Browsing by Author "Sanjeev Kumar Srivastava"

Now showing 1 - 12 of 12

A Comprehensive Review of Empirical and Dynamic Wildfire Simulators and Machine Learning Techniques used for the Prediction of Wildfire in Australia
(Springer Science and Business Media B.V., 2025) Harikesh Singh; Kenneth Li Minn Ang; Dipak Paudyal; Mauricio A. Acuna; Prashant Kumar Srivastava; Sanjeev Kumar 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. © The Author(s) 2025.
A general approach to forest stand classification
(Elsevier, 2025) Megha Paul; Prashant Kumar Srivastava; Sanjeev Kumar Srivastava; Pavan Kumar
The mapping of forests, evaluation of habitat quality, research into the dynamics of forests, and development of sustainable management techniques are only a few uses for forest typologies. The forest plots vertical and horizontal structures serve as the primary categorization standards in quantitative typologies designed for forestry applications. Forest typologies in which the univariate or bivariate distribution of tree diameters or heights is combined with species composition data to calculate coefficients that assess the dissimilarity of forest stands. One of the most important steps in planning forest management is classifying forest stands, but it takes time and is subject to subjectivity. The increasing availability of LiDAR data and multispectral photos presents an opportunity to enhance stand categorization using remotely sensed data. Using OBIA, forest stands have been automatically classified using ASTER images and low-density LiDAR data. In order to segment forests, OBIA was used in conjunction with VNIR ASTER bands to extract mean height, canopy cover, and the canopy model from LiDAR data. In order to compare the segmentation results, it was necessary to evaluate the internal heterogeneity of the segments. Multispectral information combined with OBIA and low-density LiDAR data are useful tools for stand classification. When it comes to distinguishing between broad-leaved, conifer, and mixed stands, multispectral pictures offer a limited predictive relevance for species distinction. However, the performance of ASTER data could be improved with higher spatial resolution VNIR images, especially submetric VNIR orthophotos. LiDAR data, however, has a lot of possibilities for depicting forest structure. The fast developing technology of drones and the increasing demand for high-resolution datasets from government agencies are factors that contribute to this perspective. © 2026 Elsevier Inc. All rights reserved..
AI-driven approaches for forest growth assessment and management
(Elsevier, 2025) Srishti Gwal; Ayushi Gupta; Prachi Singh; Prashant Kumar Srivastava; Sanjeev Kumar Srivastava
The advent of digital data has markedly increased the utilization of Artificial Intelligence (AI) in forestry, significantly enhancing the precision and efficiency of forest monitoring. This chapter explores the transformative impact of AI on forest management, tracing the evolution of AI from its foundational concepts to its wide-ranging applications in diverse sectors. It highlights AI’s ability to replicate human cognitive functions, such as learning and problem-solving, emphasizing its crucial role in improving the accuracy and effectiveness of forest monitoring systems. The discussion extends to the integration of AI with cutting-edge technologies such as machine learning, deep learning, and remote sensing. A detailed description of various algorithms, including the Generalized Linear Model, Generalized Additive Model, Partial Least Squares Regression, Gradient Boost Machine, Support Vector Machines, Random Forests, and Neural Networks, is provided and their applications in forest growth assessment, change detection, and the analysis of disease and fire risks, both globally and within the Indian context, are meticulously discussed. © 2026 Elsevier Inc. All rights reserved..
Aquatic Ecosystems Monitoring: Conventional Assessment to Advanced Remote Sensing
(CRC Press, 2024) Prem Chandra Pandey; Prashant K. Srivastava; Sanjeev Kumar Srivastava
This book collates traditional and modern applications of remote sensing in aquatic ecosystem monitoring. It covers conventional assessment methods like sampling, surveying, macroinvertebrates, and chlorophyll estimation for aquatic ecosystem health assessment. Advanced remote sensing technology provides timely spectral information for quantitative and qualitative assessment of water quality, shoreline changes, coral bleaching, and vegetation monitoring. The book covers different types of aquatic ecosystems like wetlands, rivers, lakes, saline, and the brackish lake. It also: Reviews the latest applications of remote sensing in the monitoring and assessment of aquatic ecosystems Includes traditional methods like cartography, sampling, surveying, phytoplankton assessment, river interlinking, and chlorophyll estimation Discusses the application of multi-source data and machine learning in monitoring aquatic ecosystems Discusses aquatic ecosystem management, services, threats, and sustainability Explores challenges, opportunities, and prospects of future Earth observation applications for aquatic ecosystem monitoring The book discusses space-borne, airborne, and drone geospatial data. The parts broadly cover aquatic ecosystem monitoring, vegetation management, advanced modeling practices, and challenges. It is meant for scientists, professionals, and policymakers working in environmental sciences, remote sensing, and geology. © 2025 selection and editorial matter, Prem Chandra Pandey, Prashant K. Srivastava, Sanjeev Kumar Srivastava; individual chapters, the contributors.
Challenges and Future Implications in Monitoring and Assessment of Aquatic Ecosystems
(CRC Press, 2024) Smrutisikha Mohanty; Prem C. Pandey; Prashant K. Srivastava; Sanjeev Kumar Srivastava
Aquatic ecosystems, encompassing freshwater and marine environments, are vital for global ecological balance and human well-being. This concluding chapter delves into the diverse classifications of aquatic ecosystems and their ecological significance, emphasizing their pivotal role in supporting biodiversity, regulating climate, and providing economic services. It discusses traditional and advanced monitoring techniques, including molecular-level monitoring with environmental DNA (eDNA), traditional in situ or lab-based experiments, and regional and global monitoring using geospatial technology consisting of remote sensing, GIS, and GNSS for providing data input and processing platform. Remote sensing, in particular, is highlighted for its ability to provide comprehensive and timely information over large spatial extents, enabling robust monitoring and assessment of aquatic ecosystems. The chapter also explores the importance of remote sensing in understanding various water quality parameters, detecting environmental changes, and assessing the impacts of climate change. Challenges associated with conventional and technological approaches to studying aquatic ecosystems are discussed, alongside recent advancements in geospatial data collection and analytics. Overall, this chapter underscores the indispensable role of remote sensing in aquatic ecosystem monitoring using derived parameters and Trophic Status Index for assessing health conditions of aquatic ecosystems. Thus, it isoffering powerful tools and techniques for sustainable management and conservation efforts. © 2025 selection and editorial matter, Prem Chandra Pandey, Prashant K. Srivastava, Sanjeev Kumar Srivastava; individual chapters, the contributors.
Ensemble of machine learning and global circulation models coupled with geospatial databases for niche mapping of Bell Rhododendron under climate change
(Taylor and Francis Ltd., 2024) K.V. Satish; Prashant K. Srivastava; Mukund Dev Behera; Mohammed Latif Khan; Srishti Gwal; Sanjeev Kumar Srivastava
Himalayan species conservation faces major challenges due to unprecedented climate change. Alpine Rhododendrons are crucial components of Himalaya, yet their vulnerability to climate change remains poorly understood. This study examines niche shifting of Rhododendron campanulatum, a keystone species of alpine treeline, under different climate change scenarios using ensemble models. The study presents extensive use of four machine learning models and three global circulation models for niche modelling. Models achieved True Skill Statistic ≥0.8, Area Under Curve ≥0.9, Cohen’s Kappa ≥0.7, and overall accuracy of ≥0.9. Results showed distribution of R. campanulatum is governed by annual temperature range, minimum temperature of coldest month and precipitation of warmest quarter. Analyses revealed niche contraction and expansion of a 3–5%. Contractions are particularly evident at lower treeline boundaries. Both upward and downward shifts are anticipated under future climatic scenarios. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Introduction to Aquatic Ecosystems - Editorial Message
(CRC Press, 2024) Prem Chandra Pandey; Prashant K. Srivastava; Sanjeev Kumar Srivastava
This editorial chapter provides a comprehensive view of the edited book Aquatic Ecosystems Monitoring: Conventional Assessment to Advanced Remote Sensing. In today’s dynamic world, understanding and preserving aquatic ecosystems have become more critical than ever. The health of these ecosystems directly impacts the well-being of both the environment and human societies. Therefore, it is imperative to employ effective monitoring techniques to assess the status of aquatic environments accurately. This comprehensive volume delves into the spectrum of aquatic ecosystems, and their monitoring techniques, ranging from traditional methodologies to the latest advancements in technology. Through the collaborative efforts of early career researchers to esteemed authors/experts in the field, this collection offers a profound exploration of the diverse methods used for assessing and understanding aquatic ecosystems. From the serene depths of freshwater lakes to the expansive realms of the coastal zones, aquatic environments harbor an incredible array of life forms and ecological processes. However, these fragile and delicate ecosystems face myriad threats, including pollution, habitat destruction, climate change, and invasive species. Effective monitoring serves as a cornerstone in our efforts to safeguard these invaluable resources for future generations. This chapter provides a depth of insight into different aspects of monitoring aquatic ecosystems and the methods incorporated accordingly to utilize resources in a sustainable way. © 2025 selection and editorial matter, Prem Chandra Pandey, Prashant K. Srivastava, Sanjeev Kumar Srivastava; individual chapters, the contributors.
New satellite missions and sensors for forest monitoring
(Elsevier, 2025) Prashant Kumar Srivastava; Bhawana Sharma; Ayushi Gupta; Srishti Gwal; Prem C. Pandey; Sanjeev Kumar Srivastava
Forests are vital for nature balance and act as sink for carbon emissions; therefore, regular monitoring of forest is crucial for uninterrupted ecosystem services and functioning. For the large-scale monitoring of forests, several advancements happened in the last few decades in the field of satellite designing and sensor development. This chapter will provide a review of older satellites as well as new satellites and sensors for monitoring and management of forests. The satellite that are used in the past and present for forest monitoring in the field of multispectral, hyperspectral, LiDAR, microwave (active and passive) are provided with their background. © 2026 Elsevier Inc. All rights reserved..
Performance assessment of the Sentinel-2 LAI products and data fusion techniques for developing new LAI datasets over the high-altitude Himalayan forests
(Taylor and Francis Ltd., 2023) Vikas Dugesar; Manish K. Pandey; Prashant K. Srivastava; George P. Petropoulos; Sanjeev Kumar Srivastava; Virendra Kumar Kumra
The present study evaluates the accuracy of SNAP-Sentinel-2 Prototype Processor (SL2P) derived Leaf Area Index (LAI) and proposes a new simple method to generate new datasets of LAI through data fusion. Rigorous optimization of the data fusion approaches (Kalman filter and Linear weighted) were performed for the generation of new LAI products over the complex hilly terrain of the Himalayan region. The results showed a good correlation (r = 0.79) and low error (RMSE = 1.63) between SNAP-derived (at 20 m) and ground-observed LAI. A lower correlation was obtained between the ground observed LAI data and the corresponding global LAI products for the Moderate Resolution Imaging Spectroradiometer (MODIS) (r = 0.1, RMSE = 1.19), Copernicus Global Land Service (CGLS) (r = 0.1, RMSE = 0.61) and the Visible Infrared Imaging Radiometer Suite (VIIRS) (r = 0.04, RMSE = 1.25). Notably, after implementing the data fusion, both SNAP-derived LAI and Global LAI products exhibited much-improved performance statistics with ground observed data sets. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Preface
(CRC Press, 2024) Prem Chandra Pandey; Prashant K. Srivastava; Sanjeev Kumar Srivastava
[No abstract available]
Tracking Post-Fire Vegetation Regrowth and Burned Areas Using Bitemporal Sentinel-1 SAR Data: A Google Earth Engine Approach in Heath Vegetation of Mooloolah River National Park, Queensland, Australia
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Harikesh Singh; Prashant Kumar Srivastava; Rajendra B. Prasad; Sanjeev Kumar Srivastava
This study utilizes the unique capabilities of Sentinel-1 C-band synthetic aperture radar (SAR) data to map post-fire burned areas and monitor vegetation recovery in a heath-dominated Queensland National Park. Sentinel-1 SAR data were used due to their cloud-penetrating capability and frequent revisit times. Using Google Earth Engine (GEE), a bitemporal ratio analysis was applied to SAR data from post-fire periods between 2021 and 2023. SAR backscatter changes over time captured fire impacts and subsequent vegetation regrowth. This differentiation was further enhanced with k-means clustering. Validation was supported by Sentinel-2 dNBR and official fire history records. The dNBR provided a quantitative assessment of burn severity and was used alongside the fire history data to evaluate the accuracy of the burned area classification. While Sentinel-2 false-colour composite (FCC) imagery was generated for visualisation and interpretation purposes, the primary validation relied on dNBR and QPWS fire history records. The results highlighted significant vegetation regrowth, with some areas returning to near pre-fire biomass levels by March 2023. This approach demonstrates the sensitivity of Sentinel-1 SAR, especially in VV polarization, for detecting subtle changes in vegetation, providing a cost-effective method for post-fire ecosystem monitoring and informing ecological management strategies amid increasing wildfire events. © 2025 by the authors.
Trending and emerging prospects of physics-based and ML-based wildfire spread models: a comprehensive review
(Springer Nature, 2024) Harikesh Singh; Li-Minn Ang; Tom Lewis; Dipak Paudyal; Mauricio Acuna; Prashant Kumar Srivastava; Sanjeev Kumar 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. © The Author(s) 2024.