Predicting iron contents in the Tamra-Douahria mining site using a deep neural network approach DOI Creative Commons

Fathi Maalaoui,

Zohra Kraiem, Salah Bouhlel

et al.

Journal of Taibah University for Science, Journal Year: 2024, Volume and Issue: 18(1)

Published: Dec. 4, 2024

The well-known Douahria-Tamra mining site is characterized by the presence of deposits with high variability in composition, colour, and structural-textural peculiarities, especially exploitable layers. Thus, understanding underlying reasons for this heterogeneity crucial to optimize extraction processes, ensuring consistent product quality, maximizing resource utilization. This was motivation beyond attempt allocated shed light on behaviour iron other related ores district. Iron content estimated from measured lead, zinc, manganese, silica arsenic using unsupervised machine learning tools (HCA PCA) deep neural network. For purpose, 357 iron-rich samples collected Tamra-Douahria sub-district were used train, test validate obtained models. Out 357, 285 data sets selected training algorithm while 72 points model testing validation. Input variables included lead (Pb), zinc (Zn), manganese (Mn), (As) (SiO2) contents, (Fe %) considered as output. Our results indicated a mean value (26.19%) perfectly predicted 26.09% DNN model. A cross-validation step necessary confirm robustness proposed models coefficient determination (R2). (R2 = 0.9978) Pearson correlation (0.999) low RMSE (0.975) which accurate predictions actual values. Therefore, robust predicting contents studied site.

Language: Английский

Evaluation of water quality indexes with novel machine learning and SHapley Additive ExPlanation (SHAP) approaches DOI
Ali Aldrees, Majid Khan, Abubakr Taha Bakheit Taha

et al.

Journal of Water Process Engineering, Journal Year: 2024, Volume and Issue: 58, P. 104789 - 104789

Published: Jan. 17, 2024

Language: Английский

Citations

65
Machine learning based computational approach for crack width detection of self-healing concrete DOI
Fadi Althoey, Muhammad Nasir Amin,

Kaffayatullah Khan

et al.

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 17, P. e01610 - e01610

Published: Oct. 25, 2022

Language: Английский

Citations

56
Evolutionary and ensemble machine learning predictive models for evaluation of water quality DOI Creative Commons
Ali Aldrees,

Muhammad Faisal Javed,

Abubakr Taha Bakheit Taha

et al.

Journal of Hydrology Regional Studies, Journal Year: 2023, Volume and Issue: 46, P. 101331 - 101331

Published: Feb. 7, 2023

Bisham Qilla and Doyian stations, Indus River Basin of Pakistan Water pollution is an international concern that impedes human health, ecological sustainability, agricultural output. This study focuses on the distinguishing characteristics evolutionary ensemble machine learning (ML) based modeling to provide in-depth insight escalating water quality problems. The 360 temporal readings electric conductivity (EC) total dissolved solids (TDS) with several input variables are used establish multi-expression programing (MEP) model random forest (RF) regression for assessment at River. developed models were evaluated using statistical metrics. findings reveal determination coefficient (R2) in testing phase (subject unseen data) all more than 0.95, indicating accurateness models. Furthermore, error measurements much lesser root mean square logarithmic (RMSLE) nearly equals zero each model. absolute percent (MAPE) MEP RF falls below 10% 5%, respectively, three phases (training, validation testing). According sensitivity generated about relevance inputs predicted EC TDS, shows bi-carbonates chlorine content have significant influence a sensitiveness score 0.90, whereas impact sodium less pronounced. All (RF MEP) lower uncertainty prediction interval coverage probability (PICP) calculated quartile (QR) approach. PICP% greater 85% stages. Thus, indicate developing intelligent parameter cost effective feasible monitoring analyzing quality.

Language: Английский

Citations

34
Energy consumption predictions by genetic programming methods for PCM integrated building in the tropical savanna climate zone DOI

Kashif Nazir,

Shazim Ali Memon, Assemgul Saurbayeva

et al.

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 68, P. 106115 - 106115

Published: Feb. 25, 2023

Language: Английский

Citations

28
Surface water quality prediction in the lower Thoubal river watershed, India: A hyper-tuned machine learning approach and DNN-based sensitivity analysis DOI
Md Hibjur Rahaman, Haroon Sajjad,

Shabina Hussain

et al.

Journal of environmental chemical engineering, Journal Year: 2024, Volume and Issue: 12(3), P. 112915 - 112915

Published: May 3, 2024

Language: Английский

Citations

9
Prediction models for marshall mix parameters using bio-inspired genetic programming and deep machine learning approaches: A comparative study DOI Creative Commons
Fadi Althoey,

Muhammad Naveed Akhter,

Zohaib Sattar Nagra

et al.

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 18, P. e01774 - e01774

Published: Dec. 14, 2022

This research study utilizes four machine learning techniques, i.e., Multi Expression programming (MEP), Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Ensemble Decision Tree Bagging (DT-Bagging) for the development of new advanced models prediction Marshall Stability (MS), Flow (MF) asphalt mixes. A comprehensive detailed database 343 data points was established both MS MF. The predicting variables were chosen among most influential, easy-to-determine parameters. trained, tested, validated, outcomes newly developed compared with actual outcomes. root squared error (RSE), Nash-Sutcliffe efficiency (NSE), mean absolute (MAE), square (RMSE), relative (RRMSE), regression coefficient (R2), correlation (R), all used to evaluate performance models. sensitivity analysis (SA) revealed that in case MS, rising order input significance bulk specific gravity compacted aggregate, Gmb (38.56%) > Percentage Aggregates, Ps (19.84%) Bulk Specific Gravity Aggregate, Gsb (19.43%) maximum paving mix, Gmm (7.62%), while MF followed was: (36.93%) (14.11%) (10.85%) (10.19%). parametric (PA) consistency results relation previous findings. DT-Bagging model outperformed other values 0.971 0.980 16.88 0.24 28.27 0.36 0.069 0.041 0.020 0.032 0.010 0.016 (PI), 0.931 0.959 MF, respectively. comparison showed ANN, ANFIS, MEP, are effective reliable approaches estimation MEP-derived mathematical expressions represent novelty MEP relatively simple reliable. Roverall >MEP >ANFIS >ANN exceeding permitted range 0.80 Hence, modeling higher performance, possessed high generalization predication capabilities, assess parameters findings this would assist safer, faster, sustainable from standpoint resources time required perform tests.

Language: Английский

Citations

33
Trend analysis and forecasting of meteorological variables in the lower Thoubal river watershed, India using non-parametrical approach and machine learning models DOI
Md Hibjur Rahaman, Tamal Kanti Saha, Md Masroor

et al.

Modeling Earth Systems and Environment, Journal Year: 2023, Volume and Issue: 10(1), P. 551 - 577

Published: June 7, 2023

Language: Английский

Citations

20
Mechanical behaviour of E-waste aggregate concrete using a novel machine learning algorithm: Multi expression programming (MEP) DOI Creative Commons

Sultan Shah,

Moustafa Houda, Sangeen Khan

et al.

Journal of Materials Research and Technology, Journal Year: 2023, Volume and Issue: 25, P. 5720 - 5740

Published: July 1, 2023

Technological advancement encourages the usage of electronic appliances in daily life and makes it possible for users to switch more advanced devices very easily at a reasonable cost. As new are produced manufactured an alarming rate around world, outdated old become e-waste. This research work aims using popular machine learning (ML) method known as multi-expression programming (MEP) examine compressive strength (CS) tensile (TS) E-waste aggregate-based concrete (EWAC). 279 105 scientific entries CS TS, respectively, were culled from reputable literature. The ten convincing input parameters selected based on multicollinearity analysis (correlation matrix variance inflation factor) coarse aggregate (ECA%), fine (EFA%), water-cement ratio (w/c), age (A days), water-absorption (WAF%), (WAC%), (WAE%), specific-gravity (SGE), (SGC), (SGF). To estimate functioning projected models, root-squared-error (RSE), mean-absolute error (MAE), mean-absolute-percent (MAPE), Nash-Sutcliffe-efficiency (NSE), root-mean-squared (RMSE), objective-function (OF), coefficient-of-correlation (R), root-mean-squared-logarithmic (RMSLE), performance-index (PI) used. R-value both MEP models exceeds 0.9, showing "excellent" with MAPE values testing stage equals 6.68% 6.78% CS-MEP TS-MEP respectively. While non-linear regression (NLR) 20% 30%, making them unsuitable future prediction. Moreover, sensitivity carried out evaluate equations' consistency observed physical phenomena, indicates that w/c, ECA%, EFA% remain most sensitive index greater than 0.60. Due accuracy viability developed they can be used reduce time needed laborious laboratory tests.

Language: Английский

Citations

17
Effects of pH, temperature and hydraulic disturbance on nitrogen release from sediments in the Sunxi River, Three Gorges Reservoir Area, China DOI Creative Commons
Ning Yu, Gao Bin, Haiyan Wang

et al.

PeerJ, Journal Year: 2025, Volume and Issue: 13, P. e19161 - e19161

Published: March 26, 2025

To clarify the influence of changes in overlying water environment on internal nitrogen release from reservoir sediments, we collected surface sediments at a depth approximately 10 cm Sunxi River tail area Three Gorges Reservoir for simulation experiments. By using orthogonal experiments laboratory, studied effects pH, temperature and hydraulic disturbance sediment established quantitative linear relationship between rate environmental factors water. The results indicated that average concentrations total (TN) phosphorus (TP) were 430 mg/kg 200 mg/kg, respectively. TN concentration had very significant positive correlation with organic matter content (P < 0.001). TN, NO3-N NH4-N intensities gradually increased increasing incubation time, maximum rates 29.24 mg/((m2⋅d), 23.11 mg/(m2⋅d) 4.32 Range analysis revealed significance ranked as follows: > pH disturbance, was disturbance. Temperature plays most important role behavior different forms sediments. capacity potential offer crucial insights assessing risks posed to highlighting importance these quality management prediction area.

Language: Английский

Citations

0
Evaluating the impact of data preprocessing to develop a robust MEP-based forecasting model for building integrated with PCM DOI

Kashif Nazir,

Shazim Ali Memon

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135763 - 135763

Published: March 1, 2025

Language: Английский

Citations

0