No place to hide: Rare plant detection through remote sensing

Cerrejón, Carlos; Valeria, Osvaldo; Marchand, Philippe; Caners, Richard T.; Fenton, Nicole J.

doi:10.1111/ddi.13244

Cited by 24 publications

(15 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the wide variety of potentially relevant predictors for rare plants that can be derived from RS (related to vegetation, humidity, forest structure, topography, etc.) [ 90 ], can allow a more realistic approach to the environment-species relationship, which can be particularly useful for species with complex ecological niches. Thus, our methodology can play an important role in filling existing knowledge gaps on bryophyte distribution ranges, as well as their ecological preferences, in largely unexplored regions such as boreal forests [ 36 ].…”

Section: Discussionmentioning

confidence: 99%

Small but visible: Predicting rare bryophyte distribution and richness patterns using remote sensing-based ensembles of small models

et al. 2022

Self Cite

View full text Add to dashboard Cite

In Canadian boreal forests, bryophytes represent an essential component of biodiversity and play a significant role in ecosystem functioning. Despite their ecological importance and sensitivity to disturbances, bryophytes are overlooked in conservation strategies due to knowledge gaps on their distribution, which is known as the Wallacean shortfall. Rare species deserve priority attention in conservation as they are at a high risk of extinction. This study aims to elaborate predictive models of rare bryophyte species in Canadian boreal forests using remote sensing-derived predictors in an Ensemble of Small Models (ESMs) framework. We hypothesize that high ESMs-based prediction accuracy can be achieved for rare bryophyte species despite their low number of occurrences. We also assess if there is a spatial correspondence between rare and overall bryophyte richness patterns. The study area is located in western Quebec and covers 72,292 km2. We selected 52 bryophyte species with <30 occurrences from a presence-only database (214 species, 389 plots in total). ESMs were built from Random Forest and Maxent techniques using remote sensing-derived predictors related to topography and vegetation. Lee’s L statistic was used to assess and map the spatial relationship between rare and overall bryophyte richness patterns. ESMs yielded poor to excellent prediction accuracy (AUC > 0.5) for 73% of the modeled species, with AUC values > 0.8 for 19 species, which confirmed our hypothesis. In fact, ESMs provided better predictions for the rarest bryophytes. Likewise, our study revealed a spatial concordance between rare and overall bryophyte richness patterns in different regions of the study area, which have important implications for conservation planning. This study demonstrates the potential of remote sensing for assessing and making predictions on inconspicuous and rare species across the landscape and lays the basis for the eventual inclusion of bryophytes into sustainable development planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Small but visible: Predicting rare bryophyte distribution and richness patterns using remote sensing-based ensembles of small models

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Confinement of the plants to specific life forms and consolidating these data within the dataset is a good tool for studies of species richness and its determinants (Liu et al, 2019;Sandanov et al, 2020), for analysis of growth-form plasticity in rare and endemic species (Mills & Schwartz, 2005), and for detection of rare plants using remote sensing (Cerrejón et al, 2021). Our results revealed the prevalence of short rhizome plants among rare and endangered species.…”

Section: Discussionmentioning

confidence: 66%

Dataset for vascular plants in the Red Data Books of Transbaikalia: species distribution and pathways towards their conservation

Санданов¹,

Brianskaia²,

Dugarova³

2022

Nat. Conserv. Res.

View full text Add to dashboard Cite

The dataset of the Red Data Book vascular plants of Transbaikalia was created based on the latest editions of the Red Data Book of the Republic of Buryatia and the Red Data Book of the Zabaikalsky Krai (Russia). The dataset provides the most updated information regarding the distribution of 271 rare vascular plants (2920 distribution records). The distribution of the studied species was recorded during field surveys using GPS navigators, georeferenced from herbarium specimens, and digitised from printed distribution maps. Each entry in the dataset has various attributes, including belt zone, distribution, ecological, and life-form group features. Distribution patterns for various groups of rare and endangered species were analysed by means of QGIS 3.10 software. Our study has revealed a number of localities of vascular plants listed in the Red Data Book and clarified their distribution within the federal Protected Areas of Transbaikalia, among which Tunkinsky National Park has the highest diversity. Distribution of some rare and endangered species fall under federal protection, but some plants, including endemic species, require better protection. Analysis of various belt zones and distribution groups showed their distinct spread within the study region. Among the studied species, mesophytes and short rhizome perennial plants prevailed. It is also important to preserve vascular plants in the Red Data Book outside Protected Areas. Hence, information from our dataset can be useful for conservation monitoring programmes. Our study provides a basis for future conservation activities and can be applied in the establishment of new Protected Areas or Important Plant Areas in Transbaikalia.

show abstract

“…Evaluation metrics that are weighted by the number of samples per class, such as Weighted F1 which was one metric used in this competition, favor models that are most accurate for abundant classes. However, for many ecological questions and applications, having strong predictions across all species, especially the rare species is important (Leitão et al, 2016;Dee et al, 2019;Cerrejón et al, 2021), and therefore an evaluation score such as Macro F1 is most appropriate. Understanding patterns of taxonomic and functional diversity or evaluating the impact of climate changes and extreme disturbance events on species are examples where poor accuracy of rare species will impact the ability to use the predictions because of the uncertainty in the predictions.…”

Section: Classificationmentioning

confidence: 99%

Data science competition for cross-site delineation and classification of individual trees from airborne remote sensing data

Graves

Marconi

Stewart

et al. 2021

Preprint

View full text Add to dashboard Cite

Delineating and classifying individual trees in remote sensing data is challenging. Many tree crown delineation methods have difficulty in closed-canopy forests and do not leverage multiple datasets. Methods to classify individual species are often accurate for common species, but perform poorly for less common species and when applied to new sites. We ran a data science competition to help identify effective methods for delineation of individual crowns and classification to determine species identity. This competition included data from multiple sites to assess the methods' ability to generalize learning across multiple sites simultaneously, and transfer learning to novel sites where the methods were not trained. Six teams, representing 4 countries and 9 individual participants, submitted predictions. Methods from a previous competition were also applied and used as the baseline to understand whether the methods are changing and improving over time. The best delineation method was based on an instance segmentation pipeline, closely followed by a Faster R-CNN pipeline, both of which outperformed the baseline method. However, the baseline (based on a growing region algorithm) still performed well as did the Faster R-CNN. All delineation methods generalized well and transferred to novel forests effectively. The best species classification method was based on a two-stage fully connected neural network, which significantly outperformed the baseline (a random forest and Gradient boosting ensemble). The classification methods generalized well, with all teams training their models using multiple sites simultaneously, but the predictions from these trained models generally failed to transfer effectively to a novel site. Classification performance was strongly influenced by the number of field-based species IDs available for training the models, with most methods predicting common species well at the training sites. Classification errors (i.e., species misidentification) were most common between similar species in the same genus and different species that occur in the same habitat. The best methods handled class imbalance well and learned unique spectral features even with limited data. Most methods performed better than baseline in detecting new (untrained) species, especially in the site with no training data. Our experience further shows that data science competitions are useful for comparing different methods through the use of a standardized dataset and set of evaluation criteria, which highlights promising approaches and common challenges, and therefore advances the ecological and remote sensing field as a whole.

show abstract

No place to hide: Rare plant detection through remote sensing

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 24 publications

References 102 publications

Small but visible: Predicting rare bryophyte distribution and richness patterns using remote sensing-based ensembles of small models

Small but visible: Predicting rare bryophyte distribution and richness patterns using remote sensing-based ensembles of small models

Dataset for vascular plants in the Red Data Books of Transbaikalia: species distribution and pathways towards their conservation

Data science competition for cross-site delineation and classification of individual trees from airborne remote sensing data

Contact Info

Product

Resources

About