Article
Engineering, Civil
Xiaohui Qi, Hao Wang, Xiaohua Pan, Jian Chu, Kiefer Chiam
Summary: The study used the MARS method to predict the elevations of geological interfaces, showing good accuracy compared to borehole data. Furthermore, the MARS method was able to generate reasonable prediction intervals that properly reflected the data density and geological complexity.
Article
Engineering, Civil
W. G. Zhang, H. R. Li, C. Z. Wu, Y. Q. Li, Z. Q. Liu, H. L. Liu
Summary: This study established predictive models for assessing surface settlement induced by EPB tunneling using different soft computing techniques and validated them with datasets from three tunnel construction projects in Singapore. The results showed that the XGBoost model had slightly better accuracy in predicting ground settlement and was more computationally efficient.
Article
Engineering, Civil
Kanhu Charan Panda, R. M. Singh, L. N. Thakural, Debi Prasad Sahoo
Summary: The study proposed a novel RGL-MARS downscaling model that reduces the dimensionality of predictor variables using the representative grid location approach, showing advantages in handling nonlinear relationships.
JOURNAL OF HYDROLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Gulsah Altinok, Pinar Karagoz, Inci Batmaz
Summary: Learning to rank is a supervised learning problem that aims to construct a ranking model for a given dataset, with MARS and CMARS being effective techniques for point-wise learning to rank. Experimental results show that MARS and ANN are effective methods for learning to rank problem and provide promising results.
COMPUTATIONAL INTELLIGENCE
(2021)
Article
Automation & Control Systems
Yu Liu, Degui Li, Yingcun Xia
Summary: This paper proposes an improvement to the MARS method by using linear combinations of covariates for dimension reduction. The proposed method achieves higher estimation efficiency by calculating gradients of the regression function using special basis functions of MARS and estimating the linear combinations through eigen-analysis. Numerical studies demonstrate the effectiveness of the proposed method in dimension reduction and regression estimation and prediction compared to traditional MARS and other nonparametric methods.
JOURNAL OF MACHINE LEARNING RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Nguyen Hong Giang, Yu-Ren Wang, Tran Dinh Hieu, Nguyen Huu Ngu, Thanh-Tuan Dang
Summary: This paper uses machine learning methods to analyze the trend of rural and industrial land-use transforming into urban land-use in central coastal region of Vietnam, and proposes future land-use planning strategies.
Article
Environmental Sciences
Sima Pourhashemi, Mohammad Ali Zangane Asadi, Mahdi Boroughani, Hossein Azadi
Summary: This study combines remote sensing and statistical models to map land susceptibility to dust emissions in the Iran-Iraq border area. It finds that land use is the most significant factor influencing dust emissions. The results are important for planners and managers in controlling and reducing the negative consequences of dust.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Environmental Sciences
Cheng-Shin Jang
Summary: This study investigated groundwater nitrate-nitrogen pollution in the Pingtung Plain of Taiwan using DRASTIC-LU-based aquifer contamination vulnerability and regression kriging. It was found that orchards and the sand fractions of vadose zones were associated with groundwater nitrate-nitrogen concentrations, with orchard fertilizer identified as the primary source of pollution. The findings highlight the importance of correctly determining groundwater nitrate-nitrogen distributions for environmental resource management and public health prevention.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
David Herrero-Perez, Sebastian Gines Pico-Vicente
Summary: This work presents an efficient parallel geometric multigrid (GMG) implementation for preconditioning Krylov subspace methods solving differential equations using non-conforming meshes for discretization. The approach calculates the restriction and interpolation operators for grid transferring between the non-conforming hierarchical meshes. Using non-Cartesian grids in topology optimization, it reduces the mesh size by discretizing only the design domain. The performance of the proposed method is evaluated using topology optimization problems, showing its computational advantages.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Engineering, Industrial
Chao Dang, Pengfei Wei, Matthias G. R. Faes, Marcos A. Valdebenito, Michael Beer
Summary: This study proposes a new method called "Parallel Adaptive Bayesian Quadrature" (PABQ) for quantifying and reducing numerical uncertainty in reliability analysis. The method uses an importance ball sampling technique and a multi-point selection criterion to effectively assess small failure probabilities with a minimum number of iterations, taking advantage of parallel computing.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Green & Sustainable Science & Technology
Abul Abrar Masrur Ahmed, Ravinesh C. Deo, Sujan Ghimire, Nathan J. Downs, Aruna Devi, Prabal D. Barua, Zaher M. Yaseen
Summary: This study develops a novel multivariate adaptive regression spline (MARS) model to predict the course grade in Introductory Engineering Mathematics. The results show that including written assignments and examination scores significantly improves the predictive performance of the MARS model.
Article
Computer Science, Interdisciplinary Applications
Xiang Que, Chao Ma, Xiaogang Ma, Qiyu Chen
Summary: The STWR model extends the GWR model by utilizing previous time stage data points for better fitting and prediction. To improve efficiency, researchers developed the F-STWR method, which significantly enhances the capability of processing large-scale spatiotemporal data in an HPC environment.
COMPUTERS & GEOSCIENCES
(2021)
Article
Thermodynamics
Mohammad Ali Sahraei, Hakan Duman, Muhammed Yasin Codur, Ecevit Eyduran
Summary: This research aims to predict transport energy demand in Turkey using the MARS model, with the third MARS model selected as the best predictive model after evaluating multiple factors.
Article
Automation & Control Systems
Junhua Zheng, Yingkai Gong, Wei Liu, Le Zhou
Summary: This paper proposes a set of ensemble Gaussian process regression (GPR) models for nonlinear spectroscopic calibration. The new subspace GPR model constructs multiple subspaces along uncorrelated directions to improve the robustness and diversity of the ensemble model. Comparative studies show that the new subspace GPR model improves both prediction accuracy and robustness.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Environmental Sciences
Arezou Dodangeh, Mohammad Mahdi Rajabi, Jesus Carrera, Marwan Fahs
Summary: Coastal aquifers, which are vital water sources for over one billion people, face the challenges of seawater intrusion and anthropogenic contamination. Identification and localization of contaminant source characteristics are needed to reduce contamination. However, most existing studies have focused on inland aquifers and have not addressed the complexities of coastal settings. This study presents an efficient methodology for identifying contaminant source characteristics and aquifer hydraulic conductivity in coastal aquifers. It uses numerical modeling and artificial neural network metamodels in the CRD-EnKF algorithm. The study successfully applies this approach to the complex setting of coastal aquifers and analyzes common issues in contaminant source identification monitoring.
JOURNAL OF CONTAMINANT HYDROLOGY
(2022)
Article
Water Resources
Dilip Kumar Roy, B. Datta
HYDROLOGICAL SCIENCES JOURNAL
(2020)
Article
Engineering, Civil
Dilip Kumar Roy, Rahim Barzegar, John Quilty, Jan Adamowski
JOURNAL OF HYDROLOGY
(2020)
Article
Engineering, Civil
Dilip Kumar Roy, Sujit Kumar Biswas, Kowshik Kumar Saha, Khandakar Faisal Ibn Murad
Summary: This study proposes a discrete Space-State modeling approach to forecast future scenarios of groundwater level fluctuations, demonstrating its potential applicability in predicting future groundwater level fluctuations in selected observation wells in Bangladesh.
WATER RESOURCES MANAGEMENT
(2021)
Article
Agronomy
Dilip Kumar Roy, Alvin Lal, Khokan Kumer Sarker, Kowshik Kumar Saha, Bithin Datta
Summary: This study evaluates and compares the performances of different hybridized ANFIS models for predicting daily ET0, with the FA-ANFIS identified as the best performing model. The findings are significant for effective irrigation scheduling in areas with similar climatic conditions.
AGRICULTURAL WATER MANAGEMENT
(2021)
Article
Meteorology & Atmospheric Sciences
Mohammad Kamruzzaman, Shamsuddin Shahid, Dilip Kumar Roy, Abu Reza Md Towfiqul Islam, Syewoon Hwang, Jaepil Cho, Md Asad Uz Zaman, Tasnim Sultana, Towhida Rashid, Fatima Akter
Summary: This study evaluated the performance of 15 Global Climate Models in replicating the rainfall climatology, variability, and trends in Bangladesh. Most models underestimated annual rainfall but accurately reproduced the spatial features of rainfall. The ensemble mean of the models showed higher skill in reconstructing rainfall characteristics, with MPI-ESM1-2-LR, MPI-ESM1-2-HR, and GFDL-ESM4 identified as the most effective models.
INTERNATIONAL JOURNAL OF CLIMATOLOGY
(2022)
Article
Engineering, Civil
Dilip Kumar Roy, Kowshik Kumar Saha, Mohammad Kamruzzaman, Sujit Kumar Biswas, Mohammad Anower Hossain
Summary: The study evaluated the potential of the PSO-HFS model in predicting ET0, demonstrating its superior performance compared to benchmark models. By ranking the models using Shannon's Entropy concept, the PSO-HFS model showed excellent performance on both training and testing datasets.
WATER RESOURCES MANAGEMENT
(2021)
Article
Environmental Sciences
Dilip Kumar Roy, Sujit Kumar Biswas, Mohamed A. Mattar, Ahmed A. El-Shafei, Khandakar Faisal Ibn Murad, Kowshik Kumar Saha, Bithin Datta, Ahmed Z. Dewidar
Summary: The study assessed the performance of various models based on ANFIS for predicting groundwater levels, proposing a weighted average ensemble model and using MOGA for model ranking. The results revealed DE-ANFIS performed best at observation well GT8194046, with the ensemble model outperforming individual models for improved prediction accuracy.
Article
Agronomy
Mohamed A. Mattar, Dilip Kumar Roy, Hussein M. Al-Ghobari, Ahmed Z. Dewidar
Summary: Wind drift and evaporation losses are significant losses in sprinkler irrigation systems. This research used five soft computing approaches to predict these losses under different conditions. The artificial neural network model showed the highest accuracy in prediction. Design variables and climate variables played important roles in the modeling.
AGRICULTURAL WATER MANAGEMENT
(2022)
Article
Meteorology & Atmospheric Sciences
H. M. Touhidul Islam, Abu Reza Md Towfiqul Islam, Shamsuddin Shahid, G. M. Monirul Alam, Jatish Chandra Biswas, Md Mizanur Rahman, Dilip Kumar Roy, Mohammad Kamruzzaman
Summary: This research evaluated the rainfall variability in Bangladesh using 40 global climate models and found an increasing trend in rainfall during significant rainfall months, while a decreasing trend in dry months. The study projected an increase in annual precipitation, indicating a possible impact on the severity and frequency of floods in the future.
INTERNATIONAL JOURNAL OF CLIMATOLOGY
(2022)
Article
Environmental Sciences
Ahmed Elbeltagi, Faisal AlThobiani, Mohammad Kamruzzaman, Shamsuddin Shaid, Dilip Kumar Roy, Limon Deb, Md Mazadul Islam, Palash Kumar Kundu, Md. Mizanur Rahman
Summary: This study examined the effectiveness of three machine learning models and their hybrid versions in predicting droughts in northern Bangladesh. The M5P model showed the highest prediction accuracy for droughts at different time scales.
Article
Agronomy
Dilip Kumar Roy, Tapash Kumar Sarkar, Sheikh Shamshul Alam Kamar, Torsha Goswami, Md Abdul Muktadir, Hussein M. Al-Ghobari, Abed Alataway, Ahmed Z. Dewidar, Ahmed A. El-Shafei, Mohamed A. Mattar
Summary: This study utilized deep learning models (LSTM and Bi-LSTM) for daily and multi-step forward forecasting of ET0, with results showing that the Bi-LSTM model outperformed other models.
Article
Engineering, Civil
Dilip Kumar Roy, Tapash Kumar Sarkar, Sujit Kumar Biswas, Bithin Datta
Summary: This study utilized multiple optimization algorithms to predict reference evapotranspiration (ET0) using fuzzy inference system (FIS) and fuzzy tree (FT) models. The FT model was developed by combining several FIS objects that received ranked meteorological variables. The evaluation results showed that the hybrid PSO-GA tuned Sugeno type 1 FT model outperformed other models. The study concluded that this model is suitable for predicting daily ET0 values.
WATER RESOURCES MANAGEMENT
(2023)
Article
Environmental Sciences
Dilip Kumar Roy, Tasnia Hossain Munmun, Chitra Rani Paul, Mohamed Panjarul Haque, Nadhir Al-Ansari, Mohamed A. Mattar
Summary: Accurate groundwater level forecasts are crucial for efficient utilization and sustainable management of groundwater resources. This study evaluates data-driven models using different machine learning algorithms and proposes a Bayesian model averaging (BMA)-based ensemble model to forecast groundwater level fluctuations in Bangladesh's Godagari upazila. The results show that the ensemble model outperforms standalone models for multi-step ahead forecasts and demonstrates superior performance for other observation wells as well.
Article
Engineering, Environmental
Dilip Kumar Roy
Summary: This study aims to provide one-step ahead predictions of ET0 using different deep and machine learning methods. The results show that the bi-directional LSTM performed the best, followed by the Sequence-to-Sequence Regression LSTM network, ANFIS, and LSTM models in terms of prediction accuracy and estimation capability.
ENVIRONMENTAL PROCESSES-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Environmental
Dilip Kumar Roy, Bithin Datta
GROUNDWATER FOR SUSTAINABLE DEVELOPMENT
(2020)
