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


Zeineb Kassouk has a total of 50 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Apports de la télédétection, de la géomatique et du modèle numérique de terrain topo-bathymétrique intégré pour l'aide à la gestion des milieux humides littoraux : application à l'estuaire de la Rance (Ouest de la France) et au lac Ichkeul (Nord de la Tunisie)

    by Zeineb Kassouk

    Les milieux humides littoraux sont des systèmes écologiques complexes qui résultent des interactions entre des processus hydrologiques, géomorphologiques et biologiques. Ils sont généralement très convoités pour leurs intérêts tant écologiques qu’économiques. Plusieurs approches ont été employées pour mieux comprendre leurs évolutions spatiotemporelles en fonction de perturbations aussi bien naturelles qu’anthropiques qu’ils subissent. Les outils de la télédétection et des potentialités des Systèmes d’Informations Géographiques (SIG) ont été largement développés. Ainsi dans cette étude, on propose une approche cartographique de deux milieux humides, basée sur la classification orientée-objet des photographies aériennes et les images satellitaires multidates et multi-résolutions et utilisant un modèle numérique de terrain (MNT) topo-bathymétrique intégré pour étudier ces perturbations. Cette approche a permis d’étudier l’évolution de deux milieux humides situés dans deux contextes climatiques et géographiques différents qui sont l’estuaire de la Rance situé à l’ouest de la France dans un contexte tempéré océanique et ayant subi la construction d’un barrage marémoteur (aménagement hydraulique majeur) en 1966. Le deuxième milieu est le lac de l’Ichkeul situé au nord de la Tunisie, un des milieux humides les plus importants de la méditerranée qui est sujet à des aménagements hydrauliques continus et fortement dépendant des perturbations climatiques. Pour l’exemple de l’estuaire de la Rance, l’étude des évolutions géomorphologiques a été effectuée en utilisant des comparaisons du MNT intégré réalisé dans le cadre de cette étude à partir de données bathymétriques et topographiques acquises avant la construction du barrage marémoteur avec des données bathymétriques acquises en 1982 puis en 1998. On a par exemple confirmé localement les évolutions de la topo-bathymétrie. On révèle la déviation du chenal principal, ainsi que l’érosion des zones situées à l’aval à proximité du fort courant ou bien au contraire leur sédimentation dans les zones protégées de l’action des courants. L’étude de l’évolution de la végétation du schorre (herbus) a été effectuée par deux méthodes : une cartographie surfacique multidate de la végétation à partir des photographies aériennes acquises en 1953, 1961, 1966, 1978, 1982, 1996 et une orthophotographie aérienne acquise en 2002 et une cartographie de la végétation du schorre faite en exploitant les capacités de segmentation des images à haute- résolution spatiale offertes par la méthode de classification orientée-objet et le modèle topobathymétrique intégré. Cette étude comparative a montré que la surface globale du schorre a augmenté suite à la mise en place du barrage marémoteur, une tendance à l’équilibre des surfaces est observée depuis 1978. Un nouvel équilibre global s’est instauré dans l’estuaire douze ans après la construction du barrage marémoteur. Dans le cas de l’étude du milieu humide du lac Ichkeul, correspondant au deuxième exemple étudié ici, la méthode de classification orientée-objet a été utilisée pour la cartographie de l’évolution de la végétation en utilisant des images satellitaires multisources, multi-résolutions et multidates (MSS-Landsat (1972), TM-Landsat (1987), ETM+ Landsat (2001) and Aster-Terra (2007)) et le MNT topobathymétrique intégré. Cette méthode a permis d’identifier les principales communautés végétatives caractéristiques des marais de l’Ichkeul, à savoir la communauté à base de Sarcocornia fruticosa, la communauté à base d’Hordeum Marinum, la communauté à base de Visnaga Daucoides et la communauté à base de Bolboschoenus. L’évolution morphologique du lac est étudiée en comparant le MNT topo-bathymétrique intégré réalisé à partir de données topographiques et bathymétriques acquises en 2003 avec des données bathymétriques acquises en 1967, 1983, 1986 et 1993. Elle fait apparaître le déplacement des zones d’accrétion et de sédimentation dans le lac suite aux aménagements hydrauliques ainsi on relève : (1) une érosion dans la partie est du lac entre 1967 et 1982 (2) un engraissement aux alentours de l’écluse entre 1982 et 1986 et (3) un déplacement des zones les plus profondes vers le sud-ouest du lac et un comblement de la partie du lac située au pied (nord-est) du Djebel Ichkeul depuis 1993. Cette étude a montré que les modifications drastiques des apports d’eau et les perturbations climatiques constituent les principales causes des altérations physiques du milieu humide de l’Ichkeul. Le retour à une dynamique naturelle est loin d’être atteint et dépend fortement des interventions humaines et des facteurs climatiques. La méthode utilisée ici a permis d’étudier deux milieux humides différents et leurs évolutions en se basant sur le degré de complexité de chacun d’eux ainsi que sur le type de la...

  • Open Access

    Processing and Analysis Techniques to Enhance the Change Surrounding the Ichkeul Marshes Wetland in North Tunisia Using Free Remote Sensing Data and Google Earth Engine

    by Zeineb Kassouk, Aicha Chahbi Bellakanji, Zohra Lili Chabaane

    The aim of this chapter is to implement user-friendly time series analysis solution to trend and seasonality analysis and change detection algorithms to identify significant changes in wetland area of free remote sensing data and GIS technology. This research employs the global surface water (JRC database) database, utilizing the Google Earth Engine platform for analysis of the spatio-temporal distribution and variations in water levels in the marshes surrounding Ichkeul Lake in northern Tunisia. Water dynamics is analyzed across the period from 1984 to 2021 based on metric indicators of wetland (water occurrence, seasonality, and transition) in link with climatic and anthropic factors. Developed steps included the water extend parameters extraction and the validation of available time series JRC database in the study area. The accuracy of water dynamic maps was analyzed based on field monitoring data collected in 2002, 2005, 2007, 2020, and 2021. The outcomes of these assessments will inform the feasibility of extending surface water mapping and can help to track the loss and degradation of marshes wetlands.

  • Open Access

    Monitoring Coastal Evolution and Geomorphological Processes Using Time-Series Remote Sensing and Geospatial Analysis: Application Between Cape Serrat and Kef Abbed, Northern Tunisia

    by Zeineb Kassouk, Emna Ayari, Benoit Deffontaines, Mohamed Ouaja

    The monitoring of coastal evolution (coastline and associated geomorphological features) caused by episodic and persistent processes associated with climatic and anthropic activities is required for coastal management decisions. The availability of open access, remotely sensed data with increasing spatial, temporal, and spectral resolutions, is promising in this context. The coastline of Northern Tunisia is currently showing geomorphic process, such as increasing erosion associated with lateral sedimentation. This study aims to investigate the potential of time-series optical data, namely Landsat (from 1985–2019) and Google Earth® satellite imagery (from 2007 to 2023), to analyze shoreline changes and morphosedimentary and geomorphological processes between Cape Serrat and Kef Abbed, Northern Tunisia. The Digital Shoreline Analysis System (DSAS) was used to quantify the multitemporal rates of shoreline using two metrics: the net shoreline movement (NSM) and the end-point rate (EPR). Erosion was observed around the tombolo and near river mouths, exacerbated by the presence of surrounding dams, where the NSM is up to −8.31 m/year. Despite a total NSM of −15 m, seasonal dynamics revealed a maximum erosion in winter (71% negative NSM) and accretion in spring (57% positive NSM). The effects of currents, winds, and dams on dune dynamics were studied using historical images of Google Earth®. In the period from 1994 to 2023, the area is marked by dune face retreat and removal in more than 40% of the site, showing the increasing erosion. At finer spatial resolution and according to the synergy of field observations and photointerpretation, four key geomorphic processes shaping the coastline were identified: wave/tide action, wind transport, pedogenesis, and deposition. Given the frequent changes in coastal areas, this method facilitates the maintenance and updating of coastline databases, which are essential for analyzing the impacts of the sea level rise in the southern Mediterranean region. Furthermore, the developed approach could be implemented with a range of forecast scenarios to simulate the impacts of a higher future sea-level enhanced climate change.


  • Open Access

    Using Machine-Learning Algorithms to Predict Soil Organic Carbon Content from Combined Remote Sensing Imagery and Laboratory Vis-NIR Spectral Datasets

    by Hayfa Zayani, Youssef Fouad, Didier Michot, Zeineb Kassouk, Nicolas Baghdadi, Emmanuelle Vaudour, Zohra Lili-Chabaane, Christian Walter

    Understanding spatial and temporal variability in soil organic carbon (SOC) content helps simultaneously assess soil fertility and several parameters that are strongly associated with it, such as structural stability, nutrient cycling, biological activity, and soil aeration. Therefore, it appears necessary to monitor SOC regularly and investigate rapid, non-destructive, and cost-effective approaches for doing so, such as proximal and remote sensing. To increase the accuracy of predictions of SOC content, this study evaluated combining remote sensing time series with laboratory spectral measurements using machine and deep-learning algorithms. Partial least squares (PLS) regression, random forest (RF), and deep neural network (DNN) models were developed using Sentinel-2 (S2) time series of 58 sampling points of bare soil and according to three approaches. In the first approach, only S2 bands were used to calibrate and compare the performance of the models. In the second, S2 indices, Sentinel-1 (S1) indices, and S1 soil moisture were added separately during model calibration to evaluate their effects individually and then together. In the third, we added the laboratory indices incrementally and tested their influence on model accuracy. Using only S2 bands, the DNN model outperformed the PLS and RF models (ratio of performance to the interquartile distance RPIQ = 0.79, 1.36 and 1.67, respectively). Additional information improved performances only for model calibration, with S1 soil moisture yielding the most stable improvement among three iterations. Including equivalent indices of the S2 indices calculated using soil spectra obtained under laboratory conditions improved prediction of SOC, and the use of only two indices achieved good validation performances for the RF and DNN models (mean RPIQ = 2.01 and 1.77, respectively).


  • Open Access

    Multi-Year Cereal Crop Classification Model in a Semi-Arid Region Using Sentinel-2 and Landsat 7–8 Data

    by Manel Khlif, Maria José Escorihuela, Aicha Chahbi Bellakanji, Giovanni Paolini, Zeineb Kassouk, Zohra Lili Chabaane

    This study developed a multi-year classification model for winter cereal in a semi-arid region, the Kairouan area (Tunisia). A random forest classification model was constructed using Sentinel 2 (S2) vegetation indices for a reference agricultural season, 2020/2021. This model was then applied using S2 and Landsat (7 and 8) data for previous seasons from 2011 to 2022 and validated using field observation data. The reference classification model achieved an overall accuracy (OA) of 89.3%. Using S2 data resulted in higher overall classification accuracy. Cereal classification exhibited excellent precision ranging from 85.8% to 95.1% when utilizing S2 data, while lower accuracy (41% to 91.8%) was obtained when using only Landsat data. A slight confusion between cereals and cereals growing with olive trees was observed. A second objective was to map cereals as early as possible in the agricultural season. An early cereal classification model demonstrated accurate results in February (four months before harvest), with a precision of 95.2% and an OA of 87.7%. When applied to the entire period, February cereal classification exhibited a precision ranging from 85.1% to 94.2% when utilizing S2 data, while lower accuracy (42.6% to 95.4%) was observed in general with Landsat data. This methodology could be adopted in other cereal regions with similar climates to produce very useful information for the planner, leading to a reduction in fieldwork.


  • Open Access

    Modeling Hydrological Responses to Land Use Change in Sejnane Watershed, Northern Tunisia

    by Manel Mosbahi, Zeineb Kassouk, Sihem Benabdallah, Jalel Aouissi, Rihab Arbi, Mouna Mrad, Reginald Blake, Hamidreza Norouzi, Béchir Béjaoui

    Land use change is a crucial driving factor in hydrological processes. Understanding its long-term dynamics is essential for sustainable water resources management. This study sought to quantify and analyze land use change between 1985 and 2021 and its impacts on the hydrology of the Sejnane watershed, northern Tunisia. Remote sensing and a SWAT model using the SUFI-2 algorithm to identify the most sensitive parameters were used to achieve this objective. Land use maps were developed for 1985, 2001 and 2021. For the last 37 years, the watershed experienced a slight decrease in forest, scrubland and forage crops, a significant reduction in grassland, and a conspicuous expansion of olive trees and vegetable crops. Given the scarcity of observed discharge data, a SWAT model was calibrated for the period 1997–2010 and validated for 2011–2019. Model performance was good for both calibration (NSE = 0.78, PBIAS = −6.6 and R2 = 0.85) and validation (NSE = 0.70, PBIAS = −29.2 and R2 = 0.81). Changes in land use strongly affected the water balance components. Surface runoff and percolation were the most influenced, showing an increase in runoff and a decrease in percolation by 15.5% and 13.8%, respectively. The results revealed that the construction of the Sejnane dam, the extension of irrigated perimeters and olive tree plantations were the major contributors to changes in hydrology.


  • Open Access

    Cereal Crops Soil Parameters Retrieval Using L-Band ALOS-2 and C-Band Sentinel-1 Sensors

    by Emna Ayari, Zeineb Kassouk, Zohra Lili-Chabaane, Nicolas Baghdadi, Safa Bousbih, Mehrez Zribi

    This paper discusses the potential of L-band Advanced Land Observing Satellite-2 (ALOS-2) and C-band Sentinel-1 radar data for retrieving soil parameters over cereal fields. For this purpose, multi-incidence, multi-polarization and dual-frequency satellite data were acquired simultaneously with in situ measurements collected over a semiarid area, the Merguellil Plain (central Tunisia). The L- and C-band signal sensitivity to soil roughness, moisture and vegetation was investigated. High correlation coefficients were observed between the radar signals and soil roughness values for all processed multi-configurations of ALOS-2 and Sentinel-1 data. The sensitivity of SAR (Synthetic Aperture Radar) data to soil moisture was investigated for three classes of the normalized difference vegetation index (NDVI) (low vegetation cover, medium cover and dense cover), illustrating a decreasing sensitivity with increasing NDVI values. The highest sensitivity to soil moisture under the dense cover class is observed in L-band data. For various vegetation properties (leaf area index (LAI), height of vegetation cover (H) and vegetation water content (VWC)), a strong correlation is observed with the ALOS-2 radar signals (in HH(Horizontal-Horizontal) and HV(Horizontal-Vertical) polarizations). Different empirical models that link radar signals (in the L- and C-bands) to soil moisture and roughness parameters, as well as the semi-empirical Dubois modified model (Dubois-B) and the modified integral equation model (IEM-B), over bare soils are proposed for all polarizations. The results reveal that IEM-B performed a better accuracy comparing to Dubois-B. This analysis is also proposed for covered surfaces using different options provided by the water cloud model (WCM) (with and without the soil–vegetation interaction scattering term) coupled with the best accuracy bare soil backscattering models: IEM-B for co-polarization and empirical models for the entire dataset. Based on the validated backscattering models, different options of coupled models are tested for soil moisture inversion. The integration of a soil–vegetation interaction component in the WCM illustrates a considerable contribution to soil moisture precision in the HV polarization mode in the L-band frequency and a neglected effect on C-band data inversion.


  • Open Access

    Ability of Vis-PIR spectroscopy to monitor changes in organic carbon of loamy soils at two depths

    by Hayfa Zayani, Youssef Fouad, Didier Michot, Zeineb Kassouk, Zohra Lili-Chabaane, Christian Walter

    Visible-Near Infrared (Vis-NIR) spectroscopy has proven its efficiency in predicting several soil properties such as soil organic carbon (SOC) content. In this preliminary study, we explored the ability of Vis-NIR to assess the temporal evolution of SOC content. Soil samples were collected in a watershed (ORE AgrHys), located in Brittany (Western France). Two sampling campaigns were carried out 5 years apart: in 2013, 198 soil samples were collected respectively at two depths (0-15 and 15-25 cm) over an area of 1200 ha including different land use and land cover; in 2018, 111 sampling points out of 198 of 2013 were selected and soil samples were collected from the same two depths. Whole samples were analyzed for their SOC content and were scanned for their reflectance spectrum. Spectral information was acquired from samples sieved at 2 mm fraction and oven dried at 40°C, 24h prior to spectra acquisition, with a full range Vis-NIR spectroradiometer ASD Fieldspec®3. Data set of 2013 was used to calibrate the SOC content prediction model by the mean of Partial Least Squares Regression (PLSR). Data set of 2018 was therefore used as test set. Our results showed that the variation ∆SOCobsobtained from observed values in 2013 and 2018 (∆SOCobs = Observed SOC (2018) - Observed SOC (2013)) is ranging from 0.1 to 25.9 g/kg. Moreover, our results showed that the prediction performance of the calibrated model was improved by including 11 spectra of 2018 in the 2013 calibration data set (R²= 0.87, RMSE = 5.1 g/kg and RPD = 1.92). Furthermore, the comparison of predicted and observed ∆SOC between 2018 and 2013 showed that 69% of the variations were of the same sign, either positive or negative. For the remaining 31%, the variations were of opposite signs but concerned mainly samples for which ∆SOCobs is less than 1,5 g/kg. These results reveal that Vis-NIR spectroscopy was potentially appropriate to detect variations of SOC content and are encouraging to further explore Vis-NIR spectroscopy to detect changes in soil carbon stocks.

  • Open Access

    Contribution of remote sensing and auxiliary variables in the study of the evolution of periods of droughts

    by Nesrine Farhani, Gilles Boulet, Julie Carreau, Zeineb Kassouk, Michel Le Page, Zohra Lili Chabaane, Rim Zitouna

    In semi-arid areas, plant water use and plant water stress can be derived over largeareas from remotely sensed evapotranspiration estimates. Those can help us to monitor theimpact of drought on the agro- and ecosystems. Both variables can be simulated by a dualsource energy balance model that relies on meteorological variables (air temperature, relativehumidity, wind speed and global radiation) and remote sensing data (surface temperature,NDVI, albedo and LAI). Surface temperature acquired in the Thermal InfraRed (TIR) domainis particularly informative for monitoring agrosystem health and adjusting irrigationrequirements. However, available meteorological observations period may often beinsufficient to account for the variability present in the study area. Statistical downscalingmethods applied to reanalysis data can serve to generate surrogate series of meteorologicalvariables that either fill the gaps in the observation period or extend the observation period inthe past. For this aim, a stochastic weather generator (SWG) is adapted in order to computetemporal extension of multiple meteorological variables. This surrogate series is then used toconstrain the dual-source model Soil Plant Atmosphere and Remote Evapotranspiration(SPARSE). Stress index anomalies retrieved from SPARSE are then compared to anomalies inother wave lengths in order to assess their capacity to detect incipient water stress and earlydroughts at the kilometer resolution. Those are the root zone soil moisture at low resolutionderived from the microwave domain, and active vegetation fraction cover deduced fromNDVI time series.

  • Open Access

    Soil moisture estimation over cereals fields using l-band alos2 data (merguellil case – KAIROUAN)

    by Emna Ayari, Zeineb Kassouk, Zohra Lili Chabaane, Safa Bousbih, Mehrez Zribi

    Soil moisture is a key component for water resources management especially for irrigation needs estimation. We analyze in the present study, the potential of L-band data, acquired by (Advanced Land Observing Satellite-2) ALOS-2, to retrieve soil moisture over bare soils and cereal fields located in semi-arid area in the Kairouan plain.In this context, we evaluate radar signal sensitivity to roughness, soil moisture and vegetation biophysical parameters. Based on multi-incidence radar data (28°, 32.5° and 36°), high correlations characterize relationships between backscattering coefficients in dual-polarization (HH and HV) and root mean square of heights (Hrms) and Zs, parameters, Sensitivity of radar data to soil moisture was discussed for three classes of NDVI (less than 0.25 for bare soils and dispersed vegetation, between 0.25 and 0.5 for medium vegetation and greater than 0.5 for dense cereals). With vegetation development, where NDVI values are higher than 0.25, SAR signal remains sensitive to soil moisture in HH pol. This sensitivity to moisture disappears, in HV pol for dense vegetation. For covered fields, L-band signal is very sensitive to Vegetation Water Content (VWC), with R² values ranging between 0.76 and 0.61 in HH and HV polarization respectively.Simulating signal behavior is carried out through various models over bare soils and covered cereal fields. Over bare soils, proposed empirical expressions, modified versions of Integral Equation Model (IEM-B) and Dubois models (Dubois-B) are evaluated, generally for HH and HV polarizations. Best consistency is observed between real data and IEM-B backscattering simulations in HH polarization. More discrepancies between real and modelled data are observed in HV polarization.Furthermore, to simulate L-band signal behavior over covered fields, the inversion of Water Cloud Model (WCM) coupled to different bare soil models is realized through direct equations and Look-up tables. Two options of WCM, are tested (with and without soil-vegetation interaction scattering term). For the first option, results highlight the good performance of IEM-B coupled to WCM in HH polarization with RMSE value between estimated and in situ moisture measurements equal to 4.87 vol.%. By adding soil – cereal interaction term in the second option of WCM, results reveal a stable accuracy in HH polarization and an important improvement of soil moisture estimations in HV polarization, with RMSE values are ranging between 6 and 7 vol.%.