A Mass Conservation Relaxed (MCR) LSTM Model for Streamflow Simulation Across CONUS

圆锥 水流 地质学 质量守恒 水文学(农业) 环境科学 地理 古生物学 岩土工程 地图学 物理 流域 量子力学
作者
Yihan Wang,Lujun Zhang,N. Benjamin Erichson,Tiantian Yang
出处
期刊:Water Resources Research [Wiley]
卷期号:61 (8) 被引量:17
标识
DOI:10.1029/2024wr039131
摘要

Abstract The recent development of the physics‐aware Mass‐Conserving Long Short‐Term Memory network (MC‐LSTM) provides an alternative to other data‐driven Deep Learning (DL) models in hydrology. Mass‐Conserving Long Short‐Term Memory incorporates mass conservation directly into the LSTM architecture. Despite the theoretical advancements, studies have reported a surprisingly limited performance of the MC‐LSTM in streamflow simulation. We hypothesize that such a limitation is due to the unrealistic mass conservation scheme in MC‐LSTM, which overlooks unobserved incoming water fluxes beyond precipitation. As an attempt to verify this hypothesis, we propose a Mass Conservation Relaxed LSTM (MCR‐LSTM), which incorporates a bi‐directional mass relaxation (MR) component to account for potential incoming water fluxes beyond precipitation. We train and test the proposed MCR‐LSTM model across 531 watersheds in the contiguous United States (CONUS) against three baseline models: the Sacramento Soil Moisture Accounting, LSTM, and MC‐LSTM. Our results show that MCR‐LSTM outperforms MC‐LSTM despite its underperformance compared to LSTM. Specifically, MCR‐LSTM's advantage over MC‐LSTM is mainly seen in the Plains and Western U.S., where the newly incorporated MR component better simulates water loss and suggests the likely existence of additional incoming water fluxes beyond precipitation, respectively. The novelty and contribution of this study are twofold: firstly, it introduces an alternative physics‐aware DL tool (i.e., MCR‐LSTM) in hydrology with higher accuracy in specific regions compared to MC‐LSTM. Secondly, it provides a diagnosis of regions where strict, precipitation‐based mass conservation constraints may be unrealistic in streamflow simulation.
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
Cynthia发布了新的文献求助10
2秒前
莫远阳完成签到,获得积分10
2秒前
英姑的应助被周周采纳,获得50
2秒前
凉白开发布了新的文献求助10
3秒前
Akim的应助被Lvc采纳,获得10
3秒前
3秒前
hantongxue完成签到,获得积分10
4秒前
秋风的应助被北林采纳,获得10
4秒前
之鱼之乐完成签到,获得积分10
6秒前
6秒前
称心匕发布了新的文献求助10
7秒前
8秒前
苹果发布了新的文献求助10
8秒前
8秒前
Orange的应助被二甲双胍采纳,获得10
8秒前
shunlimaomi发布了新的文献求助30
10秒前
踌躇前半生完成签到,获得积分10
10秒前
11秒前
12秒前
yanhong发布了新的文献求助30
12秒前
Jiangpeng完成签到,获得积分10
13秒前
秋风的应助被Lvc采纳,获得10
13秒前
Hello的应助被初初初啊采纳,获得10
14秒前
Fyq完成签到,获得积分10
14秒前
程程程发布了新的文献求助10
15秒前
脑洞疼的应助被wx采纳,获得30
15秒前
15秒前
清洋完成签到 ,获得积分10
17秒前
脑洞疼的应助被drizzle采纳,获得20
17秒前
周周发布了新的文献求助50
17秒前
凡fan完成签到,获得积分10
18秒前
荔枝学长完成签到,获得积分10
18秒前
隐形曼青的应助被renn采纳,获得10
19秒前
慕安完成签到,获得积分10
19秒前
老大发布了新的文献求助10
20秒前
zwhqqz完成签到,获得积分10
21秒前
爆米花的应助被初景采纳,获得50
21秒前
挚友完成签到,获得积分10
22秒前
22秒前
小黑完成签到 ,获得积分10
22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 8184008
求助须知:如何正确求助?哪些是违规求助? 9573151
关于积分的说明 21829656
捐赠科研通 7781040
什么是DOI,文献DOI怎么找? 3434187
关于科研通互助平台的介绍 2558337
邀请新用户注册赠送积分活动 2480658