Authors:
G. Filippone
1
;
W. Spataro
1
;
D. D'Ambrosio
1
and
D. Marocco
2
Affiliations:
1
University of Calabria, Italy
;
2
Plymouth University, United Kingdom
Keyword(s):
Evolutionary Computation, Genetic Algorithms, Parallel Computing, Cellular Automata, Lava Flow Simulation, Lava Flow Control.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolution Strategies
;
Evolutionary Computing
;
Genetic Algorithms
;
Hybrid Systems
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Soft Computing
Abstract:
The determination of areas exposed to be interested by new eruptive events in volcanic regions is crucial for
diminishing consequences in terms of human causalities and damages of material properties. Nevertheless,
urbanized areas, cultural heritage sites or even important infrastructures, such as power plants, hospitals and
schools can be protected by diverting the flow towards lower interest regions. This paper describes the application
of Parallel Genetic Algorithms for optimizing earth barriers construction by morphological evolution, to
divert a case study lava flow that is simulated by the numerical Cellular Automata model Sciara-fv2 at Mt Etna
(Sicily, Italy). In particular, the application regards the optimization of the position, orientation and extension
of an earth barrier built to protect Rifugio Sapienza, a touristic facility located near the summit of the volcano.
The study has produced extremely positive results and represents, to our knowledge, the first application o
f
morphological evolution for lava flow mitigation. Among different alternatives generated by the Genetic Algorithm,
an interesting scenario consists of an earthen barrier solution (with a length of 225 m, average height
of 25 m, base width of 10 m and volume of 56180 m$^{3}$) which completely deviates the flow avoiding that the
lava reaches the inhabited area.
(More)