Search Results (456)

Accounting for geotechnical property variability is crucial in seismic site response analysis. Traditionally, the influence of each geotechnical property on response parameters is assessed independently. However, this approach limits our understanding of the combined effects of multiple properties on ground response parameters. This study presents a novel, explainable machine learning (ML)-based approach to assess the influence of multiple geotechnical property variations on response parameters. Four ML models, namely AdaBoost, Extreme Gradient Boosting (XGBoost), Random Forest Regressor (RFR) and Gradient Boosting Machine (GBM), were developed for predictive models. The input factors were shear-wave velocity, plasticity index, soil thickness, input motion intensity and unit weight of the soils. The response parameters were peak ground acceleration (PGA) and peak ground displacement (PGD). Multiple statistical performance metrics were computed to evaluate the performance of the models. The results show the superior prediction performance of the GBM model with low error rates and high agreement index (AI), Kling–Gupta efficiency (KGE) and coefficient of determination ${(R}^2)$. The output of the GBM model was further analyzed using Shapley Additive exPlanation (SHAP) technique to explain and identify the most significant factors contributing to the predictions. Finally, the model was used to develop user-friendly web-based software to facilitate rapid predictions of PGA and PGD. Full article

In Korea, apple (Malus domestica) is one of the major fruit crops. The area occupied by apple orchards has exhibited a consistent upward trend, increasing from 26,398 hectares in 2003 to 33,313 hectares in 2024, and production reached 460,088 tons in 2024. However, stable apple production is currently threatened by global challenges such as climate change and the decline in rural labor, which hinders timely and efficient orchard management. Under these circumstances, developing automated and data-driven technologies capable of rapidly predicting and responding to apple growth conditions is essential to enhancing management efficiency and ensuring consistent fruit quality and yield stability. In this study, unmanned aerial vehicle (UAV)-based multispectral imagery was acquired and used to analyze time series data. Vegetation indices (VIs) derived from this imagery were then applied to build models predicting fruit diameter and length, which reflect apple size. A total of nine VIs were calculated from the acquired data and utilized as input variables for model development. Based on these variables, four machine learning models—Gaussian process regression (GPR), the K-Nearest Neighbors (KNNs), Random Forest Regression (RFR), and Extreme Gradient Boosting (XGB)—were developed to predict the fruit diameter and length. Both RFR and XGB showed tendencies of overfitting, and although the KNNs demonstrated relatively stable performance (diameter: R² ≥ 0.82, RMSE ≤ 7.61 mm, RE ≤ 12.53%; length: R² ≥ 0.76, RMSE ≤ 8.85 mm, RE ≤ 15.08%), this model failed to follow the prediction line consistently. In contrast, GPR maintained stable performance in both the validation and calibration stages (diameter: R² ≥ 0.79, RMSE ≤ 8.23 mm, RE ≤ 13.56%; length: R² ≥ 0.72, RMSE ≤ 9.48 mm, RE ≤ 16.16%) and followed the prediction line relatively well, indicating that it is the most suitable model for predicting apple size. These results demonstrate that UAV-based multispectral imagery, combined with machine learning techniques, is an effective tool for predicting the size of apples, and it is expected to contribute to orchard management at different growth stages and improve apple productivity in the future. Full article

Sunflowers are one of the most important agricultural crops in the world. Given the high importance of sunflower products in the world market and the scale of their cultivation, the introduction of precision farming technologies into its culture can have a significant economic and environmental effect. This study demonstrated the fundamental possibility of developing a technology for rapid, remote, and non-invasive assessment of sunflower seed moisture to determine the optimal timing for desiccation and harvesting. It has been shown that the moisture content of sunflower seeds can be assessed with high accuracy based on the spectral characteristics of the underside of the inflorescences obtained using a hyperspectral camera in the visible and near-infrared range (VNIR) (from 450 to 950 nm). Random forest regression (RFR) was used to predict sunflower seed moisture. The model performed excellently on the training data (R²_c = 1.00; MAE_c = 0.58; RMSE_c = 0.74, MAPE_c = 1.29) and with a high performance on the testing data (R²_t = 0.98, MAE_t = 2.99, RMSE_t = 3.28, MAPE_t = 12.22). The most significant vegetation indices for determining moisture are CCI, Booch, Datt3, Datt4, LSIRed, modPRI, SR5, TCARI, and TCARI2. Full article

Accurate wildfire prediction and identification of key environmental drivers are critical for effective wildfire management. We propose a spatiotemporally adaptive framework integrating ST-DBSCAN clustering with GTWR-RFR. In this hybrid model, Random Forest captures local nonlinear relationships, while GTWR assigns adaptive spatiotemporal weights to refine predictions. Using historical wildfire records from Hunan Province, China, we first derived wildfire occurrence probabilities via ST-DBSCAN, avoiding the need for artificial non-fire samples. We then benchmarked GTWR-RFR against seven models, finding that our approach achieved the highest accuracy (R² = 0.969; RMSE = 0.1743). The framework effectively captures spatiotemporal heterogeneity and quantifies dynamic impacts of environmental drivers. Key contributing drivers include DEM, GDP, population density, and distance to roads and water bodies. Risk maps reveal that central and southern Hunan are at high risk during winter and early spring. Our approach enhances both predictive performance and interpretability, offering a replicable methodology for data-driven wildfire risk assessment. Full article

Accurate inflation forecasting is of central importance for monetary authorities, governments, and businesses, as it shapes economic decisions and policy responses. While most studies focus on headline inflation, this paper analyses the Harmonised Index of Consumer Prices (HICP) and its 12 subcomponents in the euro area over the period 2000–2023, covering episodes of financial crisis, economic stability, and recent inflationary shocks. We apply a broad set of machine learning and deep learning models, systematically optimized through grid search, and evaluate their performance using the Normalized Mean Absolute Error (NMAE). To complement traditional accuracy measures, we introduce the Forecastability Index (FI) and the Interquartile Range (IQR), which jointly capture both the difficulty and robustness of forecasts. Our results show that RNN and LSTM architectures consistently outperform traditional approaches such as SVR and RFR, particularly in volatile environments. Subcomponents such as Health and Education proved easier to forecast, while Recreation and culture and Restaurants and hotels were among the most challenging. The findings demonstrate that macroeconomic stability enhances forecasting accuracy, whereas crises amplify errors and inter-model dispersion. By highlighting the heterogeneous predictability of inflation subcomponents, this study provides novel insights with strong policy relevance, showing which categories can be forecast with greater confidence and where uncertainty requires more cautious intervention. Full article

Cultivated land (CL) is essential for human survival, as its coordinated utilization plays a crucial role in both food production and ecological protection. In this study, we focus on Aksu, a typical oasis in arid areas of Xinjiang, to explore how to improve the eco-efficiency of cultivated land utilization (ECLU) from the perspective of carbon emissions under different ownership structures. The goal is to provide policy support for the sustainable intensification of CL in Aksu. The super-efficiency slack-based measure (Super-SBM) model was used to calculate the ECLU, while the carbon emissions coefficient method was employed to estimate cultivated land carbon emissions (CLCE). Additionally, the random forest regression (RFR) model was utilized to analyze differences in CLCE between collective and state-owned cultivated lands. Finally, a Geo-detector analysis was conducted to identify driving factors of CLCE. The findings indicate that the overall ECLU values in Aksu initially increased and subsequently decreased over time. During the study period, Kalpin showed the highest ECLU, followed by Wensu and Wushi. The total CLCE in Aksu demonstrated an initial increase followed by a decrease, but the overall trend was growth, from 3.7 t in 2008 to 5.63 t in 2019, on average. It was observed that carbon emissions from state-owned cultivated land were greater than those from collective cultivated land, and carbon emissions from non-food crops were higher than those from food crops. Furthermore, spatial heterogeneity was evident in the CLCE. The single factor detection results showed that the Local_GDP (q = 0.763, representing the explanatory power of the Local_GDP on cultivated land carbon emissions) was identified as the main driver of CLCE in Aksu. The interactive detection results indicated that the Local_GDP and Farmer income (0.839) had stronger effects on CLCE in Aksu than any other two factors. It was also found that ownership of CL directly affects CLCE and indirectly affects the ECLU. In conclusion, it is necessary to formulate corresponding countermeasures for improving the ECLU involving government intervention, as well as cooperation with farmers and other stakeholders, to address these issues effectively within Aksu’s agricultural sector. Full article

This study presents a gradient boosting-based machine learning (ML) approach developed to predict cutting speed and feed rate in band sawing operations. The model was built using a dataset of 1701 experimental samples from three industrially common material types: AISI 304, CK45, and AISI 4140. Each sample was defined by key process parameters, namely, material type, a hardness range of 15–44 HRC, and a diameter range of 100–500 mm, with cutting speed and feed rate as target variables. Five ML models were examined and compared in this study, including linear regression (LR), support vector regression (SVR), random forest regression (RFR), least squares boosting (LSBoost), and extreme gradient boosting (XGBoost). Model training and validation were carried out using five-fold cross-validation. The results show that the XGBoost model offers the highest accuracy. For cutting speed estimation, the performance values of XGBoost are an RMSE of 0.213, an MAE of 0.140, an R² of 0.999, and an MAPE of 0.407%; and for feed rate estimation, an RMSE of 0.259, an MAE of 0.169, an R² of 0.999, and a MAPE of 1.14%. These results indicate that gradient-based ensemble methods capture the nonlinear behavior of cutting parameters more effectively than linear or kernel-driven techniques, providing a practical and robust approach for data-driven optimization in intelligent manufacturing. Full article

As vehicle-centric perception struggles with occlusion and dense traffic, vehicle-infrastructure cooperative perception (VICP) offers a viable route to extend sensing coverage and robustness. This study proposes a feature-level VICP framework that fuses vehicle- and roadside-derived visual features via V2X communication. The model integrates four components: regional feature reconstruction (RFR) for transferring region-specific roadside cues, context-driven channel attention (CDCA) for channel recalibration, uncertainty-weighted fusion (UWF) for confidence-guided weighting, and point sampling voxel fusion (PSVF) for efficient alignment. Evaluated on the DAIR-V2X-C benchmark, our method consistently outperforms state-of-the-art feature-level fusion baselines, achieving improved ${AP}_{3D}$ and ${AP}_{BEV}$ (reported settings: 16.31% and 21.49%, respectively). Ablations show RFR provides the largest single-module gain +3.27% ${AP}_{3D}$ and +3.85% ${AP}_{BEV}$, UWF yields substantial robustness gains, and CDCA offers modest calibration benefits. The framework enhances occlusion handling and cross-view detection while reducing dependence on explicit camera calibration, supporting more generalizable cooperative perception. Full article

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