Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Imane Serbouti has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Characterisation of extreme events through satellite and model-based soil moisture products over Europe and Africa

    by Jaime Gaona, Luca Brocca, Vaibhav Kumar, Paolo Filipucci, Mohamad Usman Liaqat, Imane Serbouti

    Records of soil moisture dynamics are the land register of the convolution of footprints of the multiple water fluxes that intervene in the soil. Therefore, the variability of soil moisture changes occurring at a specific location expresses not only the stochastic nature of soil moisture but, more importantly, differences in the statistics of their distribution in space and time, which can be used to classify patterns of soil moisture regime across space and time. The analysis of hydrological extremes often deals with the scarcity of data (i.e. insufficient extreme events contained in the series, which biases the range of values from reality). Fortunately, earth observation data is increasingly providing reliable distributed datasets whose spatial detail can compensate for the limitation in time length. This is particularly true for soil moisture data whose ground records rarely surpass decades but whose distributed data is achieving resolutions that, despite persistent applicability limits below certain resolutions, can ease the analysis of soil moisture variability. Accordingly, this study analyses the temporal changes in soil moisture of various types of soil moisture products across all cells of the adopted 5 x 5 Km grid across Europe and Africa, in both the rewetting and drying signs of change, with the aim of finding distinct ranges and frequency-magnitude characteristics along the distribution of soil moisture changes. Special attention is devoted to the soil moisture changes distribution’s upper tail (extreme events like floods (positive change) and flash drought (negative change)) and lower tail (detection limit, product sensitivity). Three types of soil moisture products are used (remote sensing passive: ESA CCI passive subset; remote sensing active: EUMETSAT ASCAT; and model-based: LISFLOOD model integrated in the European Copernicus Emergency Monitoring System (CEMS)) to evaluate their ability to show consistency across ranges of the distribution of soil moisture changes so that it can ensure the efficacy of monitoring systems integrating earth observation and modelling data. The analyses to extremes applied to soil moisture change data show results consistent and complementary to those published for rainfall and runoff generation, identify the areas where soil moisture mediation of the water cycle is more relevant in relation to hydrological regime classification and map thresholds of impactful events. But more importantly, results reveal notable disparity in the estimation of the relevance of an event (magnitude (expressed as intensity of change) and occurrence (expressed in frequency or return period), particularly in the most impactful cases of extreme events, entailing gaps between the dynamics detected by current soil moisture products and their true dynamics. Such disparities among datasets must be prevented from propagating to monitoring systems. Therefore, the approach provides insights for the continuous upgrading of the products’ consistency (i.e. remote sensing and model-based datasets), while encourages adopting metrics of distribution consistency in the early warning system pipelines, particularly across impactful ranges of soil moisture value change, to improve the monitoring accuracy according to the regional characteristics, with subsequent benefits to the efficacy of responses to the impacts.

  • Open Access

    Hotspots of drought–flood abrupt transitions from hydroclimatic volatility to hydrologic extremes under land cover change

    by Imane Serbouti, Luca Brocca

    Drought–flood abrupt transitions are a manifestation of hydroclimatic volatility and can lead to hydrologic extremes that are influenced by the amplification of wet-dry anomalies through land-surface dynamics and watershed storage. In addition to meteorological forcing, land cover changes can modify infiltration–runoff partitioning, evapotranspiration feedback, and soil-moisture persistence, thereby reshaping where transition hotspots emerge and how abruptly they evolve. This study quantifies drought–flood transition regimes in the semi-arid Ebro basin and evaluates how land cover changes modulate the propagation of hydroclimatic variability into hydrologic regime transitions. The Precipitation–Evaporation Anomaly Index (PEAI) is computed from HYPER-P 1km precipitation and GLEAM evapotranspiration, providing a high-resolution description of hydroclimatic deficit–surplus anomalies over 2016–2022. PEAI is integrated with surface soil-moisture anomaly dynamics derived from Sentinel-1 radar to compute high-frequency ΔSM anomalies. These ΔSM anomaly sequences provide the basis for deriving soil-moisture memory (SMM) at fine spatial and temporal scales, with persistence, decay, and instability quantified. Drought–flood transitions are delineated by persistent PEAI anomaly reversals and retained only when accompanied by a coherent ΔSM response, after which events are mapped to delineate hotspots and summarized using metrics of frequency, duration, and abruptness. Land cover change is derived from the Copernicus datasets, which provide annual land-cover maps from 2016 to 2022, and is used to stratify SMM properties and transition metrics to compare transition behavior under similar PEAI variability across areas with different land-cover patterns. Results show pronounced dry–wet alternations and spatially heterogeneous soil-moisture memory, with short persistence and elevated instability in recurrent transition zones. These SMM signatures sharpen the delineation of hydroclimatic volatility hotspots and improve the spatial identification of rapid drought–flood abrupt transition events. Transition frequency and abruptness are not explained by PEAI intensity alone; instead, they vary systematically with land-cover patterns, revealing distinct transition regimes across cropland-dominated areas, natural vegetation, and expanding built-up surfaces. Overall, integrating PEAI derived from HYPER-P precipitation and GLEAM evapotranspiration with radar-based ΔSM and SMM provides a physically consistent, high-resolution framework to explain how hydroclimatic volatility propagates into hydrologic extremes through drought–flood abrupt transitions shaped by land cover change in a semi-arid Mediterranean basin.

  • Top Cited Papers
    Open Access

    Digital Transformation in African Heritage Preservation: A Digital Twin Framework for a Sustainable Bab Al-Mansour in Meknes City, Morocco

    by Imane Serbouti, Jérôme Chenal, Saâd Abdesslam Tazi, Ahmad Baik, Mustapha Hakdaoui

    The advent of digital transformation has redefined the preservation of cultural heritage and historic sites through the integration of Digital Twin technology. Initially developed for industrial applications, Digital Twins are now increasingly employed in heritage conservation as dynamic, digital replicas of physical assets and environments. These systems enable detailed, interactive approaches to documentation, management, and preservation. This paper presents a detailed framework for implementing Digital Twin technology in the management of heritage buildings. By utilizing advanced methods for data collection, processing, and analysis, the framework creates a robust data hub for Digital Twin Heritage Buildings (DTHB). This architecture enhances real-time monitoring, improves accuracy, reduces operational costs, and enables predictive maintenance while minimizing invasive inspections. Focusing on Bab Al-Mansour Gate in Meknes, Morocco, a significant cultural landmark, this research outlines the workflow for developing a Bab Al-Mansour DTHB platform. The platform monitors structural health and detects damage over time, offering a dynamic tool for conservation planning. By integrating innovative technologies with data-driven solutions, this study provides a replicable model for preserving heritage sites, addressing critical gaps in real-time monitoring, resource optimization, and environmental risk mitigation.


  • Open Access

    Smart PV Monitoring and Maintenance: A Vision Transformer Approach within Urban 4.0

    by Mariem Bounabi, Rida Azmi, Jérôme Chenal, El Bachir Diop, Seyid Abdellahi Ebnou Abdem, Meriem Adraoui, Mohammed Hlal, Imane Serbouti

    The advancement to Urban 4.0 requires urban digitization and predictive maintenance of infrastructure to improve efficiency, durability, and quality of life. This study aims to integrate intelligent technologies for the predictive maintenance of photovoltaic panel systems, which serve as essential smart city renewable energy sources. In addition, we employ vision transformers (ViT), a deep learning architecture devoted to evolving image analysis, to detect anomalies in PV systems. The ViT model is pre-trained on ImageNet to exploit a comprehensive set of relevant visual features from the PV images and classify the input PV panel. Furthermore, the developed system was integrated into a web application that allows users to upload PV images, automatically detect anomalies, and provide detailed panel information, such as PV panel type, defect probability, and anomaly status. A comparative study using several convolutional neural network architectures (VGG, ResNet, and AlexNet) and the ViT transformer was conducted. Therefore, the adopted ViT model performs excellently in anomaly detection, where the ViT achieves an AUC of 0.96. Finally, the proposed approach excels at the prompt identification of potential defects detection, reducing maintenance costs, advancing equipment lifetime, and optimizing PV system implementation.


  • Open Access

    Assessing the Impact of Agricultural Practices and Urban Expansion on Drought Dynamics Using a Multi-Drought Index Application Implemented in Google Earth Engine: A Case Study of the Oum Er-Rbia Watershed, Morocco

    by Imane Serbouti, Jérôme Chenal, Biswajeet Pradhan, El Bachir Diop, Rida Azmi, Seyid Abdellahi Ebnou Abdem, Meriem Adraoui, Mohammed Hlal, Mariem Bounabi

    Drought monitoring is a critical environmental challenge, particularly in regions where irrigated agricultural intensification and urban expansion pressure water resources. This study assesses the impact of these activities on drought dynamics in Morocco’s Oum Er-Rbia (OER) watershed from 2002 to 2022, using the newly developed Watershed Integrated Multi-Drought Index (WIMDI), through Google Earth Engine (GEE). WIMDI integrates several drought indices, including SMCI, ESI, VCI, TVDI, SWI, PCI, and SVI, via a localized weighted averaging model (LOWA). Statistical validation against various drought-type indices including SPI, SDI, SEDI, and SMCI showed WIMDI’s strong correlations (r-values up to 0.805) and lower RMSE, indicating superior accuracy. Spatiotemporal validation against aggregated drought indices such as VHI, VDSI, and SDCI, along with time-series analysis, confirmed WIMDI’s robustness in capturing drought variability across the OER watershed. These results highlight WIMDI’s potential as a reliable tool for effective drought monitoring and management across diverse ecosystems and climates.


  • Open Access

    Monitoring Earthquake Risks in Nador, Northeast Morocco

    by Mohammed Hlal, Rida Azmi, El Bachir Diop, Meriem Adraoui, Seyid Abdellahi Ebnou Abdem, Imane Serbouti, Mariem Bounabi, Jérôme Chenal

    Earthquake events present a high risk in urban areas. Nador City is a Mediterranean city located in a dynamic zone with seismologic movement and a frequency of earthquake events per year. This worrying rate shows that earthquake risks can hinder the urban area and damage citizens and goods if urban risk management is not taken. This study defines the areas most threatened by seismic events to protect them as a priority. Using Geographic Information System, Corine Land Cover, seismic intensity, and socioeconomic vulnerability index, we mapped the urban vulnerability index. The adopted model determines urban vulnerability levels from urban land cover, topography, geologic factors, and geomorphologic factors. These approaches reveal that $70\%$ of Nador is under the damage of a seismic disaster. In addition, the main objective is to apply a new set of guidelines to map the intensity of risks and explain the distinct risk exposure level in Nador’s urban context.


  • Open Access

    Improved Lithological Map of Large Complex Semi-Arid Regions Using Spectral and Textural Datasets within Google Earth Engine and Fused Machine Learning Multi-Classifiers

    by Imane Serbouti, Mohammed Raji, Mustapha Hakdaoui, Fouad El Kamel, Biswajeet Pradhan, Shilpa Gite, Abdullah Alamri, Khairul Nizam Abdul Maulud, Abhirup Dikshit

    In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km2 area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions.


  • Open Access

    Pixel and Object-Based Machine Learning Classification Schemes for Lithological Mapping Enhancement of Semi-Arid Regions Using Sentinel-2A Imagery: A Case Study of the Southern Moroccan Meseta

    by Imane Serbouti, Mohammed Raji, Mustapha Hakdaoui, Biswajeet Pradhan, Chang-Wook Lee, Abdullah M. Alamri

    Mapping lithological units of an area using remote sensing data can be broadly grouped into pixel-based (PBIA), sub-pixel based (SPBIA) and object-based (GEOBIA) image analysis approaches. Since it is not only the datasets adequacy but also the correct classification selection that influences the lithological mapping. This research is intended to analyze and evaluate the efficiency of these three approaches for lithological mapping in semi-arid areas, by using Sentinel-2A data and many algorithms for image enhancement and spectral analysis, in particular two specialized Band Ratio (BR) and the Independent component analysis (ICA), for that reason the Paleozoic Massif of Skhour Rehamna, situated in the western Moroccan Meseta was chosen. In this study, the support vector machine (SVM) that is theoretically more efficient machine learning algorithm (MLA) in geological mapping is used in PBIA and GEOBIA approaches. The evaluation and comparison of the performance of these different methods showed that SVM-GEOBIA approach gives the highest overall classification accuracy (OA $\approx ~93$ %) and kappa coefficient (K) of 0, 89, while SPBIA classification showed OA of approximately 89% and kappa coefficient of 0, 84, whereas the lithological maps resulted from SVM-PBIA method exhibit salt and pepper noise, with a lower OA of 87% and kappa coefficient of 0, 80 comparing them with the other classification approaches. From the results of this comparative study, we can conclude that the SVM-GEOBIA classification approach is the most suitable technique for lithological mapping in semi-arid regions, where outcrops are often inaccessible, which complicates classic cartographic work.