Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America
The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic and social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water m...
Published in: | PLOS ONE |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Public Library of Science
2023
|
Subjects: | |
Online Access: | http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10617742/ http://www.ncbi.nlm.nih.gov/pubmed/37906556 https://doi.org/10.1371/journal.pone.0290891 |
id |
ftpubmed:oai:pubmedcentral.nih.gov:10617742 |
---|---|
record_format |
openpolar |
spelling |
ftpubmed:oai:pubmedcentral.nih.gov:10617742 2023-12-03T10:20:15+01:00 Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America Hameed, Mohammed Majeed Razali, Siti Fatin Mohd Mohtar, Wan Hanna Melini Wan Rahman, Norinah Abd Yaseen, Zaher Mundher 2023-10-31 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10617742/ http://www.ncbi.nlm.nih.gov/pubmed/37906556 https://doi.org/10.1371/journal.pone.0290891 en eng Public Library of Science http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10617742/ http://www.ncbi.nlm.nih.gov/pubmed/37906556 http://dx.doi.org/10.1371/journal.pone.0290891 © 2023 Hameed et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. PLoS One Research Article Text 2023 ftpubmed https://doi.org/10.1371/journal.pone.0290891 2023-11-05T02:10:06Z The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic and social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water management and mitigating these impacts. This study introduces the Multivariate Standardized Lake Water Level Index (MSWI), a modified drought index that utilizes water level data collected from 1920 to 2020. Four hybrid models are developed: Support Vector Regression with Beluga whale optimization (SVR-BWO), Random Forest with Beluga whale optimization (RF-BWO), Extreme Learning Machine with Beluga whale optimization (ELM-BWO), and Regularized ELM with Beluga whale optimization (RELM-BWO). The models forecast droughts up to six months ahead for Lake Superior and Lake Michigan-Huron. The best-performing model is then selected to forecast droughts for the remaining three lakes, which have not experienced severe droughts in the past 50 years. The results show that incorporating the BWO improves the accuracy of all classical models, particularly in forecasting drought turning and critical points. Among the hybrid models, the RELM-BWO model achieves the highest level of accuracy, surpassing both classical and hybrid models by a significant margin (7.21 to 76.74%). Furthermore, Monte-Carlo simulation is employed to analyze uncertainties and ensure the reliability of the forecasts. Accordingly, the RELM-BWO model reliably forecasts droughts for all lakes, with a lead time ranging from 2 to 6 months. The study’s findings offer valuable insights for policymakers, water managers, and other stakeholders to better prepare drought mitigation strategies. Text Beluga Beluga whale Beluga* PubMed Central (PMC) PLOS ONE 18 10 e0290891 |
institution |
Open Polar |
collection |
PubMed Central (PMC) |
op_collection_id |
ftpubmed |
language |
English |
topic |
Research Article |
spellingShingle |
Research Article Hameed, Mohammed Majeed Razali, Siti Fatin Mohd Mohtar, Wan Hanna Melini Wan Rahman, Norinah Abd Yaseen, Zaher Mundher Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
topic_facet |
Research Article |
description |
The Great Lakes are critical freshwater sources, supporting millions of people, agriculture, and ecosystems. However, climate change has worsened droughts, leading to significant economic and social consequences. Accurate multi-month drought forecasting is, therefore, essential for effective water management and mitigating these impacts. This study introduces the Multivariate Standardized Lake Water Level Index (MSWI), a modified drought index that utilizes water level data collected from 1920 to 2020. Four hybrid models are developed: Support Vector Regression with Beluga whale optimization (SVR-BWO), Random Forest with Beluga whale optimization (RF-BWO), Extreme Learning Machine with Beluga whale optimization (ELM-BWO), and Regularized ELM with Beluga whale optimization (RELM-BWO). The models forecast droughts up to six months ahead for Lake Superior and Lake Michigan-Huron. The best-performing model is then selected to forecast droughts for the remaining three lakes, which have not experienced severe droughts in the past 50 years. The results show that incorporating the BWO improves the accuracy of all classical models, particularly in forecasting drought turning and critical points. Among the hybrid models, the RELM-BWO model achieves the highest level of accuracy, surpassing both classical and hybrid models by a significant margin (7.21 to 76.74%). Furthermore, Monte-Carlo simulation is employed to analyze uncertainties and ensure the reliability of the forecasts. Accordingly, the RELM-BWO model reliably forecasts droughts for all lakes, with a lead time ranging from 2 to 6 months. The study’s findings offer valuable insights for policymakers, water managers, and other stakeholders to better prepare drought mitigation strategies. |
format |
Text |
author |
Hameed, Mohammed Majeed Razali, Siti Fatin Mohd Mohtar, Wan Hanna Melini Wan Rahman, Norinah Abd Yaseen, Zaher Mundher |
author_facet |
Hameed, Mohammed Majeed Razali, Siti Fatin Mohd Mohtar, Wan Hanna Melini Wan Rahman, Norinah Abd Yaseen, Zaher Mundher |
author_sort |
Hameed, Mohammed Majeed |
title |
Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
title_short |
Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
title_full |
Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
title_fullStr |
Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
title_full_unstemmed |
Machine learning models development for accurate multi-months ahead drought forecasting: Case study of the Great Lakes, North America |
title_sort |
machine learning models development for accurate multi-months ahead drought forecasting: case study of the great lakes, north america |
publisher |
Public Library of Science |
publishDate |
2023 |
url |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10617742/ http://www.ncbi.nlm.nih.gov/pubmed/37906556 https://doi.org/10.1371/journal.pone.0290891 |
genre |
Beluga Beluga whale Beluga* |
genre_facet |
Beluga Beluga whale Beluga* |
op_source |
PLoS One |
op_relation |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10617742/ http://www.ncbi.nlm.nih.gov/pubmed/37906556 http://dx.doi.org/10.1371/journal.pone.0290891 |
op_rights |
© 2023 Hameed et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
op_doi |
https://doi.org/10.1371/journal.pone.0290891 |
container_title |
PLOS ONE |
container_volume |
18 |
container_issue |
10 |
container_start_page |
e0290891 |
_version_ |
1784267667036700672 |