Modern intensive agriculture relies on supplemental irrigation in order to achieve high yields. Although it is well established that timely irrigation can increase substantially irrigation efficiency and water productivity, determining the adequate timing and amount of irrigation remains a very challenging task for farmers. Numerous studies have considered the development of Decision Support Systems (DSS) which would help farmers manage irrigation more efficiently. In order to generate and/or compare irrigation schedules, such Decision Support Systems require weather forecasts for a period extending from a few days to the whole season, depending on the approach adopted. Such forecasts can be either deterministic or probabilistic (so-called ensemble forecasts). In this talk we will discuss the use of both types of forecasts within the general framework of seasonal model-based optimization. We will use a simulation study to illustrate the advantages and drawbacks of different optimization approaches and discuss the benefits that can be expected from using probabilistic forecasts.