Optimal scenario design for climate emulation

仿真 计算机科学 强迫(数学) 培训(气象学) 机器学习 概化理论 训练集 一套 人工智能 气候变化 气候模式 简单(哲学) 天花板(云) 模拟 理论(学习稳定性) 实时计算 灵活性(工程) 温室气体 数据挖掘
作者
Christopher B. Womack,Shahine Bouabid,Andrei Sokolov,Popat Salunke,Glenn R. Flierl,Sebastian D. Eastham,Noelle E. Selin
出处
期刊:Proceedings of the National Academy of Sciences of the United States of America [National Academy of Sciences]
卷期号:123 (46): e2620731123-e2620731123 被引量:2
标识
DOI:10.1073/pnas.2620731123
摘要

As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training datasets themselves can be optimized to improve generalization. We introduce a method to create datasets that produce emulators capable of generalizing to new, structurally different scenarios absent from the training data. We use a differentiable simple climate model (SCM) to calculate the sensitivity of emulator loss to perturbations in the training data, iteratively updating the training data to maximize emulator skill. For an SCM, an emulator trained on one scenario optimized in this fashion outperforms an emulator trained on six standard Scenario Model Intercomparison Project (ScenarioMIP) pathways. We achieve this higher predictive skill despite training on a smaller dataset, finding that our emulator successfully isolates distinct physical behaviors of different climate forcing agents (e.g., greenhouse gases vs. aerosols) without single-forcing runs. We then demonstrate that scenarios optimized using an SCM, when used to drive an intermediate-complexity climate model, produce a training dataset that yields a more skillful emulator than training on ScenarioMIP outputs. Our results suggest that, in the compute-constrained environment of running full-scale climate models, generating a small number of dynamically rich scenarios provides greater marginal value for emulation and characterizing system responses than expanding the suite of traditional emissions pathways.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
猴子的应助被孝择采纳,获得10
刚刚
Jenny完成签到,获得积分10
刚刚
黄晓杰2024完成签到,获得积分10
1秒前
1秒前
Wuliu发布了新的文献求助10
1秒前
会爬树的鱼完成签到,获得积分10
2秒前
汉堡包的应助被corleeang采纳,获得10
2秒前
4秒前
所所的应助被lrl采纳,获得10
4秒前
小生不才发布了新的文献求助10
4秒前
4秒前
空空伊发布了新的文献求助10
5秒前
5秒前
6秒前
asadguy发布了新的文献求助20
6秒前
慕青的应助被小陈陈采纳,获得10
6秒前
王大橙子发布了新的文献求助10
6秒前
Owen的应助被wwww采纳,获得10
6秒前
lily完成签到,获得积分10
6秒前
壁虎君完成签到,获得积分10
9秒前
9秒前
王达发布了新的文献求助10
10秒前
10秒前
heart完成签到,获得积分10
10秒前
biancaliu发布了新的文献求助10
10秒前
10秒前
随风逐梦完成签到,获得积分10
11秒前
科研通AI2S的应助被lmg采纳,获得10
11秒前
害怕的穆发布了新的文献求助10
12秒前
obtio完成签到,获得积分20
12秒前
xu1227发布了新的文献求助10
14秒前
兜兜想哒哒完成签到,获得积分10
14秒前
Tang完成签到,获得积分10
14秒前
15秒前
wang完成签到,获得积分10
15秒前
t250完成签到,获得积分10
15秒前
蓝海鸥发布了新的文献求助10
15秒前
16秒前
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183204
求助须知:如何正确求助?哪些是违规求助? 9572482
关于积分的说明 21825940
捐赠科研通 7780074
什么是DOI,文献DOI怎么找? 3433945
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480166