scholarly journals Predictive Ecosystem Mapping of South-Eastern Australian Temperate Forests Using Lidar-Derived Structural Profiles and Species Distribution Models

2019 ◽  
Vol 11 (1) ◽  
pp. 93 ◽  
Author(s):  
Melissa Fedrigo ◽  
Stephen B. Stewart ◽  
Stephen H. Roxburgh ◽  
Sabine Kasel ◽  
Lauren T. Bennett ◽  
...  
Keyword(s):  
Species Distribution ◽  
Vegetation Structure ◽  
Species Distribution Models ◽  
Sustainable Forest Management ◽  
Continuous Distribution ◽  
Forest Monitoring ◽  
Distribution Models ◽  
Study Region ◽  
South Eastern ◽  
Eastern Australia

Modern approaches to predictive ecosystem mapping (PEM) have not thoroughly explored the use of ‘characteristic’ gradients, which describe vegetation structure (e.g., light detection and ranging (lidar)-derived structural profiles). In this study, we apply a PEM approach by classifying the dominant stand types within the Central Highlands region of south-eastern Australia using both lidar and species distribution models (SDMs). Similarity percentages analysis (SIMPER) was applied to comprehensive floristic surveys to identify five species which best separated stand types. The predicted distributions of these species, modelled using random forests with environmental (i.e., climate, topography) and optical characteristic gradients (Landsat-derived seasonal fractional cover), provided an ecological basis for refining stand type classifications based only on lidar-derived structural profiles. The resulting PEM model represents the first continuous distribution map of stand types across the study region that delineates ecotone stands, which are seral communities comprised of species typical of both rainforest and eucalypt forests. The spatial variability of vegetation structure incorporated into the PEM model suggests that many stand types are not as continuous in cover as represented by current ecological vegetation class distributions that describe the region. Improved PEM models can facilitate sustainable forest management, enhanced forest monitoring, and informed decision making at landscape scales.

scholarly journals REBIOMA Data Portal, Tool for Conservation Planning in Madagascar

2018 ◽  
Vol 2 ◽  
pp. e25864
Author(s):  
Rabetrano Tsiky
Keyword(s):  
Species Distribution ◽  
Conservation Planning ◽  
Species Distribution Models ◽  
Continuous Distribution ◽  
Environmental Data ◽  
Easy Access ◽  
Species Occurrence ◽  
Distribution Models ◽  
Occurrence Data ◽  
Data Portal

Recognizing the abundance and the accumulation of information and data on biodiversity that are still poorly exploited and even unfunded, the REBIOMA project (Madagascar Biodiversity Networking), in collaboration with partners, has developed an online dataportal in order to provide easy access to information and critical data, to support conservation planning and the expansion of scientific and professional activities in Madagascar biodiversity. The mission of the REBIOMA data portal is to serve quality-labeled, up-to-date species occurrence data and environmental niche models for Madagascar’s flora and fauna, both marine and terrestrial. REBIOMA is a project of the Wildlife Conservation Society Madagascar and the University of California, Berkeley. REBIOMA serves species occurrence data for marine and terrestrial regions of Madagascar. Following upload, data is automatically validated against a geographic mask and a taxonomic authority. Data providers can decide whether their data will be public, private, or shared only with selected collaborators. Data reviewers can add quality labels to individual records, allowing selection of data for modeling and conservation assessments according to quality. Portal users can query data in numerous ways. One of the key features of the REBIOMA web portal is its support for species distribution models, created from taxonomically valid and quality-reviewed occurrence data. Species distribution models are produced for species for which there are at least eight, reliably reviewed, non-duplicate (per grid cell) records. Maximum Entropy Modeling (MaxEnt for short) is used to produce continuous distribution models from these occurrence records and environmental data for different eras: past (1950), current (2000), and future (2080). The result is generally interpreted as a prediction of habitat suitability. Results for each model are available on the portal and ready for download as ASCII and HTML files. The REBIOMA Data Portal address is http://data.rebioma.net, or visit http://www.rebioma.netfor more general information about the entire REBIOMA project.

scholarly journals A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

2021 ◽  
Vol 13 (8) ◽  
pp. 1495
Author(s):  
Jehyeok Rew ◽  
Yongjang Cho ◽  
Eenjun Hwang
Keyword(s):  
Neural Networks ◽  
Species Distribution ◽  
Best Practice ◽  
Deep Neural Networks ◽  
Species Distribution Models ◽  
Species Distribution Model ◽  
Environmental Data ◽  
Distribution Model ◽  
Distribution Models ◽  
Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Sign in / Sign up

Export Citation Format

Share Document