Search

In the paper, a new evolutionary technique called Linear Matrix Genetic Programming (LMGP) is proposed. It is a matrix extension of Linear Genetic Programming and its application is data-driven black-box control-oriented modeling in conditions of limited access to training data. In LMGP, the model is in the form of an evolutionarily-shaped program which is a sequence of matrix operations. Since the program has a hidden state, running it for a sequence of input data has a similar effect to using well-known recurrent neural networks such as Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU). To verify the effectiveness of the LMGP, it was compared with different types of neural networks. The task of all the compared techniques was to reproduce the behavior of a nonlinear model of an underwater vehicle. The results of the comparative tests are reported in the paper and they show that the LMGP can quickly find an effective and very simple solution to the given problem. Moreover, a detailed comparison of models, generated by LMGP and LSTM/GRU, revealed that the former are up to four times more accurate than the latter in reproducing vehicle behavior., (© 2024. The Author(s).)

Some of the longest and most comprehensive marine ecosystem monitoring programs were established in the Gulf of Alaska following the environmental disaster of the Exxon Valdez oil spill over 30 years ago. These monitoring programs have been successful in assessing recovery from oil spill impacts, and their continuation decades later has now provided an unparalleled assessment of ecosystem responses to another newly emerging global threat, marine heatwaves. The 2014-2016 northeast Pacific marine heatwave (PMH) in the Gulf of Alaska was the longest lasting heatwave globally over the past decade, with some cooling, but also continued warm conditions through 2019. Our analysis of 187 time series from primary production to commercial fisheries and nearshore intertidal to offshore oceanic domains demonstrate abrupt changes across trophic levels, with many responses persisting up to at least 5 years after the onset of the heatwave. Furthermore, our suite of metrics showed novel community-level groupings relative to at least a decade prior to the heatwave. Given anticipated increases in marine heatwaves under current climate projections, it remains uncertain when or if the Gulf of Alaska ecosystem will return to a pre-PMH state.