.png){kind=icon}
Return
Synthetic rainfall data generator development through decentralised model training
.png){kind=icon}
OA
AI
DOI：10.1016/j.jhydrol.2022.128210.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent heavy rainfall-induced flood events, for example in Germany, Australia and USA, have highlighted the relevance of countermeasures in saving human lives and preventing property damage. Newly introduced ML-based flood forecasting methods rely on high-intensity synthetic rainfall events due to the sparsity of their real counterpart. Such synthetic data instances can be produced by precipitation generators trained in an adversarial setting on historical rainfall data. Capturing processes for rainfall data are often highly distributed, with multiple radar stations contributing to a centralised data set. However, data centralisation entails challenges regarding data-stream logistics, data locality, and memory overhead. Distributed Analytics (DA) aims to overcome these challenges through decentralised model training by bringing the algorithm to the data instead of vice versa. In this work, we propose a feasibility study evaluating the applicability of DA on hydrological data. As example of use, we choose the decentralised training of rainfall data generators. We introduce a rainfall generator training procedure relying on Generative Adversarial Networks (GANs) and evaluate two DA algorithms: Federated Learning (FL) and Cyclic Institutional Incremental Learning (CIIL). We compare the resulting training outcomes with the centralised model training (CL) approach and find CIIL performed similarly to CL but less stable, while FL outperformed CL by 7.5%. We conclude that the proven feasibility of FL in our simulated distributed setting lays the groundwork for utilising this approach in realistic environments of grander scale while overcoming potential privacy concerns or logistical challenges in the setting of centralised analytics.
Keywords:
Hydrological data
Distributed data
Distributed analytics
Data generation
Journal
IF:
6.3
Papers:
2.4W
Citations:
9.8W
Organization
Cited Papers
ShareSave
ShareSaveAssessment of urban pluvial flood risk and efficiency of adaptation options through simulations - A new generation of urban planning tools.png)
JOURNAL OF HYDROLOGYOAAI
JOURNAL OF HYDROLOGYIF6.3
OAAIShareSaveShareSaveShareSaveCrowdsourcing air temperature from citizen weather stations for urban climate researchURBAN CLIMATE
URBAN CLIMATEIF6.9
PREAI
ShareSaveFederated learning in medicine: facilitating multi-institutional collaborations without sharing patient dataSCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAIShareSaveShareSaveShareSave
View more