Correcting for bias in distribution modelling for rare species using citizen science data

Abstract

Aim:To improve the accuracy of inferences on habitat associations and distribution patterns of rare species by combining machine-learning, spatial filtering and resampling to address class imbalance and spatial bias of large volumes of citizen science data. Innovation:Modelling rare species' distributions is a pressing challenge for conservation and applied research. Often, a large number of surveys are required before enough detections occur to model distributions of rare species accurately, resulting in a data set with a high proportion of non-detections (i.e. class imbalance). Citizen science data can provide a cost-effective source of surveys but likely suffer from class imbalance.Citizen science data also suffer from spatial bias, likely from preferential sampling. To correct for class imbalance and spatial bias, we used spatial filtering to under-sample the majority class (non-detection) while maintaining all of the limited information from the minority class (detection). We investigated the use of spatial under-sampling with randomForest models and compared it to common approaches used for imbalanced data, the synthetic minority oversampling technique (SMOTE), weighted random forest and balanced random forest models. Model accuracy was assessed using kappa, Brier score and AUC. We demonstrate the method by evaluating habitat associations and seasonal distribution patterns using citizen science data for a rare species, the tricoloured blackbird (Agelaius tricolor).Main Conclusions: Spatial under-sampling increased the accuracy of each model and outperformed the approach typically used to direct under-sampling in the SMOTE algorithm. Our approach is the first to characterize winter distribution and movement of tricoloured blackbirds. Our results show that tricoloured blackbirds are positively associated with grassland, pasture and wetland habitats, and negatively associated with high elevations or evergreen forests during both winter and breeding seasons. The seasonal differences in distribution indicate that individuals move to the coast during the winter, as suggested by historical accounts. K E Y W O R D Scitizen science, class imbalance, random forest, spatial bias, species distribution model, tricoloured blackbird | 461 ROBINSON et al.

Modeling avian full annual cycle distribution and population trends with citizen science data

“…This is a modeling concern because binary regression methods (like the first component of the zero‐inflated boosted regression tree base model, described in Base models ), become overwhelmed by the non‐detections and perform poorly (King and Zeng , Robinson et al. ). Case‐control sampling treats detection and non‐detection cases separately, resampling each case to improve spatial and temporal balance in the data and model performance (Breslow , Fithian and Hastie ).…”

“…) and biases in the distribution of survey effort across space and time (Robinson et al. , Johnston et al. ).…”

“…To meet this challenge, we began by extending the work of Robinson et al. () to develop a novel spatiotemporal case‐control sampling procedure to increase the amount of occurrence information in these data poor areas. Then we utilized the ensemble model structure of Fink et al.…”

Evaluating presence‐only species distribution models with discrimination accuracy is uninformative for many applications

“…Many investigators are currently developing methods that incorporate more biological and statistical realism into the SDM process, including the integration of physiological and trait data (Pollock et al, 2018) and explicit models of bias (Robinson, Ruiz-Gutierrez, & Fink, 2018), dispersal (Zurell, 2017), plasticity (Bush et al, 2016) and evolutionary history (Smith, Godsoe, Rodriguez-Sanchez, Wang, & Warren, 2019). Many investigators are currently developing methods that incorporate more biological and statistical realism into the SDM process, including the integration of physiological and trait data (Pollock et al, 2018) and explicit models of bias (Robinson, Ruiz-Gutierrez, & Fink, 2018), dispersal (Zurell, 2017), plasticity (Bush et al, 2016) and evolutionary history (Smith, Godsoe, Rodriguez-Sanchez, Wang, & Warren, 2019).…”

An evaluation of stringent filtering to improve species distribution models from citizen science data

“…Reducing bias and noise in citizen science datasets can be achieved by either filter‐based or statistical techniques (Bird et al, ; Isaac, Strien, August, Zeeuw, & Roy, ). Filtering removes problematic observations, such as outliers, or those contributing to sampling or spatial bias (Fink et al, ; Bonter & Cooper, ; Butt, Slade, Thompson, Malhi, & Riutta, ; Boria, Olson, Goodman, & Anderson, ; Robinson et al, ; Tye et al, ). Statistical techniques fit models that address sampling bias and observation heterogeneity.…”