Article
Environmental Sciences
Chunyue Zhu, Feidong Zheng, Genhua Yan, Xianrui Shi
Summary: Circular drop manholes are commonly used in urban drainage networks for steep catchments. Poor downstream hydraulic transition processes can severely impact water conveyance capacity. This paper defines four hydraulic stages, visualizes three types of transition processes and provides four empirical equations for predicting choking risks in different hydraulic stages.
Article
Computer Science, Artificial Intelligence
Abdulrakeeb M. Al-Ssulami, Randh S. Alsorori, Aqil M. Azmi, Hatim Aboalsamh
Summary: Coronary heart disease (CHD) is a major cause of death globally, with over 382,000 deaths in the USA alone in 2020. Early detection is crucial for reducing mortality rates. This paper proposes a novel approach that uses an augmented dataset and a machine learning model to achieve higher accuracy in CHD prediction. The bagged decision tree algorithm outperforms other models, with an accuracy of 97.1% in the 10-fold cross-validation test.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Victor Acena, Isaac Martin de Diego, Ruben R. Fernandez, Javier M. Moguerza
Summary: This study introduces a new ensemble framework called MOE, which effectively combines stable and unstable machine learning algorithms in constructing predictive models. By using resampling techniques and weighted random bootstrap sampling, the framework constructs slightly overfitted base learners, thereby improving the predictive ability.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Giang Ngo, Rodney Beard, Rohitash Chandra
Summary: In this paper, an evolutionary bagged ensemble learning method is proposed, which enhances the diversity of bags using evolutionary algorithms. The experimental results show that this method outperforms traditional ensemble learning methods on various benchmark datasets.
Article
Chemistry, Physical
Abdulrahman Mohamad Radwan Bulbul, Kaffayatullah Khan, Afnan Nafees, Muhammad Nasir Amin, Waqas Ahmad, Muhammad Usman, Sohaib Nazar, Abdullah Mohammad Abu Arab
Summary: This article analyzes machine learning techniques for forecasting the compressive strength of metakaolin concrete. The authors present different ML predictive models, including decision tree, multilayer perceptron neural network, and random forest. The models take into account various factors that affect the compressive strength of metakaolin concrete, allowing for efficient prediction and investigation. These ML algorithms estimate the mechanical characteristics of metakaolin concrete, promoting sustainability.
Article
Engineering, Environmental
Xudong Hu, Cheng Huang, Hongbo Mei, Han Zhang
Summary: A novel machine learning ensemble model, BRSNBtree, was proposed to predict landslide susceptibility in Zigui County of the Three Gorges Reservoir Area. The results showed that the distance to rivers was the most important factor in predicting landslide susceptibility, and BRSNBtree outperformed other methods in terms of prediction performance.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
Article
Environmental Sciences
S. Zhu, R. Kong, X. Luo, Z. Xu, F. Zhu
Summary: This study proposes an improved landslide susceptibility mapping method (FCM-RF) considering the heterogeneity of environmental features by combining cluster analysis and ensemble learning. The method was applied in Qichun County, China. The results show that the FCM-RF model performs better in landslide susceptibility mapping after considering the heterogeneity factor.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
Ying Liu, Peiyu Wang, Yong Li, Lixia Wen, Xiaochao Deng
Summary: With the use of the random forest algorithm, this study developed an air quality prediction model for Zhangdian District, considering industrial waste gas emissions and meteorological factors. The model showed improved prediction performance and allowed for obtaining daily emission limits through model inversion to maintain good air quality.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Md Nasim Adnan, Ryan H. L. Ip, Michael Bewong, Md Zahidul Islam
Summary: The proposed decision forest algorithm in this paper achieves better balance through effective synchronization of diversity from different sources, leading to significant improvement in accuracy according to empirical evaluations. It is also competitive in terms of complexity and other relevant parameters.
INFORMATION SCIENCES
(2021)
Article
Environmental Sciences
Junnan Xiong, Quan Pang, Weiming Cheng, Nan Wang, Zhiwei Yong
Summary: This study proposed a novel methodological approach for reservoir risk modeling using feature selection method and tree-based ensemble methods. Results showed that the J48-GA based ensemble models had higher learning and predictive capabilities, with J48-GA-RF achieving the highest classification accuracy and prediction AUC value.
GEOCARTO INTERNATIONAL
(2022)
Article
Engineering, Civil
Yahi Takai Eddine, Marouf Nadir, Sehtal Sabah, Abolfazl Jaafari
Summary: This study proposes an ensemble modeling approach that integrates support vector machine with several ensemble learning techniques to predict flow rates in natural rivers of a Mediterranean climate in Algeria. The results indicate that the ensemble models outperform the standalone support vector machine model, with SVM-Dagging model performing the best.
WATER RESOURCES MANAGEMENT
(2023)
Article
Engineering, Civil
S. E. Y. E. D. R. E. Z. A. HASHEMINEJAD, A. Z. A. M. DOLATSHAH, W. U. Y. WAN
Summary: This study investigated the effects of jet-breaker dimensions and the inlet pipe filling ratio on residence time in drop manholes. The optimal conditions were found to significantly reduce the residence time.
JOURNAL OF HYDRAULIC RESEARCH
(2022)
Article
Ecology
Aziz Ebrahimi, Akane O. Abbasi, Jingjing Liang, Douglass F. Jacobs
Summary: This study projected the current and future basal area of black walnut by using machine learning models. The results showed that under future climate scenarios, the basal area of black walnut is likely to increase and the distribution range of the species may shift. The most important variables to predict basal area were mean annual temperature and precipitation, potential evapotranspiration, topology, and human footprint.
FRONTIERS IN FORESTS AND GLOBAL CHANGE
(2022)
Article
Computer Science, Artificial Intelligence
M. A. Ganaie, M. Tanveer, P. N. Suganthan, V. Snasel
Summary: This paper proposes two new approaches known as oblique and rotation double random forests. The oblique double random forests improve the performance of decision trees by using multisurface proximal support vector machine and different regularization techniques. The rotation double random forests enhance diversity and generalization performance by generating different feature space transformations at each node.
Article
Multidisciplinary Sciences
Quynh-Anh Thi Bui, Duc Dam Nguyen, Mudassir Iqbal, Fazal E. Jalal, Indra Prakash, Binh Thai Pham
Summary: In this article, the shear stiffness modulus (K) of asphalt layers was estimated based on three factors affecting interlayer shear strength. Machine Learning (ML) methods were used to build the predictive models, which performed well in correctly predicting the K value. Among the models, Bagging-RF showed the best performance with a correlation coefficient of 0.88 between estimated and determined values. These ML models will reduce the experimental efforts and increase the efficiency in estimating the K parameter for asphalt pavement design, construction, and maintenance.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Environmental
Francesco Granata, Fabio Di Nunno
Summary: The study developed several different tidal forecast models, with models based on Artificial Intelligence algorithms performing well. The M5P algorithm showed the best performance in most cases, accurately predicting tide levels in Venice. Good predictions were achieved even when meteorological factors were neglected.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Environmental Sciences
Fabio Di Nunno, Giovanni de Marinis, Rudy Gargano, Francesco Granata
Summary: This study developed tide prediction models for the Venice Lagoon based on NARX neural networks. The models were trained, tested, and validated, showing good predictive capability in the entire lagoon.
Article
Environmental Sciences
Fabio Di Nunno, Francesco Granata, Rudy Gargano, Giovanni de Marinis
Summary: Extreme values of high tides are influenced by various factors, prompting the development of a system in Venice to protect the city from flooding caused by the highest tides. Previous research has successfully predicted these extreme values using NARX neural networks, with two distinct models demonstrating high accuracy.
Article
Environmental Sciences
Fabio Di Nunno, Marco Race, Francesco Granata
Summary: This study demonstrates the accuracy of nonlinear autoregressive with exogenous inputs neural networks in predicting nitrate plus nitrite concentrations in rivers. The inclusion of factors such as water discharge, water temperature, dissolved oxygen, and specific conductance as exogenous inputs improves the prediction accuracy. The findings are applicable for both short- and long-term predictions.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Civil
Ariele Zanfei, Andrea Menapace, Francesco Granata, Rudy Gargano, Matteo Frisinghelli, Maurizio Righetti
Summary: This study successfully addresses the challenge of short-term water consumption forecasting in small-scale water supply systems by proposing an ensemble neural network model and time-varying correction modules.
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Quoc Bao Pham, Manish Kumar, Fabio Di Nunno, Ahmed Elbeltagi, Francesco Granata, Abu Reza Md Towfiqul Islam, Swapan Talukdar, X Cuong Nguyen, Ali Najah Ahmed, Duong Tran Anh
Summary: This study compared the performance of seven machine learning models for groundwater level prediction and found that the Bagging-RT and Bagging-RF models performed the best. The results can help in formulating policies for sustainable groundwater resources management.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Environmental Sciences
Francesco Granata, Fabio Di Nunno, Giuseppe Modoni
Summary: The hydraulic conductivity of saturated soil, influenced by particle size distribution, soil compaction, and aggregation and water retention properties, plays a crucial role in engineering problems related to groundwater. Machine learning algorithms can provide effective tools for nonlinear regression problems, and hybrid models combining multiple algorithms can further enhance prediction accuracy. Five models were built, based on different predictors, to predict saturated hydraulic conductivity using a dataset from the Soil Water Infiltration Global database. Among all the models, the one with the largest number of predictors showed the most accurate predictions, and hybrid variants combining Random Forest and Support Vector Regression algorithms performed the best.
Article
Green & Sustainable Science & Technology
Fabio Di Nunno, Francesco Granata, Quoc Bao Pham, Giovanni de Marinis
Summary: This study shows that reliable models for precipitation prediction can be developed using a machine learning approach. A hybrid model based on M5P and support vector regression algorithms achieved the best predictions in this study, with high R-2 values for the stations of Rangpur and Sylhet.
Article
Engineering, Civil
Francesco Granata, Fabio Di Nunno, Giovanni de Marinis
Summary: Prediction of river flow rates is a challenging task due to the high uncertainty associated with basin characteristics, hydrological processes, and climatic factors. This study compares two different daily streamflow prediction models and finds that they have comparable forecasting capabilities. The stacked model based on the Random Forest and Multilayer Perceptron algorithms outperforms the bi-directional LSTM network model in predicting peak flow rates, but is less accurate in forecasting low flow rates. The prediction accuracy of both models decreases as the forecast horizon increases. The length of the time series and the presence of outliers in the data can also affect the accuracy of the prediction models.
JOURNAL OF HYDROLOGY
(2022)
Article
Water Resources
Francesco Granata, Fabio Di Nunno, Mohammad Najafzadeh, Ibrahim Demir
Summary: A reliable assessment of soil moisture content is crucial for irrigation planning and controlling natural disasters. This study applies a stacked model (SM) consisting of multilayer perceptron (MLP), random forest (RF), and support vector regression (SVR) to estimate daily volumetric soil water content. The results show that the SM model performs best (R-2 = 0.962) compared to MLP (R-2 = 0.957), RF (R-2 = 0.956), and SVR (R-2 = 0.951) models under different input variables. Overall, the SM model can overcome the weaknesses of basic algorithms while maintaining a limited number of parameters and short calculation times, leading to more accurate predictions of soil water content than commonly employed MLMs.
Article
Agronomy
Fabio Di Nunno, Francesco Granata
Summary: The study evaluated the reference evapotranspiration in Sicily using historical and future climate parameters, and divided the region into three homogeneous areas using a hierarchical algorithm. Machine learning algorithms were then used to forecast future evapotranspiration. The results showed that evapotranspiration increased for all three regions during the forecast period, with higher increases observed in the inland areas. This approach provides a comprehensive analysis of evapotranspiration trends in different regions.
AGRICULTURAL WATER MANAGEMENT
(2023)
Article
Engineering, Civil
Francesco Granata, Fabio Di Nunno
Summary: Predicting streamflows is crucial for flood defence and optimal management of water resources. Machine Learning algorithms, particularly neural networks, have shown promise in accurately predicting short-term and medium-term flow rates. In this study, four types of neural networks were compared, and RBF-NN models demonstrated better accuracy in predicting flood peaks and low flows.
JOURNAL OF HYDROLOGY
(2023)
Article
Green & Sustainable Science & Technology
Fabio Di Nunno, Marco De Matteo, Giovanni Izzo, Francesco Granata
Summary: This study provides a detailed depiction of evapotranspiration (ETo) in Veneto region using clustering and trends analysis methods. It assesses the evolutionary trends of ETo and precipitation from the coastal to the mountainous regions.
Article
Engineering, Environmental
Fabio Di Nunno, Carlo Giudicianni, Enrico Creaco, Francesco Granata
Summary: This study compares the accuracy of two different models for multi-step ahead prediction of groundwater level. The results show that the RBF-NN model performs better in certain wells, while the stacked MLP-RF model performs slightly better in another well. However, both models provide accurate predictions for all wells, and the RBF-NN model shows less reduction in performance as the forecasting horizon increases, leading to more reliable predictions.
GROUNDWATER FOR SUSTAINABLE DEVELOPMENT
(2023)
Article
Physics, Fluids & Plasmas
Francesco Granata, Fabio Di Nunno
Summary: Air entrainment phenomena have a significant impact on hydraulic operation of plunging drop shafts, and machine learning algorithms can be used to address this issue; experimental data supports the use of hybrid models to improve prediction accuracy.
Article
Engineering, Mechanical
Budi Rochmanto, Hari Setiapraja, Ihwan Haryono, Siti Yubaidah
Summary: This study calibrates a turbine flowmeter for compressed natural gas (CNG) application by using air as a substitute and simulating the kinematic viscosity property of CNG. The research shows that by using air instead of CNG, the flowmeter can achieve accurate measurements with a measurement uncertainty of less than 1%.
FLOW MEASUREMENT AND INSTRUMENTATION
(2024)
Article
Engineering, Mechanical
Mona Mary Varghese, Chaithanya P. Devan, Samiksha M. Masram, Teja Reddy Vakamalla
Summary: This work investigated the influence of particle shape on fluidization behavior at different inlet superficial gas velocities. The experiments were conducted using a laboratory-scale 3D circular fluidized bed column with Geldart D particles of various shapes. The results showed that non-spherical particles had lower minimum fluidization velocities and higher bed expansion compared to spherical particles. Particle shape significantly affected solids holdup, with spherical particles exhibiting higher solids holdup at the same superficial velocity. Frequency domain analysis of pressure signals using Fast Fourier Transform (FFT) and Power Spectral Density (PSD) revealed flow regime transitions associated with changes in particle shape.
FLOW MEASUREMENT AND INSTRUMENTATION
(2024)
Article
Engineering, Mechanical
Ruiming Yu, Yunyan Ma, Kuaile Liu, Xiangyu Liu
Summary: A single-seat control valve with stable flow regulation is researched and designed to address technical problems such as unstable flow at small openings and uneven force on the valve core. The mechanical and flow characteristics, as well as thermal stress, are analyzed through simulations and tests. The results show that the designed valve meets the requirements.
FLOW MEASUREMENT AND INSTRUMENTATION
(2024)
Article
Engineering, Mechanical
Alcemir Costa de Souza, Ewerton Emmanuel da Silva Calixto, Fernando Luiz Pellegrini Pessoa, Valeria L. da Sila, Luiz Octavio Vieira Pereira
Summary: This study proposes a simple CO2 meter for accurately measuring the CO2 content in Brazilian pre-salt production flows. By analyzing the pressure change during a heating assay of an imprisoned sample, the proposed meter is capable of identifying the mixture properties under different CO2 levels.
FLOW MEASUREMENT AND INSTRUMENTATION
(2024)
Article
Engineering, Mechanical
Mehdi Asadi, S. Abbas Hosseini, Kaveh Ahangari
Summary: Due to technical issues with bottom intake racks, porous intakes made of rock, gravel, or sand can be a viable alternative. This study used an experimental model to assess the performance of porous bottom intakes (PBI) and examined the impacts of various parameters such as channel slope, grain size distribution of the porous media, intake structure geometry, and water depth in the channel on diverted flow rates during sediment-free flow. The study also compared the performance of one-sided and three-sided PBI models under the same conditions. The findings suggest that a slope of 1% yields higher discharge coefficient and diverted flow compared to a slope of 1.68%, and three-sided PBI models outperform one-sided models in terms of flow rate. A formula utilizing nonlinear multivariate regression, experimental data, and dimensional analysis was proposed for calculating the discharge coefficient of PBI, with a high accuracy rate of over 95%.
FLOW MEASUREMENT AND INSTRUMENTATION
(2024)