Precision Farming Drone Imagery
This dataset contains high-resolution synthetic drone imagery of agricultural fields, each image enriched with detailed metadata, geolocation, crop type, and expert-annotated features such as weeds, diseases, and crop health indicators. It supports advanced analytics in precision agriculture, enabling crop health monitoring, automated feature detection, and field management optimization. The dataset is ideal for developing and benchmarking computer vision models and agronomic decision support tools.
Sample rows
preview · 8 of 200 rows · all 22 columns| image_idstring | annotated_feature_typestring | ndvi_meanfloat | growth_stagestring | capture_datetimedatetime | field_idstring | field_namestring | location_latitudefloat | location_longitudefloat | altitude_metersfloat | image_width_pixelsinteger | image_height_pixelsinteger | image_resolution_cm_per_pixelfloat | image_formatstring | crop_typestring | annotated_feature_countinteger | annotated_area_percentagefloat | annotation_quality_scorefloat | annotator_idstring | annotation_datetimedatetime | ndvi_stddevfloat | image_urlstring |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| IMG0001 | weed | 0.67 | vegetative | 2024-03-10T09:22:00Z | F001 | North Valley Corn Block | 39.5312 | -93.8221 | 105.4 | 4096 | 3072 | 7.5 | JPEG | corn | 18 | 6.9 | 0.92 | ann_101 | 2024-03-11T10:13:00Z | 0.13 | https://agrodata.com/IMG0001_f001_corn.jpg |
| IMG0001 | healthy_crop | 0.89 | vegetative | 2024-03-10T09:22:00Z | F001 | North Valley Corn Block | 39.5312 | -93.8221 | 105.4 | 4096 | 3072 | 7.5 | JPEG | corn | 1 | 92.2 | 0.95 | expert_jane | 2024-03-11T10:14:00Z | 0.08 | https://agrodata.com/IMG0001_f001_corn.jpg |
| IMG0002 | disease | 0.62 | flowering | 2024-07-19T17:42:00Z | F002 | West Orchard Soybean | 41.0245 | -97.0521 | 99.2 | 2048 | 2048 | 9.1 | JPEG | soy | 13 | 4.7 | 0.87 | ann_055 | 2024-07-20T13:55:00Z | 0.11 | https://agrodata.com/IMG0002_f002_soy.jpg |
| IMG0002 | healthy_crop | 0.81 | flowering | 2024-07-19T17:42:00Z | F002 | West Orchard Soybean | 41.0245 | -97.0521 | 99.2 | 2048 | 2048 | 9.1 | JPEG | soy | 1 | 88.6 | 0.93 | expert_sam | 2024-07-20T14:04:00Z | 0.09 | https://agrodata.com/IMG0002_f002_soy.jpg |
| IMG0003 | healthy_crop | 0.91 | maturity | 2024-04-02T13:09:00Z | F003 | South Ridge Wheat | 36.8911 | -88.3155 | 142.1 | 5400 | 3220 | 5.2 | JPEG | wheat | 1 | 96.3 | 0.98 | expert_emma | 2024-04-03T07:10:00Z | 0.07 | https://agrodata.com/IMG0003_f003_wheat.jpg |
| IMG0003 | disease | 0.71 | maturity | 2024-04-02T13:09:00Z | F003 | South Ridge Wheat | 36.8911 | -88.3155 | 142.1 | 5400 | 3220 | 5.2 | JPEG | wheat | 7 | 2.5 | 0.91 | ann_201 | 2024-04-03T07:11:00Z | 0.12 | https://agrodata.com/IMG0003_f003_wheat.jpg |
| IMG0004 | weed | 0.61 | vegetative | 2024-05-17T15:44:00Z | F004 | Green Acres Alfalfa | 34.1933 | -102.2421 | 92.3 | 3000 | 1440 | 4.3 | TIFF | alfalfa | 23 | 8.8 | 0.79 | ai_bot_001 | 2024-05-18T14:00:00Z | 0.16 | https://agrodata.com/IMG0004_f004_alfalfa.tif |
| IMG0004 | healthy_crop | 0.75 | vegetative | 2024-05-17T15:44:00Z | F004 | Green Acres Alfalfa | 34.1933 | -102.2421 | 92.3 | 3000 | 1440 | 4.3 | TIFF | alfalfa | 1 | 84.1 | 0.86 | ai_bot_001 | 2024-05-18T14:01:00Z | 0.1 | https://agrodata.com/IMG0004_f004_alfalfa.tif |
| IMG0005 | water_stress | 0.31 | flowering | 2024-06-13T07:30:00Z | F005 | Riverside Canola Lot | 48.2532 | -123.3812 | 135.7 | 3600 | 3600 | 13.2 | PNG | canola | 22 | 14.3 | 0.58 | ai_vision_12 | 2024-06-13T19:33:00Z | 0.17 | https://agrodata.com/IMG0005_f005_canola.png |
| IMG0005 | healthy_crop | 0.63 | flowering | 2024-06-13T07:30:00Z | F005 | Riverside Canola Lot | 48.2532 | -123.3812 | 135.7 | 3600 | 3600 | 13.2 | PNG | canola | 1 | 76.9 | 0.78 | ai_vision_12 | 2024-06-13T19:34:00Z | 0.13 | https://agrodata.com/IMG0005_f005_canola.png |
| IMG0006 | disease | 0.52 | maturity | 2024-01-22T11:47:00Z | F006 | Central Plains Potato Test | 44.9121 | -106.2221 | 65.7 | 2048 | 2560 | 8.8 | JPEG | potato | 27 | 9.8 | 0.69 | ai_rater_008 | 2024-01-23T08:11:00Z | 0.14 | https://agrodata.com/IMG0006_f006_potato.jpg |
| IMG0006 | healthy_crop | 0.74 | maturity | 2024-01-22T11:47:00Z | F006 | Central Plains Potato Test | 44.9121 | -106.2221 | 65.7 | 2048 | 2560 | 8.8 | JPEG | potato | 1 | 85.6 | 0.83 | ann_083 | 2024-01-23T08:11:30Z | 0.07 | https://agrodata.com/IMG0006_f006_potato.jpg |
| IMG0007 | pest | 0.46 | vegetative | 2024-08-30T15:11:00Z | F007 | Emerald Lettuce Patch | 36.9851 | -120.3522 | 80.2 | 1280 | 960 | 12.2 | PNG | lettuce | 44 | 13.7 | 0.67 | ai_pestbot_2 | 2024-08-30T21:09:00Z | 0.18 | https://agrodata.com/IMG0007_f007_lettuce.png |
| IMG0007 | healthy_crop | 0.64 | vegetative | 2024-08-30T15:11:00Z | F007 | Emerald Lettuce Patch | 36.9851 | -120.3522 | 80.2 | 1280 | 960 | 12.2 | PNG | lettuce | 1 | 75.6 | 0.81 | expert_lee | 2024-08-30T21:10:00Z | 0.09 | https://agrodata.com/IMG0007_f007_lettuce.png |
| IMG0008 | disease | 0.53 | maturity | 2024-02-12T10:24:00Z | F008 | Field Eight Grape Rows | 46.3125 | -123.1012 | 96.3 | 2048 | 2048 | 7.9 | TIFF | grape | 16 | 8.5 | 0.73 | qc_bot_002 | 2024-02-13T14:00:00Z | 0.09 | https://agrodata.com/IMG0008_f008_grape.tif |
| IMG0008 | healthy_crop | 0.79 | maturity | 2024-02-12T10:24:00Z | F008 | Field Eight Grape Rows | 46.3125 | -123.1012 | 96.3 | 2048 | 2048 | 7.9 | TIFF | grape | 1 | 81.1 | 0.86 | expert_sam | 2024-02-13T14:01:00Z | 0.11 | https://agrodata.com/IMG0008_f008_grape.tif |
| IMG0009 | water_stress | 0.37 | flowering | 2024-11-18T12:03:00Z | F009 | Sunrise Rice Terraces | 21.9821 | 100.2123 | 112.1 | 6400 | 4800 | 3.4 | JPEG | rice | 36 | 15.5 | 0.61 | ai_bot_005 | 2024-11-19T14:10:00Z | 0.16 | https://agrodata.com/IMG0009_f009_rice.jpg |
| IMG0009 | healthy_crop | 0.69 | flowering | 2024-11-18T12:03:00Z | F009 | Sunrise Rice Terraces | 21.9821 | 100.2123 | 112.1 | 6400 | 4800 | 3.4 | JPEG | rice | 1 | 77.3 | 0.89 | expert_lee | 2024-11-19T14:12:00Z | 0.09 | https://agrodata.com/IMG0009_f009_rice.jpg |
| IMG0010 | other | 1 | seedling | 2024-08-03T08:33:00Z | F010 | Orchard South Test Crop | 31.9901 | -99.1102 | 0 | 16 | 16 | 0.2 | PNG | test_crop | 0 | 0 | 1 | devbot_42 | 2024-08-03T09:00:00Z | 0 | https://edgecase.agro/img/IMG0010_edge.png |
| IMG0011 | bare_soil | -1 | blank | 2024-12-21T19:22:00Z | F011 | QA Edge None Field | 0 | 180 | 975 | 1 | 1 | 0 | TIFF | none | 1 | 100 | 1 | soil_bot_01 | 2024-12-22T08:44:00Z | 0 | https://edgecase.agro/img/IMG0011_none.tif |
What the 200 rows show
from the 200-row sampleBare_
- 0.56median ndvi_
mean - 3image formats
- 13crop types
- 102.3median altitude_
meters - 3,600median image_
width_ pixels - 2,984median image_
height_ pixels
Median 0.56, from -1.0 to 1.0.
- string 9
- integer 3
- float 8
- datetime 2
Columns
22 columns in three groups| column | type | description | example |
|---|---|---|---|
| Text 9 columns | |||
image_id | string | Unique identifier for each drone image.unique | IMG0001 |
field_id | string | Unique identifier for the agricultural field where the image was taken. | F001 |
field_name | string | Human-readable name or label for the agricultural field.optional | North Valley Corn Block |
image_format | string | File format of the image (e.g., JPEG, PNG, TIFF).JPEG · PNG · TIFF | JPEG |
image_url | string | URL or file path to access the image file.unique | https://agrodata.com/IMG0… |
crop_type | string | Type of crop present in the imaged field (e.g., wheat, corn, soy). | corn |
growth_stage | string | Growth stage of the crop at the time of image capture (e.g., seedling, vegetative, flowering, maturity).4 stages · optional | vegetative |
annotated_feature_type | string | Type of annotated feature present in the image (e.g., weed, disease, pest, healthy_crop, water_stress, bare_soil).7 values | weed |
annotator_id | string | Identifier for the person or system that created the annotation.optional | ann_101 |
| Numbers 11 columns | |||
location_latitude | float | Latitude coordinate of the image center point.-90 to 90 | 39.5312 |
location_longitude | float | Longitude coordinate of the image center point.-180 to 180 | -93.8221 |
altitude_meters | float | Altitude in meters at which the drone captured the image.0 or more | 105.4 |
image_width_pixels | integer | Width of the image in pixels.1 or more | 4096 |
image_height_pixels | integer | Height of the image in pixels.1 or more | 3072 |
image_resolution_cm_per_pixel | float | Spatial resolution of the image in centimeters per pixel.0 or more | 7.5 |
annotated_feature_count | integer | Number of annotated features of the specified type in the image.0 or more | 18 |
annotated_area_percentage | float | Percentage of the image area covered by the annotated feature type (0-100).0 to 100 · optional | 6.9 |
annotation_quality_score | float | Quality score of the annotation (0-1, where 1 is highest confidence).0 to 1 · optional | 0.92 |
ndvi_mean | float | Mean Normalized Difference Vegetation Index (NDVI) value for the image.-1 to 1 · optional | 0.67 |
ndvi_stddev | float | Standard deviation of NDVI values in the image.0 or more · optional | 0.13 |
| Dates and times 2 columns | |||
capture_datetime | datetime | Date and time when the image was captured. | 2024-03-10T09:22:00Z |
annotation_datetime | datetime | Date and time when the annotation was created.optional | 2024-03-11T10:13:00Z |
Use it for
An agriculture dashboard
Ndvi_
mean by annotated_ feature_ type and a breakdown of growth_ stage. Excel, Power BI or Tableau. Why do the 27 bare_
soil rows have a mean ndvi_ mean of -0.87? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Images200IMG00010.67weedIMG00010.89healthy_…IMG00020.62disease
A software demo
Believable images with capture_
datetime, field_ id and field_ name to fill a screen in front of a buyer.
This dataset200 rows22 columns
Yours1,000 rows22 columnslocation_latitude: UK only
blueprint · precision-farming-drone-imagery
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 22 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.
Rules it was built with
- Each image annotated with crop type and health score
- Features: weed patches, pest zones, irrigation
- Images vary by time of day and weather
- Resolution and geotag provided
- Fields segmented by management zone
Open the blueprint in Data Factory
1 credit per row. Preview 20 rows free. Buy rows for the full run.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- precision-farming-drone-imagery