Yuxin Zhao

Rixu Hao, Yuxin Zhao, Shaoqing Zhang et al.

El Niño-Southern Oscillation (ENSO) exerts global climate and societal impacts, but real-time prediction with lead times beyond one year remains challenging. Dynamical models suffer from large biases and uncertainties, while deep learning struggles with interpretability and multi-scale dynamics. Here, we introduce PTSTnet, an interpretable model that unifies dynamical processes and cross-scale spatiotemporal learning in an innovative neural-network framework with physics-encoding learning. PTSTnet produces interpretable predictions significantly outperforming state-of-the-art benchmarks with lead times beyond 24 months, providing physical insights into error propagation in ocean-atmosphere interactions. PTSTnet learns feature representations with physical consistency from sparse data to tackle inherent multi-scale and multi-physics challenges underlying ocean-atmosphere processes, thereby inherently enhancing long-term prediction skill. Our successful realizations mark substantial steps forward in interpretable insights into innovative neural ocean modelling.

Xingshi He, Xin-She Yang, Mehmet Karamanoglu et al.

Flower pollination algorithm is a recent metaheuristic algorithm for solving nonlinear global optimization problems. The algorithm has also been extended to solve multiobjective optimization with promising results. In this work, we analyze this algorithm mathematically and prove its convergence properties by using Markov chain theory. By constructing the appropriate transition probability for a population of flower pollen and using the homogeneity property, it can be shown that the constructed stochastic sequences can converge to the optimal set. Under the two proper conditions for convergence, it is proved that the simplified flower pollination algorithm can indeed satisfy these convergence conditions and thus the global convergence of this algorithm can be guaranteed. Numerical experiments are used to demonstrate that the flower pollination algorithm can converge quickly in practice and can thus achieve global optimality efficiently.

Xin-She Yang, M. Karamanoglu, T. O. Ting et al.

All swarm-intelligence-based optimization algorithms use some stochastic components to increase the diversity of solutions during the search process. Such randomization is often represented in terms of random walks. However, it is not yet clear why some randomization techniques (and thus why some algorithms) may perform better than others for a given set of problems. In this work, we analyze these randomization methods in the context of nature-inspired algorithms. We also use eagle strategy to provide basic observations and relate step sizes and search efficiency using Markov theory. Then, we apply our analysis and observations to solve four design benchmarks, including the designs of a pressure vessel, a speed reducer, a PID controller and a heat exchanger. Our results demonstrate that eagle strategy with Lévy flights can perform extremely well in reducing the overall computational efforts.