arXiv subjects

Mingmar Sherpa

Publications and source records attributed to Mingmar Sherpa.

4 recordsLinked to original sources

arXiv2026

Which Site, and When: A Free-Satellite-Data Test of Himalayan Glacial Lake Bursts, Landslides, and Ice Floods

Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress. A companion feasibility study found that deformation indicates which lake is destabilizing and weather indicates when it is at risk, but proposed no predictive model. To address this gap, we propose and evaluate models that predict which site is susceptible and when a trigger arrives. We test three related hazards on free data alone: large moraine- and ice-dammed bursts, rainfall-triggered landslides, and smaller floods from ponds on and around a glacier. Each hazard gets two questions, never blended. Using 589 dated outbursts from HMAGLOFDB and several thousand catalogued landslides, we match each event against similar but unfailed sites, and hold every model to a strong simple baseline under spatial cross-validation that withholds whole map tiles, so no model succeeds by recognising a trained-on neighbourhood. Antecedent weather times the trigger at ROC 0.73 for big bursts, 0.83 for landslides, and 0.82 for small floods. Terrain ranks susceptibility only in part: scored naively it appears near 0.9, largely because catalogued failures cluster in wetter ranges; matched against comparable nearby sites the honest figures are 0.76, 0.71, and 0.54 (no better than chance). The burst signal holds within single regions, reaching 0.89 in Nepal alone. Five deep-learning models do not decisively beat a simple gradient-boosted baseline. Three score marginally higher on landslides, a hint too small to confirm. For the lake hazards the baseline wins outright, reproduced by a three-rule decision tree on ruggedness and monsoon rainfall. We close with a ranked Nepal watchlist, a prioritisation aid, not a prediction, and note where free data reaches its limits.

cs.LG↗

arXiv2026

Modeling the Dynamic Relationship Between Brent Crude Oil Prices and the Nepal Stock Exchange: An Integrated Econometric and Explainable Machine Learning Approach

This study examines the dynamic relationship between the global oil prices and Nepal Stock Exchange (NEPSE) using an integrated approach which combines traditional econometric techniques with machine learning and explainable AI techniques. For this, Daily data of International Oil prices and NEPSE index is analyzed from approximately thirteen years (June 2013 to June 2026) using Granger causality, EGARCH(1,1), and DCC-GARCH models to examine different properties like predictive relationships, asymmetric volatility behaviour, and time-varying correlations. To further supplement the econometric analysis, Machine Learning Models like Random Forest, LightGBM, and XGBoost algorithms were used to capture nonlinear relationships, along with explainable artificial intelligence techniques like SHAP values, Partial Dependence Plots, and Individual Conditional Expectation plots to further interpret the results of the model. The results from the econometric analysis showed a statistically significant unidirectional Granger causality from Brent crude oil to NEPSE with a four-day lag, high volatility persistence in both markets, and weak yet highly time-varying conditional correlations. Among the machine learning models, XGBoost achieves the best performance, and explainability analysis reveals that NEPSE own momentum and short-term volatility mainly influence its own behaviour and oil-related information serves as a minor, method-dependent contributor. The findings demonstrate that econometric and explainable machine learning approaches provide insights into the oil and equity market relationship in a way that each approach complements the result of one another.

econ.EM↗

arXiv2025

Nepal Engagement with the Millennium Challenge Corporation (MCC) A Philosophical and Economic Perspective

The Millennium Challenge Corporation (MCC), started in 2004 by the United States Congress, focuses on development initiatives involving good governance, sustainable economic growth, and poverty reduction. Since its inception, it has invested over 13 billion US dollars in 30 countries. Nepal is a recent beneficiary, signing a compact valued at 500 million US dollars in 2017, ratified in 2022. The compact mainly invests in road infrastructure and electricity transmission, including construction of 315 kilometers of high-voltage transmission lines, three substations, and upgrading 100 kilometers of the East-West highway. By supporting commercialization of Nepals 40 gigawatt hydropower potential, the MCC aims to enhance Nepals structural economic prosperity. Beyond economics, the compact influences Nepals foreign policy by diversifying partnerships and reducing overdependence on neighbors China and India. The establishment of the Millennium Challenge Account (MCA)-Nepal fosters host-country ownership, mitigating geopolitical concerns. Building on International Relations scholar Shiping Tangs Institutional Foundations for Economic Development (IFED) framework, this paper shows how the MCC addresses Nepals infrastructure development capacity. Success stories from Ghana and other MCC countries highlight transformative progress toward prosperity, positioning Nepal to leverage both development and diplomatic opportunities. Drawing from multiple sources, this paper argues that the MCC compact provides Nepal with opportunities to overcome infrastructural barriers to growth.

econ.TH↗

arXiv2024

Skin Cancer Machine Learning Model Tone Bias

Background: Many open-source skin cancer image datasets are the result of clinical trials conducted in countries with lighter skin tones. Due to this tone imbalance, machine learning models derived from these datasets can perform well at detecting skin cancer for lighter skin tones. Any tone bias in these models could introduce fairness concerns and reduce public trust in the artificial intelligence health field. Methods: We examine a subset of images from the International Skin Imaging Collaboration (ISIC) archive that provide tone information. The subset has a significant tone imbalance. These imbalances could explain a model's tone bias. To address this, we train models using the imbalanced dataset and a balanced dataset to compare against. The datasets are used to train a deep convolutional neural network model to classify the images as malignant or benign. We then evaluate the models' disparate impact, based on selection rate, relative to dark or light skin tone. Results: Using the imbalanced dataset, we found that the model is significantly better at detecting malignant images in lighter tone resulting in a disparate impact of 0.577. Using the balanced dataset, we found that the model is also significantly better at detecting malignant images in lighter versus darker tones with a disparate impact of 0.684. Using the imbalanced or balanced dataset to train the model still results in a disparate impact well below the standard threshold of 0.80 which suggests the model is biased with respect to skin tone. Conclusion: The results show that typical skin cancer machine learning models can be tone biased. These results provide evidence that diagnosis or tone imbalance is not the cause of the bias. Other techniques will be necessary to identify and address the bias in these models, an area of future investigation.

eess.IV↗