Why it matters
Without AI, inconsistent assessments, delayed interventions, and unsafe felling plans can occur, risking tree failures, utility damage, and poor compliance with wildlife law and planning conditions.
From design to safety
Design
AI-guided assessment framework
The system reads crown decline classes from field surveys, roadside ash inventories, stem lesion images, and existing records to propose an initial risk ranking and a compliant felling framework. It tags high-priority units for field verification and integrates with the BS 5837 planning references for utility corridors.
- crown decline classifications
- roadside ash asset register
- stem lesion imaging data
- felling programme plan
Build
Data-to-plan execution
The AI exports a validated design package including crown management targets, buffer zones, and method statements aligned with BS 3998 and LOLER considerations. It cross-checks against LOLER inspection intervals and records the sequence in the approved method statements.
- crown decline classifications
- roadside ash asset register
- stem lesion imaging data
- felling programme plan
Operation
On-site prioritisation in real time
During fieldwork, AI re-evaluates risk as conditions change, updating work orders and pruning or felling commands while logging decisions for governance. It marks changes for supervisor review and exports updates to the audit trail.
- crown decline classifications
- roadside ash asset register
- stem lesion imaging data
- felling programme plan
Maintenance
Reinspection and record upkeep
Scheduled re-inspections reassess crown health and lesion progression, updating records, and triggering reassessment of prioritisation against revised guidance. It reissues inspection intervals and updates the asset register with revised RPAs and contingencies.
- crown decline classifications
- roadside ash asset register
- stem lesion imaging data
- felling programme plan
Safety
Compliance and protection checks
The system flags safety or wildlife-law issues, ensuring aerial rescue readiness, public protection measures, and sign-off by qualified personnel before operations. It validates PPE compliance and buffers against current permits.
- crown decline classifications
- roadside ash asset register
- stem lesion imaging data
- felling programme plan
Part by part
- 1
crown decline classifications
- Watch for
- Rising crown decline classes indicating rapid deterioration and loss of structural integrity.
- AI action
- AI flags high-risk trees and triggers immediate field verification.
- 2
roadside ash asset register
- Watch for
- Emergence of clustering failures near pavements or utilities and inconsistencies in tree IDs.
- AI action
- AI updates priority list and allocation of containment setbacks.
- 3
stem lesion imaging data
- Watch for
- New or enlarging stem lesions with potential black rot or Phytophthora signs.
- AI action
- AI assigns urgency level and schedules targeted diagnostics.
- 4
felling programme plan
- Watch for
- Conflict with utility works, setback breaches, or insufficient escape routes.
- AI action
- AI generates compliant sequencing and method statements.
- 5
inspection records and notes
- Watch for
- Gaps in historical records or missing sign-offs on last saw-cut or release plan.
- AI action
- AI prompts field team for missing data and signs off once complete.
- 6
conservation and wildlife compliance logs
- Watch for
- Unrecorded nesting or roost sites in ash stands near roads.
- AI action
- AI raises permit checks and elevates to supervisor review.
Worked example
Catching a stem lesion before a field failure
Illustrative scenario with sample data.
An outbreak signal risks roadside ash; AI prioritises felling and triggers immediate planning review.
Signal in
treeId=ASH-047; crownDecline=moderate; stemLesionArea=12%; location=MM-1 roadside; lastInspection=2026-06-12; fellingPlanVersion=V2; RPAs=2.5m; bufferZone=3.0m
System out
Priority alert: High-risk roadside ash ASH-047; schedule urgent felling; update route with traffic management; assign crew to break-back removal; generate revised method statements for audio-visual barriers.
Human sign-off: Crew supervisor approves high-priority felling sequence and confirms traffic management plan.
How to roll it out
Phase 1
Weeks 1 to 4
Baseline data ingestion from existing surveys and first AI risk ranking for all ash in scope.
Phase 2
Weeks 5 to 8
Live field validation, new lesion detection, and automated priority realignment with monitored outputs.
Phase 3
Weeks 9 to 12
Full integration with planning and safety records, with audit-ready reports and handover to maintenance.
Where people stay in charge
- Decisions on felling urgency and tree removal must be signed off by a chartered arborist or local authority tree officer.
- No work order is issued without explicit approval of the responsible utility liaison or contracts manager when roadside assets are involved.
- Records and decisions must be auditable and retained in the management system for the minimum statutory period.
Questions owners and crews ask
What data feeds should be in the ash dieback AI system?
The system should ingest crown decline classifications, stem lesion imagery, roadside asset data, historic inspections, and approved felling plans, with sign-off headers from the supervising arborist.
Who signs off a high-priority felling decision?
A chartered arborist or local authority tree officer signs off, with utility liaison validation when close to infrastructure.
How is legality and wildlife protection handled?
The AI flags potential wildlife constraints and routes to the wildlife officer for review, ensuring compliance with Wildlife and Planning laws.
What reports are generated for audits?
An auditable chain of custody report, risk ranking log, and method statements are generated, stored, and retrievable for audits.