Bikram Singh

Bikram Singh

Auto-generated profile, based on publicly available information

Bikram Singh

Divisional Forest Office Triveni, Katari Udayapur 56310 Nepal

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
2 November 2023 in Heliyon
Verified
Journal Article
Open access
BSBikram Singh
Bikram Singh
AVAMIT KUMAR Verma
AMIT KUMAR Verma
KTKasip Tiwari
Kasip Tiwari
RJRajeev Joshi
Rajeev Joshi
The monitoring of forest biomass is a crucial biophysical parameter in forest ecosystems, as it provides valuable information for managing forests sustainably and tracking carbon circulation statistics. To achieve sustainable forest management, it is essential to monitor and study forest resources, particularly biomass. This study aimed to model above ground tree biomass (AGTB) using Machine Learning Algorithms (MLAs) in the western terai Sal forest of Nepal. AGTB was calculated using a systematic inventory sample plot, while spectral and textural variables were processed and masked for the study area using Sentinel-2A satellite imagery. Three MLAs namely support vector machine (SVM), random forest (RF), and stochastic gradient boosting (SGB), were employed for modeling with eight categorized variable datasets. Among the MLAs, the RF algorithm with a combination of gray-level co-occurrence matrix (GLCM) and raw bands (RB) dataset variable demonstrated the best performance, with a low RMSE value of 78.81 t ha−1 in the test data. However, the AGTB range from this model ranged from 118.34 to 425.97 t ha−1. The study found that traditional indices, raw bands, and GLCM texture from near-infrared were important variables for AGTB. Nevertheless, the RF algorithm and the dataset combination of GLCM plus raw bands (RB) exhibited excellent performance in all model runs. Thus, this pioneering study on comparative MLAs-based AGTB assessment with multiple datasets variables can provide valuable insights for new researchers and the development of novel approaches for biomass/carbon estimation techniques in Nepal.

6 October 2023 in International Journal of Zoology
Verified
Journal Article
Open access
PDF file
RBRam Krishna Bhattarai
Ram Krishna Bhattarai
RJRajeev Joshi
Rajeev Joshi
JGJeetendra Gautam
Jeetendra Gautam
BKBirendra Kandel
Birendra Kandel
BSBikram Singh
Bikram Singh
The Asiatic wild water buffalo (Bubalus arnee Kerr), an endangered species featured on the IUCN Red List, is distributed across Nepal, India, Sri Lanka, Myanmar, Bhutan, Cambodia, and Thailand. This investigation delves into the reproductive and certain social behaviors exhibited by Bubalus arnee across distinct habitats and herd types within Nepals Koshi Tappu Wildlife Reserve (KTWR) and Chitwan National Park (CNP) during the premonsoon and postmonsoon spans of 2018. The data were amassed through direct observations employing focal animal sampling, continuous sampling, and scan sampling methodologies. Eight primary behavioral activities were noted: chasing, courtship, grazing, mating, mowing, sniffing, urination, and wallowing. We carefully structured the gathered data and input it into a Microsoft Excel spreadsheet to facilitate analysis. For a more comprehensive visualization of reproductive behavior, we utilized the ggplot2 package within R-studio, enabling the creation of informative graphical depictions. During the premonsoon phase, Bull A exhibited six reproductive behaviors in KTWR. Notably, sniffing was the most frequently observed behavior, recorded six times (37.5) daily, succeeded by fighting and urination with four (25) and three (18.35) daily observations, respectively. Chasing, mating, and courtship were each observed once (6.25) daily. In contrast, during both seasons, Bulls B, M, and J were not observed partaking in mating activities. When analyzing the postmonsoon reproductive behavior of the observed B. arnee in KTWR and CNP, a notable distinction emerged. In KTWR, there were four more instances of sniffing behavior compared to CNP. In addition, courtship behavior was slightly more frequent in KTWR, occurring three times, whereas it was observed only twice in CNP. Similarly, urination activity was recorded twice as often in KTWR as compared to CNP. As a suggestion for future research, exploring the specific factors influencing the observed variations in reproductive behaviors and habitat preferences of Bubalus arnee could provide valuable insights into the conservation and management of these endangered species.

1 January 2026 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
SKSubash Kushwaha
Subash Kushwaha
MMMenuka Maharjan
Menuka Maharjan
RJRajeev Joshi
Rajeev Joshi
VYVijay Kumar Yadav
Vijay Kumar Yadav
YYYogendra Yadav
Yogendra Yadav
BSBikram Singh
Bikram Singh
Accurate estimation of above‐ground tree biomass (AGTB) is vital for sustainable forest management and climate change mitigation. This study evaluates the performance of three machine learning algorithms (MLAs): support vector machine (SVM), random forest (RF), and stochastic gradient boosting (SGB) for predicting AGTB in Shorea robusta (Sal) forests of Nepal’s Terai region. Using field data from 198 sample plots and 11 Sentinel‐2 derived vegetation indices, models were calibrated and validated. RF outperformed SVM and SGB, achieving the lowest root mean square error (RMSE = 68.36 t ha −1 ), highest correlation coefficient ( r = 0.61), and coefficient of determination ( R 2 = 0.38). Predicted AGTB ranged from 33.93 to 567.03 t ha −1 , reflecting the forest’s heterogeneity. Variable importance analysis revealed normalized difference vegetation index (NDVI) as critical for SVM/SGB, while Modified Chlorophyll Absorption Ratio Index (MCARI) was key for RF. This study establishes RF as the most robust MLA for AGTB mapping in Sal forests, providing a scalable framework for enhancing Nepal’s forest carbon monitoring and supporting Reducing Emissions from Deforestation and Forest Degradation (REDD+) initiatives. Although the predictive accuracy was moderate, this study demonstrates the challenges of biomass estimation in Nepal’s highly heterogeneous Sal forests and provides a replicable framework under data‐limited conditions.

1 January 2026 in International Journal of Forestry Research
Verified
Journal Article
Open access
PDF file
APAman Prabhakar
Aman Prabhakar
SASantosh Ayer
Santosh Ayer
PCPrakriti Chataut
Prakriti Chataut
BSBikram Singh
Bikram Singh
Accurate estimation of stem volume is essential for forest inventory, carbon accounting, and sustainable forest management. However, variation among sectional measurement rules and predictive models may lead to materially different volume estimates at tree and stand level. Therefore, this study compares three classical sectional formulas (Smalian’s, Huber’s, and a hybrid approach) and five predictive modeling strategies (a DBH‐only regression model, a DBH–height regression model, a form factor method, a taper‐based model, and a random forest model) for Shorea robusta in the lowland Terai forests of Nepal, based on publicly available destructive sampling dataset of 81 trees. Sectional methods were evaluated relative to the Newton‐derived reference estimate, while predictive models were assessed using leave‐one‐out cross‐validation. In addition, simulation experiments were conducted to examine model sensitivity under varying error conditions. Results showed that Smalian’s and the hybrid methods produced slightly higher volume estimates (0.27% and 0.35%), whereas Huber’s rule produced slightly lower estimates (−0.13%). Although these differences were statistically detectable, deviations were practically small on the tree‐level scale relative to the Newton‐derived reference. Among predictive approaches, the DBH–height (rRMSE = 20.98%, R 2 = 0.896) and taper‐based models (rRMSE = 20.49%, R 2 = 0.913) demonstrated comparatively strong performance, while the form factor model exhibited the largest systematic bias. Simulation‐based sensitivity analysis suggested that model responses to illustrative reference‐volume error scenarios varied across approaches, with observed differences reflecting model structure and predictor constraints rather than indicating inherent methodological superiority. These findings emphasize that methodological choice and data quality both influence volume estimation outcomes. For practical applications, DBH–height and taper‐based approaches provide reliable and operationally suitable options for S. robusta forest inventory and carbon accounting in Nepal.