← Back to Real Science Applications
Case Study

Agricultural Land Abandonment in Conflict-Affected Myanmar

The Research in Action workflow demonstrates an end-to-end multi-agent research case study that involves connecting literature ingestion, gap detection, and paper drafting into a single workflow with human approval between stages.

Designers: Nidhi Jha, Siddharth Chaudhary

This case study demonstrates Research in Action using AKD Agents, showing how multiple AI agents can support an end-to-end scientific workflow, from literature discovery to research gap identification, hypothesis development, data search, code reuse, analysis support, and scientific output.

The initial case study focuses on Agricultural Land Abandonment (ALA) in conflict-affected Myanmar after the 2021 military coup, using remote sensing, AI-assisted discovery, and human scientific reasoning. A key feature of this workflow is the connection of specialized AKD agents across the research lifecycle: Literature → Research Gaps → Hypotheses → Data → Code → Analysis → Scientific Output. Each agent supports a specific stage, while core scientific reasoning, method design, implementation, interpretation, and final conclusions remain human-driven.

Inputs

Collaborative Design

This Research in Action workflow uses AKD agents as scientific support tools while keeping researchers in control of the scientific process. Users define the research question, select hypotheses, design the methodology, implement the analysis, and validate results.

The agents assist with literature exploration, gap discovery, dataset identification, code search, workflow documentation, and scientific illustration. By passing outputs through a structured agent-to-agent pipeline, the system automates processes while ensuring that scientific judgment and final conclusions are managed by users.

Outputs