Description of the organization proposing the project
Latitudo40 is an innovative startup that aims to revolutionize the use of geospatial data, with an open platform (www.earthalytics.com) and marketplace dedicated to helping developers and startups build, manage and scale geospatial products. It opens up access to geospatial data, images and processing algorithms, enabling users to develop and launch innovative products, reducing development costs and time to market. The past decade or so has seen a dramatic change in the way that economists can learn by watching our planet from above, using satellite remote sensing.
Petabytes of satellite imagery have become accessible at increasing resolution and lower cost, but despite these enormous technological advances, only a marginal part of the information contained in these images is actually used to support business processes, monitoring and prevention activities. The technology is still complex enough to use and requires specific domain knowledge and initial investment to become familiar with the technology. Knowing how to develop, train, and run algorithms to extract insights from the data, and do this at scale, is also challenging. Currently this limits the use of the solution only in large organizations and in a governmental context, making it complex to use for SMEs, system integrators and startups.
Commitment in months and preferred period:
6 months starting from september 2020
Description of the project work objectives (what to achieve):
Heavy wind and hailstorms cause enormous physical damage in agriculture, often result in disasters leading to widespread, sudden loss in harvestable produce, and at times entire loss to grownup orchards. The objective of this project is the design and the implementation of state-of-the-art methodologies for heavy wind and hailstorms damaged crops using machine/deep learning applied to VHR satellite images, eventually integrated with heterogeneous data sources. The successful candidate will be required to identify the best technique to be applied to VHR input images (already available), other useful data sources and to validate his/her findings with independent reference data.
Required profile and pre-requisites (if any):
A degree in Aerospace/Electronics/Telecommunication Engineering or Computer Science is required for the post. Experience with machine/deep learning algorithms will be considered as an advantage.
Possible compensation (financial or in kind, i.e. accommodation, canteen, transportation,…):
Financial contribution as a grant to be assessed based on the candidate’s profile
Years of Experience required:
Single trainee in cooperation with our r&d team.
Please note that due to the pandemic, at the moment all the activities are conducted in smart working, with few exceptions in case of need.
Validity of the offer: