In the background of ongoing climate change, it is important to monitor the spatial and temporal ... more In the background of ongoing climate change, it is important to monitor the spatial and temporal changes of glacial lakes (GLs) since they influence snowmelt runoff, stream discharge, water resources, and glacial lake outburst flood (GLOF). However, accurate identification and mapping of GLs in the background of snow-clad mountains through visual interpretation of satellite data is a tedious and challenging assignment when multiyear time-series analysis is considered. To overcome this challenge, automated extraction of GLs in satellite images has been carried out in this study with the help of machine learning (ML). The novelty of this study is identification and tracking of GLs over three decades using ML and geospatial analysis using pixel-based image classification. For this, Random Forest Classifier (RFC) and Artificial Neural Network (ANN) were employed. The methodology is demonstrated here for the identification and mapping of GLs in the Sikkim Himalaya from 1987 to 2020 and for forecasting the possible fate of these GLs through time-series modelling. The geospatial time-series analysis using Google Earth Engine, ML classifiers, and GIS framework, has captured the dynamics of GLs in Sikkim and has revealed the spatial and temporal patterns in GLs' dimensions as well as GLOF risk.
Visegrad Journal on Bioeconomy and Sustainable Development, 2023
Excessive fuelwood harvest is a major cause of deforestation in developing countries. To mitigate... more Excessive fuelwood harvest is a major cause of deforestation in developing countries. To mitigate this, various preventive measures have been introduced in different countries. The availability of affordable substitutes to the community dependent on the forest for domestic energy consumption may prevent further forest degradation. A stock-dependent optimal control model of fuelwood harvest from a natural forest is presented here and comparative statics has been used to show that the presence of a fuelwood substitute will reduce its harvest and increase the forest stock. The model indicates that the availability of cheaper and high-energy content alternatives for fuelwood can substantially reduce fuelwood extraction from a forest. Also, a lower discount rate and higher cultural and spiritual values (CSV) will keep the optimal forest stock close to its carrying capacity and reduce fuelwood harvest. The model reveals that the maximum sustainable yield of forest stock and the ratio of energy content per unit mass of fuel plays a central role in the fate of forest stock and the level of fuelwood harvest. An empirical example of the Southeast Asian Forest growth model along with Liquid Petroleum Gas (LPG) as a substitute has been used to illustrate the results. The outcomes of this study can be incorporated into forest conservation policies.
The data source contains the data set, feature rasters, R scripts, model outputs of Wildfire like... more The data source contains the data set, feature rasters, R scripts, model outputs of Wildfire likelihood mapping of Sikkim Himalaya using ML methods like GLM, SVM, GBM and RF.
The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) unde... more The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) under the influence of varied discount rate (delta), marginal rate of substitution of fuelwood by its substitute (alpha/beta) and Cultural & Spiritual Value (CSV) (phi). <br>Kallio, M., Dykstra, D. & Binkley, C. Z. E. The global forest sector: an analytical perspective. <i>Glob. For. Sect. Anal. Perspect.</i> (1987).<br>
The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) unde... more The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) under the influence of varied discount rate (delta), marginal rate of substitution of fuelwood by its substitute (alpha/beta) and Cultural & Spiritual Value (CSV) (phi). <br>Kallio, M., Dykstra, D. & Binkley, C. Z. E. The global forest sector: an analytical perspective. <i>Glob. For. Sect. Anal. Perspect.</i> (1987).<br>
Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent... more Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent episodes of wildfires of 2019 in Australia and Brazil are sad reminders of their heavy ecological and economical costs. Understanding the role of environmental factors in the likelihood of wildfires in a spatial context would be instrumental in mitigating it. In this study, 14 environmental features encompassing meteorological, topographical, ecological, in situ and anthropogenic factors have been considered for preparing the wildfire likelihood map of Sikkim Himalaya. A comparative study on the efficiency of machine learning methods like Generalized Linear Model (GLM), Support Vector Machine (SVM), Random Forest (RF) and Gradient Boosting Model (GBM) has been performed to identify the best performing algorithm in wildfire prediction. The study indicates that all the machine learning methods are good at predicting wildfires. However, RF has outperformed, followed by GBM in the prediction. Also, environmental features like average temperature, average wind speed, proximity to roadways and tree cover percentage are the most important determinants of wildfires in Sikkim Himalaya. This study can be considered as a decision support tool for preparedness, efficient resource allocation and sensitization of people towards mitigation of wildfires in Sikkim.
The recent episodes of forest res in Brazil and Australia of 2019 are tragic reminders of the haz... more The recent episodes of forest res in Brazil and Australia of 2019 are tragic reminders of the hazards of forest re. Globally incidents of forest re events are on the rise due to human encroachment into the wilderness and climate change. Sikkim with a forest cover of more than 47%, suffers seasonal instances of frequent forest re during the dry winter months. To address this issue, a GIS-aided and MaxEnt machine learning-based forest re prediction map has been prepared using a forest inventory database and maps of environmental features. The study indicates that amongst the environmental features, climatic conditions and proximity to roads are the major determinants of forest res. Model validation criteria like ROC curve, correlation coefficient, and Cohen’s Kappa show a good predictive ability (AUC = 0.95, COR = 0.81, κ = 0.78). The outcomes of this study in the form of a forest re prediction map can aid the stakeholders of the forest in taking informed mitigation measures.
Highway traffic-induced air pollution is a major concern for health and ecosystem. The SAQIAM was... more Highway traffic-induced air pollution is a major concern for health and ecosystem. The SAQIAM was developed to facilitate visualization and interpretation of geographic distribution of air pollution impacts due to highway broadening in East Sikkim. An analytic hierarchy process-based Spatial Air Quality Index (SAQI) was constructed for this purpose. The individual air pollutant maps of CO, NO 2 , SO 2 and suspended particulate matter were prepared using IITLS dispersal model. Model validation and spatial crossvalidation criteria suggested that SAQIAM is a reliable spatial model. Statistical analysis of SAQI showed that it is a reliable index. SAQI maps under various time horizons showed that the pre-project and project-implementation scenarios will have mostly good air quality while post-project implementation scenario will have poor air quality close to the highway. Spatially explicit sensitivity analysis indicates that SAQIAM is robust. SAQIAM has the potential to serve as decision support tool for geovisualization of transport-related project impacts on air quality. Moreover, it can facilitate environmental managers to prioritize mitigation measures by capturing the perception of stakeholders using SAQI.
Journal of Geovisualization and Spatial Analysis, 2019
Identifying the right set of Socio-Economic Descriptors (SEDs) during the spatial analysis of a S... more Identifying the right set of Socio-Economic Descriptors (SEDs) during the spatial analysis of a Socio-Economic Impact Assessment (SEIA) is pivotal for a reliable impact modelling. For this, methods like factor analysis and sensitivity analysis can be used. As a case study, the Spatial Socioeconomic Impact Assessment Model (SSEIAM) of the broadening of highway NH 10 in the East district of Sikkim is used to emphasise on this issue. Principal Component Analysis (PCA) is used to identify the most important SEDs contributing to the composite impact estimated by SSEIAM. Furthermore, Spatially Explicit Sensitivity Analysis (SESA) is performed to identify the model sensitivity to SED weights. SSEIAM is a GIS-based model that relies on experts’ opinion and peoples’ perception of the impacts of the project on the SEDs. The model uses Weighted Linear Combination (WLC) of kriging-generated SED surfaces to prepare the composite impact map. PCA indicates that farming activities, health facilities, traditional values, demographic profile, tourism and land-use & land-value are the major contributors to the variance in the descriptor space. SESA shows that SSEIAM is robust. However, land-use & land-value and farming activities contribute most to the perturbations of the composite impact value. This suggests, that model variable identification is a crucial step towards impact modelling.
Spatial Impacts of highway projects on biodiversity of NorthEastern Himalaya remains largely unex... more Spatial Impacts of highway projects on biodiversity of NorthEastern Himalaya remains largely unexplored. Usually a number of ecological criteria are required in biodiversity impact assessment. However, a wide set of such criteria can be overwhelming for the decision-makers to assess the viability of such projects. SBIAM uses landscape metrics and experts' opinion to create a single composite biodiversity value map. The weighted area loss under various project alternatives estimated from Biodiversity Value Map is compared to identify the most viable alternative. SBIAM uses AHP and curve fitting method in the biodiversity estimation. The study indicates that the highway broadening project in the study area will cause a moderate biodiversity loss. Sensitivity analysis of SBIAM indicates its robustness, and shows that forest patches near the highway are most sensitive to disturbances and patch proximity. SBIAM can be applied in varied spatial scales, terrains and development projects as a decision support tool.
In the background of ongoing climate change, it is important to monitor the spatial and temporal ... more In the background of ongoing climate change, it is important to monitor the spatial and temporal changes of glacial lakes (GLs) since they influence snowmelt runoff, stream discharge, water resources, and glacial lake outburst flood (GLOF). However, accurate identification and mapping of GLs in the background of snow-clad mountains through visual interpretation of satellite data is a tedious and challenging assignment when multiyear time-series analysis is considered. To overcome this challenge, automated extraction of GLs in satellite images has been carried out in this study with the help of machine learning (ML). The novelty of this study is identification and tracking of GLs over three decades using ML and geospatial analysis using pixel-based image classification. For this, Random Forest Classifier (RFC) and Artificial Neural Network (ANN) were employed. The methodology is demonstrated here for the identification and mapping of GLs in the Sikkim Himalaya from 1987 to 2020 and for forecasting the possible fate of these GLs through time-series modelling. The geospatial time-series analysis using Google Earth Engine, ML classifiers, and GIS framework, has captured the dynamics of GLs in Sikkim and has revealed the spatial and temporal patterns in GLs' dimensions as well as GLOF risk.
Visegrad Journal on Bioeconomy and Sustainable Development, 2023
Excessive fuelwood harvest is a major cause of deforestation in developing countries. To mitigate... more Excessive fuelwood harvest is a major cause of deforestation in developing countries. To mitigate this, various preventive measures have been introduced in different countries. The availability of affordable substitutes to the community dependent on the forest for domestic energy consumption may prevent further forest degradation. A stock-dependent optimal control model of fuelwood harvest from a natural forest is presented here and comparative statics has been used to show that the presence of a fuelwood substitute will reduce its harvest and increase the forest stock. The model indicates that the availability of cheaper and high-energy content alternatives for fuelwood can substantially reduce fuelwood extraction from a forest. Also, a lower discount rate and higher cultural and spiritual values (CSV) will keep the optimal forest stock close to its carrying capacity and reduce fuelwood harvest. The model reveals that the maximum sustainable yield of forest stock and the ratio of energy content per unit mass of fuel plays a central role in the fate of forest stock and the level of fuelwood harvest. An empirical example of the Southeast Asian Forest growth model along with Liquid Petroleum Gas (LPG) as a substitute has been used to illustrate the results. The outcomes of this study can be incorporated into forest conservation policies.
The data source contains the data set, feature rasters, R scripts, model outputs of Wildfire like... more The data source contains the data set, feature rasters, R scripts, model outputs of Wildfire likelihood mapping of Sikkim Himalaya using ML methods like GLM, SVM, GBM and RF.
The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) unde... more The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) under the influence of varied discount rate (delta), marginal rate of substitution of fuelwood by its substitute (alpha/beta) and Cultural & Spiritual Value (CSV) (phi). <br>Kallio, M., Dykstra, D. & Binkley, C. Z. E. The global forest sector: an analytical perspective. <i>Glob. For. Sect. Anal. Perspect.</i> (1987).<br>
The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) unde... more The data provides simulation of Southeast Asian Tropical forest growth (Kallio et al., 1987) under the influence of varied discount rate (delta), marginal rate of substitution of fuelwood by its substitute (alpha/beta) and Cultural & Spiritual Value (CSV) (phi). <br>Kallio, M., Dykstra, D. & Binkley, C. Z. E. The global forest sector: an analytical perspective. <i>Glob. For. Sect. Anal. Perspect.</i> (1987).<br>
Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent... more Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent episodes of wildfires of 2019 in Australia and Brazil are sad reminders of their heavy ecological and economical costs. Understanding the role of environmental factors in the likelihood of wildfires in a spatial context would be instrumental in mitigating it. In this study, 14 environmental features encompassing meteorological, topographical, ecological, in situ and anthropogenic factors have been considered for preparing the wildfire likelihood map of Sikkim Himalaya. A comparative study on the efficiency of machine learning methods like Generalized Linear Model (GLM), Support Vector Machine (SVM), Random Forest (RF) and Gradient Boosting Model (GBM) has been performed to identify the best performing algorithm in wildfire prediction. The study indicates that all the machine learning methods are good at predicting wildfires. However, RF has outperformed, followed by GBM in the prediction. Also, environmental features like average temperature, average wind speed, proximity to roadways and tree cover percentage are the most important determinants of wildfires in Sikkim Himalaya. This study can be considered as a decision support tool for preparedness, efficient resource allocation and sensitization of people towards mitigation of wildfires in Sikkim.
The recent episodes of forest res in Brazil and Australia of 2019 are tragic reminders of the haz... more The recent episodes of forest res in Brazil and Australia of 2019 are tragic reminders of the hazards of forest re. Globally incidents of forest re events are on the rise due to human encroachment into the wilderness and climate change. Sikkim with a forest cover of more than 47%, suffers seasonal instances of frequent forest re during the dry winter months. To address this issue, a GIS-aided and MaxEnt machine learning-based forest re prediction map has been prepared using a forest inventory database and maps of environmental features. The study indicates that amongst the environmental features, climatic conditions and proximity to roads are the major determinants of forest res. Model validation criteria like ROC curve, correlation coefficient, and Cohen’s Kappa show a good predictive ability (AUC = 0.95, COR = 0.81, κ = 0.78). The outcomes of this study in the form of a forest re prediction map can aid the stakeholders of the forest in taking informed mitigation measures.
Highway traffic-induced air pollution is a major concern for health and ecosystem. The SAQIAM was... more Highway traffic-induced air pollution is a major concern for health and ecosystem. The SAQIAM was developed to facilitate visualization and interpretation of geographic distribution of air pollution impacts due to highway broadening in East Sikkim. An analytic hierarchy process-based Spatial Air Quality Index (SAQI) was constructed for this purpose. The individual air pollutant maps of CO, NO 2 , SO 2 and suspended particulate matter were prepared using IITLS dispersal model. Model validation and spatial crossvalidation criteria suggested that SAQIAM is a reliable spatial model. Statistical analysis of SAQI showed that it is a reliable index. SAQI maps under various time horizons showed that the pre-project and project-implementation scenarios will have mostly good air quality while post-project implementation scenario will have poor air quality close to the highway. Spatially explicit sensitivity analysis indicates that SAQIAM is robust. SAQIAM has the potential to serve as decision support tool for geovisualization of transport-related project impacts on air quality. Moreover, it can facilitate environmental managers to prioritize mitigation measures by capturing the perception of stakeholders using SAQI.
Journal of Geovisualization and Spatial Analysis, 2019
Identifying the right set of Socio-Economic Descriptors (SEDs) during the spatial analysis of a S... more Identifying the right set of Socio-Economic Descriptors (SEDs) during the spatial analysis of a Socio-Economic Impact Assessment (SEIA) is pivotal for a reliable impact modelling. For this, methods like factor analysis and sensitivity analysis can be used. As a case study, the Spatial Socioeconomic Impact Assessment Model (SSEIAM) of the broadening of highway NH 10 in the East district of Sikkim is used to emphasise on this issue. Principal Component Analysis (PCA) is used to identify the most important SEDs contributing to the composite impact estimated by SSEIAM. Furthermore, Spatially Explicit Sensitivity Analysis (SESA) is performed to identify the model sensitivity to SED weights. SSEIAM is a GIS-based model that relies on experts’ opinion and peoples’ perception of the impacts of the project on the SEDs. The model uses Weighted Linear Combination (WLC) of kriging-generated SED surfaces to prepare the composite impact map. PCA indicates that farming activities, health facilities, traditional values, demographic profile, tourism and land-use & land-value are the major contributors to the variance in the descriptor space. SESA shows that SSEIAM is robust. However, land-use & land-value and farming activities contribute most to the perturbations of the composite impact value. This suggests, that model variable identification is a crucial step towards impact modelling.
Spatial Impacts of highway projects on biodiversity of NorthEastern Himalaya remains largely unex... more Spatial Impacts of highway projects on biodiversity of NorthEastern Himalaya remains largely unexplored. Usually a number of ecological criteria are required in biodiversity impact assessment. However, a wide set of such criteria can be overwhelming for the decision-makers to assess the viability of such projects. SBIAM uses landscape metrics and experts' opinion to create a single composite biodiversity value map. The weighted area loss under various project alternatives estimated from Biodiversity Value Map is compared to identify the most viable alternative. SBIAM uses AHP and curve fitting method in the biodiversity estimation. The study indicates that the highway broadening project in the study area will cause a moderate biodiversity loss. Sensitivity analysis of SBIAM indicates its robustness, and shows that forest patches near the highway are most sensitive to disturbances and patch proximity. SBIAM can be applied in varied spatial scales, terrains and development projects as a decision support tool.
Uploads