Data associated with: Han, B.A., Varshney, K.R., LaDeau, S., Subramaniam, A., Weathers, K.C., Zwart, J. A synergistic future for AI and ecology. PNAS 120 (38) (2023).

The file is associated with:Han, B.A., Varshney, K.R., LaDeau, S., Subramaniam, A., Weathers, K.C., Zwart, J. A synergistic future for AI and ecology. PNAS 120 (38) (2023).<b>Abstract:</b>Research in both ecology and artificial intelligence (AI) strives for predictive understanding of complex systems, where nonlinearities arise from multidimensional interactions and feedbacks across multiple scales. After a century of advances built on a staggered cycle of computational development and ecological adaptation, we foresee a critical need for intentional synergy to meet current societal challenges against the backdrop of global change.The unpredictability of systems-level phenomena and associated challenges in understanding resilience dynamics are critical challenges on a rapidly changing planet. Here, we spotlight both the promise and the urgency of a synergistic convergence research paradigm between ecology and AI. The systems studied in ecology are a challenge to fully and holistically model, even using the most prominent AI technique today: deep neural networks. Moreover, ecological systems have emergent and resilient behavior that should inspire new, robust AI architectures and methodologies. We share several examples of how challenges in ecological systems modeling will require advances in AI techniques that are themselves inspired by the systems they seek to model.Both fields have inspired each other, albeit indirectly, in an evolution toward this convergence. Here we emphasize the need for more purposeful synergy to accelerate understanding of ecological resilience whilst building the resilience currently lacking in modern AI. There are persistent epistemic barriers that require attention in both disciplines, yet the implications of a successful convergence go beyond advancing ecological disciplines or achieving an artificial general intelligence -- they are critical for both persisting and thriving in an uncertain future.<b>File list:</b>AIandML_results_SHARE.csv - contains literature search results from Clarivate Web of Science.

本数据集关联文献为：Han, B.A.、Varshney, K.R.、LaDeau, S.、Subramaniam, A.、Weathers, K.C.、Zwart, J. 合著的《AI与生态学的协同未来》，发表于《美国国家科学院院刊》（PNAS）120卷第38期（2023年）。<b>摘要：</b>生态学与人工智能（Artificial Intelligence, AI）领域的研究均致力于实现对复杂系统的预测性认知，此类系统的非线性特性源于多尺度下的多维交互与跨尺度反馈。历经一个世纪以来以计算发展与生态学适配交替推进为支撑的研究进展后，我们认为当前亟需开展针对性的协同研究，以应对全球变化背景下的各类社会挑战。在快速变化的地球环境中，系统级现象的不可预测性以及理解生态系统韧性动态的相关难题，是当前面临的核心挑战。本文聚焦生态学与AI协同融合的研究范式，既阐述其发展前景，也强调其紧迫性。尽管当前主流AI技术——深度神经网络（Deep Neural Networks）已取得长足进展，但生态学研究的系统仍难以实现完整且全面的建模。此外，生态系统所具备的涌现性与韧性行为，能够为开发更具鲁棒性的新型AI架构与方法论提供灵感。本文将列举若干案例，说明生态系统建模难题将如何推动AI技术的革新，而此类AI技术的革新本身又将从其所拟建模的系统中汲取灵感。尽管二者此前尚未形成直接的互动，两大领域在各自演进至融合的过程中，已相互给予启发。本文着重强调，我们需要开展更具目的性的协同研究，以加速对生态系统韧性的认知，同时也为弥补当前现代AI所缺乏的韧性提供助力。两大学科均存在亟待解决的认识论壁垒，而二者成功融合的意义，不仅在于推动生态学学科发展或实现通用人工智能（Artificial General Intelligence, AGI），更关乎人类在不确定性未来中的存续与发展。<b>文件列表：</b>AIandML_results_SHARE.csv：包含来自科睿唯安Web of Science的文献检索结果。