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


Mourtadha Sarhan Sachit has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Water Harvesting for Improving Rainwater Use Efficiency Using GIS: A Case Study, Tigris River Basin, Iraq

    by Basim M. Al-Zaidi, Mohammed H. Al-Umar, Mourtadha Sarhan Sachit

    The distribution of rainfall in dry areas, such as Iraq, is extremely erratic. The rainfall is mostly limited to occasional, intense, and unpredictable storms with high surface runoff and uncontrolled gullies and rills flowing on soils with low infiltration rates, and then it is collected at the end in wadis. Thus, most of the rainwater is lost as evaporation if not harvested. The objectives of this work were to explore the promising water harvesting areas of the Tigris River Basin (TRB), evaluate the amount of harvested rainwater from the river basin in Iraq, and then how to improve rainwater use efficiency. The GIS technique was utilized to examine the hydrological characteristics of the basin and locate the rainwater harvesting sites. The volumes of the harvested water (runoff) were assessed utilizing the SCS-CN method. The results showed that about 70% of the river basin inside Iraq is suitable for rainwater harvesting with a total annual runoff of 324 BCM. The results demonstrated that the harvested rainwater use efficiency ratio increases with the increasing amount of the used water or the relative water protectivity per unit area. The paper presented some suggestions and recommendations for improving rainwater use efficiency in the catchments of the TRB within Iraq.

  • Open Access

    Geospatial Artificial Intelligence-based Approach for Predicting Slum Growth, a Case in Iraq

    by Hussein Riyadh Sarhan, Yousif A. Mousa, Sarah Abdulkareem Hanoon, Mourtadha Sarhan Sachit

    The spread of slums poses a major challenge to urban planning, necessitating the development of effective predictive models to mitigate its impact on sustainable development. This study aims to spatially predict areas at risk of slum expansion in Al-Bathaa City, Iraq. To this end, conditioning factors were identified and developed using Geospatial Information Systems (GIS), including proximity to roads, agricultural lands, public services, neglected areas, and water sources. Three Artificial Intelligence (AI) algorithms were examined: Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). The models' performance was evaluated using several metrics, such as classification accuracy (CA), F1-score, recall, and precision. The most accurate model was then utilized to predict the spatial expansion of slums. The results revealed the superiority of the RF algorithm, which achieved a CA of 0.949. The slum risk index indicated that more than 12% (~600,000 m²) of the study area is at high risk of slum expansion in the near future. The developed slum expansion index will assist decision-makers in responding quickly and devising appropriate plans to prevent slum expansion, thereby promoting urban sustainability and effective land-use planning.

  • Open Access

    A Hierarchical approach for efficient DTM and building footprint extraction from UAV images

    by Yousif A Mousa, Mourtadha Sarhan Sachit, Ali Fadhil Hasan

    The utilisation of UAV imagery for the creation of digital maps is a compelling subject within the domains of photogrammetry and remote sensing. This work introduces a hierarchical method for automating the process of building, extracting, and outlining using images captured by drones. The flight plan should be initially planned to provide about 60-70\% overlap to guarantee thorough coverage and precise image matching. The altitude of the drone should be adjusted based on the intended resolution to achieve a balance between capturing fine details and covering a larger region. Next, the technique of photogrammetric image matching was utilised to generate orthophotos and the Digital Surface Model (DSM). Moreover, the Digital Terrain Model (DTM) was extracted from the DSM to differentiate non-ground objects, including buildings. Subsequently, building segments were identified by applying a threshold to the difference between the Digital Surface Model (DSM) and the Digital Terrain Model (DTM), enabling accurate extraction of building segments. Finally, building polygons were generated involving two stages: coarse and refined, considering the least squares adjustment process to guarantee accuracy and detail. The proposed method was applied to drone images captured on the campus of Al-Muthanna University in the southwest of Iraq. The qualitative and quantitative investigation indicated that the building polygons obtained were highly promising, with approximately one-meter geometric accuracy. Nevertheless, accurately differentiating between buildings and other human-made structures (such as tents) and resolving issues related to mismatching error still pose significant difficulties, highlighting the need for additional investigation and development.


  • Open Access

    Evaluating the Performance of Supervised Classification Algorithms in Classifying SENTINEL-2A Images on Land Cover and Land Uses of a Part of Baghdad, Iraq

    by Mourtadha Sarhan Sachit, Sajaa Muhsein Khazael, Hiba Akram Atiyah

    Nowadays, remote sensing (RS) technology is being recognized as the most up-to-date data source used in land cover and land use exploration. However, the sources of RS data, the type of algorithms applied, and the study area characteristics all influence how accurately relevant thematic maps are produced. This paper aims to assess the classification performance of supervised machine learning algorithms over regions affected by dust storm depositions. To this end, SENTINEL-2 imagery across the city of Baghdad, Iraq are considered. Data preprocessing is carried out using SNAP software. Maximum Likelihood (ML), Minimum Distance (MD), Random Forest (RF), K-Nearest Neighbor (KNN) and KD Tree KNN (KD-KNN) models are applied to produce land-use maps of five classes. Finally, a confusion matrix is implemented to examine the classification accuracy. The results revealed the superiority of the RF classifier with an overall accuracy of 83.33%. Followed by KNN and KD-KNN with an accuracy of 80% each. Arid lands scored the highest rating in most of the applied algorithms. The reported findings raise awareness regarding the selection of suitable algorithms for specific classification tasks.


  • Open Access

    A comprehensive evaluation of deep vision transformers for road extraction from very-high-resolution satellite data

    by Jan Bolcek, Mohamed Barakat A. Gibril, Rami Al-Ruzouq, Abdallah Shanableh, Ratiranjan Jena, Nezar Hammouri, Mourtadha Sarhan Sachit, Omid Ghorbanzadeh


  • Open Access

    Ensemble Weights-Based Geospatial Model for Optimal Allocation of Wind Turbines: A Case Study in Wasit, Iraq

    by Mourtadha Sarhan Sachit

    Accurate spatial decision-making models are increasingly needed for wind energy planning as the globe rushes towards carbon-neutral energy. This research aims to improve existing decision-making approaches by proposing an ensemble weight-based model for mapping the spatial suitability of onshore wind systems. The model addressed three weighting scenarios: subjective weighting derived from the Analytical Hierarchy Process (AHP), objective weighting derived from the Entropy Weighting Method (EWM), and Artificial Intelligence (AI) weighting based on real-world experiences. The weight sources were harnessed in weighted and fuzzy overlays in a GIS context to create multiple suitability indices. The model was applied to the Wasit governorate in Iraq, considering 10 evaluation criteria and 6 restrictions. The results highlight the dominance of techno-economic considerations, with wind speed being an important factor in all weighting scenarios. Suitability indices suggest that the western, central, and southern areas of Wasit are most suitable for wind farms, with ideal sites identified south of Al-Hay, south of Sheikh Saad, and west of Al-Kut, covering an area of 756 km 2 and potentially providing more than 3.5 GW of clean electricity. The findings could encourage wind energy investment in developing countries like Iraq.


  • Assessment of Machine Learning Algorithms for Predicting Potential Solar and Wind Energy Locations

    by Hicham Mhamdi, Omar Kerrou, Mourtadha Sarhan, Zouhair Sadoune, Mohammed Aggour


  • Large-scale assessment of date palm plantations based on UAV remote sensing and multiscale vision transformer

    by Mohamed Barakat A. Gibril, Helmi Zulhaidi Mohd Shafri, Abdallah Shanableh, Rami Al-Ruzouq, Shaiful Jahari bin Hashim, Aimrun Wayayok, Mourtadha Sarhan Sachit


  • Open Access

    Content Validity-Based Evaluation Criteria System for Siting Wind-Solar Plants

    by Mourtadha Sarhan Sachit, Helmi Zulhaidi Mohd Shafri, Ahmad Fikri Abdullah, Azmin Shakrine Mohd Rafie, Sadeq Khaleefah Hanoon

    The spatial assessment criteria system for hybridizing renewable energy sources, such as hybrid solar-wind farms, is critical in selecting ideal installation sites that maximize benefits, reduce costs, protect the environment, and serve the community. However, a systematic approach to designing indicator systems is rarely used in relevant site selection studies. Therefore, the current paper attempts to present an inclusive framework based on content validity to create an effective criteria system for siting wind-solar plants. To this end, the criteria considered in the related literature are captured, and the top 10 frequent indicators are identified. The Delphi technique is used to subject commonly used factors to expert judgments. Other factors are considered according to expert recommendations. In this context, the assessment tool was a combination of questionnaires and interviews with experts from scientific backgrounds that reflect the measurement target. The item-level content validity index (I-CVI) is applied along with the modified Kappa statistic (k*) to analyze expert ratings and suggestions. The results demonstrate the superiority of 9 and 4 commonly used factors and the suggested factors, respectively. The 13 criteria have achieved high agreement among experts at I-CVIs ≥ 0.78 and k*s > 0.76. The conclusion can be drawn that the modified Kappa statistic used in this analysis has a more significant effect on eliminating irrelevant factors. The current methodology and consequences might pave the way for making informed decisions to locate wind and solar farms.


  • Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images

    by Mohamed Barakat A. Gibril, Helmi Zulhaidi Mohd Shafri, Abdallah Shanableh, Rami Al-Ruzouq, Aimrun Wayayok, Shaiful Jahari bin Hashim, Mourtadha Sarhan Sachit

    Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.