Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions

Intensity-Duration-Frequency (IDF) curves are crucial for the design and management of engineering infrastructure, including storm sewers, retention ponds, dams, and flood mitigation systems. This study adopts a comparative approach to estimate IDF curves using a combination of traditional statistic...

Full description

Saved in:
Bibliographic Details
Main Authors: Sheeraz Majeed Ameen, Shuokr Qarani Aziz, Anwer Hazim Dawood, Azhin Tahir Sabir, Dara Muhammad Hawez
Format: Article
Language:English
Published: Erbil Polytechnic University 2025-02-01
Series:Polytechnic Journal
Subjects:
Online Access:https://polytechnic-journal.epu.edu.iq/home/vol15/iss1/3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849703206396887040
author Sheeraz Majeed Ameen
Shuokr Qarani Aziz
Anwer Hazim Dawood
Azhin Tahir Sabir
Dara Muhammad Hawez
author_facet Sheeraz Majeed Ameen
Shuokr Qarani Aziz
Anwer Hazim Dawood
Azhin Tahir Sabir
Dara Muhammad Hawez
author_sort Sheeraz Majeed Ameen
collection DOAJ
description Intensity-Duration-Frequency (IDF) curves are crucial for the design and management of engineering infrastructure, including storm sewers, retention ponds, dams, and flood mitigation systems. This study adopts a comparative approach to estimate IDF curves using a combination of traditional statistical methods, machine learning techniques, and advanced deep learning models. Rainfall data from Koya City, Iraq (2005e2022), was used, with the 2005e2015 period for training and 2016e2022 for validation. The models evaluated include the Gumbel Distribution, Linear Regression, Support Vector Regression (SVR), and Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), assessed based on three metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2 ). Among these, the RNN-LSTM model demonstrated the lowest RMSE (1.44 mm/hr), lowest MAE (0.81 mm/hr), and highest R2 (0.99), outperforming the Gumbel Distribution (RMSE: 9.13 mm/hr), Linear Regression (RMSE: 10.76 mm/hr), and SVR (RMSE: 6.19 mm/hr). This establishes RNN-LSTM as the most reliable approach for IDF curve prediction. Leveraging the RNN-LSTM model, rainfall trends for 2023e2043 were forecasted, revealing an expected increase in short-duration, high-intensity rainfall events, heightening flood risks, and emphasizing the need for adaptive stormwater management strategies. The findings underscore the significant potential of deep learning models like RNNLSTM in enhancing IDF curve predictions and guiding the development of resilient hydraulic infrastructure, particularly in regions like Koya City, where complex topography exacerbates flood challenges during intense rainfall events.
format Article
id doaj-art-1489a1cee5f0472abc8d7c4cee8e2299
institution DOAJ
issn 2707-7799
language English
publishDate 2025-02-01
publisher Erbil Polytechnic University
record_format Article
series Polytechnic Journal
spelling doaj-art-1489a1cee5f0472abc8d7c4cee8e22992025-08-20T03:17:23ZengErbil Polytechnic UniversityPolytechnic Journal2707-77992025-02-011512738https://doi.org/10.59341/2707-7799.1848Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve PredictionsSheeraz Majeed Ameen0Shuokr Qarani Aziz1Anwer Hazim Dawood2Azhin Tahir Sabir3Dara Muhammad Hawez4Petroleum Technology-Petrochemical Department, Koya Technical Institute, Erbil Polytechnic University, Erbil, IraqDepartment of Civil Engineering, College of Engineering, Salahaddin University-Erbil, Erbil, Kurdistan Region, IraqDepartment of Geotechnical Engineering, Faculty of Engineering, Koya University, Koya, Kurdistan Region, IraqDepartment of Software Engineering, Faculty of Engineering, Koya University, Koya, Kurdistan Region, IraqDepartment of Civil Engineering, University of Raparin, Ranya, Sulaymani, Kurdistan Region, IraqIntensity-Duration-Frequency (IDF) curves are crucial for the design and management of engineering infrastructure, including storm sewers, retention ponds, dams, and flood mitigation systems. This study adopts a comparative approach to estimate IDF curves using a combination of traditional statistical methods, machine learning techniques, and advanced deep learning models. Rainfall data from Koya City, Iraq (2005e2022), was used, with the 2005e2015 period for training and 2016e2022 for validation. The models evaluated include the Gumbel Distribution, Linear Regression, Support Vector Regression (SVR), and Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), assessed based on three metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2 ). Among these, the RNN-LSTM model demonstrated the lowest RMSE (1.44 mm/hr), lowest MAE (0.81 mm/hr), and highest R2 (0.99), outperforming the Gumbel Distribution (RMSE: 9.13 mm/hr), Linear Regression (RMSE: 10.76 mm/hr), and SVR (RMSE: 6.19 mm/hr). This establishes RNN-LSTM as the most reliable approach for IDF curve prediction. Leveraging the RNN-LSTM model, rainfall trends for 2023e2043 were forecasted, revealing an expected increase in short-duration, high-intensity rainfall events, heightening flood risks, and emphasizing the need for adaptive stormwater management strategies. The findings underscore the significant potential of deep learning models like RNNLSTM in enhancing IDF curve predictions and guiding the development of resilient hydraulic infrastructure, particularly in regions like Koya City, where complex topography exacerbates flood challenges during intense rainfall events.https://polytechnic-journal.epu.edu.iq/home/vol15/iss1/3rainfall intensity-duration-frequency curves,rnn-lstm,flood risk management,machine learning,koyacity, iraq
spellingShingle Sheeraz Majeed Ameen
Shuokr Qarani Aziz
Anwer Hazim Dawood
Azhin Tahir Sabir
Dara Muhammad Hawez
Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
Polytechnic Journal
rainfall intensity-duration-frequency curves,
rnn-lstm,
flood risk management,
machine learning,
koya
city, iraq
title Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
title_full Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
title_fullStr Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
title_full_unstemmed Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
title_short Utilizing Machine Learning and Deep Learning for Precise Intensity-Duration-Frequency (IDF) Curve Predictions
title_sort utilizing machine learning and deep learning for precise intensity duration frequency idf curve predictions
topic rainfall intensity-duration-frequency curves,
rnn-lstm,
flood risk management,
machine learning,
koya
city, iraq
url https://polytechnic-journal.epu.edu.iq/home/vol15/iss1/3
work_keys_str_mv AT sheerazmajeedameen utilizingmachinelearninganddeeplearningforpreciseintensitydurationfrequencyidfcurvepredictions
AT shuokrqaraniaziz utilizingmachinelearninganddeeplearningforpreciseintensitydurationfrequencyidfcurvepredictions
AT anwerhazimdawood utilizingmachinelearninganddeeplearningforpreciseintensitydurationfrequencyidfcurvepredictions
AT azhintahirsabir utilizingmachinelearninganddeeplearningforpreciseintensitydurationfrequencyidfcurvepredictions
AT daramuhammadhawez utilizingmachinelearninganddeeplearningforpreciseintensitydurationfrequencyidfcurvepredictions