Predicting the potential distribution of wheatear birds using stacked generalization-based ensembles

Alaoui, Omar El; Idri, Ali

doi:10.1016/j.ecoinf.2023.102084

Cited by 5 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that in large samples, the Super Learner approach performs at least as well as the best-performing individual algorithm (van der Laan and Dudoit 2003; van der Laan et al 2007). Yet, despite its potential, stacked generalization has remained neglected in the context of species distribution modeling (El Alaoui and Idri 2023), with studies typically relying on unweighted or weighted model averaging for combining algorithms and stacked generalization not being considered in systematic assessments of SDM ensemble methods (Hao et al 2020). We therefore recommend stacked generalization as a versatile approach for combining SDM algorithms, which should be included in future comparisons of SDM ensemble methods.…”

Section: Discussionmentioning

confidence: 99%

“…Designed as an ensemble method for combining multiple modeling algorithms, stacked generalization uses the predictions of models built at one level as the input for a metalearner built at a second level (Naimi and Balzer 2018). Although being widely applied in machine learning (Sesmero, Ledezma, and Sanchis 2015), and despite the general proliferation of algorithm ensembles in SDM studies (Buisson et al 2010;Hao et al 2019), stacked generalizations have rarely been used with SDMs (but see Bonannella et al, 2022;El Alaoui & Idri, 2023). Here, we demonstrate the use of stacked generalization as an approach for integrating expert range information with one or more SDM algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models

Oeser,

Zurell,

Mayer

et al. 2024

Preprint

View full text Add to dashboard Cite

Species distribution models (SDMs) are powerful tools for assessing suitable habitat across large areas and at fine spatial resolution. Yet, the usefulness of SDMs for mapping species realized distributions is often limited, since data biases or missing information on dispersal barriers or biotic interactions hinder them from accurately delineating species range limits. One way to overcome this limitation is to integrate SDMs with expert range maps, which provide coarse-scale information on the extent of species ranges that is complementary to information offered by SDMs. Here, we propose a new approach for integrating expert range maps in SDMs based on an ensemble method called stacked generalization. Specifically, our approach relies on training a meta-learner regression model using predictions from one or more SDM algorithms alongside the distance of training points to expert-defined ranges as predictor variables. We demonstrate our approach with an occurrence dataset for 49 bat species covering three biodiversity hotspots in the Eastern Mediterranean, Western Asia, and Central Asia. Our approach offers a flexible method to integrate expert range maps with any combination of SDM modeling algorithms, thus facilitating the use of algorithm ensembles. In addition, it provides a novel, data-driven way to account for uncertainty in expert-defined ranges not requiring prior knowledge about their accuracy, which is often lacking. Our approach holds considerable promise for better understanding species distributions, and thus for biogeographical research and conservation planning. In addition, our work highlights the overlooked potential of stacked generalization as an ensemble method in species distribution modeling.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models

Oeser,

Zurell,

Mayer

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…To avoid the potential overfitting and underfitting issues of a single model, this study adopted a stacking ensemble method (SEL) [58]. We used the four aforementioned machine learning models as base models and input their prediction results as new features into a logistic regression meta-learner for the final prediction.…”

Section: Optimizing Models Based On Hyperparameters and Ensemble Methodsmentioning

confidence: 99%

Predicting the Global Potential Suitable Distribution of Fall Armyworm and Its Host Plants Based on Machine Learning Models

Huang,

Dong,

Huang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The fall armyworm (Spodoptera frugiperda) (J. E. Smith) is a widespread, polyphagous, and highly destructive agricultural pest. Global climate change may facilitate its spread to new suitable areas, thereby increasing threats to host plants. Consequently, predicting the potential suitable distribution for the fall armyworm and its host plants under current and future climate scenarios is crucial for assessing its outbreak risks and formulating control strategies. This study, based on remote sensing assimilation data and plant protection survey data, utilized machine learning methods (RF, CatBoost, XGBoost, LightGBM) to construct potential distribution prediction models for the fall armyworm and its 120 host plants. Hyperparameter methods and stacking ensemble method (SEL) were introduced to optimize the models. The results showed that SEL demonstrated optimal performance in predicting the suitable distribution for the fall armyworm, with an AUC of 0.971 ± 0.012 and a TSS of 0.824 ± 0.047. Additionally, LightGBM and SEL showed optimal performance in predicting the suitable distribution for 47 and 30 host plants, respectively. Overlay analysis suggests that the overlap areas and interaction links between the suitable areas for the fall armyworm and its host plants will generally increase in the future, with the most significant rise under the RCP8.5 climate scenario, indicating that the threat to host plants will further intensify due to climate change. The findings of this study provide data support for planning and implementing global and intercontinental long-term pest management measures aimed at mitigating the impact of the fall armyworm on global food production.

show abstract

Habitat Suitability Assessment of Three Passerine Birds Using Ensemble Learning with Diverse Models

El Alaoui,

Idri

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Predicting the potential distribution of wheatear birds using stacked generalization-based ensembles

Cited by 5 publications

References 49 publications

The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models

The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models

Predicting the Global Potential Suitable Distribution of Fall Armyworm and Its Host Plants Based on Machine Learning Models

Habitat Suitability Assessment of Three Passerine Birds Using Ensemble Learning with Diverse Models

Contact Info

Product

Resources

About