Atlas

Indigo’s eyes on agricultural trends, worldwide

Crop reports. Satellite imagery. Expert commentary.

Get notified of new reports

Get updates

Indigo Atlas delivers a living map of the world’s food system. Capable of characterizing localized soil conditions, drawing field boundaries to meter-level accuracy, and discerning subtle differences in crop health across a region, Atlas’s proprietary algorithms generate a range of high-resolution, real-time, and actionable outputs. Atlas information enables growers to make more informed planting, harvest, and marketing decisions. It also grants buyers and consumers a greater degree of control and choice over their supply chain.

Featured Report

October 2021 Market Report

The 2021 harvest is underway.

Access the Report

September 2021 Market Report

Aerial Views

August 2021 Market Report

View All Reports

July 2021 Market Report

Zooming in on our reports

Every month, the directors and data scientists behind Indigo's ag intelligence offer a closer look at our reports. See how we generate our insights, what they mean for the market, and how growers are reacting across the world.

Receive county-level visibility into freeze impacts

Atlas’ models, powered by the application of machine learning to historical, weather, and remote sensing data, track the movement and impact of different weather patterns.

A realtime plant health index optimized for agriculture

For decades, vegetation indices have seen many use cases across life sciences, but none has been tailored to the unique needs of agriculture. To track the dynamic variables affecting crop health, Indigo has created the Crop Health Index (CHI). We follow multiple crops across several geographies to better understand our global food system — and help you make better decisions in realtime.

Hover for realtime statistics

How we generate insights

1. Data Cleaning

Our systems collect raw imagery and weather data, clean it and normalize it into a single consistent map

2. Crop Masking

We then create masks to ensure that we are looking at the right parts of the map for each crop

3. Cleaning Metrics

Our software then summarizes metrics by geography to create historical data streams

4. Creating Models

We introduce these data streams as variables to our machine learning models, which take the best of each metric to inform predictions

Atlas Gallery

A global collection of agriculture from space

New Mexico, U.S.

Color is absent in Atlas imagery where little to nothing grows – in these places, there is not enough vegetation to reflect or absorb any wavelengths of light. In the desert, sandy red expanses show up as black voids. What’s left is a palette of fully formed circles, and sometimes chunks of the pie – central pivot irrigators that are sustaining different crops, to varying degrees of success.

Arkansas, U.S.

With field boundaries drawn, Atlas imagery looks like a blend between abstract art and stained glass. The orange on the left side of the image could be attributed to specific land management practices used there, such as double cropping – a process that seeks to harness the full potential of the calendar by planting more than one crop type, either at the same time or after a first harvest. A majority of these fields are terraces for rice farming, distinct in their oblong shape.

Quebec, Canada

This is the farmland outside of Montreal: staggered, sharp, thin strips, built next to rivers and (sometimes) roadways. Known as “ribbon farming,” the practice of dividing the land into narrow areas originated in Europe, as a way to bring as many growers as possible in one town close to water resources. Dividing the land like this, too, allows for easy surveying and boundary establishment – a practice as relevant when the French migrated out across Canada to Montreal as it is today. We have taught Atlas to draw boundaries on its own, instantly, a practice that would take a human being several hours for each field.

Wisconsin, U.S.

If you were to drive down any of the roads in this image – those black lines running like seams across a patchwork of neat, square fields – you would struggle to determine degrees of difference. Don’t chalk this up to moving at 60 mph, but to your ability to only perceive certain bands of light. Satellites can move at over 17,000 mph. Their ability to capture many light bands outside the spectrum visible to humans brings the psychedelic hue to what is likely only degrees of yellow, green, and brown.

Arkansas, U.S.

You can pull multiple data layers together in one image out of Atlas. What appears as one frame to the left, for example, actually represents farmland around the wending Arkansas River over the course of a year. Need to position yourself in time? The color key here: red pigments in the image represents developments of the crop in the spring; green, in the summer; and blue, for the fall. What crops are on the field themselves requires further analysis, but a safe bet is soybeans or rice – Arkansas ranks tenth and first in the country for those row crops.

New Jersey, U.S.

Central pivots galore. New Jersey is often known for its greenhouse and nursery products sector, but it’s also a major producer of asparagus, bell peppers, eggplant, endive, lettuce, and spinach.

A living map of the world's food supply

The Indigo Dispatch app displays grain loads that growers and shippers have communicated to Indigo.

As part of its living map of the world's food system, Indigo forecasts crop yield and production around the globe with a satellite imaging and machine learning platform called Atlas. Atlas’ yield prediction capabilities have outperformed the USDA's in recent years. With the application of machine learning and artificial intelligence to satellite imagery, Indigo Atlas generates global crop health and performance daily. Indigo stakeholders, including growers and partners, leverage this data for myriad objectives throughout the season.

If you take a look at the image shown here of the Mississippi River, you can see what is called an Enhanced Vegetation Index (EVI) where the image is comprised of multiple data layers stacked over time. The input images were acquired throughout the 2018 growing season by the European Space Agency 's twin Sentinel -2 satellites, which image the earth every four days. These multi-temporal image composites are the raw ingredients used in Indigo 's field boundary identification and crop type mapping efforts.

For Farmers

For Buyers

Future of Ag

Resources

Marketplace

Transport

Carbon

About

Careers

Para Productores

Para Futuro

Indigo Biológicos

Sobre

For Growers

Biologicals

Carbon

European Countries

About

Für Landwirt*innen

Biologicals

Carbon Programm

Über uns

Biológiai készítmények

Rólunk

Karrier

біопрепарати

Про нас

кар'єра

Biyolojik maddeler

Hakkında

Kariyer