随着单一模型能力不断增强，我们发现许多现实世界的问题需要跨领域的综合洞察。回答诸如“飓风可能在何处登陆？哪些社区最易受灾害影响，应如何准备？”等复杂问题，需要对影像、人口和环境信息进行综合推理。Earth AI 将前沿模型与地理空间推理代理相结合，以应对全球重大挑战。

As individual models grow more powerful, we’ve learned that many real-world questions require the combination of insights across domains. Answering complex queries like, "Where is a hurricane likely to make landfall? Which communities are most vulnerable and how should they prepare?" requires reasoning about imagery, population and the environment. Earth AI unites state-of-the-art models with geospatial reasoning agents to address critical global challenges.

随着单个模型能力不断增强，我们逐渐认识到，许多现实世界的问题需要跨领域的洞察整合。回答诸如“飓风可能在何处登陆？哪些社区最易受威胁，应如何应对？”这类复杂问题，需要对影像数据、人口分布和环境状况进行综合推理。Earth AI 将最先进的模型与地理空间推理代理相结合，以应对全球性重大挑战。我们在17个国家对Population Dynamics Foundations模型进行了评估；按国家划分的预测人口密度、树冠覆盖、夜间灯光和高程的R²得分（范围为0–1，数值越高表示性能越好）。全球趋势与我们最初在美国展示的优异表现一致。通过美国邮政编码可视化展示Population Dynamics Foundations嵌入向量各维度间的相似性。各维度中的模式捕捉了美国人口的多样化特征。我们此前发表的研究已证明，在中短期天气、季风 onset、空气质量及河流洪水方面达到行业领先水平的预测能力。近期，我们已将这些环境模型扩展至覆盖全球的降水实时预报，并已为20亿人提供重大河流洪水的预报服务。尽管每个基础模型都能提供强大的洞见，但我们的研究结果证实，模型融合可带来更强的预测能力。这种协同方法能够更全面、更准确地理解现实世界现象，并显著提升关键应用中的预测效果。以一位用户希望识别易受即将到来风暴威胁的特定人群为例，该代理会执行一系列透明的推理步骤：为评估该代理，我们开发了两种新方法：基于公开数据且答案可验证的事实核查问答基准，以及用于复杂预测场景的危机响应案例研究（例如，解决上述全部挑战）。Earth AI 代表了对地球认知的根本性飞跃。研究结果表明，基于最先进的地理空间AI基础模型，采用多模态、基于推理的方法，能够解锁仅靠孤立分析无法实现的深刻洞见。我们才刚刚开始探索Earth AI的全部潜力，致力于扩大其可及性，以帮助全球社会应对地球面临的最紧迫挑战。例如：

As individual models grow more powerful, we’ve learned that many real-world questions require the combination of insights across domains. Answering complex queries like, "Where is a hurricane likely to make landfall? Which communities are most vulnerable and how should they prepare?" requires reasoning about imagery, population and the environment. Earth AI unites state-of-the-art models with geospatial reasoning agents to address critical global challenges. Evaluation of our Population Dynamics Foundations across 17 countries; R2 score (range is 0–1, higher is better) by country for predicting population density, tree cover, night time lights, and elevation. The global trend matches the strong performance we originally demonstrated in the US only. Similarity per dimension of the Population Dynamics Foundations embeddings, visualized by US zip code. The patterns across dimensions capture the diverse characteristics of the US population. Our previously-published research demonstrates state-of-the-art forecasts for medium-range weather, monsoon onsets, air quality and riverine floods. We've recently expanded these Environment models to make precipitation nowcasts for the entire planet, and we’re now covering 2 billion people with forecasts for the most significant riverine floods. While each foundation model provides powerful insights, our findings confirm that combining models yields even more predictive power. This synergistic approach produces a more comprehensive and accurate understanding of real-world phenomena and dramatically improves predictions across critical applications. To see how it works, consider a user who wishes to identify specific populations that are vulnerable to the risk of an oncoming storm. The agent executes a transparent series of reasoning steps: To evaluate the agent, we developed two new methods for evaluation: a Q&A benchmark for fact-finding and analysis with verifiable ground truth answers based on publicly available data and Crisis Response case studies for complex, predictive scenarios (e.g., solving the entire challenge above). Earth AI represents a fundamental leap in planetary understanding. Our findings show that a multimodal, reasoning-based approach, built upon a foundation of state-of-the-art geospatial AI models, can unlock insights that are intractable with siloed analysis alone. We are just beginning to explore the full potential of Earth AI and are committed to expanding access in order to help the global community address the planet’s most pressing challenges. For example: