UP-TO-DATE INFORMATION
You can trust that all the information on forests is up to date. Issues can be addressed quickly and for example forest carbon storages can be reported reliably.
Forest analytics by Bitcomp are based on satellite monitoring. The information you receive on the current state, risks and changes of forests is accurate and up to date. Our forest analytics utilize self-learning artificial intelligence. This enables the continuous improvement of the results based on user feedback and field observations.
How our analyses work
Data is only reliable when it is up to date. This is especially true when it comes to forest and nature values. Key to being current lays in satellite data. Our machine learning based forest analytics uses optical satellite imagery (from Sentinel 2) in addition to other data sources to calculate the variables describing forest state at the moment. Other data sources include synthetic-aperture radar (SAR), other remote sensing data sources (LiDAR, aerial photography, commercial satellite data), geospatial big data sources, field observations, open maps (National Land Survey of Finland, Inspire), weather data, and customer own data sources.
Synthetic-aperture radars (SAR) and commercial satellites
Other remote sensing datasets (drone photography, aerial photography, LiDAR)
Optical satellites (Sentinel 2, Landset)
Weather data
Customer’s own datasets
Other big data sources
Field observations collected by users
Information on forest features, nature values, trees and soil
Open maps (NLS, Inspire)
Results as map layers (WMS/WFS) or in a real-time calculation service
You can trust that all the information on forests is up to date. Issues can be addressed quickly and for example forest carbon storages can be reported reliably.
Field visits and work can be focused on the areas where they are most needed. This way costs can be cut and possible additional damages prevented.
Ensure that your forest stays in good condition and continues to grow in value with forest management suggestions by artificial intelligence. AI recognizes management needs and their optimal timing. Automation also enables fluent communication between a forest professional and a forest owner.
AI based forest analyses utilize high-quality and up-to-date satellite data. The machine learning algorithms are run weekly. They can determine for example the current state and development possibilities by sites and find damaged areas quickly and accurately.
The results are served as illustrative theme maps (WMS/WFS) that are updated weekly. In this result format, planning, monitoring and other development work becomes much more efficient. Both the change types and the magnitude of change can be seen from the maps.
When analytics recognize sites that require special attention or management, the system automatically sends out an announcement. This allows professionals to focus work and inspections on sites where they are needed the most. Forest owners can quickly contact a forest professional to request management. This is especially helpful, if their forest is located far away from where they are living.
User can add their own notes and observations on sites using the mobile application, thus enriching forest analytics. Analysis becomes more intelligent the more data it gets to process.
Get to know the EnviNavigator project