Bishal Dhungana
26.7153° N, 80.0534° W — WEST PALM BEACH, FL

Turning raw spatial data into systems that hold up for real infrastructure.

Geospatial Data Scientist working across LiDAR, aerial imagery, computer vision, and agentic AI systems — from field survey through production platforms supporting critical utility infrastructure.

0
Asset Types Classified
0
Condition Classes
0
Addresses Geocoded
0
Platform Components Built
Simulated LiDAR scan
drag to rotate
01 — About

Field-to-production, end to end

I work at the intersection of geospatial engineering, applied AI, and the software/platform work that ties them together — currently as a Data Scientist at The Spear Group, supporting Florida Power & Light's FPLAir/NextVision program, where I lead AI/ML image recognition workflows for power equipment assessment and build the geospatial data pipelines, infrastructure-as-code, and internal platform tooling behind them.

My background started in the field: control and topographic surveys, GNSS and UAV data collection, and geodatabase design in Nepal, before an MSc in Geosciences (GIS concentration) at Florida Atlantic University sharpened the AI/ML and geospatial data engineering side. That combination — knowing how spatial data is actually collected and knowing how to build production systems on top of it — is the throughline across everything I build.

Day to day that means moving fluidly between layers: writing the Python/PyTorch models, designing the AWS CDK infrastructure they run on, building the FastAPI/React consoles that operate them, and — increasingly — building LLM agents that let people query all of it in plain English. I'm FAA Part 107 certified and hold graduate research contributions in flood hazard exposure modeling.

beesal13dh@gmail.com 561-713-5428 FAA Part 107 — Remote Pilot
02 — Experience

Professional experience

APR 2025 — PRESENT
The Spear Group, on behalf of FPL
Data Scientist (Geospatial and AI)
  • Technical lead for AI/ML image recognition workflows — deep learning models for power equipment segmentation, damage detection, and classification across 30+ asset types and 400+ condition classes.
  • Designed an AWS CDK infrastructure-as-code framework with enterprise naming, tagging, and deployment abstractions used across ML and application workloads.
  • Built a modular enterprise data integration platform (Python, SQL, DuckDB) handling taxonomy alignment, schema publishing, and quality validation.
  • Developed a FastAPI/React API operations console with shared authentication and environment-aware routing for cross-team API management.
  • Design and manage enterprise geospatial infrastructure: spatial databases (PostgreSQL/PostGIS), feature services, and cloud-native pipelines on AWS (Lambda, S3, SageMaker).
  • Build GIS applications with Esri technologies (ArcGIS Enterprise, Experience Builder, Dashboards) for infrastructure monitoring and disaster response.
SEP 2024 — MAR 2025
The Spear Group, on behalf of FPL
Associate Geospatial Analyst
  • QA/QC of LiDAR-derived power grid data for infrastructure resilience initiatives, including pole hardening.
  • Managed PostGIS databases and automated data workflows (FME, Python, ArcPy); supported Hurricane Milton restoration with real-time spatial dashboards.
  • Built a FastAPI geospatial processing sidecar for heavier geoprocessing and format conversion tasks.
JAN 2023 — AUG 2024
Florida Atlantic University
Graduate Research Assistant
  • Led FEMA-based flood risk assessment projects across multiple Florida communities, cutting geoprocessing time 50% via ArcGIS Pro automation.
  • Built a Python geocoding tool processing 3M addresses with open-source libraries, replacing a paid service — 3 months to 1 week turnaround, $20K saved.
2020 — 2022
Freelance & ADMC Engineering, Nepal
Geomatics Engineer / GIS Intern
  • Led survey teams for municipal road, GNSS, and UAV-based topographic surveys; trained 40+ officials in spatial analysis for Nepal's Survey Department.
  • Designed integrated municipal geodatabases with topology/attribute integrity rules.
03 — Featured Builds

Agentic AI systems

Two self-directed builds applying LLM agents and RAG to real problems — documented honestly, including the bugs I hit and how I fixed them. Both run entirely locally via Ollama: no API keys, no usage cost.

Geospatial Data Copilot

Repo ↗

A natural-language interface over spatial/infrastructure data. Ask a question in plain English about San Francisco's utility infrastructure — a local LLM agent (LangGraph ReAct, Ollama llama3.1:8b) translates it into a spatial SQL query, runs it, and answers with a natural-language summary and an interactive map. Seeded with ~1,500 real utility assets pulled live from OpenStreetMap's Overpass API.

LangGraphOllamaDuckDB + spatial FastAPIStreamlitFolium Chroma

Conversational AI Assistant

Repo ↗

A LangChain-based RAG chatbot that indexes local documents into a Chroma vector store and answers questions in a context-aware, multi-turn conversation — grounding every answer in retrieved source material and citing which files it used. Runs entirely locally via Ollama.

LangChain (LCEL)OllamaChroma StreamlitPython CLI
04 — Systems & Platform Engineering

What sits behind the models

Production AI needs infrastructure, data pipelines, and internal tooling around it. This is a selection of the platform-layer components I've built to support enterprise geospatial and AI systems.

Cloud Infrastructure

Cloud Infrastructure Components

AWS CDK component framework with enterprise naming, tagging, and deployment abstractions for ML and app workloads.

Data Integration

Enterprise Data Integration Platform

Modular platform for taxonomy alignment, schema publishing, quality validation, and operational patch workflows (Python, SQL, DuckDB).

Developer Platform

API Operations Console

CLI and web console for environment-aware API operations with shared authentication and endpoint tooling (FastAPI, React, Typer).

Data Engineering

Schema Migration Utility

PostgreSQL schema migration CLI with source/target connection separation, dry runs, and preflight checks.

Computer Vision

Utility Asset Detection Inference Service

ONNX-based object detection package for utility equipment with COCO JSON output and optional visualization.

Integration Toolkit

API + Taxonomy Integration Toolkit

Reusable package for API extraction, taxonomy joins, metadata patching, and downstream publishing automation.

Subsystem

Integration Boundaries Layer

Boundary-focused architecture separating API adapters, data sync logic, and publishing interfaces from generic scripts.

Subsystem

Quality & Remediation Script Layer

Modular script layer for analysis, checks, loaders, fixes, and patch orchestration with migration-safe wrappers.

Subsystem

Geospatial Processing Sidecar

Optional FastAPI sidecar for heavier geospatial processing, conversion runtimes, and algorithm endpoints.

Service

Analytics Summary API

Focused API exposing health, pagination, and entity summary endpoints for analytics demos and stakeholder review.

Subsystem

Pre-Production Mapping API

Local map and API demo environment for assignment workflows, status transitions, and pre-publish validation.

Product

Notebook-Embedded GIS Widget

Jupyter integration embedding the full GIS app with two-way project state sync for notebook-driven workflows.

Frontend

Operator Workflow Frontend

React/TypeScript (Vite) frontend for validating operator lifecycle actions before production integration.

Operations

Operations Dashboard Workstream

Storm and pilot deployment dashboard monorepo combining ArcGIS runbooks, SQL and shell automation, and demo APIs.

ML Project

Applied ML Project Template

Data science workspace scaffold for experimentation, feature engineering, and model lifecycle workflows.

Documentation

Delivery Runbooks & Release Standards

Structured runbooks, standards, acceptance gates, and deployment checklists for end-to-end delivery governance.

05 — Toolkit

What I build with

AI / ML / Agents

PyTorchTensorFlowOpenCV Computer VisionONNXLangChain LangGraphRAGChromaOllama

Geospatial

ArcGIS EnterprisePostGISLiDAR / PDAL GeoPandasGDALFMEDuckDB Spatial

Platform / Engineering

PythonFastAPIAWS / CDK React / TypeScriptSQLRTyper / CLI Tooling
06 — Simulation

Flood inundation model

A small browser-side terrain model in the spirit of the FEMA-based hydrologic exposure work below — procedurally generated elevation, not the published dataset. Drag the slider to raise sea level and watch inundation spread.

Inundated area0%
Peak elevation

Color ramp: low-lying green → upland tan/white. Blue = below current sea level.

Utility corridor: 0 of 7 poles below sea level

07 — Research & Selected Work

Publications & academic projects

Most of my professional work is confidential to the organizations I've supported. Below is research and academic/course work I can share in full.

Dhungana, B.; Liu, W. Urban–Rural Exposure to Flood Hazard and Social Vulnerability in the Conterminous United States. ISPRS Int. J. Geo-Inf. 2024, 13, 339. doi.org/10.3390/ijgi13090339 ↗
Contributing author, documentation — PyWMP ↗, an open-source Python watershed modeling and planning tool (Florida Atlantic University).Unpublished, ongoing

Multi-temporal Land Cover Mapping

Land cover classification and change prediction using Google Earth Engine.

View on GitHub ↗

LiDAR Point Cloud Processing

Intensity image generation and DSM/DEM derivation from LAS datasets.

View on GitHub ↗

UAV Orthophoto Generation

Flight planning, image capture, and processing for a full campus orthophoto — Pashchimanchal Campus, Nepal.

View on GitHub ↗

Flood Inundation Mapping, Gaur, Nepal

Footprint mapping in flood-prone regions using OpenStreetMap and HEC-RAS hydrologic modeling.

View on GitHub ↗

Predictive Modeling of Voter Turnout

Census-tract-level 2016 turnout prediction for Florida using forest-based classification and regression.

View on GitHub ↗

Suitable HQ Siting Analysis

Suitability modeling for low-carbon-footprint corporate site selection, Hardee County, FL.

View on GitHub ↗
08 — Credentials

Education & certifications

MSc, Geosciences — GIS Concentration · Florida Atlantic University · 2023–2024 · GPA 4.0/4.0

BSc, Geomatics Engineering · Tribhuvan University, Nepal · 2016–2021 · GPA 3.64/4.0

09 — Contact

Let's talk about what you're building.

Open to Data Science, GIS/Geospatial Engineering, and Data/Platform roles. Based in West Palm Beach, FL.