Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction

Belayneh, Anteneh; Adamowski, Jan; Khalil, Bahaa; Quilty, John

doi:10.1016/j.atmosres.2015.12.017

Cited by 135 publications

(53 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Droughts are high impact weather events, estimated to have cost $1.5 billion globally between year 1998-2017, and representing 33% of the costs of weather hazards over that period. AI offers the potential to leverage recent advances in drought forecasting accuracy (Belayneh et al 2016) to improve decisionmaking. The Horn of Africa drought in 2011, for instance, impacted over 9 million people and the resulting food insecurity likely caused between 143 000 and 273 000 deaths in Somalia alone (Checchi and Robinson 2013).…”

Section: Ai To Support Climate Adaptation With An Emphasis On Droughmentioning

confidence: 99%

Machine learning and artificial intelligence to aid climate change research and preparedness

Huntingford

Jeffers

Bonsall

et al. 2019

Environ. Res. Lett.

258

131

View full text Add to dashboard Cite

Climate change challenges societal functioning, likely requiring considerable adaptation to cope with future altered weather patterns. Machine learning (ML) algorithms have advanced dramatically, triggering breakthroughs in other research sectors, and recently suggested as aiding climate analysis (Reichstein et al 2019 Nature 566 195-204, Schneider et al 2017 Geophys. Res. Lett. 44 12396-417).Although a considerable number of isolated Earth System features have been analysed with ML techniques, more generic application to understand better the full climate system has not occurred. For instance, ML may aid teleconnection identification, where complex feedbacks make characterisation difficult from direct equation analysis or visualisation of measurements and Earth System model (ESM) diagnostics. Artificial intelligence (AI) can then build on discovered climate connections to provide enhanced warnings of approaching weather features, including extreme events. While ESM development is of paramount importance, we suggest a parallel emphasis on utilising ML and AI to understand and capitalise far more on existing data and simulations.

show abstract

Section: Ai To Support Climate Adaptation With An Emphasis On Droughmentioning

confidence: 99%

Machine learning and artificial intelligence to aid climate change research and preparedness

Huntingford

Jeffers

Bonsall

et al. 2019

Environ. Res. Lett.

258

131

View full text Add to dashboard Cite

show abstract

“…Dzeroski & Zenko (2004) documents stacking as having better performance as compared to the selection of the the best classifier. The study in Belayneh et al (2016), for example, uses both bagging and boosting in drought prediction using wavelet transforms while Ganguli & Reddy (2014) used the copula method on support vector regression (SVR) to simulate ensembles of drought forecasts. Common to both Belayneh et al (2016) and Ganguli & Reddy (2014) is the use of a single drought index in the prediction of meteorological drought.…”

Section: Introductionmentioning

confidence: 99%

“…The study in Belayneh et al (2016), for example, uses both bagging and boosting in drought prediction using wavelet transforms while Ganguli & Reddy (2014) used the copula method on support vector regression (SVR) to simulate ensembles of drought forecasts. Common to both Belayneh et al (2016) and Ganguli & Reddy (2014) is the use of a single drought index in the prediction of meteorological drought. On the contrary, the systems in Wardlow et al (2012) and Tadesse et al (2010), for example, use multiple indices in the forecasting of future vegetation conditions.…”

Section: Introductionmentioning

confidence: 99%

Model Ensembles of Artificial Neural Networks and Support Vector Regression for Improved Accuracy in the Prediction of Vegetation Conditions and Droughts in Four Northern Kenya Counties

Adede

Oboko

Wagacha

et al. 2019

IJGI

View full text Add to dashboard Cite

There is increasing need for highly predictive and stable models for the prediction of drought as an aid to better planning for drought response. This paper presents the performance of both homogenous and heterogenous model ensembles in the prediction of drought severity using the study case techniques of artificial neural networks (ANN) and support vector regression (SVR). For each of the homogenous and heterogenous model ensembles, the study investigates the performance of three model ensembling approaches: linear averaging (non-weighted), ranked weighted averaging and model stacking using artificial neural networks. Using the approach of "over-produce then select", the study used 17 years of data on 16 selected variables for predictive drought monitoring to build 244 individual ANN and SVR models from which 111 models were selected for the building of the model ensembles. The results indicate marginal superiority of heterogenous to homogenous model ensembles. Model stacking is shown to realize models that are superior in performance in the prediction of future vegetation conditions as compared to the linear averaging and weighted averaging approaches. The best performance from the heterogenous stacked model ensembles recorded an R 2 of 0.94 in the prediction of future vegetation conditions as compared to an R 2 of 0.83 and R 2 of 0.78 for both ANN and SVR respectively in the traditional champion model approaches to the realization of predictive models. We conclude that despite the computational resource intensiveness of the model ensembling approach to drought prediction, the returns in terms of model performance is worth the investment, especially in the context of the recent exponential increase in computational power.

show abstract

“…The medium-term drought like SPI-6 influences the streamflow variability, and the long-term drought like SPI-12 influences the groundwater component (Janga Reddy & Ganguli, 2012;NDMC, 2006). In the past, several studies have performed SPI-based drought prediction considering a pure time series approach or cause effect approach (in which other climate variables or indices are considered along with lagged time step values of SPI as inputs) using simple regression, data-driven techniques, or their hybrid variants involving wavelets (Belayneh, Adamowski, Khalil, & Ozga-Zielinski, 2014;Belayneh, Adamowski, Khalil, & Quilty, 2016;Ganguli & Janga Reddy, 2014;Morid, Smakhtin, & Bagherzadeh, 2007). Even though many SPI-based drought prediction models were developed in different parts of the world, only very few studies have focused on Indian region.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of trends and predictability of short‐term droughts in three meteorological subdivisions of India using multivariate EMD‐based hybrid modelling

Adarsh

Reddy

2018

Hydrological Processes

View full text Add to dashboard Cite

This paper presented trend analysis of droughts in Kerala, Telangana, and Orissa meteorological subdivisions in India and proposed a framework for drought prediction by employing the Empirical Mode Decomposition (EMD)‐based prediction models. The study used 3‐month standardized precipitation index (SPI3) for drought analysis. The trend analysis of SPI3 series for the period 1871–2012 using Mann–Kendall method showed statistically significant increasing trend in Kerala and Telangana subdivisions and a decreasing trend in Orissa subdivision. In addition, the non‐linear trend component extracted from EMD showed statistically significant changes in all the three subdivisions. Then, the study proposed a hybrid approach for prediction of short‐term droughts by coupling multivariate extension of EMD (MEMD) with stepwise linear regression (SLR) and genetic programming (GP) methods. First, the multivariate dataset comprising the SPI3 series of current and lagged time steps are decomposed using the MEMD. Then, SLR/GP models are developed to predict each subseries of SPI3 of desired time step considering the subseries of predictor variables at the corresponding timescales as inputs. The resulting models at different timescales are recombined to obtain the SPI3 values of the desired time step. The method is applied for prediction of short‐term droughts in the three subdivisions. The results obtained by the hybrid models are compared with that obtained by conventional prediction models using M5 Model Trees and GP. The rigorous performance evaluation based on multiple statistical criteria clearly exhibited the superiority of the hybrid approaches (i.e., prediction models with MEMD‐based decomposition over models without decomposition) for prediction of SPI3 in three subdivisions. Further, the study found that MEMD‐GP model performs marginally better than the MEMD‐SLR model due to its efficacy in modelling high frequency modes.

show abstract

Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction

Cited by 135 publications

References 53 publications

Machine learning and artificial intelligence to aid climate change research and preparedness

Machine learning and artificial intelligence to aid climate change research and preparedness

Model Ensembles of Artificial Neural Networks and Support Vector Regression for Improved Accuracy in the Prediction of Vegetation Conditions and Droughts in Four Northern Kenya Counties

Evaluation of trends and predictability of short‐term droughts in three meteorological subdivisions of India using multivariate EMD‐based hybrid modelling

Contact Info

Product

Resources

About