Zaharaddeen Karami Lawal
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
Zaharaddeen Karami Lawal has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Rufai Yusuf Zakari
Universiti Brunei Darussalam
9 shared publications - Hayati Yassin
Universiti Brunei Darussalam
5 shared publications - Azam Che Idris
Universiti Brunei Darussalam
4 shared publications Hayati Yassin
4 shared publications- Daphne Teck Ching Lai
Universiti Brunei Darussalam
3 shared publications - Navod Neranjan Thilakarathne
University of Colombo
3 shared publications
Latest Publications
- 27 March 2026
- Published by Elsevier
- p. 103-128
AI-driven digital twin for sustainable management of wave energy conversion systems
- 27 March 2026
- Published by Elsevier
- p. 103-128
AI-driven digital twin for sustainable management of wave energy conversion systems
- 27 March 2026
- Published by Elsevier
Contributors
- 2 December 2025
- Published by Elsevier in Environmental Modelling & Software
- Vol. 197
Optimizing significant wave height forecasting through Ensemble Patch-TST and attention-enhanced recurrent models
- 2 December 2025
- Published by Elsevier in Environmental Modelling & Software
- Vol. 197
Optimizing significant wave height forecasting through Ensemble Patch-TST and attention-enhanced recurrent models
- 17 July 2025
- Published by Taylor & Francis
- p. 9-35
Advances in Wildfire Spread Detection and Prediction
This study explores the latest advancements in wildfire spread detection and forecasting techniques, focusing on the complex challenges and practical applications in this field. We provide an exhaustive review of state-of-the-art methods and technologies for detecting and predicting wildfires. We examine the fundamental principles of wildfire behavior and spread dynamics, remote sensing (RS) methodologies such as satellite imagery and unmanned aerial vehicles (UAVs), and the role of artificial intelligence (AI)-driven approaches such as machine learning (ML) and deep learning (DL) algorithms in enabling rapid analysis of vast datasets. We investigated predictive modeling approaches that integrate various environmental factors, topographical features, and fuel characteristics to forecast wildfire behavior and spread patterns. Real-world case studies illustrated the practical implications of these technologies in wildfire management and emergency response efforts. We also addressed the challenges and limitations of current wildfire detection and prediction systems, including data accuracy, computational resources, and operational constraints. Our target audience includes researchers, practitioners, policymakers, and stakeholders in wildfire management, environmental science, and disaster preparedness. Ultimately, we contributed to the literature by offering a comprehensive review of advances in wildfire spread detection and prediction, addressing key challenges, showcasing practical applications, and outlining future research directions to foster collaboration and innovation in wildfire management efforts worldwide.
- 17 July 2025
- Published by Taylor & Francis
- p. 9-35
Advances in Wildfire Spread Detection and Prediction
This study explores the latest advancements in wildfire spread detection and forecasting techniques, focusing on the complex challenges and practical applications in this field. We provide an exhaustive review of state-of-the-art methods and technologies for detecting and predicting wildfires. We examine the fundamental principles of wildfire behavior and spread dynamics, remote sensing (RS) methodologies such as satellite imagery and unmanned aerial vehicles (UAVs), and the role of artificial intelligence (AI)-driven approaches such as machine learning (ML) and deep learning (DL) algorithms in enabling rapid analysis of vast datasets. We investigated predictive modeling approaches that integrate various environmental factors, topographical features, and fuel characteristics to forecast wildfire behavior and spread patterns. Real-world case studies illustrated the practical implications of these technologies in wildfire management and emergency response efforts. We also addressed the challenges and limitations of current wildfire detection and prediction systems, including data accuracy, computational resources, and operational constraints. Our target audience includes researchers, practitioners, policymakers, and stakeholders in wildfire management, environmental science, and disaster preparedness. Ultimately, we contributed to the literature by offering a comprehensive review of advances in wildfire spread detection and prediction, addressing key challenges, showcasing practical applications, and outlining future research directions to foster collaboration and innovation in wildfire management efforts worldwide.
- 17 July 2025
- Published by Taylor & Francis
- p. 36-66
Leveraging Remote Sensing for Agriculture Mapping
Remote Sensing (RS) technologies have emerged as indispensable tools for mapping agricultural landscapes, offering unprecedented capabilities for monitoring crop health, assessing land use changes, and optimizing agricultural practices. This study provides an exhaustive review of the utilization of RS techniques in agricultural mapping. Beginning with an introduction to the fundamental principles of RS, the study explores the various platforms and sensors commonly employed in agricultural mapping activities. It explores the complexity of data acquisition, emphasizing preprocessing techniques essential for enhancing data quality and accuracy. The study then discusses image classification methodologies using advanced artificial intelligence (AI)-driven techniques such as machine learning (ML), deep learning (DL), and transformers-based algorithms for crop type classification and land cover mapping. It highlights the significance of feature extraction and selection in refining agricultural mapping outputs. Furthermore, the study showcases a range of applications of RS in agriculture, from monitoring crop health and detecting anomalies to estimating biophysical parameters critical for yield prediction and resource management. Real-world case studies exemplify the practical implementation of RS technologies in diverse agricultural settings. Despite its immense potential, RS in agricultural mapping presents certain challenges, including data availability, spatial and temporal resolution limitations, and the need for robust validation frameworks. The study addresses these challenges and offers insights into emerging trends and advancements poised to shape the future of agricultural mapping.
- 17 July 2025
- Published by Taylor & Francis
- p. 36-66
Leveraging Remote Sensing for Agriculture Mapping
Remote Sensing (RS) technologies have emerged as indispensable tools for mapping agricultural landscapes, offering unprecedented capabilities for monitoring crop health, assessing land use changes, and optimizing agricultural practices. This study provides an exhaustive review of the utilization of RS techniques in agricultural mapping. Beginning with an introduction to the fundamental principles of RS, the study explores the various platforms and sensors commonly employed in agricultural mapping activities. It explores the complexity of data acquisition, emphasizing preprocessing techniques essential for enhancing data quality and accuracy. The study then discusses image classification methodologies using advanced artificial intelligence (AI)-driven techniques such as machine learning (ML), deep learning (DL), and transformers-based algorithms for crop type classification and land cover mapping. It highlights the significance of feature extraction and selection in refining agricultural mapping outputs. Furthermore, the study showcases a range of applications of RS in agriculture, from monitoring crop health and detecting anomalies to estimating biophysical parameters critical for yield prediction and resource management. Real-world case studies exemplify the practical implementation of RS technologies in diverse agricultural settings. Despite its immense potential, RS in agricultural mapping presents certain challenges, including data availability, spatial and temporal resolution limitations, and the need for robust validation frameworks. The study addresses these challenges and offers insights into emerging trends and advancements poised to shape the future of agricultural mapping.
- Open Access
Impact of Seasonal Variation and Population Growth on Coliform Bacteria Concentrations in the Brunei River: A Temporal Analysis with Future Projection
Coliform bacteria pollution poses a significant challenge to water quality in the Brunei River, a critical resource in Brunei Darussalam. This study investigates the impact of seasonal variations and population growth on coliform concentrations across eight monitoring stations while addressing data limitations in forecasting future trends. Seasonal variations, analyzed using box plots, revealed significantly higher coliform levels during the rainy season, driven by urban and residential runoff. Population growth, assessed using propensity score matching, showed that stations in densely populated areas experienced elevated contamination levels. Temporal trends, analyzed using the Rescaled Adjusted Partial Sums (RAPS) method, indicated a declining trend from 2013 to 2018, followed by a sharp increase post-2018, linked to urbanization, wastewater discharge, and overburdened sewage infrastructure, particularly in upstream stations. To forecast coliform levels, ARIMA, Logistic Regression, and Bidirectional Long Short-Term Memory (BiLSTM) models were employed and their predictive performance evaluated. Despite the constraints of a small dataset, the BiLSTM model outperformed others in most stations, emphasizing its ability to capture complex temporal relationships. Furthermore, a Mann–Kendall trend analysis of the BiLSTM predicted data over a five-year period and revealed significant upward trends in coliform levels. This study highlights the potential of combining advanced predictive models with robust analytical techniques and focused data collection efforts to support sustainable water quality management in data-scarce environments.
Open AccessImpact of Seasonal Variation and Population Growth on Coliform Bacteria Concentrations in the Brunei River: A Temporal Analysis with Future Projection
Coliform bacteria pollution poses a significant challenge to water quality in the Brunei River, a critical resource in Brunei Darussalam. This study investigates the impact of seasonal variations and population growth on coliform concentrations across eight monitoring stations while addressing data limitations in forecasting future trends. Seasonal variations, analyzed using box plots, revealed significantly higher coliform levels during the rainy season, driven by urban and residential runoff. Population growth, assessed using propensity score matching, showed that stations in densely populated areas experienced elevated contamination levels. Temporal trends, analyzed using the Rescaled Adjusted Partial Sums (RAPS) method, indicated a declining trend from 2013 to 2018, followed by a sharp increase post-2018, linked to urbanization, wastewater discharge, and overburdened sewage infrastructure, particularly in upstream stations. To forecast coliform levels, ARIMA, Logistic Regression, and Bidirectional Long Short-Term Memory (BiLSTM) models were employed and their predictive performance evaluated. Despite the constraints of a small dataset, the BiLSTM model outperformed others in most stations, emphasizing its ability to capture complex temporal relationships. Furthermore, a Mann–Kendall trend analysis of the BiLSTM predicted data over a five-year period and revealed significant upward trends in coliform levels. This study highlights the potential of combining advanced predictive models with robust analytical techniques and focused data collection efforts to support sustainable water quality management in data-scarce environments.
- 7 February 2025
- Published by Springer Nature
- p. 71-95
Big Data Analytics in Bioinformatics and Healthcare
- 7 February 2025
- Published by Springer Nature
- p. 71-95
Big Data Analytics in Bioinformatics and Healthcare
- 8 January 2025
- Published by Elsevier in Neurocomputing
- Vol. 622
VQA and Visual Reasoning: An overview of approaches, datasets, and future direction
- 8 January 2025
- Published by Elsevier in Neurocomputing
- Vol. 622
VQA and Visual Reasoning: An overview of approaches, datasets, and future direction
- Open Access
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 178536-178551
Optimized Ensemble Methods for Classifying Imbalanced Water Quality Index Data
River water pollution has increased due to human activities. Initially, numerical and analytical methods were used to classify river water quality, but machine learning now enables faster and more accurate water quality index (WQI) classification. This study aimed to develop an effective ensemble model for classifying river water as drinkable or polluted using advanced machine learning. The objective was to apply a classification method to predict WQI using Kinta River data in Malaysia and improve on existing models’ 70-95% accuracy range. The dataset of this study comprises 301 records collected from eight monitoring stations along the Kinta River, encompassing 31 pollution indicators, including hydrological, chemical, physical, and microbiological parameters. Six algorithms used include decision tree, logistic regression, random forest, support vector machine, AdaBoost, and XGBoost. The three experiments were conducted with and without hyperparameter tuning. The dataset was normalized and oversampled to address the imbalance. In all experiments, XGBoost performed best individually, while SVM was worst. The ensemble models outperformed individuals, with the GridSearchCV ensemble achieving 97.3% accuracy, an improvement exceeding the existing literature’s models by 2.3%. The study had limitations, such as the absence of advanced optimization or dimensionality reduction. In conclusion, it demonstrated that an ensemble model with optimized hyperparameters could classify river water quality more effectively than individual models, contributing to the advancement of sustainable development goals (SGD) related to water access.
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 178536-178551
Open AccessOptimized Ensemble Methods for Classifying Imbalanced Water Quality Index Data
River water pollution has increased due to human activities. Initially, numerical and analytical methods were used to classify river water quality, but machine learning now enables faster and more accurate water quality index (WQI) classification. This study aimed to develop an effective ensemble model for classifying river water as drinkable or polluted using advanced machine learning. The objective was to apply a classification method to predict WQI using Kinta River data in Malaysia and improve on existing models’ 70-95% accuracy range. The dataset of this study comprises 301 records collected from eight monitoring stations along the Kinta River, encompassing 31 pollution indicators, including hydrological, chemical, physical, and microbiological parameters. Six algorithms used include decision tree, logistic regression, random forest, support vector machine, AdaBoost, and XGBoost. The three experiments were conducted with and without hyperparameter tuning. The dataset was normalized and oversampled to address the imbalance. In all experiments, XGBoost performed best individually, while SVM was worst. The ensemble models outperformed individuals, with the GridSearchCV ensemble achieving 97.3% accuracy, an improvement exceeding the existing literature’s models by 2.3%. The study had limitations, such as the absence of advanced optimization or dimensionality reduction. In conclusion, it demonstrated that an ensemble model with optimized hyperparameters could classify river water quality more effectively than individual models, contributing to the advancement of sustainable development goals (SGD) related to water access.
- Open Access
- 19 August 2024
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 38 (1)
Understanding the Dynamics of Ocean Wave-Current Interactions Through Multivariate Multi-Step Time Series Forecasting
- 19 August 2024
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 38 (1)
Open AccessUnderstanding the Dynamics of Ocean Wave-Current Interactions Through Multivariate Multi-Step Time Series Forecasting