This　research　aims　to　investigate　the　intricate　dynamics　between　energy　futures　prices　and　both　tropical　and　traditional　commodities　futures　prices,　with　a　particular　focus　on　the　critical　role　of　oil　futures　prices　in　predicting　the　trajectory　of　agricultural　futures　prices.　The　study　employs　the　Dynamic　Conditional　Correlation-Multivariate　Generalized　Autoregressive　Conditional　Heteroskedasticity　(DCC-MGARCH)　model　to　analyse　the　interplay　among　oil　and　agricultural　futures　price　series　over　2008:01-2021:06.　Additionally,　it　incorporates　the　innovative　Spatio-temporal　Information　Recombination　Hypergraph　Neural　Network　(STIR-HGNN)　model　to　highlight　the　differences　in　how　energy　futures　prices　predict　tropical　and　traditional　agricultural　futures　prices.　The　findings　reveal　numerous　connections　between　oil　prices　and　both　tropical　and　traditional　agricultural　futures　prices,　underscoring　the　significant　role　of　oil　prices　in　forecasting　agricultural　futures　price　movements.　The　empirical　insights　from　this　study　provide　valuable　guidance　for　futures　market　participants,　encouraging　them　to　use　these　findings　to　refine　and　optimize　their　market　strategies,　thus　enhancing　their　ability　to　navigate　and　capitalize　on　the　complexities　of　these　interconnected　markets.