Agro-hydrological modeling is crucial for designing climate change adaptations such as irrigation management. However, the accuracy of the simulation results greatly relies on the availability and accessibility of reliable ground data. Many countries extremely vulnerable to climate change have limited ground data as input for agro-hydrological modeling that restricts the validity of model results. A ‘model inversion’ technique can potentially tackle this data-scarce situation. Here, we combine alternative data sources, such as remote sensing for the estimation of crop development, with intense simulations to find missing input data such as irrigation.The present study aims to assess the performance of the model inversion technique using the AquaCrop model under different synthetic scenarios. The main research question is, ‘Is an inverted AquaCrop model able to identify the irrigation pattern of the crop growing period?’ The different synthetic scenarios for testing the performance include variations in the rainfall amount, irrigation amount and interval, soil texture, and initial soil moisture conditions. Preliminary results for synthetic scenarios show that inverse modeling is feasible for the estimation of irrigation patterns. The results indicate that under conditions of zero rainfall and dry initial soil moisture state, best inversion results were produced in both scenarios where continuous and non-continuous irrigation was applied. The scenarios near real-world conditions yielded the best results when continuously using uniform irrigation. Further research will investigate whether integrating remote sensing-based crop growth indicators like LAI or NDVI into the inverse modeling approach can improve scenarios' simulation with non-continuous irrigation.