Aerial wildfire suppression requires decisions about when, where, and how to deploy limited aircraft. We present an intervention-design framework built on a frozen hybrid convolutional neural network and cellular automaton (CNN-CA) simulator trained jointly on six historical wildfires. First, we jointly optimize binary drop execution and continuous location and orientation, with aircraft-specific footprints, wind drift, and availability, turnaround, and grounded-day constraints. Second, we model water as an immediate transfer of burning probability to the unburned state and retardant as a persistent reduction in the fuel contribution to spread. Third, we remove drops by a rollout-verified backward elimination while limiting degradation in selected fire-performance metrics. Fourth, we evaluate fixed schedules under daily state sampling and spatially correlated model-discrepancy perturbations. Fifth, we compare the optimizer with random, tactical, greedy, and derivative-free planners under shared fleet, drop-budget, and simulator-evaluation allowances, and measure computational scaling. A 2020 Bear Fire case study considers two objectives: total fire-affected area and protected-region exposure. Both stages run at a suppression effectiveness below the nominal one, which gives the schedule a margin against model error. The two-stage total-area schedule reduces deterministic terminal extent by 97.5% relative to the simulator baseline with 1,032 drops, and the Day-15 area by 90.9% under sampled model error. The tactical heuristic is more economical at small evaluation allowances; the gradient planner achieves better objectives with more computation. All reductions are conditional on the frozen simulator and modeled suppression response. They are not estimates of historical acreage saved or evidence of operational validity.

翻译：暂无翻译