Spatial Data Analysis






Spatial Analytics – the Heart of Our Services



Bitcomp offers versatile spatial analysis services for enhancing business in forestry, agriculture and environmental sectors. We utilize newest machine learning algorithms and cloud solutions, which enable quick combining and refining of large spatial data sets into custom-tailored analysis products.

Recently we have been focusing on utilizing of Sentinel 1 radar (SAR) data and drone data for forest inventory and change detection, and monitoring of vegetation in agricultural fields. In addition, we use optic satellite data (Sentinel 2, Landsat) and other remote sensing data (LiDAR, aerial images) in combination with other spatial ‘big data’ sources, such as spatial notes created by mobile users, open map data and weather data.

The analysis products are available as map layers (WMS/WFS) or can be accessed via real-time analysis service, with which the summary statistics can be calculated dynamically for user-given area.


Our analysis products are fully customizable to customers’ needs and they can be included both in Bitcomp’s own or 3rd party web or mobile applications via data interfaces.

LET'S PLAN

——————– Recent Projects ———————

Multi-source forest inventory

Pilots in Finland and Germany

Read more

Online forest value estimation service,

used by OP-Metsä

read more

Drone-based forest mapping and species recognition using machine learning

(pilots in Finland and Germany)

read more


Using drones for monitoring quality of forest operations

LaatuKuva project


Monitoring agricultural fields and detecting vegetation based on Sentinel 1 radar data

Detecting of storm damages and environmental risk mapping based on drone data and satellite images
(pilot in Finland)
 

Detecting snow damages based on Sentinel 1 radar data
 

Contact us and let’s plan analysis services for your needs.



Image

Sanna Härkönen
R&D Manager
Tel. +358 40 120 9451
email sanna.harkonen(at)bitcomp.fi





Normalized difference vegetation index (NDVI) based on spectral UAV images.


Automatic tree detection based on canopy height model. Based on Fine-resolution UAV data.

Canopy height model based on RGB-derived 3D point cloud.

Automatic detection of storm areas based on UAV images.