Ensemble learning model identifies adaptation classification and turning points of river microbial communities in response to heatwaves

Heatwaves are a global issue that threaten microbial populations and deteriorate ecosystems. However, how river microbial communities respond to heatwaves and whether and how high temperatures exceed microbial adaptation remain unclear. In this study, we proposed four types of pulse temperature-induced microbial responses and predicted the possibility of microbial adaptation to high temperature in global rivers using ensemble machine learning models. Our findings suggest that microbial communities in parts of South American (e.g., Brazil and Chile) and Southeast Asian (e.g., Vietnam) countries are likely to change due to heatwave disturbance from 25 °C to 37 °C for consecutive days. Furthermore, the microbial communities in approximately 48.4% of the global river gauge stations are prone to fast stress inadaptation, with approximately 76.9% of these stations expected to exceed microbial adaptation after heatwave disturbances. If emissions of particulate matter with sizes not more than 2.5 μm (PM2.5, an indicator of human activities) increase by 2-fold, the number of global rivers associated with the fast stress adaptation type will decrease by ~13.7% after heatwave disturbances. Understanding microbial responses is crucially important for effective ecosystem management, especially for fragile and sensitive rivers facing heatwave events. All data and code aim to repeat the above findings.Other public data sourceFor global prediction, the physical and chemical properties of global rivers from the “GEMStat” website (https://gemstat.org/) were analyzed. A total of 6101 stations were extracted, including all physical and chemical river parameters mentioned in Table S3. Due to the scarcity of the data, their high resolution and the large extent of population shifts, human parameters were extracted at the national scale. The extracted human-related information and river parameters are provided in Table S3. Information from the nearest station calculated by the spherical distance was used to replenish the missing data. Net growth rates (number of rivers=5308) were obtained for global rivers.Population of the countries of the world: https://population.un.org/wpp/Download/Standard/Population/(Department of Economic and Social Affairs Population Dynamics)Per capita GDP: http://data.worldbank.org.cn (World Bank Database)Forest cover and education index (HDI): http://hdr.undp.org/en/data (United Nations Development Programme Human Development Reports)Carbon emissions: https://stats.oecd.org/The average annual PM2.5 concentration: healtheffects.org/https://www.stateofglobalair.org/data/#/health/mapGlobal emissions of polluting gases: https://edgar.jrc.ec.europa.eu/dataset_ap50 (Emissions Database for Global Atmospheric Research (EDGAR))Population density: http://data.un.org/Total number of tourists: https://www.unwto.org/(World Tourism Organization (UNWTO))Total in-use vehicles: https://www.oica.net/production-statistics/(World Automobile Organization)Coal consumption: https://www.iea.org/(World Energy Organization)https://unstats.un.org/unsd/mbs/app/DataSearchTable.aspxhttps://data.wto.org/(World Trade Organization)Total amount of goods transported by road: https://d.qianzhan.com/xdata/list/x2HvyF-3.html (Qianzhan website; data from China's National Bureau of Statistics)UN Environment: https://wesr.unep.org/downloaderSocioeconomic Data and Applications Center (SEDAC): https://sedac.ciesin.columbia.edu/data/set/gpw-v3-population-density-futureestimates/data-download