Loading...

Research

Reading the land through data.

A research program built around one question: how can AI turn Earth observation data into timely, local decisions — starting with Nepal's farms, glaciers, and floodplains.

Research Interests

Core areas

GeoAI

Deep learning architectures purpose-built for spatial and temporal Earth data.

Remote Sensing

Multispectral & SAR imagery analysis for land, water, and vegetation monitoring.

GIS

Spatial data infrastructure, geoprocessing, and web mapping.

Computer Vision

Image classification and segmentation applied to satellite imagery.

Machine Learning

Ensemble methods, cross-validation rigor, and model interpretability.

Deep Learning

CNNs and transformer-based models for spatio-temporal prediction.

Earth Observation

Sentinel, Landsat, and ERA5 data pipelines for continuous monitoring.

Climate Change

Climate risk indicators and long-term environmental trend analysis.

Current Research

Active work

Ensemble Learning for NDVI-Based Crop Yield Prediction

Comparing SVR, Random Forest, Gradient Boosting, and XGBoost on multi-stage NDVI and canopy temperature data for wheat yield estimation, with emphasis on rigorous cross-validation and generalization across growth stages.

Pythonscikit-learnXGBoostSentinel-2

Nepal-Scale Geospatial Dataset Construction

Extracting NDVI, ERA5 climate, and Copernicus land-cover datasets over Nepal's bounding box via Google Earth Engine for open, reusable research datasets.

Google Earth EngineColabCopernicus

Future Research

Where this goes next

  • Multi-decadal glacier retreat mapping across Himalayan basins using SAR time series.
  • Transformer-based flood forecasting fusing precipitation, terrain, and river-gauge data.
  • Transferable crop-monitoring models for data-scarce smallholder regions across South Asia.

Research Goals

The five-year arc

2026

Publish first preprint; finalize scholarship applications.

2027

Graduate B.E.; begin fully funded MSc/PhD program.

2028–29

Publish peer-reviewed GeoAI research; contribute to open datasets.

2030+

Lead applied GeoAI research for climate resilience in South Asia.

Research Output

Papers & posters in progress

Working Paper

Ensemble Methods for NDVI-Driven Crop Yield Estimation

In preparation · Target: 2026

Conference Paper

A GeoAI Dashboard for Nepal-Scale Disaster Response

In preparation · Target: 2026

Poster

Open Earth Observation Datasets for the Nepal Terai

Planned · 2027

Preprint

Transferable Crop Monitoring for Smallholder Agriculture

Planned · 2027