TY - GEN
T1 - Data Assimilation Versus Machine Learning
T2 - 2019 OCEANS - Marseille, OCEANS Marseille 2019
AU - Horiuchi, Yuka
AU - Kokaki, Yuya
AU - Kobayashi, Tetsunori
AU - Ogawa, Tetsuji
N1 - Funding Information:
This research and development work was supported by the MIC/SCOPE #172302010. The authors would like to thank the Ohtomo Suisan Co., Ltd. for sharing the fish catch data, and the project members for the helpful discussions.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Data assimilation (DA) and machine learning (ML) are empirically compared for automatic daily fish catch forecasting (DFCF). ML would be a promising approach if large-scale data are available for training. Otherwise, DA would perform well, where prior knowledge on a monitoring target is incorporated into modeling. The present study aims to clarify the robustness of both approaches in DFCF with a small amount of data, and their evolution as the amount of training data increases. Experimental comparisons using catch and meteorological data demonstrate that a DA-based DFCF system yields a significant improvement over an ML-based systems with a small amount of data, and is comparable with ML-based systems with sufficient amount of data.
AB - Data assimilation (DA) and machine learning (ML) are empirically compared for automatic daily fish catch forecasting (DFCF). ML would be a promising approach if large-scale data are available for training. Otherwise, DA would perform well, where prior knowledge on a monitoring target is incorporated into modeling. The present study aims to clarify the robustness of both approaches in DFCF with a small amount of data, and their evolution as the amount of training data increases. Experimental comparisons using catch and meteorological data demonstrate that a DA-based DFCF system yields a significant improvement over an ML-based systems with a small amount of data, and is comparable with ML-based systems with sufficient amount of data.
KW - data assimilation
KW - fish catch forecasting
KW - gradient boosting decision trees
KW - machine learning
KW - state space models
UR - http://www.scopus.com/inward/record.url?scp=85103685934&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85103685934&partnerID=8YFLogxK
U2 - 10.1109/OCEANSE.2019.8867066
DO - 10.1109/OCEANSE.2019.8867066
M3 - Conference contribution
AN - SCOPUS:85103685934
T3 - OCEANS 2019 - Marseille, OCEANS Marseille 2019
BT - OCEANS 2019 - Marseille, OCEANS Marseille 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 17 June 2019 through 20 June 2019
ER -