Useful Tip:
Please refer to the Parameters page of the documentation for detailed information on all parameters!
AutoMap runs on the AWS cloud infrastructure and is built with python and dask or loky backends. Classifications use extreme gradient boosting.
AutoMap is designed to be simple to handle. Under the hood we take care of efficient workflows that are scientifically correct and efficiently smart. In general, the processes can be boiled down to these basic steps:
The virtual machine processing the data needs a storage medium capable of handling a very high throughput (Mbits). Data needs to be secured and all ressources must be structured and tagged accordingly. A monitoring system helps to follow the workflow.
We use freely available satellite data that just needs to be downloaded, but depending on the user input parameters, the number of files could go in the thousands and the storage needs in the terabytes.
Every single satellite image has a default cloud mask attached to it. That mask is created by NASA or ESA in ways to satisfy the most basic needs of all their users. Such a mask is not either-or but contains triggered bits for each pixel, where every bit contains different information. This enables the programmatic distinction of cirrus clouds, cloud shadows, snow, etc.
A picture taken with a smartphone contains three layers of information
for the colors red, green and blue (RGB image).
The combination of those three image bands provides the end product.
At this point in the workflow a single satellite scene consists of separate
image files per (color) band, the cloud mask and further metadata that helps
to get rid of different distortions.
For convenience, all bands and data is packed in one single multiband image.
NDVI and NDWI, two important indices to identify vegetation and water, are
appended by default.
Every spot in the area of interest was recoreded between zero and n times over the defined time range. This step merges the data over the time axis, considering clouds, shadows and intra-temporal variances, in order to produce a single representation of the area for the given time.
Training data is collected from the user-provided locations and the temporally aggregated satellite images. The hyperparameters of the classifiers are tuned in order to enhance accuracy. The feature space is first enlarged by calculating neighborhood relationships and later distilled to the major principal components.
The results for different satellites will not be mixed but stored separately.
Metadata holds detailed information concerning considered images,
while every image holds further descriptions concerning the stored bands.
Please refer to the FAQs of the
documentation for detailed information on the output!
Once the operation is finished, users will be notified per mail, inviting them to download the compressed results from Amazon AWS S3. The monitoring system will be updated for further references. Every run can be tracked via a weblink to a dashboard.
AutoMap is designed to work with the most common freely available missions from NASA and ESA.
Satellite Name | Product | Resolution (Spatial) | Bands (Spectral) |
---|---|---|---|
Landsat 5 | Top-of-Atmosphere (TOA) | 30x30 m | 1, 2, 3, 4, 5, 7 |
Landsat 7 | Top-of-Atmosphere (TOA) | 30x30 m | 1, 2, 3, 4, 5, 7 |
Landsat 8 | Top-of-Atmosphere (TOA) | 30x30 m | 2, 3, 4, 5, 6, 7 |
Sentinel 2 | Top-of-Atmosphere (TOA) | 10x10 m | 2, 3, 4, 8, 11, 12 |
The easiest way to generate a new call for action is the click-and-go user-interface that is made available in the Menu after login. Pick a mode for a set of satellites, specify a time interval, select one of your uploaded vector files as boundary for your area of interest and start a run. The description field is here to make it easier to identify your runs later on. After a successful launch, the monitoring system will keep you updated on the current state of the process and entails a link to a designated dashboard. When finished, an email will be sent to the specified email adress(es), containing final informations and a download link that remains valid for 48 hours.
Please refer to the Parameters page of the documentation for detailed information on all parameters!
The Code Launcher has a dedicated documentation page. It provides programmatic access to AutoMap with a simple Python interface within the website. Write your own script to iterate over different time ranges, areas and satellites, tag the runs with individual descriptions and easily process in bulk. Note: The code launcher is reserved for premium users.
The AutoMap API has a dedicated documentation page. The API enables you and your team to automate the launch of AutoMap runs. Note: The API access is reserved for premium users.
Upload and delete your boundary and sample files here. All files relevant for a processing job need to be uploaded beforehand.
Keep track of your orders. We maintain a database of submitted jobs, their current status, description, costs and other important information.