A machine learning approach to map the potential agroecological complexity in an indigenous community of Colombia.

Agroecological systems are potential solutions to the environmental challenges of intensive agriculture. Indigenous communities, such as the Kamëntsá Biyá and Kamëntsá Inga from the Sibundoy Valley (SV) in Colombia, have their own ancient agroecological systems called chagras. However, they are threatened by population growth and expansion of intensive agriculture. Establishing new chagras or enhancing existing ones faces impediments such as the necessity for continuous monitoring and mapping of agroecological potential. However, this method is often costly and time consuming. To address this limitation, we created a digital map of the Biodiversity Management Coefficient (BMC) (as a proxy of agroecological potential) using Machine Learning. We utilized 15 environmental predictors and in-situ BMC data from 800 chagras to train an XGBoost model capable of predicting a multiclass BMC structure with 70% accuracy. This model was deployed across the study area to map the extent and spatial distribution of BMC classes, providing detailed information on potential areas for new agroecological chagras as well as areas unsuitable for this purpose. This map captured footprints of past and present disturbance events in the SV, revealing its usefulness for agroecological planning. We highlight the most significant predictors and their optimal values that trigger higher BMC status.

Potential negative impacts of climate change outweigh opportunities for the Colombian Pacific Ocean Shrimp Fishery.

Climate change brings a range of challenges and opportunities to shrimp fisheries globally. The case of the Colombian Pacific Ocean (CPO) is notable due the crucial role of shrimps in the economy, supporting livelihoods for numerous families. However, the potential impacts of climate change on the distribution of shrimps loom large, making it urgent to scrutinize the prospective alterations that might unfurl across the CPO. Employing the Species Distribution Modeling approach under Global Circulation Model scenarios, we predicted the current and future potential distributions of five commercially important shrimps (Litopenaeus occidentalis, Xiphopenaeus riveti, Solenocera agassizii, Penaeus brevirostris, and Penaeus californiensis) based on an annual cycle, and considering the decades 2030 and 2050 under the Shared Socioeconomic Pathways SSP 2.6, SSP 4.5, SSP 7.0, and SSP 8.5. The Bathymetric Projection Method was utilized to obtain spatiotemporal ocean bottom predictors, giving the models more realism for reliable habitat predictions. Six spatiotemporal attributes were computed to gauge the changes in these distributions: area, depth range, spatial aggregation, percentage suitability change, gain or loss of areas, and seasonality. L. occidentalis and X. riveti exhibited favorable shifts during the initial semester for both decades and all scenarios, but unfavorable changes during the latter half of the year, primarily influenced by projected modifications in bottom salinity and bottom temperature. Conversely, for S. agassizii, P. brevirostris, and P. californiensis, predominantly negative changes surfaced across all months, decades, and scenarios, primarily driven by precipitation. These changes pose both threats and opportunities to shrimp fisheries in the CPO. However, their effects are not uniform across space and time. Instead, they form a mosaic of complex interactions that merit careful consideration when seeking practical solutions. These findings hold potential utility for informed decision-making, climate change mitigation, and adaptive strategies within the context of shrimp fisheries management in the CPO.