Abdul Razzak T. Ziboon

Prof. Dr. Abdul Razzak T. Ziboon


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Abbas Mohammed NooriAbbas Mohammed Noori
Abbas Mohammed Noori
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
AAAmjed N. Al-Hameedawi
Amjed N. Al-Hameedawi
Flash floods are natural disasters that have significant impacts on human life and economic damage. The detection of flash floods using remote-sensing techniques provides essential data for subsequent flood-risk assessment through the preparation of flood inventory samples. In this research, a new deep-learning approach for bi-temporal flash-flood detection in Synthetic Aperture Radar (SAR) is proposed. It combines a U-Net convolutional network with a Transformer model using a compact Convolutional Tokenizer (CCT) to improve the efficiency of long-range dependency learning. The hybrid model, namely CCT-U-ViT, naturally combines the spatial feature extraction of U-Net and the global context capability of Transformer. The model significantly reduces the number of basic blocks as it uses the CCT tokenizer instead of conventional Vision Transformer tokenization, which makes it the right fit for small flood detection datasets. This model improves flood boundary delineation by involving local spatial patterns and global contextual relations. However, the method is based on Sentinel-1 SAR images and focuses on Erbil, Iraq, which experienced an extreme flash flood in December 2021. The experimental comparison results show that the proposed CCT-U-ViT outperforms multiple baseline models, such as conventional CNNs, U-Net, and Vision Transformer, obtaining an impressive overall accuracy of 91.24%. Furthermore, the model obtains better precision and recall with an F1-score of 91.21% and mIoU of 83.83%. Qualitative results demonstrate that CCT-U-ViT can effectively preserve the flood boundaries with higher precision and less salt-and-pepper noise compared with the state-of-the-art approaches. This study underscores the significance of hybrid deep-learning models in enhancing the precision of flood detection with SAR data, providing valuable insights for the advancement of real-time flood monitoring and risk management systems.

14 August 2024 in Sustainable Water Resources Management
Verified
Journal Article
Open access
PDF file
IHIsraa Hatem
Israa Hatem
IAImzahim A. Alwan
Imzahim A. Alwan
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
Alban KuriqiAlban Kuriqi
Alban Kuriqi
Droughts, stemming from prolonged periods of scarce precipitation, lead to significant economic and societal consequences. Iraq has recurrently experienced the impact of severe droughts. This study assessed meteorological drought over Iraq, employing the Standardized Precipitation Index (SPI) on 12-month time scales from 2000 to 2022. The SPI values were calculated for 27 meteorological stations over Iraq based on the monthly datasets. The analysis of the SPI highlighted that the years 2000, 2008, 2009, 2010, 2012, 2018, and 2022 stood out as the driest in Iraq from 2000 to 2022. Notably, 2022 emerged as a particularly severe drought year, with the Ramadi weather station recording the maximum SPI value at -3.48. Different time scales in the analysis provided a more precise depiction of drought severity and frequency in Iraq. Namely, the findings resulting from this study offer a nuanced understanding of the magnitude, intensity, frequency, and duration of drought events in Iraq. This nuanced approach equips stakeholders with valuable insights for implementing more cost-effective mitigation and adaptation measures. This study contributes crucial information for understanding and addressing droughts challenges in Iraq. The comprehensive analysis aids in formulating targeted strategies to alleviate the impact of droughts on people and ecosystems.

1 January 2024 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
PDF file
MMMuthmainnah Muthmainnah Muthmainnah
Muthmainnah Muthmainnah Muthmainnah
AYAhmad Al Yakin
Ahmad Al Yakin
AOAhmad J. Obaid
Ahmad J. Obaid
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
Every form of intelligence relies on learning, but artificial intelligence seeks to understand how computers learn, while human intelligence seeks to understand Every form of intelligence relies on learning, but artificial intelligence seeks to understand how computers learn, while human intelligence seeks to understand

17 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Abbas Mohammed NooriAbbas Mohammed Noori
Abbas Mohammed Noori
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
AAAmjed Naser Al-Hameedawi
Amjed Naser Al-Hameedawi
A new deep learning approach for bi-temporal flash flood detection in synthetic aperture radar (SAR) is proposed in this research. It combines a U-Net convolutional network with a Transformer model using a compact Convolutional Tokenizer (CCT) to improve the efficiency of long-range dependency learning. The hybrid model, namely CCT-U-ViT, that naturally combines the spatial feature extraction of U-Net and the global context capability of Transformer. The model significantly reduces the number of basic blocks as it uses the CCT tokenizer instead of conventional Vision Transformer tokenization, which makes it the right fit for small flood detection datasets. This model improves flood boundary delineation by involving local spatial patterns and global contextual relations. However, the method is based on Sentinel-1 SAR images and focuses on Erbil, Iraq, that experienced an extreme flash flood in December 2021. The experimental comparison results show that the proposed CCT-U-ViT outperforms multiple baseline models, such as conventional CNNs, U-Net, and Vision Transformer, obtaining an impressive overall accuracy of 91.24%. In addition, Furthermore, the model gets better precision and recall with F1-score of 91.21% and mIoU of 83.83%. Qualitative results demonstrate that CCT-U-ViT can effectively preserve the flood boundaries with higher precision and less salt-and-pepper noise compared with the state-of-the-art approaches. This study underscores the significance of hybrid deep learning models in enhancing the precision of flood detection with SAR data, providing valuable insights for the advancement of real-time flood monitoring and crisis management systems.

1 January 2023 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
TATamara Sami Abdul-Jabbar
Tamara Sami Abdul-Jabbar
MAMuthana Mohammed A. Albayati
Muthana Mohammed A. Albayati
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
Crop yield estimation is critical for planning and making diverse policy decisions. Many countries depend on traditional methods of collecting data, such as ground-based inspections and reports, for crop yield estimation. These techniques are uncertain, expensive, and time-consuming. Environmental conditions have the primary effect on crop productivity. The weather influences crop growth and development, resulting in significant intra-seasonal yield diversity. The remote sensing dataset offers the opportunity to estimate cropland at different scales, from field-level to district-level, depending on plant and vegetation properties relating to vegetation indices. This study aims to assess the effects of environmental factors, radiometric and spatial resolution, and the coverage area of different remote sensing data sets; Landsat-8 OLI (30m), Sentinel-2 (10m), and Spot-7 (6m) images on wheat crop yield estimates in the Az-Zubaydiyah District in Wasit province in Iraq for the period between (2016–2021). Statistical analysis determined the association between the normalized difference vegetation index (NDVI), the soil-adjusted vegetation index (SAVI), and actual wheat croplands. The images showed an efficient estimate at different scales, with accurate results of 96%, with Sentinel-2 data and more than 97%, with Landsat-8 data when using (NDVI), and more than 97% with Sentinel-2 and Landsat-8 data when using (SAVI) at the sub-district level, where the results were dropped down about 5% at the district level, more significant than 90% with Landsat-8 using (NDVI), and bigger than 91% using (SAVI). The large pixel size of the Landsat-8 OLI causes many mixed pixels of wheat crop and other objects in which the accuracy of its production estimate is lower than that of the Sentinel-2 image. Also, environmental factors had an apparent effect on crop yield in 2018, when the temperature was less than the optimal determination degree for wheat limitation. As a result, it shows a sudden drop between the early estimation and the remote sensing rating, which was more accurate.

1 January 2023 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
MFMohammed Fadhil
Mohammed Fadhil
AZAbdul Razzak T. Ziboon
Abdul Razzak T. Ziboon
MHMustafa N. Hamoodi
Mustafa N. Hamoodi
Modelling Near-Surface Temperature (NST) is critical for a wide range of environmental applications, including air pollution, human comfort, climate change, and urban planning policy energy management. It impacts most biogeophysical and biogeochemical processes of the earth’s surface system, making it one of the most important input factors in land surface and hydrological models. In this research, a new approach was proposed for computing the near-surface temperature, which refers to the air temperature at 2 meters above the land surface based on land surface temperatures. Landsat images, digital elevation models, and ground weather stations over the study area were utilized for this purpose. Parameters like LST and duration day length were computed to be input data in the modeling. The results revealed that the LST data could be utilized to constantly estimate air temperature by some parameters, including (LST, DEM, and DDL) in the model. The finding also shows that the model accuracy of the suggested approach was acceptable.