See it from space.
Confirm it from the sky.
Respond before it's too late.
An AI-driven platform combining satellite screening, autonomous drone verification, and precision response — for disease control, fire control, animal surveillance, flood monitoring, and emergency delivery.
One platform. Five missions.
Same satellite-to-drone architecture — screen, verify, respond — applied wherever climate and emergency response need eyes in the sky.
Disease Control
Satellite screens for standing water, drones confirm breeding sites, precision spray response.
Fire Control
Satellite thermal anomalies flag ignition risk, drones verify spread, retardant response.
Animal Surveillance
Satellite habitat change detection, drones track and count wildlife, anti-poaching response.
Flood Monitoring
Satellite water-level trends flag rising risk, drones verify inundation, evacuation alerts.
Emergency Delivery
Satellite routing around hazards, drones verify landing zones, autonomous supply drop.
Climate change and emergencies are outpacing manual response.
Warming temperatures, shifting weather patterns, and growing climate volatility are creating new risks — disease outbreaks, wildfires, floods, wildlife loss — faster than manual, ground-based response can keep up.
- ✗Paper-based surveillance, 2–4 week lag
- ✗Field teams patrol at-risk zones — find ~30% of targets
- ✗Blanket response regardless of confirmation
- ✗No early warning — reactive, not predictive
- ✓Satellite screens 100% of district area weekly, free
- ✓Drone validates only flagged zones — 70–80% fewer flights
- ✓Precision response at confirmed sites only
- ✓4–6 week risk prediction from fused data
Three tiers. One mission. Faster response.
Each stage costs less and moves faster than the one before. Satellite screens everything. Drone validates what matters. Intervention targets only what is confirmed — with a full georeferenced audit trail from pixel to response.
Wide-area screening
Sentinel-2 imagery scans entire districts weekly at 10m resolution. NDWI water index + change detection flags target signatures automatically. Zero marginal cost. 100% district coverage.
Drone verification
Autonomous drones target only satellite-flagged zones, capturing sub-10cm imagery. AI detects the target signature for the active mission — standing water, thermal anomaly, wildlife presence, flood extent, or drop zone. Close-range descent confirms when needed.
Precision intervention
Confirmed targets trigger a response mission. Same drone airframe — payload swapped for the mission (larvicide tank, retardant canister, tracking tag, supply pod) in under 5 minutes. Precision delivery at exact confirmed coordinates only.
End-to-end cycle: Instant vs. 2–4 weeks manually·Same drone, swappable payload, three stages — across five missions.
Detect → Verify → Respond → Predict. One shared pipeline, five missions.
The same satellite-to-drone architecture powers every scope. Here's the pipeline in action for Disease Control — our most mature, furthest-along implementation.
Sentinel-2 acquisition
ESA Copernicus satellite passes over target districts weekly. Cloud-masked Sentinel-2 L2A tiles are ingested automatically via Google Earth Engine at zero cost.
NDWI water detection
Normalized Difference Water Index isolates standing water. Week-over-week change detection flags new or growing water bodies. Permanent rivers and reservoirs are excluded via historical mask.
Mission planning
Flagged candidate zones are ranked by area, proximity to settlements, and historical case burden. Top N zones are queued for drone validation. Operator approves the mission in ~15 minutes.
Survey drone flight
Autonomous drone flies only to flagged zones at 30m altitude, capturing 5–10cm GSD imagery. YOLOv8 detects standing water, containers, blocked drains, and tire piles across the full zone.
Nano-shot confirmation
For each high-confidence water surface, the drone descends to 2–5m. EfficientNet-B0 classifier analyzes macro close-ups for larval signatures — turbidity, organic film, container type, visible larvae.
Intervention dispatch
larvae_confirmed detections trigger an intervention mission. Drone returns to base — camera payload swapped for larvicide tank in <5 minutes. Precision spray applied at exact confirmed coordinates.
Risk prediction
XGBoost model fuses satellite trends, confirmed habitat density, IoT sensor readings, and historical case data to generate ward-level outbreak risk scores 4–6 weeks ahead.
Closed-loop audit
Every intervention traces back through detection → flight → mission → satellite pixel. Full georeferenced audit trail with timestamp. FCHVs receive alerts in Nepali. Risk scores updated.
Numbers that matter.
Drishti is designed for measurable outcomes across every mission. These figures reflect our Disease Control pilot — the first scope in active development.
Built by drone engineers and public health experts.
A cross-disciplinary team combining deep software engineering, epidemiology expertise, and operational drone experience in Nepal.
Foundation → Pilot → Scale.
A disciplined 12-month path to measurable impact, starting with Disease Control in Nepal — designed to expand across five response domains and to any country facing these hazards.
- ·Open-source codebase — Apache 2.0, all code on GitHub
- ·Satellite NDWI pipeline — Chitwan demo data
- ·YOLOv8 survey + EfficientNet nano-shot models trained
- ·FastAPI backend with XGBoost prediction engine
- ·MapLibre dashboard + landing page
- ·Live Sentinel-2 acquisition (weekly automated)
- ·First drone survey flights in Chitwan district
- ·Real annotated dataset → model retrain
- ·Nepal MoHP / EDCD dashboard onboarding
- ·First complete verify→validate→execute cycle
- ·3 additional Nepal districts
- ·Malaria + Japanese Encephalitis models
- ·Offline-first PWA for field workers
- ·Peer-reviewed impact metrics published
- ·India and Bangladesh pilots
- ·Multi-country adaptation guide
- ·Aquaculture monitoring vertical
- ·Open-source community in 5+ countries
- ·Fire Control and Flood Monitoring pilot programs
Partner with us. Build with us.
Are you a public health authority, emergency response agency, NGO, research institution, or developer working on climate-response challenges? We want to hear from you — especially if you operate in a region facing disease, wildfire, flooding, wildlife, or emergency-logistics challenges.