Case study

Non-invasive DInSAR monitoring of ground subsidences induced by tunnelling excavation in urban areas


Big cities future plans usually require the construction of large underground infrastructures, in order to ensure proper communication and optimize urban use. Monitoring ground subsidences is therefore one of the main challenges in changing urban environments. Current conventional monitoring techniques are very accurate (topography, levelling, etc.) although they are quite expensive and limited to small areas. For these reasons, applications based on complementary techniques applied to wide areas and capable of analyzing time series and with positive relation profit/cost are being developed.


Since 2000 satellite radar techniques have become a complementary method for measuring ground surface displacements. Among these, differential SAR interferometry (DInSAR) has shown the capability for successfully measuring small displacement of structures with millimetric precision. DInSAR applied to measure surface subsidence has several advantages including large area coverage with a single image (10,000 km2), lower cost per m2 compared to conventional techniques and the possibility of obtaining data before, during and after the construction or phenomenon that is being studied. In this case, a total of 26 images from the Envisat satellite were used from August 2003 to April 2008.


An overall RMSE of deformation between 2.6mm and 3.5mm was obtained. The results were validated with more than 1500 field measurements made from leveling reference points and strips. The capabilities of the technique to assess deformations have been proven and, it is important to take into account that the number of controlled buildings when using the PSI technique dramatically increases when compared to the on ground techniques. Differential interferometry is a valuable tool to complement in-situ monitoring techniques in tunneling works.


  • The integration of artificial intelligence (AI) algorithms into the DInSAR deformation time series analysis, together with other technologies such as cloud computing and online interactive data analysis & visualization to early detect anomalies would allow increasing: i) Security and reduction of incidents through the improvement of early warning systems ii) Exploitation efficiency and preventive maintenance of the infrastructure iii) Infrastructure profitability due to the reduction of in-situ control instrumentation costs iv) Improving maintenance efficiency in all the phases of the infrastructure

Case study details

Client name
Receiver organization type
Client WWW
Activity type

Compare products

0 products added


Services comparison


Related Content

DynaCrop API
Crop monitoring
Use different indices such as NDVI, MSAVI and EVI or biophysical parameters such as LAI or fAPAR to show current and historical dynamics of crop growth to your customers.

Field scouting
Let your users prioritize field visits based on satellite field scouting. We identify anomalies in the crop growth and allow farmers to visit problematic places sooner than they become a real threat.

Zoning for variable applications
Finetune fertilizing and seeding of your customers with the satellite prescription maps based on long term or short term analysis of the field performance. Apply dynamic variations in the strategies and indices used for each specific use case.

Soil moisture
Water availability is becoming a crucial limiting factor for crop yields. Our high resolution soil moisture maps allow farmers to recognise underlying patterns of water distribution in their fields.

Soil organic carbon
Soil organic carbon is an important indicator of soil health and it plays a key role in the soil management. Help your farmers to make more informed decisions based on the regular satellite monitoring.
Land and Land Cover Analysis
Agriculture, Infrastructure, Land Ecosystems, Land use, Farming, Insurance & Finance, Local and regional planners
With AutoMap, the handling of satellite images has never been easier! We simplify the production of maps based on earth observation data and handle the application of machine learning algorithms for land surface classifications by providing a solid data processing pipeline in a fully managed cloud infrastructure. Bring your own samples or use our default solution, while we take care of the thousands of images that fit your request, all the clouds in your area of interest and every aspect of process optimization and secure data storage. Don't worry about machine learning concepts, intelligent training data collection, hyperparameter optimization or informative feature spaces - That's our job as well! Seeing the world from above is now as demanding as ordering a pizza!
Snow Monitoring
climate change, Assess ground water and run-off, Monitor snow cover, snow cover, Environment, Hydroelectric, Ski, Tourism
Continous Snow Monitoring System is available as global 500 m resolution snow cover, regional 20 m resolution snow cover for various areas and 20 m resolution snow depth product for Switzerland, the Rocky Mountains and Sierra Nevada. All algorithms can be further extended to any regions of interest.