Groundwater Quality Forecasting Using Machine Learning Algorithms: Case Study Berrechid Aquifer, Central Morocco

Abstract

In order to provide a recommendation on the quality of groundwater in the region of Berrechid, Morocco, we analysed the concentration of conductivity as one of the main measures to identify the salinity of the water. We applied artificial intelligence models for predicting the conductivity of water while analysing several physical parameters as input parameters of the models. To achieve this purpose, we exploited and evaluated the Random Forest (RF), Support Vector Regression (SVR), and k-nearest neighbour models using 400 data samples related to ten groundwater quality parameters in the Berrechid aquifer, Morocco. The results revealed that the overall prediction performance of the RF models is higher than the SVR and KNN models. Overall, the developed models are able to predict conductivity with high accuracy. The approaches developed in this study are promising for real-time and low-cost prediction of groundwater quality by using physical parameters as input variables.

Agriculture and Economic Development of the Ait Werra Tribe During the French Colonialism Period and Its Local Characteristics (1912-1956) Within the Middle Atlas Region of Morocco

“…The climate of Morocco is Mediterranean in the north, becoming more extreme in the interior; in the south, hot, dry desert; rain is rare; cold offshore air currents produce fog and heavy dew (Moukhliss et al, 2022;Elfanne et al, 2022). The climate of El Kssiba is temperate and rainy, with some years receiving more than 1000 mm of rainfall.…”

“…Agricultural land is about 67.5%, arable land, 17.5%; permanent crops, 2.9%; permanent pasture, 47.1%; forest, 11.5%; other: 21%. The most significant population density in Morocco is concentrated along the Atlantic and Mediterranean coasts, with numerous densely populated urban areas dispersed across the Atlas Mountains (Moukhliss et al, 2022;Elfanne et al, 2022;Sabri et al, 2022;Abubakar, 2016;Abubakar, 2008).…”

“…Nevertheless, the current reality shows that many of these youths face unemployment due to a disparity in job creation, which has not kept pace with the expanding working-age population. Those who do find employment are often engaged in the informal sector, where job security and benefits are typically limited (Moukhliss et al, 2022;Elfanne et al, 2022;Abubakar, 2016;Abubakar, 2008).…”

“…Age structure Based on the reports available at the national statistics, but also to the publications of various authors (Moukhliss et al, 2022;Elfanne et al, 2022;Abubakar, 2016;Abubakar, 2008), population with the age of 0-14 years is 26.01% (male 4,919,266/female 4,722,463); 15-64 years: 65.92% (male 12,124,939/female 12,311,552); 65 years and over: 8.06% (2023 est.) (male 1,455,355/female 1,533,845).…”