Vultus is utilizing state-of-the-art algorithms and API’s to deliver insightful information to the growers around the globe.
|Landsat-8||Sentinel L1C||Sentinel L2A||Planet (Coming soon)|
|Description||NASA satellite , high spatial and temporal resolution with good spectral bands||European union satellite, very high spatial, spectral and temporal resolution||Same as sentinel L1C, but with additional calibration||Commercial satellites, very high spectral, spatial and temporal resolution , a bit costlier|
|Revisit rate||16 days||3-5 days||3-5 days||Up to daily|
|Archive||Since 2013||Since 2016||Since 2019||Since 2017|
Plant Health Indices
Normalized difference vegetation index NDVI is one of the most used vegetation indices in crop monitoring. NDVI is robust and straightforward to calculate, is in the following equation:
NDVI = (NIR - Red) / (NIR + Red)
Where NIR is the near-infrared part of the spectrum and Red is the red band.
The purpose of using Modified Soil Adjusted Vegetation Index (MSAVI2) is to minimize the background soil effect on the vegetation index. MSAVI2 is calculated as follows:
MSAVI2 = (NIR + 1) − (1/2)[(2NIR + 1)2 − 8(NIR − Red)]½
The modular agile structure of Vultus pipeline allows also for adding more vegetation indices and specialized algorithms based on the needs of our partners and users.
The above image shows two planet health indices visualized as heatmaps with color ranging from green (healthy plants) to red (bare soil or unhealthy plants)
Is the true color composite for the red, green, and blue spectral bands.
Our one pagers PDF for Plant Health can be found in the following link
Synthetic Aperture Radar (SAR) - NDVIS
When it is cloudy, optical remote sensing satellites (e.g., Sentinel-2) cannot provide data for farmer's fields. Optical satellite sensors cannot penetrate clouds. Hence, when weather conditions are cloudy for a long time, farmers lose important insights into their crop performance at critical junctures. These clouds are often a problem for farmers using satellite technology in regions of the world that have a monsoon season or in Northern European coastal areas during the summer months. Cloud cover has been a major stumbling block that limits the use of satellite technology in agriculture across the globe.
Vultus uses the radar antenna's motion (Synthetic Aperture Radar technique) from Sentinel-1 microwave bands over a target region to penetrate the clouds and provide finer spatial resolution than conventional beam-scanning radars. This includes extremely complex signal processing, filtering, and analysis to derive useful results. Vultus captures images every 1-2 days in Northern Europe, and every 6 days in other geolocations.
By using SAR, Vultus eliminates the cloud cover issue in satellite applications for agriculture. This ensures that every farmer can be guaranteed data on their crops, independent of the weather.
Our one pagers PDF for SAR can be found in the following link
Management zones are the areas within the field that demonstrate homogeneous performance (based on the VIs values). A classification algorithm is used to divide the field into a number of MZs that remain stable over time. There are five management zones with predefined thresholds. Zones range from bare soil to plant with low performance (low yield potential) to average performance and high performance and in between classes.
The above image demonstrates Zoning algorithm output. In general, the plant health shows an increasing order from zone 1 to zone 5
Our one pagers PDF for Zoning can be found in the following link
Crop Specific Nitrogen Recommendation
Crop specific Nitrogen recommendations use various Vultus algorithms and provides the prescription based on the crop types such as Soybeans, Sugarcane, Corn, Rapeseed, and Potato. We use different vultus algorithm for other crops.
The above image demonstrates Crop Specific Nitrogen Recommendation algorithm output. An ascending trend for nitrogen recommendation should be given in line with cluster 1,2,3,5,4 with our suggestion.
Our one pagers PDF for nitrogen recommendation can be found in the following link
NDWI (water stress)
The Normalized Difference Water Index (NDWI) is a remote sensing derived index estimating the leaf water content at canopy level.
The above images show the water stress in the farm in different times. Yellow color means low value of the NDWI, Blue color means high value of the NDVI.
Our one pagers PDF for water stress can be found in the following link
Link: WATER STRESS
Soil Organic Carbon
Patent pending Soil Organic Carbon Maps clearly show farmers the amount of SOC present in their fields, based on a 0-10 cm soil depth in measures of g/kg at a 10 m resolution. No field surveys, expensive lab tests or lengthy waits required – growers get year-round instant results. Instead of a snapshot in time, growers can measure changes in soil health over years (with up to 4 years of historical data), gaining deeper insight into fields and helping to create the best possible farming strategy.
Vultus creates SOC maps using satellite remote sensing data, patented techniques and data from thousands of in situ soil samples. Satellite images are available every 2-3 days. Our service processes images, calculates the soil spectral indices, optimizes reflectance matches, and combines our dataset using patent pending AI algorithms to continually improve our SOC maps.
Our one pagers PDF for SOC can be found in the following link
Productivity zones is a unique product from Vultus that shows which areas in a field are either less productive or more productive over the long-term (1-8 years). The identification of productivity zones is based on vegetation as the primary source of data. Productivity zone maps can be considered by farmers as one of several valuable inputs, such as pH maps, cultivation plans, or yield information from previous seasons. Likewise, productivity zones can increase economic prosperity and reduce the environmental burden by employing site-specific crop management practices which implement advanced geospatial technologies that respect soil heterogeneity.
Nitrogen recommendation maps are delivered in two standard formats, ISO XML according to the industry standard and shape-file format.
Time Series is a set of data points or observations taken at specified times usually at equal intervals (e.g hourly, daily, weekly, quarterly, yearly, etc). Time series provides a digital archive of measurements. In the case of agriculture applications, time series is used to analyze plants performance for the season. Satellite-based plants health indices like Normalized Difference Vegetation Index (NDVI) presents a reach source for time series observation. Linking NDVI with other plants performance limiting factors such as irrigation, fertilization, and local weather could help to understand the effect of these factors on plants and their relationship to the seasonal changes.
The above images show the vegetation index of a field expressed as a heat map. Each plot outline the plant performance in different developing stage.
To ensure a high degree of quality we are applying two-steps mechanism to remove satellite images contain cloud cover. The first step is to remove any scene/tile with cloud cover larger than 20%. The information about the cloud cover percentage for this step is provided by the data providers (ESA and NASA/USGS). The second step is to apply a pixel-based classification algorithm to classify each pixel in the scene/tile into a cloud or no cloud.
The process status API will check all server status of data being processing. User can check the status for there data on real time processing. If the data finish processing, them the process status will change from False to True. The cloud tag will indicate the polygon whether covered by cloud. Without cloud covered status will be false. And the polygon have cloud in side will be True. This days data will be skipped in server and process status will update to True. That means user can not download the data, when “processstatus” and “cloud” both True.