Harikesh Singh

Dr. Harikesh Singh

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
27 September 2024 in Journal of Forestry Research
Verified
Journal Article
Open access
PDF file
HSHarikesh Singh
Harikesh Singh
LALi-Minn Ang
Li-Minn Ang
TLTom Lewis
Tom Lewis
DPDipak Paudyal
Dipak Paudyal
MAMauricio Acuna
Mauricio Acuna
SSSanjeev Srivastava
Sanjeev Srivastava
The significant threat of wildfires to forest ecology and biodiversity, particularly in tropical and subtropical regions, underscores the necessity for advanced predictive models amidst shifting climate patterns. There is a need to evaluate and enhance wildfire prediction methods, focusing on their application during extended periods of intense heat and drought. This study reviews various wildfire modelling approaches, including traditional physical, semi-empirical, numerical, and emerging machine learning (ML)-based models. We critically assess these models’ capabilities in predicting fire susceptibility and post-ignition spread, highlighting their strengths and limitations. Our findings indicate that while traditional models provide foundational insights, they often fall short in dynamically estimating parameters and predicting ignition events. Cellular automata models, despite their potential, face challenges in data integration and computational demands. Conversely, ML models demonstrate superior efficiency and accuracy by leveraging diverse datasets, though they encounter interpretability issues. This review recommends hybrid modelling approaches that integrate multiple methods to harness their combined strengths. By incorporating data assimilation techniques with dynamic forecasting models, the predictive capabilities of ML-based predictions can be significantly enhanced. This review underscores the necessity for continued refinement of these models to ensure their reliability in real-world applications, ultimately contributing to more effective wildfire mitigation and management strategies. Future research should focus on improving hybrid models and exploring new data integration methods to advance predictive capabilities.

21 December 2021 in Forests
Verified
Journal Article
Open access
PDF file
SSSachchidanand Singh
Sachchidanand Singh
HSHarikesh Singh
Harikesh Singh
VSVishal Sharma
Vishal Sharma
VSVaibhav Shrivastava
Vaibhav Shrivastava
Pankaj KumarPankaj Kumar
Pankaj Kumar
Suraj Kumar SinghSuraj Kumar Singh
Suraj Kumar Singh
Forests are an important natural resource and are instrumental in sustaining environmental sustainability. Burning biomass in forests results in greenhouse gas emissions, many of which are long-lived. Precise and consistent broad-scale monitoring of fire intensity is a valuable tool for analyzing climate and ecological changes related to fire. Remote sensing and geographic information systems provide an opportunity to improve current practice’s accuracy and performance. Spectral indices techniques such as normalized burn ratio (NBR) have been used to identify burned areas utilizing satellite data, which aid in distinguishing burnt areas using their standard spectral responses. For this research, we created a split-panel web-based Google Earth Engine app for the geo-visualization of the region severely affected by forest fire using Sentinel 2 weekly composites. Then, we classified the burn severity in areas affected by forest fires in Wolgan Valley, New South Wales, Australia, and the surrounding area through Difference Normalized Burn Ratio (dNBR). The result revealed that the region’s burnt area increased to 6731 sq. km in December. We also assessed the impact of long-term rainfall and land surface temperature (LST) trends over the study region to justify such incidents. We further estimated the effect of such incidents on air quality by analyzing the changes in the column number density of carbon monoxide and nitrogen oxides. The result showed a significant increase of about 272% for Carbon monoxide and 45% for nitrogen oxides. We conclude that, despite fieldwork constraints, the usage of different NBR and web-based application platforms may be highly useful for forest management to consider the propagation of fire regimes.

6 March 2025 in Natural Hazards
Verified
Journal Article
Open access
PDF file
HSHarikesh Singh
Harikesh Singh
LALi-Minn Ang
Li-Minn Ang
SSSanjeev Kumar Srivastava
Sanjeev Kumar Srivastava
Forests worldwide play a critical role in biodiversity conservation and climate regulation, yet they face unprecedented challenges, particularly from wildfires. Early wildfire detection is essential for preventing rapid spread, protecting lives, ecosystems, and economies, and mitigating climate change impacts. Traditional wildfire detection methods relying on human surveillance are limited in scope and efficiency. However, advancements in remote sensing technologies offer new opportunities for more efficient and comprehensive detection. This study highlights the integration of satellite sensors, capable of detecting thermal anomalies, smoke plumes, and vegetation health changes, with machine learning, particularly Support Vector Machines (SVMs), to enhance detection efficiency and accuracy. These algorithms analyse satellite data to identify fire patterns and provide near real-time alerts. SVMs’ adaptability over time improves performance, making them suitable for evolving fire regimes influenced by climate change. Focusing on the Wolgan Valley in Eastern Australia, the study utilised Landsat-8 imagery and SVMs to detect active fires and classify burned areas. Results demonstrated that combining various spectral bands, such as the Shortwave Infrared (SWIR) and Near-Infrared (NIR), enhances the identification of active fires and smoke. The introduction of the Normalized Difference Fire Index (NDFI) further refines detection capabilities by leveraging distinct spectral characteristics from Landsat 8 imagery. Despite the promise of these technologies, challenges such as data availability and model interpretability remain. Future research should focus on integrating diverse data sources, advancing machine learning techniques, developing real-time monitoring systems, addressing model interpretability, integrating unmanned aerial vehicles, and considering climate change impacts. This study underscores the potential of machine learning algorithms and innovative indices like NDFI to improve wildfire detection and management strategies, ultimately enhancing our ability to protect lives and ecosystems in fire-prone regions.

2 April 2025 in Technology, Knowledge and Learning
Verified
Journal Article
Open access
PDF file
HSHarikesh Singh
Harikesh Singh
LALi-Minn Ang
Li-Minn Ang
DPDipak Paudyal
Dipak Paudyal
MAMauricio Acuna
Mauricio Acuna
PSPrashant Kumar Srivastava
Prashant Kumar Srivastava
SSSanjeev Srivastava
Sanjeev Srivastava
Wildfires pose significant environmental threats in Australia, impacting ecosystems, human lives, and property. This review article provides a comprehensive analysis of various empirical and dynamic wildfire simulators alongside machine learning (ML) techniques employed for wildfire prediction in Australia. The study examines the effectiveness of traditional empirical methods, dynamic physical models, and advanced ML algorithms in forecasting wildfire spread and behaviour. Key simulators discussed include PHOENIX Rapidfire, SPARK, AUSTRALIS, REDEYE, and IGNITE, each evaluated for their inputs, models, and outputs. Additionally, the application of ML methods such as artificial neural networks, logistic regression, decision trees, and support vector machines is explored, highlighting their predictive capabilities and limitations. The integration of these advanced techniques is essential for enhancing the accuracy of wildfire predictions, enabling better preparedness and response strategies. This review aims to inform future research and development in wildfire prediction and management, ultimately contributing to more effective fire mitigation efforts in Australia and beyond.

19 July 2020 in Modeling Earth Systems and Environment
Verified
Journal Article
Closed access
PDF file
HSHarikesh Singh
Harikesh Singh
APA. C. Pandey
A. C. Pandey

13 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
HSHarikesh Singh
Harikesh Singh
LALi-Minn Ang
Li-Minn Ang
SSSanjeev Kumar Srivastava
Sanjeev Kumar Srivastava
Effective wildfire susceptibility mapping is critical for managing forest fire risks, especially in vulnerable regions like Lamington National Park, Queensland, Australia. This study compares Artificial Neural Networks (ANN) and U-Net Convolutional Neural Networks (CNN), highlighting their strengths and limitations. ANN, known for its simplicity and efficiency, is ideal for rapid assessments and resource-constrained applications, achieving higher overall accuracy. Conversely, the U-Net model excels in precision, recall, and F1 score, leveraging its advanced spatial feature extraction and localization capabilities. This makes U-Net particularly suitable for detailed mapping and critical decision-making in complex terrains or high-stakes scenarios. Utilizing geospatial datasets, including elevation, slope, vegetation indices, and proximity to infrastructure, the study demonstrates that ANN is effective for broad applications, while U-Net addresses scenarios where minimizing false positives and negatives is essential. These findings guide stakeholders in selecting the appropriate model for tailored wildfire management and proactive mitigation strategies.