AI helps Ukraine remove 21,500 km² of farmland from its hazard records

An evaluation of UNDP's mine action project found that AI-assisted approaches let Ukraine cancel over 21,500 km² of farmland from its hazard database in 2023.

  • 3 society

    The evaluator found that cancelling over 21,500 km² of farmland from the hazard database in 2023 let farming resume quickly.

  • 2 an organization

    The evaluator found that AI-enabled approaches supported land cancellation and prioritization for the national authorities in charge of mine action.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the evaluators support the benefit.

The system’s part
Not isolated. The evaluator credits AI-assisted and data-driven approaches, including satellite imagery and machine learning, but does not name the tool, describe the model or say who built it. The area figure has no cited source, and the evaluator does not separate the AI's part from the other survey and information work.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Increased Scalability
System
AI-assisted, satellite-imagery and machine-learning approach to cancelling and prioritizing suspected hazardous areas in Ukraine's mine action database (unnamed tool)
Made by
Not named in the evaluation (UNDP research and innovation work under the Mine Action Project)
Used by
Ukraine's mine action authorities (Secretariat of the National Mine Action Authority, Ministry of Economy, Environment and Agriculture and State Emergency Service) with UNDP
Where
Ukraine (national)
Stage
Expanding
Date
Kind
Aggregate result
Broad benefit
Analyzing Data or Information, Organizing, Planning, and Prioritizing Work
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Evaluation report, by an evaluator that the makers or users commissioned.

    Shubitidze, G. Midterm Evaluation of the project 'United Nations Development Programme (UNDP) Mine Action Project (MAP) in Ukraine'. Evaluation report commissioned by UNDP Ukraine, 30 December 2025. Published in the UN Evaluation Group repository.

    Land release is among the Project’s most impactful achievements. AI-assisted and data-driven approaches enabled the cancellation of over 21,500 km² of agricultural land from the national database in 2023 alone, allowing rapid resumption of farming and contributing directly to food security and economic recovery.

Details

AI system

Workflow

UNDP's research and innovation work applied satellite imagery, artificial intelligence and machine learning. The approach supported land cancellation and prioritization for the national authorities in charge of mine action. Cancelled land was removed from the national database.

Follow-up

Conditions for replication

Information systems must stay aligned with the national IMSMA database. Mine action must stay embedded in government-led planning and prioritization.

Entry details

Sector

Humanitarian mine action.

Purpose

Unnamed developers working with UNDP built the AI-assisted approach to cancel and prioritize suspected hazardous areas in Ukraine's mine action database.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). AI helps Ukraine remove 21,500 km² of farmland from its hazard records (AIBD-0694). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0694.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions