Water Management / AgTech

Drought Monitoring

Name: Satalyse
Author: Satalyse

Real-time drought stress signals for any region on Earth.

15-year CHIRPS history

Precipitation baseline

5 km (CHIRPS), 10 m (NDVI)

Spatial resolution

Near real-time

Update frequency

Yes (60°S–75°N)

Global coverage

The Problem

Water management authorities, agricultural lenders, and commodity traders need current drought stress signals across wide regions, but drought indices (PDSI, SPI) update monthly and require complex meteorological inputs. Ground-based weather station density is insufficient in rural areas most affected by drought. By the time a drought is declared officially, agricultural losses are already locked in.

How Satalyse Solves It

Satalyse combines Feature Extraction (live NDVI and moisture index from Sentinel-2), Risk Scoring (drought component using CHIRPS precipitation versus a 15-year location-specific historical baseline), and Temporal Analysis (vegetation trend over the growing season) to give a real-time, satellite-grounded picture of drought severity. Every drought score is calibrated to the historical norm for that specific location and calendar period, so arid regions aren't falsely flagged, and anomalous moisture deficits in normally wet regions are correctly identified.

Risk Scoring

POST /api/v1/satellite/score-risk

Returns drought risk score using local precipitation baseline (15-year CHIRPS history)

Feature Extraction

POST /api/v1/satellite/extract-features

Returns live NDVI and moisture index indicating vegetation stress

Temporal Analysis

POST /api/v1/satellite/analyze-temporal-trends

Tracks seasonal vegetation trend against prior-year baselines

Code Example

drought-monitoring.py

REQUEST

1"color:#c084fc">import requests
2
3"color:#4b5563"># Score drought risk "color:#c084fc">for an agricultural region "color:#c084fc">in Rajasthan
4response = requests.post(
5    "https://api.satalyse.dev/api/v1/satellite/score-risk",
6    headers={"Authorization": "Bearer sat_sk_live_..."},
7    json={
8        "geometry": {
9            "type": "Polygon",
10            "coord">inates": [[
11                [74.312, 26.914], [74.341, 26.914],
12                [74.341, 26.891], [74.312, 26.891],
13                [74.312, 26.914]
14            ]]
15        },
16        "asset_type": "agricultural",
17        "location_context": "rural",
18        "risk_factors": ["drought"],
19        "time_horizon_days": 365
20    }
21)
22
23data = response.json()
24drought = data["component_scores"]["drought"]
25"color:#c084fc">print(f"Drought score: {drought['score']}/100")
26"color:#c084fc">print(f"Risk level: {drought['level']}")
27"color:#c084fc">print(f"Overall risk: {data['overall_risk_level']}")

200 OKRESPONSE

{
  "request_id": "req_drought001",
  "status": "success",
  "timestamp": "2025-01-15T12:00:00Z",
  "location": { "area_km2": 0.25, "asset_type": "agricultural" },
  "overall_risk_score": 68,
  "overall_risk_level": "high",
  "overall_risk_trend": "increasing",
  "component_scores": {
    "drought": { "score": 68, "level": "high", "confidence": 0.75 }
  },
  "risk_summary": {
    "primary_risks": [
      { "risk": "drought", "score": 68, "action": "Activate irrigation contingency plan" }
    ]
  },
  "insurance_implications": {
    "estimated_annual_premium_multiplier": 1.28,
    "recommendation": "Drought coverage strongly recommended"
  },
  "recommendations": [
    { "priority": "high", "action": "Deploy irrigation backup systems", "estimated_cost": "medium", "risk_reduction": 20 }
  ],
  "api_metadata": { "version": "2.0", "execution_time_ms": 3600, "cost_credits": 40, "cache_hit": false }
}