Ensemble learning fishery forecasting method utilizing ocean remote sensing multi-environmental elements

Abstract

The invention relates to the field of remote sensing information fishery application, in particular to an ensemble learning fishery forecasting method utilizing ocean remote sensing multi-environmental elements. The method aims at the problem that an existing fishery forecasting model is prone to be caught in overfitting on sample data, and consequently the generalization ability of the forecasting model is reduced, an ensemble learning method is adopted, a plurality of decision-making trees of simple structures are adopted as meta learning machines, learning machine integration is carried out based on a boosting algorithm, and the ensemble learning fishery forecasting method utilizing the ocean remote sensing multi-environmental elements is constructed. Each simple meta learning machine only learns a subset of characteristic space, the weight of samples, forecast to be wrong, in trained sub-learning machines as samples of the subsequent meta learning machines can be improved in the model training process to guarantee the different degree of the meta learning machines, and the learning machines learn information of different characteristic space subsets. According to the method, the generalization error can be reduced while prediction precision is improved, and the position of a fishery is effectively, fast and accurately located.

Description

technical field [0001] The invention relates to the field of fishery application of remote sensing information, in particular to an integrated learning fishery forecasting method utilizing multiple environmental elements of marine remote sensing. Background technique [0002] Marine environment and fishery resources information is an important information support for the utilization and protection of marine fishery resources. The use of marine remote sensing to provide fishery information services has become an important guarantee for marine fishery production and management planning. The distribution of marine fishery conditions is related to many factors such as the natural environment and human activities, and the forecast of fishery distribution is affected by many factors such as the accuracy of fishery production data records and the accuracy of remote sensing inversion of environmental elements. The existing fishery forecast method is to use a single statistical learn...

AI Technical Summary

Problems solved by technology

From the forecasting method, the traditional single statistical learning model is a strong learning machine, which is easy to fall into the overfitting of the sample data and reduce the generalization ability of the forecasting model.

Using a single traditional machine learning model to establish a mapping relationship often has the problem of over-learning, that is, the over-fitting of the mapping model to the sample data leads to a small fitting error of the mapping model to the sample, but the generalization and promotion performance is insufficient. The actual data prediction error rate involved in learning and training is very high

Images