Farah Chouikhi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Farah Chouikhi has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Abderrazak Tlili
Animal and Forage Productions Laboratory (LR16INRAT01), National Institute of Agricultural Research of Tunisia, Carthage University, Ariana, Tunisia
2 shared publications - Ali Ben Abbes
Manouba School of Engineering, Manouba University
2 shared publications - Imed Riadh Farah
RIADI Laboratory, National School of Computer Sciences, University of Manouba, Mannouba, Tunisia
2 shared publications - Abir Zaied
Laboratoire d’Elevage et de Faune Sauvage, Institut des Régions Arides de Médenine, (LR16IRA04), Médenine, Tunisia
1 shared publication Ali Ben Abbes
1 shared publication- Ali Zaidi
Laboratoire d’Elevage et de Faune Sauvage, Institut des Régions Arides de Médenine, (LR16IRA04), Médenine, Tunisia
1 shared publication
Latest Publications
- 23 July 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 65-71
Enhancing change detection in multi-date images using a Multi-temporal Siamese Neural Network
- 23 July 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 197, 65-71
Enhancing change detection in multi-date images using a Multi-temporal Siamese Neural Network
- Open Access
Assessing the Impacts of Climate Change Scenarios on Soil-Adjusted Vegetation Index in North African Arid Montane Rangeland: Case of Toujane Region
Radiometric vegetation indices are considered good indicators of vegetation health and can contribute to explaining its current and future evolutions. This study is carried out in the arid mountain rangeland of Toujane (southeast of Tunisia). The aim is to predict how climate change will affect the Soil-Adjusted Vegetation Index (SAVI) values under dryland conditions. Current and future SAVI indices are analyzed using the maximum entropy algorithm (MaxEnt). The Canadian Earth System Model version 5 (CanESM5) represents the data source of two future climatic scenarios. These last, called Shared Socioeconomic Pathways (SSP245, SSP585), concern four time periods (2021–2040, 2041–2060, 2061–2080, and 2081–2100). Three topographic, twelve soil, and nineteen climatic variables are undertaken during each period. The main results of the jackknife test show that temperature, precipitation, and some soil variables are the main factors influencing SAVI indices. Specifically, they affect plant growth and vegetation cover, which in turn modify the SAVI index. Based on the area under the receiving curve, the model shows high predictive accuracy for a high SAVI (AUC = 0.88 − 0.92). These findings show that land management strategies may be incumbent upon to reduce the vulnerability linked to climate change in Toujane rangelands.
Open AccessAssessing the Impacts of Climate Change Scenarios on Soil-Adjusted Vegetation Index in North African Arid Montane Rangeland: Case of Toujane Region
Radiometric vegetation indices are considered good indicators of vegetation health and can contribute to explaining its current and future evolutions. This study is carried out in the arid mountain rangeland of Toujane (southeast of Tunisia). The aim is to predict how climate change will affect the Soil-Adjusted Vegetation Index (SAVI) values under dryland conditions. Current and future SAVI indices are analyzed using the maximum entropy algorithm (MaxEnt). The Canadian Earth System Model version 5 (CanESM5) represents the data source of two future climatic scenarios. These last, called Shared Socioeconomic Pathways (SSP245, SSP585), concern four time periods (2021–2040, 2041–2060, 2061–2080, and 2081–2100). Three topographic, twelve soil, and nineteen climatic variables are undertaken during each period. The main results of the jackknife test show that temperature, precipitation, and some soil variables are the main factors influencing SAVI indices. Specifically, they affect plant growth and vegetation cover, which in turn modify the SAVI index. Based on the area under the receiving curve, the model shows high predictive accuracy for a high SAVI (AUC = 0.88 − 0.92). These findings show that land management strategies may be incumbent upon to reduce the vulnerability linked to climate change in Toujane rangelands.
- 13 September 2023
- Published by Springer Nature
- p. 513-525
Desertification Detection in Satellite Images Using Siamese Variational Autoencoder with Transfer Learning
- 13 September 2023
- Published by Springer Nature
- p. 513-525
Desertification Detection in Satellite Images Using Siamese Variational Autoencoder with Transfer Learning