This study investigates the vulnerability of Alberta's agricultural sector to extreme weather events, particularly drought, which has historically caused significant financial losses. Accurate downscaling techniques are crucial for obtaining reliable results to identify trends and patterns in hydro-climatological variables. Traditional statistical downscaling methods may be inefficient in downscaling data from multiple sources or complex datasets. As such, deep learning methods, such as Long Short-Term Memory (LSTM), may offer a promising solution. In this study, monthly climatological data spanning 35 years (1979 to 2014) from 17 NCEP grid points in Alberta were downscaled using LSTM to analyze trends and patterns in precipitation in agricultural areas. The Mann-Kendall and Pettitt tests were employed to analyze precipitation patterns and breakpoints. Additionally, the Standardized Precipitation Index (SPI) was used to identify drought severity at different time scales (SPI 3, 6, 12). The results demonstrate that drought occurrences have been observed in some agricultural regions, with rising tendencies in larger areas which southern parts such as Calgary agricultural areas highly prone to severe drought. The findings highlight the importance of developing effective strategies to mitigate the impacts of drought on Alberta's agricultural sector. The LSTM downscaling technique used in this study can be applied to other regions to identify trends and patterns in hydro-climatological variable.