Intership | Automatic 3d Vectorisation Of Historical Mining Maps With Deep Learning Tools

Introduction
After decades of coal exploitation in Limburg during the early 20th century, lagging aftereffects at the surface, such as local sinkholes, are still experienced today. Additionally, using satellite geodesy (InSAR, GPS), we also observed regional surface uplift, which has been attributed to the cessation of mine water pumping after the end of coal exploitation.

Many efforts have been made to understand how sinkholes are formed and to understand the regional uplift signal and faults at the surface. However, proper modelling of these processes requires a well-known geometry and location of the mined areas.
In 2015 TNO published tens of thousands of georeferenced historical maps of the mining activities of Limburg. These historical mining maps indicate where the coal was mined, the pathways from which the coal was transported and many other essential features that could provide a good indication of vulnerable locations from a subsurface mining configuration perspective.

While these historical maps hold helpful information about the subsurface, the fact that they are in raster and not in vector format makes them heavy and difficult to visualise and use for subsurface modelling. Additionally, these maps have information (e.g. handwritten values) which would be good to retain together with the vectorised information.

What you will be doing
With Deep Neural Network algorithms, using solution types such as Convolutional Neural Network (CNN), you will train an existing data set to extract relevant information from historical maps. You will do this building up on an existing approach. Since the information within the historical maps cover vector, text and numeric, you will approach extraction of this information from two sides: CNN and Optical Character Recognition. You will use previously vectorized maps as training datasets and perform your own training dataset. You will analyze how these and other technologies (e.g. Recurrent Convolutional Neural Networks) lead to an automatic vectorised product. You will be working within a team that will help you with these technologies and to interpret the relevant features to be extracted from the maps. You will also contact with stakeholders that will use your final product. Your final product will contribute to a newly 3D vectorized database of the Limburg mining areas, shafts and galleries, supporting research and decision-making.

We are looking for a master's student or a student who would use this topic for a master's thesis with the following profile:

• Study: you are studying computer or data science and have an interest in geosciences or a geoscientist with knowledge in the computer science field. Any other field with an image processing component: mathematics or engineering with an affinity for AI and training Deep Learning networks and a passion for applied Earth sciences.
• Language: English required, Dutch optional but desirable
• Interests: Deep Learning, Geology, image processing
• Skills: Quickly grasping new concepts and identifying the most crucial aspects of a complex problem involving different expertise. Good math, statistical, and computing skills. Skilled in Python, MATLAB, or similar tools.

You want to work on the precursor of your career; a work placement gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Naturally, we provide suitable work placement compensation.

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy. Since 1932, we have been making knowledge and technology available for the common good. We find each other in wonder and ingenuity. We are driven to push boundaries. There is all the space and support for your talent and ambition. You work with people who will challenge you: who inspire you and want to learn from you. Our state-of-the-art facilities are there to realize your vision. What you do at TNO matters: impact makes the difference. Because with every innovation you contribute to tomorrow’s world. Read more about TNO as an employer.

At TNO we encourage an inclusive work environment, where you can be yourself. Whatever your story and whatever unique qualities you bring to the table. It is by combining our unique strengths and perspectives that we are able to develop innovations that make a real difference in society. Want to know more? Read what steps we are taking in the area of diversity and inclusion.

After the first CV selection, the application process will be conducted by the concerning department. TNO will provide a suitable internship agreement. If you have any questions about this vacancy, you can contact the contact person mentioned below.

Students must reside in the Netherlands before the start and also throughout the internship or graduation project at TNO.