Search

A new pre-processing methodology for gridded Satellite Precipitation Products (SPPs) is developed to improve the performance of Machine Learning (ML) algorithms for runoff prediction. The developed approach was applied to capture the rainfall patterns, and to select relevant input data. This approach was tested using the FeedForward Neural Network (FFNN) and the Extreme Learning Machine (ELM) given their flexibility and ability in hydrological modelling. The methodology was tested in a semiarid transboundary watershed located in North Africa (Algeria, Tunisia) with the Integrated MultisatellitE Retrievals for Global Precipitation Measurement (GPMIMERG) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) products. The results demonstrate the effectiveness of the proposed approach using all employed SPPs. In terms of Nash-Sutcliffe efficiency, the suggested pre-processing technique improved the prediction ability of FFNN by 13%, and of ELM by 15%, which highlights how pre-processing techniques significantly enhance ML models with SPP data. [ABSTRACT FROM AUTHOR]

The aims objective of this work consists to study the storage system effects on the thermal performance of a tunnel agricultural greenhouse. The study focus on the use of the data climate analysis to predict the outside needs as comparison with another without storage system. The obtained results indicate that the outside needs are less than the no heated with 3 to 5°c during winter night. The thermal behavior of the greenhouse was study numerically and the results are corroborating with the literature. In addition, we conducted a comparative study designed to identify the optimal form of the greenhouse; two geometrical configuration are considered.