Skill and value in recruitment forecasting
semanticscholar(2021)
Abstract
9 Forecasting variation in the recruitment to fish stocks is one of the most challenging problems in fisheries 10 science and one that essentially remains unsolved today. Traditionally recruitment forecasting involves 11 assumptions of stationarity, is evaluated on explanatory power and rarely includes environmental 12 processes.. Here we apply the lessons from fisheries science and other fields to propose a new generic 13 approach to recruitment forecasting that allows the skill and value of recruitment forecasts to be assessed 14 appropriately. We employ empirical multi-model ensembles to account for model structural uncertainty 15 and consider forecasts in terms of both continuous and categorical forecasts. Forecast skill is assessed 16 based on predictive power, using retrospective forecasts, while value is quantified using an economic cost17 loss decision model. We demonstrate this framework using four stocks of lesser sandeel (Ammodytes 18 marinus) in the North Sea. We find the skill and value of the forecasts for each stock is strongly influenced 19 by the quality of the stock assessment: skilful and valuable forecasts are shown to be feasible in some 20 management areas. This result shows the ability to produce valuable short-term recruitment forecasts, 21 evaluated in a realistic setting, and paves the way for revisiting our ability to make skilful and valuable 22 recruitment forecasts. 23
MoreTranslated text
求助PDF
上传PDF
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined