LARHYSS Journal


Description

English Larhyss journal is an international peer-reviewed journal published by the research laboratory in subterranean and surface hydraulics since 2002. The scope of the Journal covers the fields in which the teams of the research laboratory in subterranean and surface hydraulics are active. Original research papers, short communications and critical reviews from all fields of science and engineering related to water are welcomed. Larhyss journal is devoted to the rapid publication of research in water engineering, acting as a link between the diverse research communities and practitioners in the field of hydraulics. The journal accepts manuscripts exclusively in English. Larhyss journal publishes articles on all aspects of hydraulics including hydrology, water and wastewater treatment, surface, and groundwater protection, flow in channels, and pipes, hydraulic modeling… Français LARHYSS journal est une revue scientifique internationale publiée par le laboratoire de recherche en hydraulique souterraine et de surface depuis 2002. La portée du Journal couvre les domaines dans lesquels les équipes du laboratoire de recherche en hydraulique souterraine et de surface sont actives. Des documents de recherche originaux, des communications brèves et d'analyses critiques de tous les domaines de la science et de l'ingénierie liées à l'eau sont les bienvenus. LARHYSS Journal est consacré à la publication rapide de la recherche en ingénierie de l'eau, agissant comme un lien entre les communautés de recherche diverses et praticiens dans le domaine de l'hydraulique. La revue accepte des manuscrits exclusivement en anglais LARHYSS journal publie des articles sur tous les aspects de l'hydraulique, y compris l'hydrologie, le traitement des eaux, la protection des eaux souterraines et de surface, ecoulements dans les canaux et conduites, modelisation hydraulique...


22

Volumes

56

Numéros

670

Articles


USE OF MACHINE LEARNING ALGORITHMS AND IN SITU DATA FOR ESTIMATING PARTICULATE ORGANIC CARBON FROM THE MEDITERRANEAN SEA

Fellous Samir, 
2022-08-22

Résumé: Water quality indicators, including biological, chemical, and physical properties, are usually determined by collecting data from the field and analyzing them in the laboratory. Although these in situ measurements are costly and time-consuming, they offer high accuracy. This study focuses on the estimation of particulate organic carbon (POC) as a water quality parameter using a combination of machine learning algorithms and hyperspectral in situ data. A data-driven approach that does not need any domain knowledge was used. We were interested in POC generated by bacteria, phytoplankton, zooplankton, detritus, and sediments in the Mediterranean Sea from the period of 15 May to 10 June 2017. Therefore, the objective of this study was to use five regression frameworks from machine learning algorithms, to estimate POC with hyperspectral in situ data and evaluate their performance. Based on the coefficient of determination R2 the best-performing modes were nearest neighbors (KNN), Gradient boosting (GB) and random forest (RF) with an R2 in the range of 72.33 to 74.7%. These machine learning models can be used to investigate more water quality parameters, as they reveal a great potential of this approach.

Mots clés: POC, machine learning, in situ measurement, phytoplankton, hyperspectral


PERFORMANCE ANALYSIS OF A TUBULAR SOLAR STILL INCORPORATED WITH POROUS SOIL TO IMPROVE DISTILLATE OUTPUT

Shah Syed Muzzamil Hussain ,  Qamar Naeem ,  Qureshi Haris Uddin ,  Mustaffa Zahiraniza ,  Teo Fang Yenn ,  Saleem Shahid ,  Qamar Nadia ,  Ahmed Farhan ,  Ali Zohaib ,  Hussain Sadam , 

Received date: 19-01-2023    Publication date: 10-06-2023    pages  7-23.