An empirical dynamic modeling framework for missing or irregular samples

Empirical dynamic modeling (EDM) is a powerful method for forecasting and analyzing nonlinear dynamics. However, typical applications of EDM assume that samples are evenly spaced over time. This presents problems in ecology, which data often missing or sampled irregularly. Standard methods handling irregularity suffer under conditions common such as short time series large fluctuations, so there need to adapt the framework cope with these challenges more effectively. Here we consider variable step-size extension EDM, incorporates temporal spacing between into delay-coordinate vectors circumvents faced by other approaches. We evaluated forecast accuracy along two methods: (1) exclusion (2) linear interpolation ordinary EDM. tested using simulated from three chaotic ecological models various amounts patterns data. also them empirical datasets: laboratory rotifer dynamics aphid field. Results showed while can produce accurate forecasts some scenarios, consistently gives wide range scenarios. Our analysis demonstrates an effective coping irregular expands number datasets be applied. Furthermore, extended estimate Lyapunov exponents irregularly approximate continuous discrete-time