Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Abstract

Accurate habitat prediction is important to improve fishing efficiency. Most of the current habitat-prediction studies use the single-source datasets and the sequence model based on single-source datasets, which, to a certain extent, limits the further improvement of prediction accuracy. In this paper, we propose a habitat-prediction method based on the multi-source heterogeneous remote-sensing data fusion, using product-level remote-sensing data and L1B-level original remote-sensing data. We designed a heterogeneous data feature extraction model based on a Convolution Neural Network (CNN) and Long and Short-Term Memory network (LSTM), and we designed a decision-fusion model based on multi-source heterogeneous data feature extraction. In the habitat prediction for the Northwest Pacific Saury, the mean R2 of the model reaches 0.9901 and the RMSE decreases to 0.01588 in the model validation experiment. It is significantly better than the results of other models, with the single datasets as input. Moreover, the model performs well in the generalization experiment because we limited the prediction error to less than 8%. Compared with the single-source sequence network model in the existing literature, the proposed method in this paper solves the problem of ineffective fusion caused by the differences in the structure and size of heterogeneous data through multilevel feature fusion and decision fusion, and it deeply explores the features of remote-sensing fishery data with different data structures and sizes. It can effectively improve the accuracy of fishery prediction, proving the feasibility and advancement of using multi-source remote-sensing data for habitat prediction. It also provides new methods and ideas for future research in the field of habitat prediction.

Effect of the Synergetic Use of Sentinel-1, Sentinel-2, LiDAR and Derived Data in Land Cover Classification of a Semiarid Mediterranean Area Using Machine Learning Algorithms

“…De Fioravante et al [29] proposed a land cover classification methodology for Italy based on decision rules using the EAGLE-compliant classification system [30], obtaining an overall accuracy of 83%, which seems to be much lower than those obtained using machine learning. Most recent and innovative research includes further comparisons with methods of Deep Learning and Artificial Neural Networks, as in [31] or [32].…”

Forecasting Albacore (Thunnus alalunga) Fishing Grounds in the South Pacific Based on Machine Learning Algorithms and Ensemble Learning Model

“…Fishing ground forecasts have shifted from small-scale and short-term fishery data to large-scale fishery data. Traditional models are limited by the dimensionality of the input data, which makes it challenging to achieve high-accuracy fishing ground forecasts for large-scale, complex and variable high-dimensional ocean data [11,12]. At the same time, traditional models also have problems, such as being influenced by human factors, not having generalizability, having difficulty in feature conversion and experiencing insufficient fitting [13,14].…”