University Of Basrah

Significant progress has been made in flood prediction through the development of intelligent data-driven models. However, most existing approaches rely solely on hydrogeological data, ignoring scientific knowledge of flood dynamics during the training process. Consequently, these models often struggle to detect flood events effectively, becoming biased toward non-flood conditions, achieving reasonable accuracy but limited effectiveness in detecting flood peak events. Therefore, this study proposes a composite data-driven model guided by expert knowledge of flood events through a modified Huber loss function for improved flood forecasting. The model integrates a time-distributed approach and a spatial attention mechanism to capture complex spatial dependencies, while temporal features are extracted using a combination of long short-term memory (LSTM) and temporal convolutional networks (TCN) equipped with a temporal attention module. Furthermore, expert knowledge is incorporated directly into the loss function, allowing the model to prioritize accurate flood peak prediction during training. The framework was evaluated using 6-hourly hydrometeorological data from Changhua, Heihe, and Tunxi basins in China, with a focus on flood peak forecasting. Results demonstrate that the knowledge-guided loss function outperforms conventional mean squared error (MSE) and standard Huber loss. Compared to baseline models -including convolutional neural network (CNN), long short-term memory (LSTM), convolutional LSTM (ConvLSTM), temporal convolutional network (TCN), spatial-temporal attention LSTM (STA-LSTM), Informer, and time-distributed CNN-LSTM (TD-CNN-LSTM)- the proposed model improves mean absolute error (MAE) by 6.9-25 %, 27.7-88 %, and 10.8-52 %, while reduces root mean square error (RMSE) by 2.5-19.3 %, 14.3-73.4 %, and 14.6-37.1 % across three basins, respectively.

The management of ITP has evolved with evidence-based international guidelines. However, Iraq's unique challenges, including variations in clinical practice and treatment disparities, necessitate localized guidance to bridge global recommendations and real-world practice. This expert consensus aims to provide a comprehensive and practical framework for diagnosing and managing ITP within the Iraqi healthcare setting.

A 16-member multidisciplinary ITP specialist panel (Iraq, Norway, UK), including hematologists, laboratory experts, and related specialists, conducted a systematic PubMed / PubMed Central / Embase review (January 2003-December 2024) using key terms 'primary immune thrombocytopenia' and 'idiopathic thrombocytopenic purpura' (English human studies, excluding conference abstracts). Using a modified Delphi method, consensus was reached on 43 ITP diagnosis/treatment/management statements. After a single voting round, the panel refined the recommendations to ensure their applicability to Iraq's healthcare system. Final recommendations were categorized using evidence grading system.

Corticosteroids were the preferred first-line therapy, with intravenous immunoglobulin (IVIG) reserved for urgent platelet elevation. The panel discouraged prolonged corticosteroid use due to adverse effects and defined clear criteria for second-line therapies. Thrombopoietin receptor agonists (TPO-RAs) and rituximab were recommended second-line, while splenectomy was considered a last resort, only after the failure of multiple medical therapies. Special populations received tailored recommendations, including pregnant patients, pediatric cases, and high-thrombosis-risk individuals. Recommendations incorporated quality of life, emphasizing patient-centered care and minimizing unnecessary medication exposure.

This expert consensus provides a structured, evidence-informed approach to ITP diagnosis and management in Iraq, balancing best practices with local healthcare realities.

This study provides a fundamental understanding of the geometry of a quasi-Sasakian manifold ( __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifold), highlighting their structural properties and enhancing the knowledge of their geometric framework. A pseudo quasi-conformal curvature tensor ( __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__PQC -curvature tensor) of __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifold has been identified. The components of the __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__PQC -curvature tensor are established employing the __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__G -adjoined structure space( __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__GADS -space). It is demonstrated that the Ricci flat __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifold is locally equivalent to the product of the complex Euclidean space __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__ C n and the real line. Furthermore, it has been demonstrated that a __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__ξ -pseudo quasi conformal flat __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifold is a quasi-Einstein manifold. The conditions under which a quasi-symmetric __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifold becomes a quasi-Einstein manifold are also specified. Subsequently, it has been shown for __-mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"-__QS -manifolds that pseudo quasi conformal symmetric and pseudo quasi conformal flat are equivalent.•The pseudo quasi-conformal curvature tensor of the quasi Sasakian manifold has been identified.•The Ricci flat quasi Sasakian manifold is studied.•An application of the quasi-symmetric quasi Sasakian manifold to be a quasi-Einstein manifold is specified.