AgTech

Crop Health Monitoring

Name: Satalyse
Author: Satalyse

Detect crop stress before it becomes yield loss.

10 m (NDVI)

Spatial resolution

NDVI, EVI, moisture, temp

Metrics returned

5 days

Revisit frequency

Multi-image composite

Cloud handling

The Problem

Agtech platforms and large-scale farming operations need continuous crop health signals across thousands of parcels, but deploying soil sensors or scouting teams at that scale is cost-prohibitive. In-season stress events (drought, pest, disease, waterlogging) cause yield losses that go undetected until harvest. Existing remote sensing tools require GIS expertise and per-image licensing fees that don't fit product economics.

How Satalyse Solves It

Satalyse's Feature Extraction endpoint returns NDVI, surface temperature, moisture index, and canopy metrics for any field polygon in a single API call. Combine with Temporal Analysis to build season-over-season baselines per field and automatically flag when current-season readings deviate, surfacing stress events weeks earlier than visual inspection.

Feature Extraction

POST /api/v1/satellite/extract-features

Returns NDVI, moisture index, and surface temperature for the field polygon

Temporal Analysis

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

Builds season-over-season NDVI baselines and detects deviations

Code Example

crop-health-monitoring.py

REQUEST

1"color:#c084fc">import requests
2
3"color:#4b5563"># Get vegetation health metrics "color:#c084fc">for a corn field
4response = requests.post(
5    "https://api.satalyse.dev/api/v1/satellite/extract-features",
6    headers={"Authorization": "Bearer sat_sk_live_..."},
7    json={
8        "geometry": {
9            "type": "Polygon",
10            "coord">inates": [[
11                [-93.142, 41.882], [-93.128, 41.882],
12                [-93.128, 41.871], [-93.142, 41.871],
13                [-93.142, 41.882]
14            ]]
15        },
16        "measurement_date": "2024-08-15",
17        "features_requested": ["vegetation", "water", "temperature"]
18    }
19)
20
21data = response.json()
22veg = data["features"]["vegetation"]
23"color:#c084fc">print(f"NDVI: {veg['NDVI']['value']:.3f}")
24"color:#c084fc">print(f"Health score: {data['health_score']['overall']}/100")
25"color:#c084fc">print(f"Stress detected: {veg['vegetation_stress']['detected']}")

200 OKRESPONSE

{
  "request_id": "req_def456",
  "status": "success",
  "timestamp": "2025-01-15T12:00:00Z",
  "location": { "area_km2": 0.12, "centroid": { "lat": 41.877, "lng": -93.135 } },
  "measurement_date": "2024-08-15",
  "features": {
    "vegetation": {
      "NDVI": { "value": 0.61, "range": [0, 1], "interpretation": "moderate", "confidence": 0.88 },
      "EVI": { "value": 0.49, "interpretation": "moderate vegetation activity" },
      "vegetation_type": "cropland",
      "vegetation_stress": { "detected": true }
    },
    "water": {
      "NDWI": { "value": 0.15, "interpretation": "low water presence" },
      "water_surface_area_percent": 4.2,
      "drought_risk": "moderate"
    },
    "temperature": {
      "surface_temperature_celsius": 29.4,
      "temperature_range_celsius": [25.8, 33.1],
      "anomaly_from_baseline": 2.1
    }
  },
  "health_score": { "overall": 58, "vegetation": 55, "water": 42 },
  "api_metadata": { "version": "2.0", "execution_time_ms": 1350, "cost_credits": 6, "cache_hit": false }
}