Megharaj Poudel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Megharaj Poudel has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Bharat Prashad Bhatt
Ministry of Forests and Environment, Singha Durbar, Kathmandu 44600, Nepal
1 shared publication - Bijaya Dhami
Department of Biological Sciences, University of Alberta, Edmonton, Canada
1 shared publication - Bijaya Neupane
Department of Forest Sciences, Viikki Tropical Resources Institute, University of Helsinki, Helsinki, Finland
1 shared publication - Deepak Gautam
School of Ecology and Nature Conservation, Beijing Forestry University, Beijing 100083, China
1 shared publication - Nolaraj Poudel1 shared publication
- Sagar Godar Chhetri
Arkansas Center for Forest Business, College of Forestry, Agriculture and Natural Resources, University of Arkansas at Monticello, Monticello, USA
1 shared publication
Latest Publications
- Open Access
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
Machine Learning-Driven Surrogate Modeling for Rapid Seismic Response Prediction of Irregular Reinforced Concrete Buildings under Nonlinear Soil–Structure Interaction
Earthquake loading is inherently stochastic and complex, rendering accurate seismic response assessment a computationally demanding. This study employs established machine learning (ML) algorithms for the seismic performance assessment of torsionally irregular reinforced concrete (RC) buildings founded on nonlinear soil conditions, with explicit consideration of soil–structure interaction (SSI) effects. Six building configurations representing varying degrees of plan irregularity, four base conditions encompassing fixed and flexible foundation scenarios, and twenty-two ground motion records were systematically considered. Incremental Dynamic Analysis (IDA) was performed, yielding 3,696 full three-dimensional nonlinear finite element (FE) simulations. The extracted structural response parameters were used to train and validate ML models and to develop GUI-based prediction framework. To assess the generalizability of the model across broader seismic scenarios, 120,000 additional simulations were generated using randomized seismic attributes. The results demonstrate that nonlinear SSI significantly amplifies seismic demand, with response increasing progressively from stiff to soft soil conditions and from regular to torsionally irregular configurations, thereby highlighting the limitations of conventional fixed-base assumptions. Among the evaluated algorithms, XGBoost and LightGBM consistently exhibited the superior predictive performance, accurately capturing the complex nonlinear structural behaviour of the FE models with mean absolute percentage errors below 0.2% and coefficients of determination exceeding 0.976 across all cases. Similarly, feature importance analyses identified Peak Ground Acceleration (PGA) and other dynamic ground-motion characteristics as the dominant parameters governing structural seismic response. Rotational angle as a torsional irregularity measure emerged as a highly sensitive response parameter, exhibiting strong alignment with plan irregularity and SSI effects, which are not fully represented in conventional threshold-based classifications. The developed framework incorporates a comprehensive set of structural, geotechnical, and seismic features, enabling rapid response estimation across a wide range of realistic scenarios. The proposed ML models accurately replicated nonlinear FE simulations with negligible computational cost, demonstrating their effectiveness as high-fidelity surrogate tools for reliable seismic performance assessment under nonlinear SSI conditions.
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMachine Learning-Driven Surrogate Modeling for Rapid Seismic Response Prediction of Irregular Reinforced Concrete Buildings under Nonlinear Soil–Structure Interaction
Earthquake loading is inherently stochastic and complex, rendering accurate seismic response assessment a computationally demanding. This study employs established machine learning (ML) algorithms for the seismic performance assessment of torsionally irregular reinforced concrete (RC) buildings founded on nonlinear soil conditions, with explicit consideration of soil–structure interaction (SSI) effects. Six building configurations representing varying degrees of plan irregularity, four base conditions encompassing fixed and flexible foundation scenarios, and twenty-two ground motion records were systematically considered. Incremental Dynamic Analysis (IDA) was performed, yielding 3,696 full three-dimensional nonlinear finite element (FE) simulations. The extracted structural response parameters were used to train and validate ML models and to develop GUI-based prediction framework. To assess the generalizability of the model across broader seismic scenarios, 120,000 additional simulations were generated using randomized seismic attributes. The results demonstrate that nonlinear SSI significantly amplifies seismic demand, with response increasing progressively from stiff to soft soil conditions and from regular to torsionally irregular configurations, thereby highlighting the limitations of conventional fixed-base assumptions. Among the evaluated algorithms, XGBoost and LightGBM consistently exhibited the superior predictive performance, accurately capturing the complex nonlinear structural behaviour of the FE models with mean absolute percentage errors below 0.2% and coefficients of determination exceeding 0.976 across all cases. Similarly, feature importance analyses identified Peak Ground Acceleration (PGA) and other dynamic ground-motion characteristics as the dominant parameters governing structural seismic response. Rotational angle as a torsional irregularity measure emerged as a highly sensitive response parameter, exhibiting strong alignment with plan irregularity and SSI effects, which are not fully represented in conventional threshold-based classifications. The developed framework incorporates a comprehensive set of structural, geotechnical, and seismic features, enabling rapid response estimation across a wide range of realistic scenarios. The proposed ML models accurately replicated nonlinear FE simulations with negligible computational cost, demonstrating their effectiveness as high-fidelity surrogate tools for reliable seismic performance assessment under nonlinear SSI conditions.
- Open Access
- 9 February 2022
- Published by Springer Nature in Ecological Processes
- Vol. 11 (1) , 1-10
Niche breadth and overlap of spotted deer and domestic cattle with swamp deer in tropical region of Nepal
Background: Knowledge about the niche overlap among wild species and domestic cattle is helpful to conserve and manage wildlife. We assessed the habitat niche breadth and overlap of sympatrically living spotted deer (Axis axis) and domestic cattle with swamp deer (Cervus duvaucelii) in Shuklaphanta National Park, Nepal during the dry season to explore the possibility of interspecific competition by studying the habitat use by these species. The assumption was made that the presence of pellets is proof of habitat used by species. Methods: Grids of 2 km × 2 km have four subgrids, each with four sample plots, making a total of 16 plots (20 m × 20 m) in each grid. The size of each sub-grid was 200 m × 200 m and they were placed randomly inside the grid but at least 1 km apart from one another. The data was collected in a 96 plots in total. Levin’s niche breadth and Morisita’s overlap index were calculated to determine the niche breadth and the habitat overlap, respectively. Results: The Levin’s measure of niche breadth suggested that spotted deer had the highest acclimatization with an index value of 0.94, followed by domestic cattle at 0.50, and swamp deer at 0.33 in our study area. Thus, our findings supported the evidence that spotted deer are habitat generalists, whereas swamp deer are habitat specialists. The swamp deer had lower niche breadth and more overlap with domestic cattle. Conclusion: Our study showed the least niche breadth of swamp deer in comparison to spotted deer and domestic cattle. The domestic cattle had the highest and least niche overlap with spotted deer and swamp deer, respectively, in terms of habitat use. Our study suggests that domestic cattle grazing should be stopped, and grassland management should be carried out for the benefit of ungulates. Similar studies should be conducted, including different seasons and places, prior to appropriate habitat management. In addition, further studies are needed to quantify the extent of interspecific competition by incorporating more species.
- 9 February 2022
- Published by Springer Nature in Ecological Processes
- Vol. 11 (1) , 1-10
Open AccessNiche breadth and overlap of spotted deer and domestic cattle with swamp deer in tropical region of Nepal
Background: Knowledge about the niche overlap among wild species and domestic cattle is helpful to conserve and manage wildlife. We assessed the habitat niche breadth and overlap of sympatrically living spotted deer (Axis axis) and domestic cattle with swamp deer (Cervus duvaucelii) in Shuklaphanta National Park, Nepal during the dry season to explore the possibility of interspecific competition by studying the habitat use by these species. The assumption was made that the presence of pellets is proof of habitat used by species. Methods: Grids of 2 km × 2 km have four subgrids, each with four sample plots, making a total of 16 plots (20 m × 20 m) in each grid. The size of each sub-grid was 200 m × 200 m and they were placed randomly inside the grid but at least 1 km apart from one another. The data was collected in a 96 plots in total. Levin’s niche breadth and Morisita’s overlap index were calculated to determine the niche breadth and the habitat overlap, respectively. Results: The Levin’s measure of niche breadth suggested that spotted deer had the highest acclimatization with an index value of 0.94, followed by domestic cattle at 0.50, and swamp deer at 0.33 in our study area. Thus, our findings supported the evidence that spotted deer are habitat generalists, whereas swamp deer are habitat specialists. The swamp deer had lower niche breadth and more overlap with domestic cattle. Conclusion: Our study showed the least niche breadth of swamp deer in comparison to spotted deer and domestic cattle. The domestic cattle had the highest and least niche overlap with spotted deer and swamp deer, respectively, in terms of habitat use. Our study suggests that domestic cattle grazing should be stopped, and grassland management should be carried out for the benefit of ungulates. Similar studies should be conducted, including different seasons and places, prior to appropriate habitat management. In addition, further studies are needed to quantify the extent of interspecific competition by incorporating more species.
- 1 September 2021
- Published by Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences in Journal of Resources and Ecology
- Vol. 12 (5) , 620-627
Economic Contribution of Forestry Sector to National Economy in Nepal
Forests are major sources of energy, timber and non-timber forest products, medicinal and aromatic plants, hydrological functions, biodiversity conservation, and also fundamental sources of revenue collection to the nation. Studies indicate that forests could significantly enhance economic growth and create employment opportunities for local communities under intensive management. This paper aims to predict the contribution of the forest sector to the national economy. The economic facets of forestry considered in this paper are revenue generated from timber, non-timber forest products (NTFPs) and medicinal and aromatic plants (MAPs), and protected areas. The ARIMA model was used to forecast the economic contribution of the forestry sector. The study found that the total revenue generated from the selling of timber and fuelwood (USD 50.19 million) was higher than the total revenue collected from protected areas (USD 37.58 million) and NTFPs/MAPs (USD 6.9 million) in the past 15 years. The model projected that the mean revenue for the timber and fuelwood sale will USD 3.5 million for the next ten years. Similarly, the mean revenue will be generated about USD 0.5 million and USD 6.2 million from NTFPs/MAPs and protected areas, respectively, for the next ten years. The study limits to take account the in-kind use of forest products such as timber, fodder, fuelwood, etc., as used by community people within a forest users' groups. Thus, practicing sustainable forest management, enabling policy documents, establishing forest-based industries, establishing forestry nurseries, conducting agroforestry practices, and tenure security could enhance the forestry sector's economic aspects.
- 1 September 2021
- Published by Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences in Journal of Resources and Ecology
- Vol. 12 (5) , 620-627
Economic Contribution of Forestry Sector to National Economy in Nepal
Forests are major sources of energy, timber and non-timber forest products, medicinal and aromatic plants, hydrological functions, biodiversity conservation, and also fundamental sources of revenue collection to the nation. Studies indicate that forests could significantly enhance economic growth and create employment opportunities for local communities under intensive management. This paper aims to predict the contribution of the forest sector to the national economy. The economic facets of forestry considered in this paper are revenue generated from timber, non-timber forest products (NTFPs) and medicinal and aromatic plants (MAPs), and protected areas. The ARIMA model was used to forecast the economic contribution of the forestry sector. The study found that the total revenue generated from the selling of timber and fuelwood (USD 50.19 million) was higher than the total revenue collected from protected areas (USD 37.58 million) and NTFPs/MAPs (USD 6.9 million) in the past 15 years. The model projected that the mean revenue for the timber and fuelwood sale will USD 3.5 million for the next ten years. Similarly, the mean revenue will be generated about USD 0.5 million and USD 6.2 million from NTFPs/MAPs and protected areas, respectively, for the next ten years. The study limits to take account the in-kind use of forest products such as timber, fodder, fuelwood, etc., as used by community people within a forest users' groups. Thus, practicing sustainable forest management, enabling policy documents, establishing forest-based industries, establishing forestry nurseries, conducting agroforestry practices, and tenure security could enhance the forestry sector's economic aspects.