An improved SPEI drought forecasting approach using the long short-term memory neural network.

Dikshit, A; Pradhan, B; Huete, A

An improved SPEI drought forecasting approach using the long short-term memory neural network.

Dikshit, A

Pradhan, B

Huete, A

Permalink

Publisher:: ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
Publication Type:: Journal Article
Citation:: Journal of environmental management, 2021, 283, pp. 111979
Issue Date:: 2021-04

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Apr 2023

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (1.9 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Dikshit, A https://orcid.org/0000-0003-2876-4080
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054
dc.contributor.author	Huete, A https://orcid.org/0000-0003-2809-2376
dc.date.accessioned	2021-05-05T00:16:25Z
dc.date.available	2021-01-09
dc.date.available	2021-05-05T00:16:25Z
dc.date.issued	2021-04
dc.identifier.citation	Journal of environmental management, 2021, 283, pp. 111979
dc.identifier.issn	0301-4797
dc.identifier.issn	1095-8630
dc.identifier.uri	http://hdl.handle.net/10453/148633
dc.description.abstract	Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R<sup>2</sup>), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R<sup>2</sup> value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed and forecasted values were analysed for the summer months of 2016-2018. The findings from the study show an improvement relative to machine learning models for a lead time of 1 month in terms of different drought characteristics. The results from this work can be used for drought mitigation purposes and different models need to be tested to further enhance our capabilities.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
dc.relation.ispartof	Journal of environmental management
dc.relation.isbasedon	10.1016/j.jenvman.2021.111979
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject.classification	Environmental Sciences
dc.subject.mesh	Memory, Short-Term
dc.subject.mesh	Forecasting
dc.subject.mesh	Australia
dc.subject.mesh	New South Wales
dc.subject.mesh	Droughts
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Australia
dc.subject.mesh	Droughts
dc.subject.mesh	Forecasting
dc.subject.mesh	Memory, Short-Term
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	New South Wales
dc.title	An improved SPEI drought forecasting approach using the long short-term memory neural network.
dc.type	Journal Article
utslib.citation.volume	283
utslib.location.activity	England
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Life Sciences
pubs.organisational-group	/University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Information, Systems and Modelling
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2023-04-01T00:00:00+1000Z
dc.date.updated	2021-05-05T00:16:23Z
pubs.publication-status	Published
pubs.volume	283

Abstract:

Droughts are slow-moving natural hazards that gradually spread over large areas and capable of extending to continental scales, leading to severe socio-economic damage. A key challenge is developing accurate drought forecast model and understanding a models' capability to examine different drought characteristics. Traditionally, forecasting techniques have used various time-series approaches and machine learning models. However, the use of deep learning methods have not been tested extensively despite its potential to improve our understanding of drought characteristics. The present study uses a deep learning approach, specifically the Long Short-Term Memory (LSTM) to predict a commonly used drought measure, the Standard Precipitation Evaporation Index (SPEI) at two different time scales (SPEI 1, SPEI 3). The model was compared with other common machine learning method, Random Forests, Artificial Neural Networks and applied over the New South Wales (NSW) region of Australia, using hydro-meteorological variables as predictors. The drought index and predictor data were collected from the Climatic Research Unit (CRU) dataset spanning from 1901 to 2018. We analysed the LSTM forecasted results in terms of several drought characteristics (drought intensity, drought category, or spatial variation) to better understand how drought forecasting was improved. Evaluation of the drought intensity forecasting capabilities of the model were based on three different statistical metrics, Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The model achieved R² value of more than 0.99 for both SPEI 1 and SPEI 3 cases. The variation in drought category forecasted results were studied using a multi-class Receiver Operating Characteristic based Area under Curves (ROC-AUC) approach. The analysis revealed an AUC value of 0.83 and 0.82 for SPEI 1 and SPEI 3 respectively. The spatial variation between observed and forecasted values were analysed for the summer months of 2016-2018. The findings from the study show an improvement relative to machine learning models for a lead time of 1 month in terms of different drought characteristics. The results from this work can be used for drought mitigation purposes and different models need to be tested to further enhance our capabilities.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/148633