Fishing Spot Detection Using Sea Water Temperature Pattern by Nonlinear Clustering

Determining fishing spots is an important decision-making for fishery. Fishers use environmental pattern information such as tide and vortex, and this process can be thought of as a good fishing spot determination problem from sea water temperature patterns. In this paper, we address this problem by a machine learning approach. Following an assumption that sea water temperature patterns of good fishing spots form some clusters, we discover these clusters and construct a classifier that discriminates whether an input sea water temperature pattern corresponds to good fishing spots clusters. We evaluated the effectiveness of our method using fishery data.