Observed and projected trends in climate extremes in a tropical highland region: An agroecosystem perspective

Tropical highland environments present substantial challenges for climate projections due to sparse observations, significant local heterogeneity and inconsistent performance of global climate models (GCMs). Moreover, these areas are often densely populated, with agriculture-based livelihoods sensitive to transient climate extremes not always included in available climate projections. In this context, we present an analysis of observed and projected trends in temperature and precipitation extremes across agroecosystems (AESs) in the northwest Ethiopian Highlands, to provide more relevant information for adaptation. Limited observational networks are supplemented with a satellite-station hybrid product, and trends are calculated locally and summarized at the adaptation-relevant unit of the AES. Projections are then presented from GCM realizations with divergent climate projections, and results are interpreted in the context of agricultural climate sensitivities. Trends in temperature extremes (1981-2016) are typically consistent across sites and AES, but with different implications for agricultural activities in the other AES. Trends in temperature extremes from GCM projected data also generally have the same sign as the observed trends. For precipitation extremes, there is greater site-to-site variability. Summarized by AES, however, there is a clear tendency towards reduced precipitation, associated with decreases in wet extremes and a tendency towards temporally clustered wet and dry days. Over the retrospective analysis period, neither of the two analysed GCMs captures these trends. Future projections from both GCMs include significant wetting and an increase in precipitation extremes across AES. However, given the lack of agreement between GCMs and observations with respect to trends in recent decades, the reliability of these projections is questionable. The present study is consistent with the "East Africa Paradox" that observations show drying in summer season rainfall while GCMs project wetting. This has an expression in summertime Ethiopian rain that has not received significant attention in previous studies.