Biologically meaningful distribution models highlight the benefits of the Paris Agreement for demersal fishing targets in the North Atlantic Ocean Data.zip

This data was used to demonstrate the benefits of complying to the Paris Agreement and limiting environmental change, by assessing future distributional shifts in 10 commercially important demersal fish species in the Northern Atlantic Ocean. Distributional shift analysis compared near present-day conditions (2000-2017) with two Representative Concentration Pathway (RCP) scenarios of future climate change. One following the Paris Agreement climate forcing (RCP2.6) and another without stringent mitigation measures (RCP8.5). We use machine learning distribution models coupled with biologically meaningful predictors to project future latitudinal and depth shifts. We show that limiting future climate changes by complying with the Paris Agreement can translate into reduced distributional shifts for demersal fish, supporting biodiversity conservation and marine resource management. Furthermore, including predictors beyond temperature in species distribution modelling can improve predictive performances. <br>本数据集通过评估北大西洋海域10种具有重要商业价值的底栖鱼类（demersal fish）未来的分布偏移情况，用以论证遵守《巴黎协定》、限制环境变化的益处。分布偏移分析将近当代气候条件（2000-2017年）与两种未来气候变化典型浓度路径（Representative Concentration Pathway, RCP）情景进行对比：其中一种情景遵循《巴黎协定》的气候强迫要求（RCP2.6），另一种则未采取严格的气候减缓措施（RCP8.5）。本研究采用耦合生物学意义预测变量的机器学习分布模型，对未来的纬度与深度分布偏移进行预测。研究结果显示，通过遵守《巴黎协定》限制未来气候变化，可降低底栖鱼类的分布偏移幅度，从而为生物多样性保护与海洋资源管理提供支撑。此外，在物种分布模型构建过程中纳入温度以外的预测变量，可有效提升模型的预测性能。