Water Transmissible Pavement: A physics of Granular Sub-base Permeability through Road Dust Analysis using Machine Learning DOI Creative Commons

Indian Journal of Pure & Applied Physics, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Amidst the rapid urbanization and heightened infrastructure demands, contemporary cities are capitalizing on every available space, converting previously permeable land into impermeable surfaces. This transition obstructs absorption of storm water, leading to intensified runoff. To counteract this challenge address requirements, Low Impact Development (LID) techniques have emerged, among which pavement stands out as a widely adopted solution. Serving transient storage facility, pavements store water within their Granular Sub-Base (GSB) or reservoir layer, thereby diminishing size drains contributing implementation Sustainable Urban Drainage Systems (SUDS). Nevertheless, utilization is commonly recommended for walkways, parking lots, low-volume roads due susceptibility clogging. study delves potential clogging in employing Machine Learning models such Random Forest (RF), Gradient Boosting Regressor (GBR), Light (LGBM), Extra Trees (ET). The investigation incorporates data from 200 instances with varying GSB layers, thicknesses, combinations road dust particle sizes. results reveal robust correlation (R2 > 0.97) experimental data, indicating that GSB-III demonstrates optimal clog resistance under high loads. findings suggest GSB-V GSB-VI may be suitable areas loads below gm/month. research provides valuable insights development clog-resistant tailored moderate high-volume roads.

Language: Английский

Investigation of impact of aggregate shape on pervious concrete using machine learning classification methods DOI
Sathushka Heshan Bandara Wijekoon, Navakulan Ahilash,

Varatharaja Pravinjan

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 143, P. 110008 - 110008

Published: Jan. 7, 2025

Language: Английский

Citations

2
Surface response regression and machine learning techniques to predict the characteristics of pervious concrete using non-destructive measurement: Ultrasonic pulse velocity and electrical resistivity DOI
Navaratnarajah Sathiparan, Pratheeba Jeyananthan, Daniel Niruban Subramaniam

et al.

Measurement, Journal Year: 2023, Volume and Issue: 225, P. 114006 - 114006

Published: Dec. 10, 2023

Language: Английский

Citations

31
Predicting compressive strength of quarry waste-based geopolymer mortar using machine learning algorithms incorporating mix design and ultrasonic pulse velocity DOI
Navaratnarajah Sathiparan, Pratheeba Jeyananthan

Nondestructive Testing And Evaluation, Journal Year: 2024, Volume and Issue: 39(8), P. 2486 - 2509

Published: Jan. 11, 2024

The current study aimed to investigate the possibility of predicting compressive strength geopolymer mortar by mix design parameters, ultrasonic pulse velocity (UPV) and machine learning techniques. Here is produced from eggshell ash rice husk as precursors, NaOH solution activator quarry waste fine aggregate. Twenty-seven combinations a total 189 cubes were cast tested for UPV strength. Seven different techniques used predict assessment tools: linear regression, artificial neural networks, boosted tree random forest K-Nearest Neighbor, support vector regression XGboost. Among diverse models evaluated in this study, XGboost exhibited remarkable efficacy forecasting mortar. investigation conducted using SHAP indicates that concentration shows most substantial influence on prediction

Language: Английский

Citations

11
A machine learning approach to predicting pervious concrete properties: a review DOI
Navaratnarajah Sathiparan, Pratheeba Jeyananthan, Daniel Niruban Subramaniam

et al.

Innovative Infrastructure Solutions, Journal Year: 2025, Volume and Issue: 10(2)

Published: Jan. 23, 2025

Language: Английский

Citations

1
Optimizing compressive strength prediction of pervious concrete using artificial neural network DOI
Sathushka Heshan Bandara Wijekoon,

Asoharasa Janarth,

Joseph Dharmar

et al.

Engineering Research Express, Journal Year: 2025, Volume and Issue: 7(1), P. 015418 - 015418

Published: Jan. 31, 2025

Abstract The prediction of compressive strength is crucial, as it influenced by various mix parameters such aggregate size, aggregate-to-cement ratio, and compaction. Accurate forecasting ensures optimized designs, enhancing both performance material efficiency in construction projects. novelty this study lies integrating machine learning techniques to predict the pervious concrete, incorporating these key improve predictive accuracy facilitate more precise sustainable design choices. For experimental study, 600 samples were prepared with varying ratios (3.0–5.0), compaction (0–60 blows from standard proctor rammer), size (4.75–25 mm) monitored for porosity strength. A modified Ryshkewitch model assessed alongside evaluations optimization. effect parameter variability on investigate uncertainty propagation. Key uncertainties are highlighted sensitivity analysis, output distributions produced Monte Carlo simulations, reducing essential practical applications, guarantees that forecasts remain constant across a range materials environmental circumstances. In addition, neural network models analyzed accuracy. Incorporating enhanced R 2 empirical 0.63 0.78 0.92, respectively, while was comparable observations. Aggregate size-based improved than 0.95 all cases, insisting dominant impact models. research concludes designs not only but also promote sustainability waste durability concrete. These findings provide valuable insights efficient environmentally friendly concrete urban infrastructure

Language: Английский

Citations

1
Predicting compressive strength of cement-stabilized earth blocks using machine learning models incorporating cement content, ultrasonic pulse velocity, and electrical resistivity DOI
Navaratnarajah Sathiparan, Pratheeba Jeyananthan

Nondestructive Testing And Evaluation, Journal Year: 2023, Volume and Issue: 39(5), P. 1045 - 1069

Published: July 24, 2023

ABSTRACTThe quality monitoring technique for Cement stabilised earth blocks (CSEBs) is so challenging that it often neglected. This study has investigated the possibility of using machine learning to predict compressive strength CSEBs based on cement content, electrical resistivity and Ultrasonic pulse velocity (UPV) as a potential way enhance control. The considered three types soil different content in preparation with 10 cement-soil mixtures. Various models were proposed CSEBs. evaluated 180 experimental datasets, best model predicting was selected. ANN BTR performed better than other tested this results show combination UPV can be used assess more accurately, which contribute knowledge base applied real world. Materials scientists engineers use reliable predictive properties both new old brick structures without damage or loss use.KEYWORDS: CSEBcompressive strengthUPVelectrical resistivitymachine Disclosure statementNo conflict interest reported by author(s).

Language: Английский

Citations

22
Soft computing techniques to predict the electrical resistivity of pervious concrete DOI
Daniel Niruban Subramaniam, Pratheeba Jeyananthan, Navaratnarajah Sathiparan

et al.

Asian Journal of Civil Engineering, Journal Year: 2023, Volume and Issue: 25(1), P. 711 - 722

Published: July 17, 2023

Language: Английский

Citations

19
Prediction of compressive strength of fly ash blended pervious concrete: a machine learning approach DOI
Navaratnarajah Sathiparan, Pratheeba Jeyananthan, Daniel Niruban Subramaniam

et al.

International Journal of Pavement Engineering, Journal Year: 2023, Volume and Issue: 24(2)

Published: Jan. 28, 2023

ABSTRACTThis study presents a prediction model for estimating the compressive strength of pervious concrete through utilisation machine learning techniques. The models were trained and tested using 437 datasets sourced from published literature. This work employed collection six algorithms as statistical evaluation tools to determine optimal dependable forecasting concrete. Out all considered, eXtreme Gradient Boosting had greater performance in predicting strength. coefficient determination value train data is 0.99, indicating strong correlation between predicted actual values. root mean squared error 0.86 MPa, representing average deviation measured Similarly, test determined be 0.95, accompanied by 2.53 MPa. model's sensitivity analysis findings suggest that aggregate size greatest parameter on delivers systematic assessment concrete, contributing current knowledge base practical implementation this field.KEYWORDS: Pervious concretefly ashmachine learningcompressive Disclosure statementNo potential conflict interest was reported author(s).Data availability statementData can made available request interested parties.Authors' contributionsN.S: Conceptualisation, Data curation, Analysis, Writing – original draft. P.J: Machine modelling, D.N.S: draft, review & editing.Consent participateThis article does not contain any studies with human participants or animals performed authors.

Language: Английский

Citations

19
Optimisation of pervious concrete performance by varying aggregate shape, size, aggregate-to-cement ratio, and compaction effort by using the Taguchi method DOI
Sathushka Heshan Bandara Wijekoon, Navaratnarajah Sathiparan, Daniel Niruban Subramaniam

et al.

International Journal of Pavement Engineering, Journal Year: 2024, Volume and Issue: 25(1)

Published: July 22, 2024

Language: Английский

Citations

7
Soft computing to predict the porosity and permeability of pervious concrete based on mix design and ultrasonic pulse velocity DOI
Navaratnarajah Sathiparan, Sathushka Heshan Bandara Wijekoon, Pratheeba Jeyananthan

et al.

International Journal of Pavement Engineering, Journal Year: 2024, Volume and Issue: 25(1)

Published: April 9, 2024

The present study explores the potential of machine learning to predict porosity and permeability pervious concrete constructed on mix parameters (compaction energy, aggregate-to-cement ratio aggregate size) ultrasonic velocity. prediction models use non-destructive measurements mixed design variables, which can help construction sector apply without any theoretical expertise. uses 225 data samples from an experimental study. This used six algorithms, namely, linear regression, artificial neural networks, boosted decision tree random forest K-nearest neighbour support vector determine best predictive model. results show that ANN model is technique for predicting (R2 = 0.9502 training datasets R2 0.8958 testing datasets) tress 0.9323 0.7574 datasets). sensitivity analysis regression reveals pulse velocity most influential parameter concrete. proposed provide a more accurate method estimating

Language: Английский

Citations

6