Expert Knowledge as a Basis for Landscape Ecological Predictive Models

Drew, C. Ashton; Perera, Ajith H.

doi:10.1007/978-1-4419-7390-0_12

Cited by 18 publications

(22 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial assessment metrics from alternative data should matter the most. Expert experience and ecological common knowledge of the species of interest could sometimes also be highly effective (Drew & Perera, 2011), albeit nonstandard, evaluation methods (see Kandel et al, 2015 for an example). Additionally, one alternative method for rapid assessment we find is to use a reliable SDM, and thus Random Forest would be a good choice in the future given our consistent results (Figs.…”

Section: Discussionmentioning

confidence: 99%

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

Huettmann

Guo

et al. 2017

PeerJ

194

108

View full text Add to dashboard Cite

Species distribution models (SDMs) have become an essential tool in ecology, biogeography, evolution and, more recently, in conservation biology. How to generalize species distributions in large undersampled areas, especially with few samples, is a fundamental issue of SDMs. In order to explore this issue, we used the best available presence records for the Hooded Crane (Grus monacha, n = 33), White-naped Crane (Grus vipio, n = 40), and Black-necked Crane (Grus nigricollis, n = 75) in China as three case studies, employing four powerful and commonly used machine learning algorithms to map the breeding distributions of the three species: TreeNet (Stochastic Gradient Boosting, Boosted Regression Tree Model), Random Forest, CART (Classification and Regression Tree) and Maxent (Maximum Entropy Models). In addition, we developed an ensemble forecast by averaging predicted probability of the above four models results. Commonly used model performance metrics (Area under ROC (AUC) and true skill statistic (TSS)) were employed to evaluate model accuracy. The latest satellite tracking data and compiled literature data were used as two independent testing datasets to confront model predictions. We found Random Forest demonstrated the best performance for the most assessment method, provided a better model fit to the testing data, and achieved better species range maps for each crane species in undersampled areas. Random Forest has been generally available for more than 20 years and has been known to perform extremely well in ecological predictions. However, while increasingly on the rise, its potential is still widely underused in conservation, (spatial) ecological applications and for inference. Our results show that it informs ecological and biogeographical theories as well as being suitable for conservation applications, specifically when the study area is undersampled. This method helps to save model-selection time and effort, and allows robust and rapid assessments and decisions for efficient conservation.

show abstract

Section: Discussionmentioning

confidence: 99%

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

Huettmann

Guo

et al. 2017

PeerJ

194

108

View full text Add to dashboard Cite

show abstract

“…Even so, the levels of disagreement between the experts suggest that various unquantified biases may have influenced their judgment. For example, a species whose abiotic niche varies geographically will be wrongly evaluated if the expert's home‐range did not include the full range of the species (Drew & Perera, ; Murray et al, ; Appendix ). In addition to these expert‐centered sources of variation, we suspect that the simplicity of the univariate model summaries may have also mitigated against more accurate (nearer to the truth) and more precise (less uncertainty surrounding estimates of the truth) assessments.…”

Section: Resultsmentioning

confidence: 99%

Assessment of a large number of empirical plant species niche models by elicitation of knowledge from two national experts

Smart

Jarvis

Mizunuma

et al. 2019

Ecology and Evolution

View full text Add to dashboard Cite

Quantitative models play an increasing role in exploring the impact of global change on biodiversity. To win credibility and trust, they need validating. We show how expert knowledge can be used to assess a large number of empirical species niche models constructed for the British vascular plant and bryophyte flora. Key outcomes were (a) scored assessments of each modeled species and niche axis combination, (b) guidance on models needing further development, (c) exploration of the trade‐off between presenting more complex model summaries, which could lead to more thorough validation, versus the longer time these take to evaluate, (d) quantification of the internal consistency of expert opinion based on comparison of assessment scores made on a random subset of models evaluated by both experts. Overall, the experts assessed 39% of species and niche axis combinations to be “poor” and 61% to show a degree of reliability split between “moderate” (30%), “good” (25%), and “excellent” (6%). The two experts agreed in only 43% of cases, reaching greater consensus about poorer models and disagreeing most about models rated as better by either expert. This low agreement rate suggests that a greater number of experts is required to produce reliable assessments and to more fully understand the reasons underlying lack of consensus. While area under curve (AUC) statistics showed generally very good ability of the models to predict random hold‐out samples of the data, there was no correspondence between these and the scores given by the experts and no apparent correlation between AUC and species prevalence. Crowd‐sourcing further assessments by allowing web‐based access to model fits is an obvious next step. To this end, we developed an online application for inspecting and evaluating the fit of each niche surface to its training data.

show abstract

“…The identification of the geographical distribution that is suitable for pests under climate change scenarios is essential for the development of long‐term management strategies. Many models are used to project the potential distributions of species under climate change scenarios, such as species distribution models (SDMs), bioclimatic models, and ecological niche models . In particular, a number of SDMs have been developed, such as CLIMEX, DOMAIN, GARP, and MaxEnt .…”

Section: Introductionmentioning

confidence: 99%

Impacts of climate change and host plant availability on the global distribution of Brontispa longissima (Coleoptera: Chrysomelidae)

Guo

et al. 2019

Pest Management Science

View full text Add to dashboard Cite

BACKGROUND The coconut hispine beetle Brontispa longissima Gestro (Coleoptera: Chrysomelidae) is one of the most serious pests of the coconut palm, Cocos nucifera L. (Arecales: Arecaceae) and other palms. The invasion of B. longissima causes major economic and ecological losses worldwide. In this study, the impacts of climate change on the risk of spread were evaluated. CLIMEX was used to project its global potential distribution based on historical climate data (1987–2016) and simulated future climate data (2071–2100). RESULTS The distribution of B. longissima included each continent under historical and future climate conditions. However, climate suitability was predicted to decrease in most tropical and subtropical regions under a climate change scenario. Temperature was a more important determinant of the climatic suitability of the pest than relative humidity or precipitation. The availability of host plants (Arecaceae) only had a slight impact on climate suitability in some regions. CONCLUSION The projected potential distribution of B. longissima will help to determine the impacts of climate change and will provide supportive information for the development of management strategies to reduce future economic and ecological losses. © 2019 Society of Chemical Industry

show abstract

Expert Knowledge as a Basis for Landscape Ecological Predictive Models

Cited by 18 publications

References 58 publications

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

Assessment of a large number of empirical plant species niche models by elicitation of knowledge from two national experts

Impacts of climate change and host plant availability on the global distribution of Brontispa longissima (Coleoptera: Chrysomelidae)

Contact Info

Product

Resources

About