Project ACROPOLIS will develop a system for the classification of ponds against potential risks, combining GIS and Machine Learning technologies.
ACROPOLIS, “Classification of ponds against potential risk combining GIS and Machine Learning”, aims to build an aid system for the classification of ponds according to potential risk. The system will optimise various processes using Machine Learning (ML) techniques, Geographic Information Systems (GIS) and infrastructure asset management using BIM (Building Information Modelling) methodology.
The project will result in three different versions with the aim of addressing the problems of:
- A web application that will make it possible to know what type of pond it is according to the potential risk. It will allow the pre-classification of ponds on a massive scale, determining the priority of investment in carrying out the study and in improving safety in the event of a possible breach.
- An automated tool for the elaboration of Pond Classification Reports by means of an optimal process. In addition, it will integrate an optimized calculation engine with the use of graphic cards (GPUs), breakage methodologies and specific and updated risk criteria, a wizard to extract the results, and a module for semi-automatic generation of the report according to the current legislation.
- A BIM model in which all the information on the reservoir is integrated. This will increase the performance of the GIS model in that the infrastructure assets can be represented in 3 dimensions together with their technical attributes with a high level of detail.
IDP, as coordinator, will lead the development of a GIS – BIM platform tool for the integration of breakage models and information related to the safety of the pond.
ACROPOLIS is framed in the call “Retos-Colaboración 2019” of the Plan Estatal De Investigación Científica y Técnica y de Innovación del Ministerio de Ciencia, Innovación y Universidades del Gobierno de España.
Funded by: FEDER/Ministerio de Ciencia, Innovación y Universidades- Agencia Estatal de Investigación/ Project RTC-2019-007343-5