scholarly journals Inventory statistics meet big data: Complications for estimating numbers of species

2019 ◽  
Author(s):  
Ali Khalighifar ◽  
Laura Jiménez ◽  
Claudia Nuñez-Penichet ◽  
Benedictus Freeman ◽  
Kate Ingenloff ◽  
...  
Keyword(s):  
Big Data ◽  
Species Richness ◽  
New Jersey ◽  
Rare Species ◽  
Large Scale ◽  
Species Numbers ◽  
Biodiversity Inventory ◽  
Approach Zero ◽  
Upward Biases

Abstract We point out complications inherent in biodiversity inventory metrics when applied to large-scale datasets. The number of samples in which a species is detected saturates, such that crucial numbers of detections of rare species approach zero. Any rare errors can then come to dominate species richness estimates, creating upward biases in estimates of species numbers. We document the problem via simulations of sampling from virtual biotas, illustrate its potential using a large empirical dataset (bird records from Cape May, New Jersey, USA), and outline the circumstances under which these problems may be expected to emerge.

scholarly journals Inventory statistics meet big data: Complications for estimating numbers of species

2019 ◽  
Author(s):  
Ali Khalighifar ◽  
Laura Jiménez ◽  
Claudia Nuñez-Penichet ◽  
Benedictus Freeman ◽  
Kate Ingenloff ◽  
...  
Keyword(s):  
Big Data ◽  
Species Richness ◽  
New Jersey ◽  
Rare Species ◽  
Large Scale ◽  
Species Numbers ◽  
Biodiversity Inventory ◽  
Approach Zero ◽  
Upward Biases

Abstract We point out complications inherent in biodiversity inventory metrics when applied to large-scale datasets. The number of samples in which a species is detected saturates, such that crucial numbers of detections of rare species approach zero. Any rare errors can then come to dominate species richness estimates, creating upward biases in estimates of species numbers. We document the problem via simulations of sampling from virtual biotas, illustrate its potential using a large empirical dataset (bird records from Cape May, New Jersey, USA), and outline the circumstances under which these problems may be expected to emerge.

scholarly journals Inventory statistics meet big data: complications for estimating numbers of species

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e8872
Author(s):  
Ali Khalighifar ◽  
Laura Jiménez ◽  
Claudia Nuñez-Penichet ◽  
Benedictus Freeman ◽  
Kate Ingenloff ◽  
...  
Keyword(s):  
Big Data ◽  
Species Richness ◽  
Rare Species ◽  
Large Scale ◽  
Species Numbers ◽  
Biodiversity Inventory ◽  
Approach Zero ◽  
Upward Biases

We point out complications inherent in biodiversity inventory metrics when applied to large-scale datasets. The number of units of inventory effort (e.g., days of inventory effort) in which a species is detected saturates, such that crucial numbers of detections of rare species approach zero. Any rare errors can then come to dominate species richness estimates, creating upward biases in estimates of species numbers. We document the problem via simulations of sampling from virtual biotas, illustrate its potential using a large empirical dataset (bird records from Cape May, NJ, USA), and outline the circumstances under which these problems may be expected to emerge.

scholarly journals Distribution of Panama’s narrow-range trees: are there hot-spots?

2021 ◽  
Author(s):  
Elizabeth Tokarz ◽  
Richard Condit
Keyword(s):  
Species Richness ◽  
Tree Species ◽  
Rare Species ◽  
Large Scale ◽  
Narrow Range ◽  
Extinction Risk ◽  
High Elevation ◽  
Total Species Richness ◽  
Range Tree ◽  
Many Sources

AbstractBackgroundTree species with narrow ranges are a conservation concern because heightened extinction risk accompanies their small populations. Assessing risks for these species is challenging, however, especially in tropical flora where their sparse populations seldom appear in traditional plots and inventories. Here, we utilize instead large scale databases that combine tree records from many sources to test hypotheses about where the narrow-range tree species of Panama are concentrated.MethodsAll individual records were collected from public databases, and the range size of each tree species found in Panama was estimated as a polygon around all its locations. Rare species were defined as those with ranges < 20,000 km2. We divided Panama into geographic regions and elevation zones and counted the number of individual records and the species richness in each, separating rare species from all other species.ResultsThe proportion of rare species peaked at elevations above 2000 m, reaching 17.3% of the species recorded. At lower elevation across the country, the proportion was 6-11%, except in the dry Pacific region, where it was 1.5%. Wet forests of the Caribbean coast had 8.4% rare species, slightly higher than other regions. The total number of rare species, however, peaked at mid-elevation, not high elevation, because total species richness was highest there.ConclusionsHigh elevation forests of west Panama have higher endemicity of trees than all low-elevation regions. Dry forests had the lowest endemicity. This supports the notion that montane forests of Central America should be a conservation focus, however, given generally higher diversity at low- to mid-elevation, lowlands are also important habitats for rare species.

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

Sign in / Sign up

Export Citation Format

Share Document