Cyanobacterial blooms in lakes and reservoirs pose significant environmental and public health risks. This paper presents an effective exploration strategy to detect them from Autonomous Surface Vehicles (ASVs) equipped with probes, whose sensing trajectories are optimized by an AI-based planner that considers the 3D spatial-temporal evolution of the cyanobacteria concentration obtained by a multiphysics model. The planner, simultaneously working on the AI decision-making and robotic domains, optimizes the surface displacement of the ASV and the depth of its probe by solving a constrained multi-objective optimization problem that minimizes the mission duration and trajectory length, maximizes the possibilities of the probe to overpass areas with high concentration of cyanobacteria, and satisfies operational constraints (such as ASV velocity or acceleration limits, and obstacle avoidance). The optimization is supported by two well-known versions of the Non-Sorted Generic Algorithm (NSGA-II and NSGA-III) and by encoding the trajectories with spline curves whose number of control points can be fixed, progressively increased, or freely manipulated by the algorithm. The performance of different configurations of the planner is tested against six scenarios obtained from different simulations of the multiphysics model (which couples water dynamics and temperature, light transmission, daily vertical migration of the cyanobacteria and their growth). The statistical analysis of the planner results determines that NSGA-III working with variable-length chromosomes and NSGA-II with the progressive increment of spline points as the best configurations for maximizing cyanobacteria detection, and minimizing mission duration and trajectory length.
Carazo-Barbero et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: