Browsing by Author "Srishti Gwal"

Now showing 1 - 5 of 5

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..
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.
Identifying Conservation Priority Areas of Hydrological Ecosystem Service Using Hot and Cold Spot Analysis at Watershed Scale
(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Srishti Gwal; Dipaka Ranjan Sena; Prashant K. Srivastava; Sanjeev K. Srivastava
Hydrological Ecosystem Services (HES) are crucial components of environmental sustainability and provide indispensable benefits. The present study identifies critical hot and cold spots areas of HES in the Aglar watershed of the Indian Himalayan Region using six HES descriptors, namely water yield (WYLD), crop yield factor (CYF), sediment yield (SYLD), base flow (LATQ), surface runoff (SURFQ), and total water retention (TWR). The analysis was conducted using weightage-based approaches under two methods: (1) evaluating six HES descriptors individually and (2) grouping them into broad ecosystem service categories. Furthermore, the study assessed pixel-level uncertainties that arose because of the distinctive methods used in the identification of hot and cold spots. The associated synergies and trade-offs among HES descriptors were examined too. From method 1, 0.26% area of the watershed was classified as cold spots and 3.18% as hot spots, whereas method 2 classified 2.42% area as cold spots and 2.36% as hot spots. Pixel-level uncertainties showed that 0.57 km2 and 6.86 km2 of the watershed were consistently under cold and hot spots, respectively, using method 1, whereas method 2 identified 2.30 km2 and 6.97 km2 as cold spots and hot spots, respectively. The spatial analysis of hot spots showed consistent patterns in certain parts of the watershed, primarily in the south to southwest region, while cold spots were mainly found on the eastern side. Upon analyzing HES descriptors within broad ecosystem service categories, hot spots were mainly in the southern part, and cold spots were scattered throughout the watershed, especially in agricultural and scrubland areas. The significant synergistic relation between LATQ and WYLD, and sediment retention and WYLD and trade-offs between SURFQ and HES descriptors like WYLD, LATQ, sediment retention, and TWR was attributed to varying factors such as land use and topography impacting the water balance components in the watershed. The findings underscore the critical need for targeted conservation efforts to maintain the ecologically sensitive regions at watershed scale. © 2024 by the authors.
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..
Scatterometers for leaf area index estimation: A review
(Elsevier, 2025) Damanti Murmu; Bhawana Sharma; Srishti Gwal; Ayushi Gupta; Prashant Kumar Srivastava
Scatterometers are active remote sensing instruments that emit and receive radio detection and ranging (RADAR) pulses backscattered from targeted features on the Earth's surface. Scatterometer-based leaf area index (LAI) estimation is demonstrated as a potential approach to understand ecosystem productivity, crop yields, vegetation health, etc., as LAI serves as an important variable in empirical, semi-empirical, and process-based models used in studying vegetation dynamics. Scatterometers are anticipated to facilitate large-scale, uninterrupted LAI monitoring as they penetrate dense vegetation canopies under varying weather conditions. LAI computation using a scatterometer demands backscattering signal strength measurement, which primarily depends upon the dynamics of vegetation structure, surface texture, and soil moisture. The water-cloud model estimates soil moisture of areas possessing vegetation using backscattering data. The model provides a precise estimation of LAI as it can explicitly distinguish between the soil and vegetation backscatter. Further enhancement of these estimations can be carried out by data fusion methods that incorporate the scatterometer data with optical or synthetic aperture radar data. With the aid of case studies, this chapter demonstrates versatile applications of scatterometer across a wide range of environmental aspects, including estimation of above-ground biomass, carbon sequestration, soil moisture, yield prediction, vegetation structure analysis, etc., for forest, agriculture, and grassland ecosystems. Scatterometer data in agricultural areas provides accurate production calculation and periodic crop growth monitoring. Because scatterometers provide a stable and scalable method of measuring LAI, they may be used to monitor vegetation dynamics, agricultural productivity, and environmental changes globally. © 2026 Elsevier Ltd. All rights reserved..