A group of scientists from Algeria used machine learning models to predict the prevalence of antibiotic resistance genes in soil microbes under future climate scenarios. Agricultural soils are the largest reservoirs of these genes, as manure from livestock transfers leftover antibiotics into the soil. The team compiled microbial data from 3 public databases, creating a final dataset of about 2,000 agricultural soil samples from 67 countries across 6 continents. They integrated this with climate data, including global temperature and precipitation measurements from WorldClim, and land use data from the European Space Agency Climate Change Initiative Land Cover maps. The researchers also included future climate projections for 2050 and 2070 from the World Climate Research Programme based on low, medium, and high global greenhouse gas emission scenarios. They set up 6 machine learning models: Light Gradient Boosting Machine, eXtreme Gradient Boosting, Random Forest, Support Vector Machine, Deep Neural Network, and Logistic Regression, running each with different variable combinations to identify key environmental drivers and high-risk areas.