Forecasting Floods Using Deep Learning Models: A Longitudinal Case Study of Chenab River, Pakistan

被引:0
作者
Aatif, Khansa [1 ]
Fahiem, Muhammad Abuzar [1 ]
Tahir, Fahima [1 ]
机构
[1] Lahore Coll Women Univ, Dept Comp Sci, Lahore 54000, Pakistan
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Floods; Rivers; Predictive models; Forecasting; Rain; Mathematical models; Long short term memory; Deep learning; flood forecasting; geospatial analysis; GMDH; LSTM; remote sensing; time-series modeling; UNIVERSAL; RUNOFF;
D O I
10.1109/ACCESS.2024.3445586
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This study presents an integrated methodological approach for forecasting future floods. Over the course of human history, floods have undoubtedly been the most common form of catastrophe. In this study, hydrological analysis was combined with time-series modeling, and this integrated approach was used to forecast daily river flow. The daily runoff of the catchment area was calculated using curve number modeling by incorporating static spatial statistics and temporal rainfall data. The applicability of time-series modeling is checked through two deep learning algorithms: Long Short-Term Memory (LSTM) and Multilayer Group Method of Data Handling (ML-GMDH). This integrated approach yielded an optimal set of attributes for river flow prediction. The proposed methodology was applied to the Chenab River Basin, Pakistan, where the absence of machine learning and deep learning models tailored for flood prediction emphasizes the urgent need for innovative and advanced tools that facilitate timely flood forecasts. The LSTM model obtained the best results, attaining the highest R-2 of 0.91, and the highest coefficient of correlation of 0.96. Additionally, the ML-GMDH model signifies its capability with 0.88 R-2. The findings of this study demonstrate that the proposed hybrid approach is a promising and reliable choice for river flow prediction, particularly for ungauged basins where upstream hydrological data is not available. The proposed model is advanced and effective, and can be employed to forecast future flood events in the Chenab Basin and similar locations worldwide.
引用
收藏
页码:115802 / 115819
页数:18
相关论文
共 80 条
  • [21] climate.copernicus, The Copernicus Climate Change Service: 'Flooding'
  • [22] Cronshey R., 1986, Urban hydrology for small watersheds
  • [23] developers.google, ESAWorldCover10mV100
  • [24] developers.google, CHIRPS Daily: Climate Hazards Center InfraRed Precipitation with Station Data
  • [25] developers.google, OpenLandMap Soil Texture Class (USDA System)
  • [26] developers.google, ERA5-Land Daily AggregatedECMWF Climate Reanalysis
  • [27] earthengine, Google Earth Engine Explorer
  • [28] Prediction of daily water level using new hybridized GS-GMDH and ANFIS-FCM models
    Ebtehaj, Isa
    Sammen, Saad Sh
    Sidek, Lariyah Mohd
    Malik, Anurag
    Sihag, Parveen
    Al-Janabi, Ahmed Mohammed Sami
    Chau, Kwok-Wing
    Bonakdari, Hossein
    [J]. ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS, 2021, 15 (01) : 1343 - 1361
  • [29] Streamflow Prediction Upstream of a Dam Using SWAT and Assessment of the Impact of Land Use Spatial Resolution on Model Performance
    El Harraki, Wafae
    Ouazar, Driss
    Bouziane, Ahmed
    El Harraki, Imad
    Hasnaoui, Driss
    [J]. ENVIRONMENTAL PROCESSES-AN INTERNATIONAL JOURNAL, 2021, 8 (03): : 1165 - 1186
  • [30] Elbisy M. S., 2019, ASRJETS, V60, P183