A comparative approach of ML algorithms to rank irrigation water quality: case of Oriental-Coast shallow aquifer in Cap-Bon, northeastern of Tunisia

Yahyaoui, Naima; Néji, Mahmoud; Kallel, Monem; Wali, Ali; Hajji, Soumaya

doi:10.1007/s40808-023-01694-6

Cited by 4 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proportion of redress expectations of indications of the malady to the whole number of inputs [37].…”

Section: Accuracymentioning

confidence: 99%

“…The ratio of correctly predicted parameters to the total number of parameters to be classified is called precision [37].…”

Section: Precisionmentioning

confidence: 99%

“…It is also known as the true positive rate or affectability. Wherever true positive, TN = true negative, FP = false positive, and FN = false negative [37].…”

Section: Recallmentioning

confidence: 99%

“…When FP and FN costs about similar, accuracy performs best. It is better to embrace both precision and recall if the costs of FP and FN differ considerably [37]. Accuracy results of ML methods are displayed in Table 1 and the following figures 8, 9, 10, 11, and 12.…”

Section: F1-scorementioning

confidence: 99%

See 3 more Smart Citations

An IoT and machine learning solutions for monitoring agricultural water quality: a robust framework

Rahu,

Shaikh,

Karim

et al. 2024

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

All living things, comprising animals, plants, and people require water to survive. The world is covered in water, just 1 percent of it is fresh and functional. The importance and value of freshwater have increased due to population growth and rising water demands. Approximately more than 70 percent of the world's freshwater is used for agriculture. Agricultural employees are the least productive, inefficient, and heavily subsidized water users in the world. They also utilize the most water overall. Irrigation consumes a considerable amount of water. The field's water supply needs to be safeguarded. A critical stage in estimating agricultural production is crop irrigation. The global shortage of fresh water is a serious issue, and it will only get worse in the years to come. Precision agriculture and intelligent irrigation are the only solutions that will solve the aforementioned issues. Smart irrigation systems and other modern technologies must be used to improve the quantity of high-quality water used for agricultural irrigation. Such a system has the potential to be quite accurate, but it requires data about the climate and water quality of the region where it will be used. This study examines the smart irrigation system using the Internet of Things (IoT) and cloud-based architecture. The water's temperature, pH, total dissolved solids (TDS), and turbidity are all measured by this device before the data is processed in a cloud using the range of machine learning (ML) approaches. Regarding water content limits, farmers are given accurate information. Farmers can increase production and water quality by using effective irrigation techniques. ML methods comprising support vector machines (SVM), random forests (RF), linear regression, Naive Bayes, and decision trees (DT) are used to categorize pre-processed data sets. Performance metrics like accuracy, precision, recall, and f1-score are used to calculate the performance of ML algorithms.

show abstract

“…The proportion of redress expectations of indications of the malady to the whole number of inputs [37].…”

Section: Accuracymentioning

confidence: 99%

“…The ratio of correctly predicted parameters to the total number of parameters to be classified is called precision [37].…”

Section: Precisionmentioning

confidence: 99%

“…It is also known as the true positive rate or affectability. Wherever true positive, TN = true negative, FP = false positive, and FN = false negative [37].…”

Section: Recallmentioning

confidence: 99%

Section: F1-scorementioning

confidence: 99%

See 2 more Smart Citations

An IoT and machine learning solutions for monitoring agricultural water quality: a robust framework

Rahu,

Shaikh,

Karim

et al. 2024

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

show abstract

“…They indicated the robustness of these algorithms to support the decision-making process for sustainable crop yield. Yahyaoui et al (2023) conducted a comparative study to examine the capabilities of several ML algorithms, including K-nearest neighbor (KNN), support vector machine (SVM) and decision trees in predicting irrigational water quality indices (IWQI) in Cap-Bon, Tunisia. Their study revealed the efficiency of KNN techniques over the others.…”

Section: Introductionmentioning

confidence: 99%

Application of GIS-based machine learning algorithms for prediction of irrigational groundwater quality indices

Mohammed,

Kaya,

Mohamed

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Agriculture is considered one of the primary elements for socioeconomic stability in most parts of Sudan. Consequently, the irrigation water should be properly managed to achieve sustainable crop yield and soil fertility. This research aims to predict the irrigation indices of sodium adsorption ratio (SAR), sodium percentage (Na%), permeability index (PI), and potential salinity (PS) using innovative machine learning (ML) techniques, including K-nearest neighbor (KNN), random forest (RF), support vector regression (SVR), and Gaussian process regression (GPR). Thirty-seven groundwater samples are collected and analyzed for twelve physiochemical parameters (TDS, pH, EC, TH, Ca+2, Mg+2, Na+, HCO3−, Cl, SO4−2, and NO3−) to assess the hydrochemical characteristics of groundwater and its suitability for irrigation purposes. The primary investigation indicated that the samples are dominated by Ca-Mg-HCO3 and Na-HCO3 water types resulted from groundwater recharge and ion exchange reactions. The observed irrigation indices of SAR, Na%, PI, and PS showed average values of 7, 42.5%, 64.7%, and 0.5, respectively. The ML modeling is based on the ion’s concentration as input and the observed values of the indices as output. The data is divided into two sets for training (70%) and validation (30%), and the models are validated using a 10-fold cross-validation technique. The models are tested with three statistical criteria, including mean square error (MSE), root means square error (RMSE), and correlation coefficient (R2). The SVR algorithm showed the best performance in predicting the irrigation indices, with the lowest RMSE value of 1.45 for SAR. The RMSE values for the other indices, Na%, PI, and PS, were 6.70, 7.10, and 0.55, respectively. The models were applied to digital predictive data in the Nile River area of Khartoum state, and the uncertainty of the maps was estimated by running the models 10 times iteratively. The standard deviation maps were generated to assess the model’s sensitivity to the data, and the uncertainty of the model can be used to identify areas where a denser sampling is needed to improve the accuracy of the irrigation indices estimates.

show abstract

Probabilistic slope stability analysis using subset simulation enhanced by ensemble machine learning techniques

Ahmad,

Samui,

Mishra

2023

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

A comparative approach of ML algorithms to rank irrigation water quality: case of Oriental-Coast shallow aquifer in Cap-Bon, northeastern of Tunisia

Cited by 4 publications

References 29 publications

An IoT and machine learning solutions for monitoring agricultural water quality: a robust framework

An IoT and machine learning solutions for monitoring agricultural water quality: a robust framework

Application of GIS-based machine learning algorithms for prediction of irrigational groundwater quality indices

Probabilistic slope stability analysis using subset simulation enhanced by ensemble machine learning techniques

Contact Info

Product

Resources

About