Release Notes

The UP42 offering is expanding fast. The ability to offer a wide range of data from multiple providers is key to our customers seeing value from UP42. Indeed, this previously included a respectable 15 satellites, along with a great selection of aerial imagery, weather data, AIS data, and processed data sets.

However, the UP42 offering has just expanded from 15 to 55 satellites in just over a month. This enables us to offer you higher revisit at very high-resolution, a more comprehensive range of data types, and more flexibility on price, AOI, and minimum corridor size.

UP42 Partners with HEAD Aerospace

HEAD Aerospace's constellations bring several capabilities that augment UP42's expanding portfolio of high-value data providers. In addition, the breadth of HEAD Aerospace's satellite data offering opens up a host of new use cases for UP42 customers while improving our ability to deliver high-revisit tasking requests for any AOI.

First and foremost, the HEAD Aerospace constellation adds 27 satellites that capture imagery at a submeter spatial resolution. This furthers UP42’s ability to reliably deliver high-resolution imagery of anywhere on Earth in partnership with HEAD Aerospace and our other data providers.

The EarthScanner constellation offers another incredible capability. With swaths up to 136km, imagery of very large areas can be captured in a single pass. This is perfect for monitoring entire countries or large cities up to 40,000km² without mosaicking.

Monitoring use cases are only as effective as the revisit capabilities from the underlying data providers. Combining constellations, HEAD Aerospace can capture imagery of the same AOI multiple times a day and night, unlocking surveillance, monitoring, and change detection use cases. Additionally, capturing data at night opens tons of new monitoring and surveillance use capabilities. HEAD Aerospace brings to UP42 the ability to capture both imagery and video with nine on-orbit satellites that capture nighttime in true color.

But the capabilities are certainly not limited to surveillance and monitoring use cases. For example, the HyperScan constellation allows for data acquisition with 25 spectral bands spanning the visible, near-infrared, and mid-infrared portions of the spectrum. This is ideal for enhanced agricultural insights, such as identifying vegetation species or crop health moving far beyond elementary analysis, such as NDVI.

The HEAD Aerospace offering differentiates itself further by including satellites equipped with altimeters and able to acquire tri-stereo imagery. These capabilities translate to vertical accuracies of up to 2 meters, enabling industry-leading maps and elevation models.

UP42 Partners with SIIS

Further supplementing our rapidly-growing virtual constellation is our partnership with SIIS, making tasking and archive data acquisition from very high-resolution optical satellites, KOMPSAT 3 and 3A, and high-resolution SAR satellite KOMPSAT 5, available to UP42 users.

These two new partnerships take the total number of satellites that UP42 offers data from to over 50, making UP42 even more competitive in terms of revisit, resolution, and a whole host of unique and innovative capabilities. Check out our complete data offering, including optical, radar, elevation models, and hyperspectral data, by clicking the link below!

Order data

We've integrated one of the leading map providers, HERE Maps, into our catalog search and job configuration screen. This integration brings a much nicer search experience, as well as a more feature-rich and aesthetically pleasing basemap!

The integration with HERE Maps brings much more advanced geocoding, which among other enhancements, provides better performance for non-Latin words. We can now also support searching based on coordinate formats, such as 45.314483, 30.714823 or 45°18'52.1" N 30°42'53.4 "E. You can search based on coordinates, and the platform will simply go ahead and select a small AOI around that point. You can then manipulate that AOI to fit your requirements. Of course, users can still upload their AOI in GeoJSON format and have their AOI automatically selected!

Search for data

Back in December, we launched our price estimation - one of our most hotly-requested features. Backed by data on the thousands of jobs that UP42 customers have run previously, our data science team built a machine-learning algorithm and a basic rule set algorithm that provides an estimated range of data, processing, and infrastructure costs.

This estimate is available both within the console or through the Python SDK, leveraging the command, workflow.estimate_job(input_parameters).

This estimate, along with the prices given during the data ordering process within the catalog search, is now used to ensure that you don't send your account spiraling into minus, even when you're running multiple jobs or ordering multiple data sets concurrently. As a result, you and your team can concentrate on analysis or data acquisition, running jobs, and ordering data with confidence, knowing that you won't end up with an account in minus.

Run a job

This block from our new partner and leader in forestry inventory management solutions, Tesera, generates GeoJSON polygons that follow major land surface features, including water bodies, rivers, vegetation cover, and types. It uses Sentinel-2 multispectral imagery at 10-meter resolution as an input, generating two sets of land line polygon segments that average 1 hectare and 10 hectares, respectively.

Specifically, this processing block uses the Sentinel-2 L2A Analytic (GeoTIFF) block from UP42 that provides bottom-of-atmosphere reflectance values that are analysis-ready. This increases the reliability and reduces errors in the results caused by atmospheric interference and other non-feature-related noise that can be present in uncorrected satellite imagery.

The polygon output can be used for multiple use cases. Firstly, analysis can delineate vegetation changes and disturbances, like fires or cutblocks, at much a larger scale faster and lower than airborne remote sensing. The land lines can also be used as a pre-processing step for classification use cases, such as land cover classification or forestry mapping.

Use the block

We're excited to launch this state-of-the-art field boundary detection algorithm, provided by Airbus and Agrimetrics. The FieldFinder processing block runs on SPOT imagery and accurately delineates agricultural fields, outputting a shapefile.

FieldFinder applied to SPOT imagery in the UK

The block has been rigorously trained and tested across many European countries and the entire state of Iowa, US, enabling consistent wide area coverage. Boasting a mean F1 value of 0.85 in the regions shown below, FieldFinder is a reliable model for detecting even small fields.

Continent	Country or Region
Europe	Austria Belgium Czech Republic Denmark France Germany Ireland Luxembourg United Kingdom
North America	Iowa

The model accuracy and use of SPOT imagery rather than Sentinel-2 differentiate the algorithm from other automated boundary detection solutions and ensure it meets the cartographic quality demands for users' from crop growers to developers building agricultural solutions.

If the FieldFinder blocks don't currently cover your required region, get in touch, and we'd be happy to arrange model training to fulfill your requirements.

FieldFinder Europe | FieldFinder Iowa

Our partner and a leader in vegetation management analytics, Spacept, has released a new and improved version of all three of their algorithms - Tree Detection and Height From Shadow, Tree Detection, and Shadow Detection.

The algorithm benefited from significant accuracy improvements in the Tree Detection and Shadow Detection algorithms, where the Shadow Detection block has been benchmarked against human annotators on 10,000+ Pléiades images. The Shadow Detection model showed a precision of 91%, recall of 94.5%, and an F1 score of 93%.

These developments make Spacept's capabilities a compelling replacement or complementary technology for existing vegetation management processes for railway operators and utility providers. You can find out more about how satellite-based vegetation management solutions compare to existing LiDAR and new UAV technologies in our recent blog post.

Check out the blocks

Several processing blocks on UP42 require the input Sentinel-2 image to be in 8-bit rather than 16-bit format. This new block developed by the UP42 data science team enables you to use the new Sentinel-2 L2A Analytic (GeoTIFF), and Sentinel-2 L2A (SAFE) blocks with a whole host of algorithms as part of an UP42 workflow.

In order to run 16-Bit to 8-Bit Conversion block with these data blocks, try either of the following workflows:

• Sentinel-2 L2A Analytic (GeoTIFF) -> Pan-sharpening -> 16-to-8 Bit Conversion
• Sentinel-2 L2A (SAFE) -> Super-resolution Sentinel-2 -> 16-to-8 Bit Conversion

Use the block

Real-time order statuses have now been added to the "Orders" tab and continued visibility into the type of order - either Archived Storage or Live.

You can get even more information about assets in your user storage through the UP42 API, with geometry, productType, area, and sceneId added as variables.

View your user storage

We've provided increased transparency in the delivery timeframe for data sources. The majority of the data available on the UP42 marketplace is returned with low latency, with data delivered within 10 minutes.

However, to increase the choice of images that you can access, we activated access to OneAtlas's Archived Storage, roughly doubling the number of high-resolution satellite images available to you. This data is delivered within 24 hours, a timeframe now clearly indicated within the search results, allowing you to prioritize latency if and when required.

You can now search more efficiently for the satellite imagery that suits your needs with our new resolution filters. Pick from high resolution (<2m), medium resolution (2m - 10m), and low resolutions (>300m) to return search results of images containing only the data you require.

Search for data

We have 50 different data sets on the UP42 marketplace that can be seamlessly accessed through the console or API. But did you know that you can also easily task a satellite or order custom data with us?

We're excited to share our new Order Data page, outlining our extensive and expanding tasking and custom data ordering options. On this page, you will find a selection of industry-leading optical, radar, and aerial data providers.

Our team of geospatial data experts are here to help you every step of the way. They’ll be happy to advise you on the best constellations for your use case and in no time at all, they’ll be ensuring the safe delivery of your data sets to the UP42 platform and available via API to integrate into your own data ecosystem.

Task a satellite or order custom data

We aim to provide a seamless out of the box experience with the UP42 platform, but with such a wide variety of capabilities both within the core platform and offered by our amazing partners, some pointers are sometimes needed.

Launching our new Documentation Hub - a central place to find information on how to use the UP42 platform, our data and processing capabilities, and the Python SDK and API. The Documentation Hub is a complete overhaul of our documentation, carried out with user experience front and center.

This clean, fresh uncluttered approach will allow you to quickly find what you’re looking for whether you’re a product manager trying to search and order satellite imagery from the archive or a data scientist building and selling algorithms through the UP42 marketplace.

Keep your eyes peeled in the coming days for a blog post from John Ngo, our Senior UX Designer, who will discuss how the Documentation Hub was developed with you, the user, in mind. And in the meantime, head over to the Documentation Hub and let us know what you think!

Check out the Documentation Hub

Last month, we announced our new Sentinel-2 block that provides access to the latest 12-bit Sentinel 2 imagery, ideal for processing and analytics purposes. This block comes with 12 spectral bands from visible and NIR to short-wave IR, enabling a wide range of use cases.

However, most analytics and processing capabilities require all bands to be processed at the same resolution. As such, this block is now compatible with our Pan-Sharpening block. This enables you to upsample all 13 bands to a 10m resolution and consolidate them into a single GeoTIFF file that can be easily processed and connected to a range of analytics.

Sentinel-22 L2A Analytic | Pan-Sharpening

We've relaxed our limits on the maximum AOI from 1000km² to 180,000km² and the number of jobs you can run concurrently from 10 to 1000. This allows you to parallelize your analysis more efficiently and cover more land than ever before.

How To Change Your Project Settings

1. Open a project in UP42.

2. Click the settings button in the subnavigation. 3. Scroll down to the Threshold Limits section.

4. Adjust the sliders as required.

More details in the documentation

You can now search and discover data to purchase or process in one unified set of search results. We’ve added tags to the catalog search results to differentiate between data that can be purchased or processed.

Sentinel-1, 2, 3, and 5 imagery that can only be processed is marked only with the tag “processing”, while Pléiades and SPOT imagery in archived cold storage is tagged with “purchase”. The latter is ordered and delivered to your user storage within 24 hours. Pléiades and SPOT imagery that is warm is tagged with both “processing” and “purchase” and is available almost immediately.

You can also use the “Usage Type” search filter to narrow your results to either data available to process or purchase. Finally, in the “Cart”, you can switch between “Purchase” and “Processing” tabs, depending on whether you want to order data for download or configure a job to process your selected data.

We are excited to launch WorldDEM™ from Airbus. Hailed as "The New Standard for Global Elevation Models", WorldDEM™ brings UP42 users a Digital Surface Model (DSM) with pole-to-pole coverage, high accuracy, and consistency.

WorldDEM™ is based on radar satellite data acquired during the TanDEM-X Mission, which had the primary goal of generating a high-quality DSM of the entirety of the Earth's surface, based on SAR interferometry.

The goal of the mission was clearly achieved with all 148.5 million km² of the Earth's surface being captured in the space of four and half years, driving consistency in the generated DSM and global coverage. The elevation models' accuracy is evident, with the Absolute Vertical Accuracy and Absolute Horizontal Accuracy being <4m and <6m, respectively.

For more information about WorldDEM™ and its use cases, check out the following video:

Access the WorldDEM™ block

Viewshed from Intermap provides the line-of-sight from any point, height, radius, and azimuth on an elevation model. The model outputs a GeoTIFF, with the pixels visible from the point of origin are in green, while the pixels not visible from the point of origin are in red (see below).

Viewshed is primarily used in the telecommunications industry to evaluate the reach of signals from telecom transmitters. To ensure signal strength is uninterrupted, telecommunications providers must place communicating transmitters within each others' line of sight, avoiding buildings, trees, and terrain. As such, viewshed is the perfect tool to analyze and optimize signal strength.

Use this block

This new processing block from Terra Cover enables you to create a robust surface water extent map using a deep neural network. This allows you to visualize the presence and area of a lake or reservoir for your area of interest. The approach of generating surface extent maps are significantly less impacted by atmospheric disturbances compared to traditional index-based thresholding methods, ensuring the accuracy of the reservoir and lake surface is higher.

The model first checks for the presence of a lake or reservoir using Terra Cover’s time series data set, also available on UP42. The pre-check ensures that you don’t spend money or time on computationally-intensive deep learning models when there is no presence of water within your area of interest. The block also automatically utilizes the s2cloudless cloud mask to minimize the disruption of clouds in your analysis.

Use this block

The latest version of the SDK reflects the changes previously announced for the UP42 console. Firstly, you can now order data without running a workflow, whether that data is available directly or needs to be ordered from the OneAtlas archived storage. Orders can now be created using the Catalog.place_order command.

Secondly, you can now reuse your purchased OneAtlas imagery through the Python SDK by specifying your asset ID in the Workflow.construct_paramaters command. This enables you to access and process data that is currently in your user storage.

Running geospatial analytics at scale requires powerful computing infrastructure. Indeed, as most geospatial developers are painfully aware, complex algorithms can take hours or even days to train or analyze large areas of interest.

With an expanding range of increasingly complex machine-learning algorithms available on the UP42 marketplace, it is incumbent upon us as a company to ensure we continue to provide an efficient infrastructure for such analysis.

As such, we now provide block builders with new options for larger CPU machines with 8 or 16 cores and 40 or 80 GB RAM and a GPU machine type - GPU P100 - to increase performance.

These new machine types will reduce job runtime significantly, ensuring you get the insights you need promptly. We've also significantly reduced the infrastructure costs associated with all our machine types making using UP42 for complex analysis more affordable.

We've radically expanded the amount of SPOT and Pléiades available through UP42 by enabling the collection of scenes in the OneAtlas Archived Storage.

This brings much more consistency to our OneAtlas coverage and provides you with more options for many AOIs. For example, you can now choose between 2.7 times more scenes in the US than were previously available.

Flood and Water Finder from the UP42 team generate a binary water or flood mask from Pléiades or SPOT imagery. This enables you to run analysis on SPOT or Pléiades imagery omitting water bodies or flooded areas from your analysis.

Alternatively, you can convert your output into a vector file to use the water body or flooded area as an area-of-interest for any water-related analysis.

The Water Finder generates a GeoTIFF output highlighting the presence of water on a single SPOT or Pléiades image. Alternatively, the Flood Finder generates a similar output but looking at the area of water that is not present in an initial SPOT or Pléiades image but is present in a subsequent image.

Use the Water Finder | Use the Flood Finder

Detecting oil on the ocean surface and differentiating between natural oil seepage and oil slicks is essential for oil exploration companies.

Developed over 20 years, Airbus has collated a global oil seep database covering 76 million sq km. It is updated yearly with new areas and updates on existing areas. This database acts as an invaluable cost-effective risk ranking tool for the OGME industry.

Use this block

Basemaps act as a layer upon which you can overlay geospatial information and visualize information within its broader context. This essential component of many geospatial analyses is now available through UP42 with sharp, consistent, and fresh imagery from OneAtlas.

This block provides 1.5 m SPOT imagery globally and 0.5 m Pléiades imagery for major urban areas. The data can be downloaded and streamed from UP42 in GeoTIFF format.

Download block | Streaming block

You may recall that we implemented our user storage functionality last month, which enabled the seamless delivery of tasked imagery. We're building on that functionality and are happy to announce that any SPOT and Pléiades imagery you purchase through our download blocks will now be automatically accessible through your user storage.

Within the user storage, you'll find the data's asset_id that you can use when configuring a job to reuse the data as many times as you'd like.