Capability and robustness of novel hybridized models used for drought hazard modeling in southeast Queensland, Australia

Rahmati, Omid; Panahi, Mahdi; Kalantari, Zahra; Soltani, Elinaz; Falah, Fatemeh; Dayal, Kavina; Mohammadi, Farnoush; Deo, Ravinesh C.; Tiefenbacher, John P.; Bui, Dieu Tien

doi:10.1016/j.scitotenv.2019.134656

Cited by 33 publications

(29 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Nationalmentioning

confidence: 99%

“…In Queensland, Australia, hybridization of the adaptive neuro-fuzzy inference system (ANFIS) with other machine-learning, metaheuristic optimization algorithms significantly increased prediction accuracy of spatial occurrence and distribution of drought over ANFIS alone [77]. Plant-available water capacity, percentage of sand in soil, and mean annual precipitation were the most valuable drought-predicting factors [77]. With NOAA's VIIRS-based vegetation health (VH) technology to determine VH, while wheat is most sensitive to drought, it was possible to create early warning of drought-related wheat yield losses and predicted yield 1 to 2 months ahead of harvest [78].…”

Section: Nationalmentioning

confidence: 99%

See 1 more Smart Citation

Drought Early Warning in Agri-Food Systems

Ginkel¹,

Biradar²

2021

Climate

View full text Add to dashboard Cite

Droughts will increase in frequency, intensity, duration, and spread under climate change. Drought affects numerous sectors in society and the natural environment, including short-term reduced crop production, social conflict over water allocation, severe outmigration, and eventual famine. Early action can prevent escalation of impacts, requiring drought early warning systems (DEWSs) that give current assessments and sufficient notice for active risk management. While most droughts are relatively slow in onset, often resulting in late responses, flash droughts are becoming more frequent, and their sudden onset poses challenging demands on DEWSs for timely communication. We examine several DEWSs at global, regional, and national scales, with a special emphasis on agri-food systems. Many of these have been successful, such as some of the responses to 2015–2017 droughts in Africa and Latin America. Successful examples show that early involvement of stakeholders, from DEWS development to implementation, is crucial. In addition, regional and global cooperation can cross-fertilize with new ideas, reduce reaction time, and raise efficiency. Broadening partnerships also includes recruiting citizen science and including seemingly subjective indigenous knowledge that can improve monitoring, data collection, and uptake of response measures. More precise and more useful DEWSs in agri-food systems will prove even more cost-effective in averting the need for emergency responses, improving global food security.

show abstract

Section: Nationalmentioning

confidence: 99%

Section: Nationalmentioning

confidence: 99%

Drought Early Warning in Agri-Food Systems

Ginkel¹,

Biradar²

2021

Climate

View full text Add to dashboard Cite

show abstract

“…The importance of developing a unique drought risk index, specific to the area of investigation, when assessing agricultural drought risk on local community scales, has been emphasised in earlier studies (Wilhelmi and Wilhite 2002;Raikes et al 2019). A recent study by Rahmati et al (2020) developed a drought risk index to map drought risk in a drought-stricken region of 123,897 km 2 in South-East Queensland. Although the study region of Rahmati et al (2020) included areas within the Northern MDB, drought risk in these areas was investigated together with other areas in South-East Queensland on a regional level.…”

Section: Introductionmentioning

confidence: 99%

“…A recent study by Rahmati et al (2020) developed a drought risk index to map drought risk in a drought-stricken region of 123,897 km 2 in South-East Queensland. Although the study region of Rahmati et al (2020) included areas within the Northern MDB, drought risk in these areas was investigated together with other areas in South-East Queensland on a regional level. There has been no previous research on tailoring a drought risk index for drought risk mapping on a LGA level within the Northern MDB.…”

Section: Introductionmentioning

confidence: 99%

Assessing agricultural drought management strategies in the Northern Murray–Darling Basin

et al. 2021

View full text Add to dashboard Cite

The Northern Murray-Darling Basin (MDB) is a key Australian agricultural region requiring efficient Agricultural Drought Management (ADM), focused on resilience. Although a need for resilience in local farming communities has long been recognised, previous studies assessing ADM in the Northern MDB did not consider two key elements of resilient management: proactivity (preparing for drought prior to a drought event) and suitability (localised drought management targeted at decision-makers). This study assessed the current ADM Strategy (ADMS) implemented within five selected Northern MDB Local Government Areas (LGAs) (Paroo Shire, Balonne Shire, Murweh Shire, Maranoa Region, and Goondiwindi Region), specifically investigating the extent of ADMS proactivity, effectiveness, and suitability. To investigate suitability, drought risk extent of each LGA was determined. A region-specific drought risk index consisting of hazard, vulnerability and exposure indices was developed; risk mapping was conducted. All LGAs displayed very high levels of drought risk due to hazardous climatic conditions, vulnerable socio-economic attributes, and drought-exposed geographical features. A Criteria-Based Ranking (CBR) survey produced a quantitative effectiveness and proactivity rank for each major ADMS used in the Northern MDB. Government Assistance was the most proactive and effective ADMS. Strategy effectiveness ranks of the major ADMS used and drought risk extent found in each LGA were correlated to determine ADMS suitability. Overall, Balonne Shire and the Goondiwindi Region were identified as high priority areas requiring improved ADM. A user-centred Integrated Early Warning System (I-EWS) for drought could potentially increase ADM proactivity and suitability in such areas, strengthening drought resilience of farming communities.

show abstract

“…Examples of recent proposed and hybrid ensemble models for predicting landslides include ANN, SVM, SVR, and ANFIS integrated with genetic algorithm, particle swarm optimization, and gray wolf optimizer [30,[34][35][36]; alternative decision tree (ADTree) combined with ensemble techniques such as AdaBoost (AB), Random Subspace, MultiBoost, Bagging, and Dagging [24,37]; SVM combined with ensemble techniques [38,39], Naïve Bayes tree coupled with Random Subspace [40], radial basis function ANN combined with Rotation Forest [41], best first decision tree combined with Rotation Forest [42], and Bayesian logistic regression combined with AB, MultiBoost, and Bagging [43]. Hybrid ensemble models also have been successfully used in studies of other hazards, including flooding [44][45][46][47][48], wildfire [34,49], sinkhole formation [50], dust storm [51], drought [52], gully erosion [53][54][55], and land subsidence [56], as well as in other environmental studies, such as land-use planning [57] and groundwater potential mapping [54,[58][59][60][61][62].…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Mapping Using Machine Learning Algorithms and Remote Sensing Data in a Tropical Environment

Nhu

Mohammadi

Shahabi

et al. 2020

IJERPH

114

View full text Add to dashboard Cite

We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 landslides compiled using Synthetic Aperture Radar Interferometry, Google Earth images, and field surveys, and 17 conditioning factors (slope, aspect, elevation, distance to road, distance to river, proximity to fault, road density, river density, normalized difference vegetation index, rainfall, land cover, lithology, soil types, curvature, profile curvature, stream power index, and topographic wetness index). We carried out the validation process using the area under the receiver operating characteristic curve (AUC) and several parametric and non-parametric performance metrics, including positive predictive value, negative predictive value, sensitivity, specificity, accuracy, root mean square error, and the Friedman and Wilcoxon sign rank tests. The AB model (AUC = 0.96) performed better than the ensemble AB-ADTree model (AUC = 0.94) and successfully outperformed the ADTree model (AUC = 0.59) in predicting landslide susceptibility. Our findings provide insights into the development of more efficient and accurate landslide predictive models that can be used by decision makers and land-use managers to mitigate landslide hazards.

show abstract

Capability and robustness of novel hybridized models used for drought hazard modeling in southeast Queensland, Australia

Cited by 33 publications

References 110 publications

Drought Early Warning in Agri-Food Systems

Drought Early Warning in Agri-Food Systems

Assessing agricultural drought management strategies in the Northern Murray–Darling Basin

Landslide Susceptibility Mapping Using Machine Learning Algorithms and Remote Sensing Data in a Tropical Environment

Contact Info

Product

Resources

About