Related references
Note: Only part of the references are listed.
Article
Engineering, Civil
Peiru Yan et al.
Summary: In this study, an improved beetle antennae search-extreme learning machine (IBAS-ELM) water level prediction model is proposed to accurately predict the water levels in front of pumping stations in open-channel water transfer projects. The model combines the improved beetle antennae search (IBAS) algorithm with extreme learning machine (ELM). Results show that the IBAS-ELM model has higher prediction accuracy compared to other models, with lower MAE, RMSE, and MAPE values and higher NSE values. The model can provide support for the operation of water transfer projects.
JOURNAL OF HYDROLOGY
(2023)
Article
Engineering, Civil
Xiaotong Zhu et al.
Summary: In this study, a hybrid model named CVXS was proposed to forecast the concentrations of Chlorophyll-a and total nitrogen. The model was validated at three hydrological monitoring stations in Hong Kong and compared with other models. The results showed that the CVXS model had the best accuracy in predicting Chlorophyll-a and total nitrogen.
JOURNAL OF HYDROLOGY
(2023)
Article
Engineering, Civil
Huichao Yin et al.
Summary: In this study, a novel prediction method based on the analysis of water level variation anomalies in borehole groups is proposed using the coupled model of long short-time memory (LSTM) and Isolation forest (IForest). The method accurately and timely detects anomalous variations of water level data as possible precursors of water inrush accidents and establishes a set of risk level grading rule. The method demonstrated extraordinary timeliness and high accuracy in predicting water inrush accidents in Xingdong coal mine.
JOURNAL OF HYDROLOGY
(2023)
Article
Environmental Sciences
Shah Fahad et al.
Summary: Variations in rainfall have a negative impact on crop productivity, especially in developing regions. This study presents a deep forecasting model based on an optimized neural network to accurately predict rainfall in Pakistan using 30 years of climate data. The proposed model achieved high prediction accuracy and demonstrated the feasibility of selected variables in precise rainfall forecasting.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Agronomy
Yingjie Lu et al.
Summary: This study established hybrid prediction models based on VMD, EMD, and EEMD combined with BPNN to improve the prediction accuracy of ET0 time series. The results indicated the superiority of the VMD-BPNN model in terms of accuracy and stability. The effectiveness of the VMD method in reducing the non-stationarity of the original daily ET0 data was demonstrated.
AGRICULTURAL WATER MANAGEMENT
(2023)
Article
Thermodynamics
Charan Sekhar et al.
Summary: This paper proposes a novel hybrid strategy for building load prediction, combining bilateral long short-term memory (BiLSTM), convolution neural networks (CNN), and grey wolf optimization (GWO). The strategy is tested on four buildings with distinct characteristics and compared to other cutting-edge technologies. Results demonstrate that the proposed GWO-CNN-BiLSTM technique outperforms standard CNN-LSTM, CNN-BiLSTM, optimized BiLSTM, and traditional LSTM and BiLSTM techniques in terms of accuracy.
Article
Automation & Control Systems
Zihao Zheng et al.
Summary: Reference evapotranspiration can cause significant discrepancies in soil moisture and runoff, leading to uncertainties in drought warning systems. An innovative approach, MVMD-SoFeFilterGRU, is proposed to forecast one-day daily ETo based on Multivariate Variational Mode Decomposition hybridized with Soft Feature Filter and Gated Recurrent Unit.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Yuezhong Wu et al.
Summary: This study proposes a GA-BPNN model by optimizing the initial weights and thresholds of the BPNN model using a genetic algorithm. The valve opening is added as an input variable, along with motor shaft power and speed, to improve the prediction accuracy of the flow rate in a multistage centrifugal pump. The results show that the GA-BPNN model significantly improves the accuracy of flow rate prediction, especially at low flow rates, without the need for flow sensors.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
K. Venkatachalam et al.
Summary: Weather forecasting plays a crucial role in various aspects of modern society, and this study proposes a deep learning model called LSTM and T-LSTM for accurate weather prediction. Evaluation metrics demonstrate the effectiveness and reliability of the T-LSTM method.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yuchen Duan et al.
Summary: The collaboration-based Hybrid GWO-SCA optimizer (cHGWOSCA) is a novel improved GWO that incorporates Sine Cosine Algorithm (SCA) to enhance global exploration. It balances the exploitation using weight-based individual position update and crossover with personal best. Experimental results demonstrate that cHGWOSCA is a high-performing algorithm in global optimization.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Geological
Jian Zhou et al.
Summary: This paper develops six machine learning algorithms optimized by the sparrow search algorithm for specific energy (SE) prediction in roadheader excavation. The results show that cutting depth, uniaxial compressive strength of the rock, and tensile strength of the rock are the most significant input variables for SE prediction.
Article
Engineering, Marine
Chenhua Ni et al.
Summary: This paper provides a brief review of the two typical approaches for predicting wave energy generation: physical models and data-driven models. It proposes a hybrid deep learning model that combines empirical wavelet transform (EWT) and a convolutional neural network (CNN) for wave power prediction. The EWT decomposes wave power observations into sub-bands with high and low frequencies, while the CNN model extracts spatial features from multi-dimensional grid data. The proposed hybrid model outperforms benchmark models based on time-space domain information, indicating its strong potential for wave energy exploitation.
Article
Engineering, Industrial
Pinsheng Duan et al.
Summary: Many studies have examined the impact of the COVID-19 pandemic on construction safety and have found conflicting views on whether it increased or decreased safety performance. However, these studies did not use a comparative time series approach to evaluate the impact. This study focused on comparing the impact of the pandemic on construction safety in China and the United States. Using SciNet, the study found a reduced number of construction accidents during the pandemic, but minimal changes in fatality rates. The study highlights the need for targeted safety measures during crises and helps nations prepare for future pandemics.
Article
Environmental Sciences
Songlin Yang et al.
Summary: Traditional mine water inflow prediction is uncertain due to complex mechanisms and uncertain model parameters. Data-driven models play a key role in predicting water inflow mechanisms without considering physical changes. This study proposes two robust models, the DIFF-TCN and DIFF-LSTM models, for predicting the average daily water inflow.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Energy & Fuels
Zhihua Deng et al.
Summary: In this study, an accurate and efficient degradation prediction method for proton exchange membrane fuel cells (PEMFCs) is proposed, combining extreme learning machine based on auto-encoder (ELM-AE) and fuzzy extension broad learning system (FEBLS). The ELM-AE inherits the fast learning ability of ELM and the dimensionality reduction and feature learning ability of AE. The proposed FEBLS consists of TSK fuzzy subsystems, enhancement layer, and extension layer, and it effectively represents and transforms the power time series of PEMFCs. The results from two different aging datasets show that ELM-AE-FEBLS method has competitive accuracy in predicting the remaining useful life of fuel cells compared to other methods.
Article
Computer Science, Artificial Intelligence
Liling Zeng et al.
Summary: This study proposes an optimal forecast combination framework for agricultural commodity prices forecasting, which integrates decomposition-reconstruction-ensemble methodology with an improved nature-inspired global optimization algorithm. Experimental results demonstrate that the PSO-CS weight assignment approach is superior to other combination approaches, the CGCD approach effectively reduces forecasting computational cost and improves prediction performance, and the Full-PSO-CS model provides the most accurate forecast due to the diversity of individual forecasts.
APPLIED SOFT COMPUTING
(2023)
Article
Biodiversity Conservation
Lingxuan Chen et al.
Summary: With the acceleration of industrialization and urbanization, water pollution in rivers has become increasingly serious, causing ecological and environmental issues. The prediction of river water quality index (WQI) is essential for pollution prevention and management. By combining machine learning with intelligent optimization algorithms, the proposed model accurately predicts WQI and outperforms other algorithms in terms of prediction accuracy.
ECOLOGICAL INDICATORS
(2023)
Article
Thermodynamics
Shuyi Du et al.
Summary: This study develops an autonomous data governance system that combines supervised learning and unsupervised learning for anomaly detection and missing value supplement in coalbed methane (CBM) production data. A data-driven production forecasting model is also designed to tackle different production curve patterns of CBM wells.
Article
Thermodynamics
Yue Yu et al.
Summary: Solar energy plays an irreplaceable role in the global energy transition due to its abundance and accessibility. However, effectively managing solar energy on the grid becomes challenging due to its volatile and intermittent nature, requiring an accurate and stable forecasting system. In this study, a hybrid forecasting system has been developed, incorporating feature extraction, pattern recognition, and optimization modules, to address the challenges caused by intermittency and the lack of weather information.
ENERGY CONVERSION AND MANAGEMENT
(2023)
Article
Environmental Studies
Xiaowei Fu et al.
Summary: This paper presents a methodology for assessing the surface water quality and long-term trends of China's seven major basins. The study reveals significant improvement in water quality over the past 15 years and weekly water quality changes. It also highlights the spatial heterogeneity of water quality between southern and northern rivers in China.
ENVIRONMENTAL IMPACT ASSESSMENT REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Yao Ji et al.
Summary: This study proposes an Intuitionistic Fuzzy-Combined Weight-Mahalanobis distance-Multiple Attribute Decision Making (IFCM-MADM) method to solve the comprehensive evaluation problem of pollution control technologies for non-point sources in the planting industry. The method integrates intuitionistic fuzzy theory, AHP and entropy weighting method, and Mahalanobis distance to improve the traditional TOPSIS method in quantitative data processing, index weight calculation, and relative closeness calculation. The results show that the IFCM-MADM method provides a scientific evaluation and selection of technologies with high comprehensive benefits, and it overcomes the limitations of objective and subjective weighting methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Green & Sustainable Science & Technology
Xiaoman Zhao et al.
Summary: Digitalization has become the core engine of a scientific and technological revolution and a new phase of industrial transformation. The study empirically tested the impact of the digitalization of government environmental governance (DGEG) on environmental pollution and its spatial spillover effect. The findings indicate that DGEG can reduce environmental pollution locally and improve the environmental quality of surrounding areas through spatial spillover effects, showcasing a clear digital pollution reduction dividend.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Engineering, Mechanical
Xiaobing Ma et al.
Summary: This paper proposes a new prognosis framework for machinery fault diagnosis based on original condition monitoring signals. The framework uses Box-Cox transformation to extract a series of degradation features and utilizes N-BEATS algorithm for time-series prediction. A parameter-based transfer learning method is also introduced to reduce computation complexity. The future original signals of machinery are reconstructed through inverse Box-Cox transformation, and a new failure criterion suitable for decision-level fault prognosis is defined.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Geosciences, Multidisciplinary
Xiaoying Zhang et al.
Summary: In this study, artificial intelligence techniques were used to develop time convolutional network (TCN) and long short-term memory (LSTM) models for predicting groundwater levels with different leading periods in coastal aquifers. The TCN-based models showed higher prediction accuracy and lower root mean square error (RMSE) values in a shorter time compared to the LSTM-based model. Both models demonstrated the ability to learn complex patterns from historical data with different leading periods, making them valuable tools for localized groundwater level prediction in subsurface environments.
HYDROLOGY AND EARTH SYSTEM SCIENCES
(2023)
Article
Energy & Fuels
Dongchuan Yang et al.
Summary: Short-term load forecasting is crucial for power demand-side management and system planning. This study proposes a new learning approach which significantly improves the accuracy of load forecasting, showing potential in interval load forecasting.
Article
Thermodynamics
Lei Hua et al.
Summary: In this paper, a wind speed prediction method based on VMD, PLS, IASO, and ELM is proposed. By comparing the results between the proposed model and other benchmark models, it is found that the proposed model demonstrates superior performance in short-term wind speed prediction.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Environmental Sciences
Chenguang Song et al.
Summary: This paper proposes a novel water quality prediction model that integrates synchrosqueezed wavelet transform and deep extreme learning machine optimized with the sparrow search algorithm. The model outperforms similar models in terms of predictive performance by reducing noise and optimizing hyperparameters.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Multidisciplinary
He Jian et al.
Summary: This article introduces a data acquisition system based on spectral analysis method and a classification algorithm using Principal Component Analysis, Particle Swarm Optimization, and Extreme Learning Machine for the color depth classification of sunglass lenses. The feasibility and effectiveness of this algorithm are proven through experiments.
Article
Engineering, Civil
Yongtao Wang et al.
Summary: This study proposes an innovative approach for medium and long-term precipitation prediction using wavelet decomposition, optimization algorithms, and neural networks. The model demonstrates high prediction accuracy and low error rates, allowing for effective guidance in flood control, drought relief, and water resource allocation.
WATER RESOURCES MANAGEMENT
(2022)
Article
Hospitality, Leisure, Sport & Tourism
Chengyuan Zhang et al.
Summary: The study systematically investigated the forecasting performance of decomposition methods in tourism demand, concluding that all decomposition methods generally outperform benchmarks at all horizons, with variational mode decomposition consistently providing the best forecasts.
JOURNAL OF TRAVEL RESEARCH
(2022)
Article
Chemistry, Applied
Hadeel Alsolai et al.
Summary: Activated carbon is a highly effective adsorbent for organic chemicals in wastewater treatment. This paper presents a hybrid technique of Voting-Based Extreme Learning Machine with sine cosine algorithm (VELM-SCA) to improve the accuracy of water quality status classification.
ADSORPTION SCIENCE & TECHNOLOGY
(2022)
Article
Thermodynamics
Feng Gao et al.
Summary: Accurate carbon price forecasting is crucial for policy-makers and market participants. Previous studies have focused solely on point-valued forecasting, neglecting the importance of interval carbon price forecasting. This study proposes a novel interval decomposition ensemble model based on MVMD and iMLP optimized by Jaya algorithm to accurately predict interval carbon price. Experimental results demonstrate that the proposed model outperforms benchmark models, with average values of U-I and ARVI of 0.3003 and 0.0569, respectively, in two datasets. Overall, the proposed model serves as an effective tool for future interval carbon price forecasting.
Article
Thermodynamics
Xiang Chen et al.
Summary: In this paper, an online photovoltaic (PV) power prediction model is proposed based on chaotic characteristic analysis, improved particle swarm optimization (PSO), and kernel-based extreme learning machine (KELM). The proposed method includes data pre-processing, offline parameters extraction, and online prediction, aiming to improve the prediction accuracy.
Article
Environmental Sciences
Jin-Won Yu et al.
Summary: Water quality forecasting is crucial for public health protection and water resources management. This paper proposes a novel hybrid model that combines data decomposition, fuzzy C-means clustering, and bidirectional gated recurrent unit. The model is evaluated using water quality data from Poyang Lake, China and shows highly accurate results, outperforming other models.
ENVIRONMENTAL POLLUTION
(2022)
Article
Engineering, Civil
Lei Chen et al.
Summary: Short-term water demand forecast is crucial for urban water supply management. This study proposes a new framework, including a data preprocessing method S-H-ESD and a forecasting model Conv1D-GRU. Experimental results show that the S-H-ESD method effectively handles abnormal values and significantly improves the accuracy of the forecast. Moreover, the Conv1D-GRU model performs better in forecast accuracy and data features extraction compared to other models.
JOURNAL OF HYDROLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Tongfei Lao et al.
Summary: Reasonable prediction of natural gas consumption and production in China is important for policy-making. This paper proposes a novel discrete fractional nonlinear grey Bernoulli model to study natural gas consumption and production in China, and demonstrates its feasibility and effectiveness compared to other models.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2022)
Article
Engineering, Civil
R. Sarma et al.
Summary: This study compares the accuracy of five commonly used data-driven models for forecasting declining groundwater levels in three monitoring wells in Delhi, India. The results show that the Multi-Layer Perceptron model is more accurate in forecasting than the other models. The study also predicts further decline in groundwater levels for 2025 if the current situation continues. Such research helps determine appropriate models for regions with limited data and aids policymakers in identifying areas that require immediate attention in groundwater management.
WATER RESOURCES MANAGEMENT
(2022)
Article
Environmental Sciences
Zhizhou Yang et al.
Summary: Urban water quality is deteriorating due to lack of monitoring data and complexity of urban water systems. The integration of different methods and models, supported by multi-remote sensing data, provides a better understanding of the mechanisms and dynamics of water quality changes. The developed integrated method successfully predicts urban water quality and suggests possible driving factors for deterioration.
Article
Geosciences, Multidisciplinary
Eric Ofori-Ntow Jnr et al.
Summary: Solar energy is a highly promising and regular source of sustainable energy. This study proposes a new stacked generalization methodology for predicting long-term photovoltaic power, showing superiority over other standalone methods in terms of accuracy. By comparing statistical indicators, the proposed method achieves lower errors and higher accuracy in forecasting photovoltaic power.
NATURAL RESOURCES RESEARCH
(2022)
Article
Environmental Sciences
Guoyu Xu et al.
Summary: This study developed a machine learning method and applied it to predict water quality in a karst watershed, revealing potential factors influencing water quality impairments. The research findings are important for decision-making in water quality restoration projects and bridging the science:policy gap.
ENVIRONMENTAL RESEARCH
(2022)
Article
Environmental Sciences
Salim Heddam et al.
Summary: This study evaluates the usefulness and effectiveness of four machine learning models for modelling cyanobacteria blue-green algae (CBGA) in two rivers in the USA. The results show that the random forest regression model has the best predictive accuracy, while the other models perform poorly. Preprocessing the models using signal decomposition methods significantly improves their performance.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Civil
Shaokun He et al.
Summary: This study develops LSTM models for ensemble streamflow predictions (ESPs) and demonstrates their application in cascade reservoir operation. The ESP-based operation contributes to additional hydropower generation and slight improvement in water supply, addressing water-energy shortage issues.
JOURNAL OF HYDROLOGY
(2022)
Article
Engineering, Civil
Peng Mei et al.
Summary: Accurately predicting the quality of raw water is of great significance for the operation and management of waterworks. In this study, a CGA model was proposed to predict the turbidity and CODcr of raw water with light industrial-agricultural pollution, based on long-term water quality data. The CGA model, which combines CNN, GRU, and attention layers, outperforms individual LSTM and GRU models. The study findings also indicate a gradual decline in the overall raw water quality due to local industrial-agricultural pollution.
JOURNAL OF HYDROLOGY
(2022)
Article
Construction & Building Technology
Yiman Li et al.
Summary: A hybrid model for predicting AQI is proposed in this paper, which combines TVFEMD decomposition, sample entropy, GWO algorithm, etc., achieving good prediction results compared to benchmark models.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Mathematics
Chien-Chih Wang et al.
Summary: Demand forecasting is crucial for a company's operating costs and can help reduce unnecessary waste. This study proposes an error compensation mechanism using the I-MR control chart to enhance prediction accuracy. The results show that the proposed mechanism can improve the accuracy of forecasting.
Article
Agronomy
Chin-Hung Kuan et al.
Summary: This study proposes a marriage in honey bees optimization/support vector regression (MBO/SVR) model to minimize the effects of highly volatile data and enhance prediction accuracy. The results show that the MBO/SVR model performs better than other models in predicting long-term agricultural output, with lower errors and higher directional symmetry.
Article
Agriculture, Multidisciplinary
Yue Jia et al.
Summary: By using the SSA-ELM model, accurate estimation of evapotranspiration for spring maize with film-mulching is achievable. The SSA-ELM model provides higher accuracy in estimating ET during different growth periods compared to other models.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Environmental Sciences
Wenqi Wu et al.
Summary: This study investigates the impact of internet public participation on environmental protection and finds that it can effectively reduce industrial wastewater discharge, while the government plays an important intermediary role in environmental pollutant emissions. In terms of regional differences, internet public participation has significantly reduced the discharge of industrial sulfur dioxide, industrial wastewater, and industrial solid waste in the east.
ENVIRONMENTAL SCIENCE & POLICY
(2022)
Article
Engineering, Civil
Hang Wan et al.
Summary: This study developed a novel deep learning model, SOD-VGG-LSTM, to improve the accuracy of water quality prediction with non-point source pollution. The model outperformed traditional methods, achieving the highest accuracy in extreme value prediction and demonstrating superior computational performance.
JOURNAL OF HYDROLOGY
(2022)
Article
Engineering, Environmental
Lin Peng et al.
Summary: This study introduces a deep learning model using transfer learning framework to improve the accuracy of long-term water quality prediction in data-constrained scenarios.
Article
Construction & Building Technology
Ji-yu Feng et al.
Summary: This paper presents a novel online loader payload prediction method based on a multi-stage progressive model. The method utilizes a dynamic model, optimized least squares method, and back propagation neural network to accurately predict the load of a loader in real time. Experimental results demonstrate that the method performs well in terms of accuracy, robustness, portability, and fault tolerance.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Agriculture, Multidisciplinary
Ruiqin Ma et al.
Summary: This study used bio-sensing and modeling evaluation to accurately perceive and acquire key parameters by continuously monitoring the transportation environment and dynamically sensing the physiological conditions of meat sheep. It constructed a stress assessment method and a prediction model for transportation stress, and ultimately improved the reliability and quality control of meat sheep transportation.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Environmental Sciences
Chunlei Ji et al.
Summary: With the rapid development of the economy, air pollution has become increasingly severe, causing significant negative impacts on human health and urban ecosystems. This study proposes a dual-scale ensemble learning framework for complex Air Quality Index (AQI) time series prediction. By decomposing and reconstructing the AQI series using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Sample Entropy (SE), the difficulty of direct modeling is reduced. High-frequency components are predicted using Long Short-Term Memory (LSTM) neural network, while low-frequency items are predicted using Regularized Extreme Learning Machine (RELM). The hyper-parameters of the RELM and LSTM models are optimized using an improved Whale Optimization Algorithm (WOA). The proposed hybrid prediction model effectively improves the accuracy of AQI prediction, which is of great significance to the sustainable development of cities.
ENVIRONMENTAL RESEARCH
(2022)
Article
Mathematical & Computational Biology
Sungwon Kim et al.
Summary: This study investigated the efficiency of three standalone models and double-stage synthesis models in predicting BOD5 concentration, showing that the double-stage synthesis models were not always superior to standalone models. Wavelet-SVR demonstrated excellent performance in predicting BOD5 concentration at two observation stations, showcasing it as the most superior model in the study.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Environmental Sciences
Mohammad Zounemat-Kermani et al.
Summary: This paper evaluates the performance of the OS-ELM model in predicting daily turbidity values in Brandywine Creek, Pennsylvania. The OS-ELM model is found to be superior to other models, improving the accuracy of predicted values.
WATER AND ENVIRONMENT JOURNAL
(2021)
Article
Thermodynamics
Lei Yao et al.
Summary: This study proposes an intelligent fault diagnosis method based on support vector machine for Lithium-ion batteries. It includes denoising, modification of covariance matrix to reduce current fluctuation influence, and optimization of SVM parameters through grid search method to achieve high accuracy and timeliness.
Article
Engineering, Civil
Tonglin Fu et al.
Summary: The study proposed a novel hybrid estimation approach to estimate monthly evapotranspiration (ET) using historical ET time series in the southeastern margins of the Tengger Desert, China. The hybrid model based on variational mode decomposition (VMD), grey wolf optimizer (GWO), and support vector machine (SVM) achieved superior computational performance compared to other methods, with an increase in Nash-Sutcliffe coefficient of efficiency (NSCE) and decrease in mean absolute percentage error (MAPE) during testing. The hybrid VMD-GWO-SVM model is suggested as the best choice for estimating ET in the absence of regional meteorological monitoring.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Civil
Zongjun Wu et al.
Summary: This study proposed three hybrid models integrating ELM with three biological heuristic algorithms for predicting ET0, and found that the PSO-ELM model performed the best in accurately estimating daily ET0 in different climatic zones of China.
JOURNAL OF HYDROLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Rana Muhammad Adnan et al.
Summary: The proposed ELM-PSOGWO method for monthly runoff prediction in the Mangla watershed in northern Pakistan outperformed standalone methods and other hybrid methods, with the addition of precipitation as input improving prediction accuracy. The results suggest the potential of ELM-PSOGWO model to be recommended for monthly runoff prediction.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Green & Sustainable Science & Technology
Meysam Alizamir et al.
Summary: In this study, different models were developed to predict the daily chlorophyll-a concentration in river and lake ecosystems, with the Bat-ELM model showing the most robust performance. The results indicated that periodicity is the most influential parameter affecting the daily chlorophyll-a concentration.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Engineering, Multidisciplinary
Khandaker Noman et al.
Summary: This paper presents a PE calculation method based on tunable Q factor wavelet transform, which quantifies the health status of bearings by separating the fundamental signal component of bearing signals using an oscillation-based approach. Experimental results demonstrate that this oscillation-based PE method provides better performance in dynamic bearing health monitoring compared to traditional PE application.
Article
Engineering, Geological
Zening Zhao et al.
Summary: This study proposes a novel soil liquefaction potential evaluation system combining CPT and Vs measurements, using the machine learning model PSO-KELM to assess soil liquefaction potential, and develops a new probabilistic model to improve prediction accuracy.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2021)
Article
Water Resources
Saber Kouadri et al.
Summary: Groundwater quality appraisal is essential for safe drinking water sources, and the study utilized 8 artificial intelligence algorithms to predict water quality index in Illizi region, southeast Algeria. Key drivers influencing WQI were identified as total dissolved solids (TDS) and total hardness (TH), with different input combinations and analysis strategies impacting time consumption and error rates in WQI computation.
APPLIED WATER SCIENCE
(2021)
Article
Environmental Sciences
Chester G. Scotch et al.
Summary: The study utilized thermal methods, Darcy's law, and electrical resistivity evaluations to improve understanding of flow and transport processes in low permeability, low-flow coastal streams. The seasonal-trend decomposition using Loess (STL) method was tested and validated as a means to differentiate between advection and conduction. Results showed that conduction and diffusion are dominant processes of heat and solute transfer in fine-sediment streambeds, providing insights into groundwater-stream interaction and water resources in semiarid coastal areas.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Thermodynamics
Qing Li et al.
Summary: The study proposed a similar day-based ultrashort-term multi-step ahead prediction model of photovoltaic power, which combines various optimization methods and algorithms. Experimental results demonstrated that the model has high accuracy in multi-step prediction, strong intelligence capabilities, and can be easily applied and popularized in practical projects.
Article
Environmental Sciences
Chenguang Song et al.
Summary: A water quality evaluation model based on KELM and optimized with SSA in the Luoyang River Basin outperformed other benchmark models, showing fast learning speed and good generalization performance. The hybrid model can successfully overcome nonstationarity, randomness, and nonlinearity in water quality data and provide valuable insights for water environment protection and management planning in the basin.
ENVIRONMENTAL EARTH SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Gang Shi et al.
Summary: This study proposes a novel hybrid multi-step prediction model based on VMD-EWT-LSTM, which accurately predicts the cutterhead torque of shield tunneling machine in multiple time steps and demonstrates higher accuracy compared to other methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Environmental
Jagadeesh Anmala et al.
Summary: The study investigates the prediction of stream water quality parameters using decision trees, with the quantitative prediction of water quality parameters in the Upper Green River watershed. Multivariate statistical techniques, including artificial neural networks, have been used to gain a deeper understanding of stream water quality status.
WATER ENVIRONMENT RESEARCH
(2021)
Article
Water Resources
Senlin Zhu et al.
WATER QUALITY RESEARCH JOURNAL OF CANADA
(2020)
Article
Environmental Sciences
Ozgur Kisi et al.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2020)
Article
Water Resources
Jian Jin et al.
HYDROLOGICAL SCIENCES JOURNAL
(2020)
Article
Engineering, Chemical
Narjes Nabipour et al.
Article
Computer Science, Artificial Intelligence
Pei Du et al.
APPLIED SOFT COMPUTING
(2020)
Article
Engineering, Civil
S. Abba et al.
JOURNAL OF HYDROLOGY
(2020)
Article
Engineering, Civil
J. L. Zhang et al.
JOURNAL OF HYDROLOGY
(2020)
Article
Engineering, Geological
Han-Lin Wang et al.
ENGINEERING GEOLOGY
(2020)
Article
Computer Science, Information Systems
Jian Yin et al.
INFORMATION PROCESSING & MANAGEMENT
(2020)
Article
Engineering, Civil
Jingran Liu et al.
JOURNAL OF HYDROLOGY
(2020)
Article
Environmental Sciences
Jingzhe Wang et al.
ENVIRONMENTAL POLLUTION
(2020)
Article
Agricultural Engineering
Weijian Cao et al.
AQUACULTURAL ENGINEERING
(2019)
Article
Geography, Physical
Kyle T. Peterson et al.
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING
(2019)
Article
Thermodynamics
Shaoqian Pei et al.
ENERGY CONVERSION AND MANAGEMENT
(2019)
Review
Engineering, Civil
Tuo Xie et al.
JOURNAL OF HYDROLOGY
(2019)
Article
Engineering, Environmental
Yanyang Zhang et al.
Article
Engineering, Civil
Wei Fang et al.
JOURNAL OF HYDROLOGY
(2019)
Article
Engineering, Multidisciplinary
Shengxiang Huang et al.
Article
Environmental Sciences
Elham Fijani et al.
SCIENCE OF THE TOTAL ENVIRONMENT
(2019)
Article
Multidisciplinary Sciences
Mohamed Djerioui et al.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2019)
Article
Engineering, Environmental
Rahim Barzegar et al.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2018)
Article
Automation & Control Systems
Xi Meng et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2018)
Article
Engineering, Civil
Qiao-Feng Tan et al.
JOURNAL OF HYDROLOGY
(2018)
Article
Engineering, Mechanical
Dong Wang et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Ke Zeng et al.
Article
Environmental Sciences
Salim Heddam et al.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2017)
Article
Biodiversity Conservation
Dong Liu et al.
ECOLOGICAL INDICATORS
(2017)
Review
Multidisciplinary Sciences
Zoubin Ghahramani
Article
Engineering, Mechanical
Ruqiang Yan et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2012)
Article
Multidisciplinary Sciences
C. J. Voeroesmarty et al.
