CONTEXT Changing cropping pattern is a potentially effective lever to cope with unreliable water resources, but given the multiple factors driving crop choices, assessing if farmers actually use it specifically for this objective remains difficult. OBJECTIVE We aimed at analyzing whether and how farmers choose crop categories with different water requirements to cope with limited water resources in peninsular India. METHODS We monitored over a 10 year period crop choices, weather, and groundwater level for the three cropping seasons in 205 irrigable farms in the Berambadi watershed, in southern India. We categorized crops according to their seasonal water requirement. We built farm types based of Sequence Analysis and Agglomerative Hierarchical Clustering of crop category sequences over 10 years for each cropping season. For each type, we correlated the variation in crop category choices to variations in rainfall and groundwater availability, to identify tactical adaptations. Finally, we grouped the crop category choices of the three seasons to identify the main strategic pathways followed by farmers. RESULTS AND CONCLUSIONS Sequence analysis of crop category choices revealed different types of crop category sequences, reflecting farmers' different strategies, which were not significantly linked with groundwater availability. We identified five main pathways across the three cropping seasons, including combining long-cycle irrigated crop and other crop categories, specializing in short-cycle irrigated crops over two or three seasons, specializing in rainfed crops or abandoning agriculture. Within each type, correlations between variation in water availability and crop categories highlighted specific tactical adaptations. SIGNIFICANCE The opportunity for farmers to choose their crops among a variety of species encompassing a large range of water requirements allows them to base their system resilience on a large diversity of strategies and tactics. This suggests that some farmers empirically estimate the water balance of their cropping systems at seasonal scale to take tactical decisions. Providing them with science-based tools to refine this estimation could therefore improve their decision-making. This also implies that modelling farmer decisions must account for their diversity. Maintaining or increasing the capacity of farmers to cultivate a broad range of crops with different seasonal water requirements is important for farming system resilience, and should therefore be part of the agenda of policy makers for agricultural or environmental regulations.