicating that the RFR was able to accurately simulate lettuce biomass. This research achieves three-dimensional reconstruction and accurate biomass prediction of facility lettuce, and provides a portable and lightweight solution for facility crop growth detection. Full article